Downloads: 1
Diff of
/1_simple_data.ipynb
[000000]
..
[418e14]
Switch to side-by-side view
--- a
+++ b/1_simple_data.ipynb
@@ -0,0 +1,33087 @@
+{
+ "cells": [
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "%matplotlib inline\n",
+ "from IPython.display import display, HTML"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Build Data Definitions"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import icu_data_defs"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": [
+ "data_dict = icu_data_defs.data_dictionary('config/data_definitions.xlsx')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>units</th>\n",
+ " <th>variable_type</th>\n",
+ " <th>clinical_source</th>\n",
+ " <th>list_id</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>def_id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>heart rate</td>\n",
+ " <td>beats/min</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>blood pressure systolic</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>blood pressure diastolic</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>blood pressure mean</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>respiratory rate</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label units variable_type clinical_source \\\n",
+ "def_id \n",
+ "0 heart rate beats/min qn observation \n",
+ "1 blood pressure systolic mmHg qn observation \n",
+ "2 blood pressure diastolic mmHg qn observation \n",
+ "3 blood pressure mean mmHg qn observation \n",
+ "4 respiratory rate insp/min qn observation \n",
+ "\n",
+ " list_id \n",
+ "def_id \n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN "
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data_dict.tables.definitions.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "inr_id = data_dict.add_definition(label='INR')\n",
+ "pt_id = data_dict.add_definition(label='Prothrombin Time',units='seconds')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>units</th>\n",
+ " <th>variable_type</th>\n",
+ " <th>clinical_source</th>\n",
+ " <th>list_id</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>def_id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>23</th>\n",
+ " <td>lactate</td>\n",
+ " <td>mmol/L</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>24</th>\n",
+ " <td>lactate</td>\n",
+ " <td>mg/dL</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25</th>\n",
+ " <td>hemoglobin</td>\n",
+ " <td>g/dL</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26</th>\n",
+ " <td>INR</td>\n",
+ " <td>NaN</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>27</th>\n",
+ " <td>Prothrombin Time</td>\n",
+ " <td>seconds</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label units variable_type clinical_source list_id\n",
+ "def_id \n",
+ "23 lactate mmol/L qn observation NaN\n",
+ "24 lactate mg/dL qn observation NaN\n",
+ "25 hemoglobin g/dL qn observation NaN\n",
+ "26 INR NaN qn observation NaN\n",
+ "27 Prothrombin Time seconds qn observation NaN"
+ ]
+ },
+ "execution_count": 30,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data_dict.tables.definitions.tail()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>units</th>\n",
+ " <th>variable_type</th>\n",
+ " <th>clinical_source</th>\n",
+ " <th>list_id</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>def_id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>26</th>\n",
+ " <td>INR</td>\n",
+ " <td>NaN</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>27</th>\n",
+ " <td>Prothrombin Time</td>\n",
+ " <td>seconds</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label units variable_type clinical_source list_id\n",
+ "def_id \n",
+ "26 INR NaN qn observation NaN\n",
+ "27 Prothrombin Time seconds qn observation NaN"
+ ]
+ },
+ "execution_count": 31,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "from itertools import product\n",
+ "\n",
+ "panel_map = list(product([data_dict.table_names.definitions],[inr_id,pt_id]))\n",
+ "panel_id = data_dict.add_panel('coagulation labs',panel_map)\n",
+ "data_dict.get_panel_defintions(panel_id)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 32,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>panel_name</th>\n",
+ " <th>list_id</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>panel_id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>blood pressure</td>\n",
+ " <td>3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>vital signs</td>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>urine output</td>\n",
+ " <td>5</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>glasgow coma scale</td>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>normal saline</td>\n",
+ " <td>7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>lactated ringers</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>common fluids</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>norepinephrine</td>\n",
+ " <td>10</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>vasopressin</td>\n",
+ " <td>11</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>common pressors</td>\n",
+ " <td>12</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>lactate</td>\n",
+ " <td>13</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>oxygen delivery labs</td>\n",
+ " <td>14</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>12</th>\n",
+ " <td>simple dataset</td>\n",
+ " <td>15</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13</th>\n",
+ " <td>coagulation labs</td>\n",
+ " <td>16</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " panel_name list_id\n",
+ "panel_id \n",
+ "0 blood pressure 3\n",
+ "1 vital signs 4\n",
+ "2 urine output 5\n",
+ "3 glasgow coma scale 6\n",
+ "4 normal saline 7\n",
+ "5 lactated ringers 8\n",
+ "6 common fluids 9\n",
+ "7 norepinephrine 10\n",
+ "8 vasopressin 11\n",
+ "9 common pressors 12\n",
+ "10 lactate 13\n",
+ "11 oxygen delivery labs 14\n",
+ "12 simple dataset 15\n",
+ "13 coagulation labs 16"
+ ]
+ },
+ "execution_count": 32,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data_dict.tables.panels"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>units</th>\n",
+ " <th>variable_type</th>\n",
+ " <th>clinical_source</th>\n",
+ " <th>list_id</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>def_id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>heart rate</td>\n",
+ " <td>beats/min</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>blood pressure systolic</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>blood pressure diastolic</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>blood pressure mean</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>respiratory rate</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>temperature body</td>\n",
+ " <td>degF</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>oxygen saturation pulse oximetry</td>\n",
+ " <td>percent</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>weight body</td>\n",
+ " <td>kg</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>output urine</td>\n",
+ " <td>mL</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>output urine</td>\n",
+ " <td>mL/hr</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>output urine</td>\n",
+ " <td>mL/kg/hr</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>glasgow coma scale motor</td>\n",
+ " <td>NaN</td>\n",
+ " <td>ord</td>\n",
+ " <td>observation</td>\n",
+ " <td>0.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>12</th>\n",
+ " <td>glasgow coma scale eye opening</td>\n",
+ " <td>NaN</td>\n",
+ " <td>ord</td>\n",
+ " <td>observation</td>\n",
+ " <td>2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13</th>\n",
+ " <td>glasgow coma scale verbal</td>\n",
+ " <td>NaN</td>\n",
+ " <td>ord</td>\n",
+ " <td>observation</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>14</th>\n",
+ " <td>normal saline</td>\n",
+ " <td>mL</td>\n",
+ " <td>qn</td>\n",
+ " <td>intervention</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>15</th>\n",
+ " <td>normal saline</td>\n",
+ " <td>mL/hr</td>\n",
+ " <td>qn</td>\n",
+ " <td>intervention</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>16</th>\n",
+ " <td>lactated ringers</td>\n",
+ " <td>mL</td>\n",
+ " <td>qn</td>\n",
+ " <td>intervention</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>17</th>\n",
+ " <td>lactated ringers</td>\n",
+ " <td>mL/hr</td>\n",
+ " <td>qn</td>\n",
+ " <td>intervention</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18</th>\n",
+ " <td>norepinephrine</td>\n",
+ " <td>mcg</td>\n",
+ " <td>qn</td>\n",
+ " <td>intervention</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>19</th>\n",
+ " <td>norepinephrine</td>\n",
+ " <td>mcg/min</td>\n",
+ " <td>qn</td>\n",
+ " <td>intervention</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>20</th>\n",
+ " <td>norepinephrine</td>\n",
+ " <td>mcg/kg/min</td>\n",
+ " <td>qn</td>\n",
+ " <td>intervention</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>21</th>\n",
+ " <td>vasopressin</td>\n",
+ " <td>units</td>\n",
+ " <td>qn</td>\n",
+ " <td>intervention</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>22</th>\n",
+ " <td>vasopressin</td>\n",
+ " <td>units/min</td>\n",
+ " <td>qn</td>\n",
+ " <td>intervention</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25</th>\n",
+ " <td>hemoglobin</td>\n",
+ " <td>g/dL</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>23</th>\n",
+ " <td>lactate</td>\n",
+ " <td>mmol/L</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>24</th>\n",
+ " <td>lactate</td>\n",
+ " <td>mg/dL</td>\n",
+ " <td>qn</td>\n",
+ " <td>observation</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label units variable_type \\\n",
+ "def_id \n",
+ "0 heart rate beats/min qn \n",
+ "1 blood pressure systolic mmHg qn \n",
+ "2 blood pressure diastolic mmHg qn \n",
+ "3 blood pressure mean mmHg qn \n",
+ "4 respiratory rate insp/min qn \n",
+ "5 temperature body degF qn \n",
+ "6 oxygen saturation pulse oximetry percent qn \n",
+ "7 weight body kg qn \n",
+ "8 output urine mL qn \n",
+ "9 output urine mL/hr qn \n",
+ "10 output urine mL/kg/hr qn \n",
+ "11 glasgow coma scale motor NaN ord \n",
+ "12 glasgow coma scale eye opening NaN ord \n",
+ "13 glasgow coma scale verbal NaN ord \n",
+ "14 normal saline mL qn \n",
+ "15 normal saline mL/hr qn \n",
+ "16 lactated ringers mL qn \n",
+ "17 lactated ringers mL/hr qn \n",
+ "18 norepinephrine mcg qn \n",
+ "19 norepinephrine mcg/min qn \n",
+ "20 norepinephrine mcg/kg/min qn \n",
+ "21 vasopressin units qn \n",
+ "22 vasopressin units/min qn \n",
+ "25 hemoglobin g/dL qn \n",
+ "23 lactate mmol/L qn \n",
+ "24 lactate mg/dL qn \n",
+ "\n",
+ " clinical_source list_id \n",
+ "def_id \n",
+ "0 observation NaN \n",
+ "1 observation NaN \n",
+ "2 observation NaN \n",
+ "3 observation NaN \n",
+ "4 observation NaN \n",
+ "5 observation NaN \n",
+ "6 observation NaN \n",
+ "7 observation NaN \n",
+ "8 observation NaN \n",
+ "9 observation NaN \n",
+ "10 observation NaN \n",
+ "11 observation 0.0 \n",
+ "12 observation 2.0 \n",
+ "13 observation 1.0 \n",
+ "14 intervention NaN \n",
+ "15 intervention NaN \n",
+ "16 intervention NaN \n",
+ "17 intervention NaN \n",
+ "18 intervention NaN \n",
+ "19 intervention NaN \n",
+ "20 intervention NaN \n",
+ "21 intervention NaN \n",
+ "22 intervention NaN \n",
+ "25 observation NaN \n",
+ "23 observation NaN \n",
+ "24 observation NaN "
+ ]
+ },
+ "execution_count": 33,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data_dict.get_panel_defintions(12)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "data_dict.save()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# MIMIC Exploration"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import mimic\n",
+ "from icu_data_defs import data_dictionary"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": [
+ "reload(mimic)\n",
+ "conn = mimic.connect()\n",
+ "data_dict = data_dictionary('config/data_definitions.xlsx')\n",
+ "explorer = mimic.explorer(conn)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict = {}"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Vital Signs"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Heart Rate"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>227018</th>\n",
+ " <td>HR_ApacheIV</td>\n",
+ " <td>HR_ApacheIV</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223765</th>\n",
+ " <td>Orthostatic HR sitting</td>\n",
+ " <td>Orthostatic HR sitting</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1332</th>\n",
+ " <td>pulse</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227581</th>\n",
+ " <td>BiPap bpm (S/T -Back up)</td>\n",
+ " <td>BiPap bpm (S/T -Back up)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220047</th>\n",
+ " <td>Heart Rate Alarm - Low</td>\n",
+ " <td>HR Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224363</th>\n",
+ " <td>VAD Beat Rate L</td>\n",
+ " <td>VAD Beat Rate L</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226764</th>\n",
+ " <td>HrApacheIIValue</td>\n",
+ " <td>HrApacheIIValue</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1341</th>\n",
+ " <td>PULSE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220045</th>\n",
+ " <td>Heart Rate</td>\n",
+ " <td>HR</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223775</th>\n",
+ " <td>VAD Beat Rate R</td>\n",
+ " <td>VAD Beat Rate R</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220046</th>\n",
+ " <td>Heart rate Alarm - High</td>\n",
+ " <td>HR Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224751</th>\n",
+ " <td>Temporary Pacemaker Rate</td>\n",
+ " <td>Temp Pacemaker Rate</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Cardiovascular (Pacer Data)</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223764</th>\n",
+ " <td>Orthostatic HR lying</td>\n",
+ " <td>Orthostatic HR lying</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1725</th>\n",
+ " <td>Pulse</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224422</th>\n",
+ " <td>Spont RR</td>\n",
+ " <td>Spont RR</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224647</th>\n",
+ " <td>Orthostatic HR standing</td>\n",
+ " <td>Orthostatic HR standing</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>bpm</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>211</th>\n",
+ " <td>Heart Rate</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220181</th>\n",
+ " <td>Non Invasive Blood Pressure mean</td>\n",
+ " <td>NBPm</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220052</th>\n",
+ " <td>Arterial Blood Pressure mean</td>\n",
+ " <td>ABPm</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3494</th>\n",
+ " <td>Lowest Heart Rate</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>92.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation \\\n",
+ "itemid \n",
+ "227018 HR_ApacheIV HR_ApacheIV \n",
+ "223765 Orthostatic HR sitting Orthostatic HR sitting \n",
+ "1332 pulse \n",
+ "227581 BiPap bpm (S/T -Back up) BiPap bpm (S/T -Back up) \n",
+ "220047 Heart Rate Alarm - Low HR Alarm - Low \n",
+ "224363 VAD Beat Rate L VAD Beat Rate L \n",
+ "226764 HrApacheIIValue HrApacheIIValue \n",
+ "1341 PULSE \n",
+ "220045 Heart Rate HR \n",
+ "223775 VAD Beat Rate R VAD Beat Rate R \n",
+ "220046 Heart rate Alarm - High HR Alarm - High \n",
+ "224751 Temporary Pacemaker Rate Temp Pacemaker Rate \n",
+ "223764 Orthostatic HR lying Orthostatic HR lying \n",
+ "1725 Pulse \n",
+ "224422 Spont RR Spont RR \n",
+ "224647 Orthostatic HR standing Orthostatic HR standing \n",
+ "211 Heart Rate \n",
+ "220181 Non Invasive Blood Pressure mean NBPm \n",
+ "220052 Arterial Blood Pressure mean ABPm \n",
+ "3494 Lowest Heart Rate \n",
+ "\n",
+ " linksto category unitname score \n",
+ "itemid \n",
+ "227018 chartevents Scores - APACHE IV (2) bpm 110.000000 \n",
+ "223765 chartevents Routine Vital Signs bpm 110.000000 \n",
+ "1332 chartevents 110.000000 \n",
+ "227581 chartevents Respiratory bpm 110.000000 \n",
+ "220047 chartevents Alarms bpm 110.000000 \n",
+ "224363 chartevents Hemodynamics bpm 110.000000 \n",
+ "226764 chartevents Scores - APACHE II bpm 110.000000 \n",
+ "1341 chartevents 110.000000 \n",
+ "220045 chartevents Routine Vital Signs bpm 110.000000 \n",
+ "223775 chartevents Hemodynamics bpm 110.000000 \n",
+ "220046 chartevents Alarms bpm 110.000000 \n",
+ "224751 chartevents Cardiovascular (Pacer Data) bpm 110.000000 \n",
+ "223764 chartevents Routine Vital Signs bpm 110.000000 \n",
+ "1725 chartevents 110.000000 \n",
+ "224422 chartevents Respiratory bpm 110.000000 \n",
+ "224647 chartevents Routine Vital Signs bpm 110.000000 \n",
+ "211 chartevents 110.000000 \n",
+ "220181 chartevents Routine Vital Signs mmHg 100.666667 \n",
+ "220052 chartevents Routine Vital Signs mmHg 100.666667 \n",
+ "3494 chartevents 92.666667 "
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'heart rate',\n",
+ " 'beats',\n",
+ " 'bpm',\n",
+ " 'pulse'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "label = data_dict.labels.HEART_RATE\n",
+ "keep_dict[label] = [211,220045,1341,1725,1332]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Respiratory Rate"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>3603</th>\n",
+ " <td>Resp Rate</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224688</th>\n",
+ " <td>Respiratory Rate (Set)</td>\n",
+ " <td>Respiratory Rate (Set)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226774</th>\n",
+ " <td>RRApacheIIValue</td>\n",
+ " <td>RRApacheIIValue</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>618</th>\n",
+ " <td>Respiratory Rate</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224690</th>\n",
+ " <td>Respiratory Rate (Total)</td>\n",
+ " <td>Respiratory Rate (Total)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223875</th>\n",
+ " <td>Fspn High</td>\n",
+ " <td>Fspn High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224689</th>\n",
+ " <td>Respiratory Rate (spontaneous)</td>\n",
+ " <td>Respiratory Rate (spontaneous)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220210</th>\n",
+ " <td>Respiratory Rate</td>\n",
+ " <td>RR</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224161</th>\n",
+ " <td>Resp Alarm - High</td>\n",
+ " <td>Resp Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227050</th>\n",
+ " <td>RR_ApacheIV</td>\n",
+ " <td>RR_ApacheIV</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224162</th>\n",
+ " <td>Resp Alarm - Low</td>\n",
+ " <td>Resp Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>insp/min</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>619</th>\n",
+ " <td>Respiratory Rate Set</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>102.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225949</th>\n",
+ " <td>NIV Mask</td>\n",
+ " <td>NIV Mask</td>\n",
+ " <td></td>\n",
+ " <td>Respiratory</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223840</th>\n",
+ " <td>ETT Re-taped</td>\n",
+ " <td>ETT Re-taped</td>\n",
+ " <td></td>\n",
+ " <td>Respiratory</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223838</th>\n",
+ " <td>ETT Location</td>\n",
+ " <td>ETT Location</td>\n",
+ " <td></td>\n",
+ " <td>Respiratory</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223837</th>\n",
+ " <td>ETT Size (ID)</td>\n",
+ " <td>ETT Size (ID)</td>\n",
+ " <td></td>\n",
+ " <td>Respiratory</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224373</th>\n",
+ " <td>Sputum Amount</td>\n",
+ " <td>Sputum Amount</td>\n",
+ " <td></td>\n",
+ " <td>Respiratory</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223836</th>\n",
+ " <td>Airway Type</td>\n",
+ " <td>Airway Type</td>\n",
+ " <td></td>\n",
+ " <td>Respiratory</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226815</th>\n",
+ " <td>Airway problems</td>\n",
+ " <td>Airway problems</td>\n",
+ " <td></td>\n",
+ " <td>Respiratory</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223835</th>\n",
+ " <td>Inspired O2 Fraction</td>\n",
+ " <td>FiO2</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>None</td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation \\\n",
+ "itemid \n",
+ "3603 Resp Rate \n",
+ "224688 Respiratory Rate (Set) Respiratory Rate (Set) \n",
+ "226774 RRApacheIIValue RRApacheIIValue \n",
+ "618 Respiratory Rate \n",
+ "224690 Respiratory Rate (Total) Respiratory Rate (Total) \n",
+ "223875 Fspn High Fspn High \n",
+ "224689 Respiratory Rate (spontaneous) Respiratory Rate (spontaneous) \n",
+ "220210 Respiratory Rate RR \n",
+ "224161 Resp Alarm - High Resp Alarm - High \n",
+ "227050 RR_ApacheIV RR_ApacheIV \n",
+ "224162 Resp Alarm - Low Resp Alarm - Low \n",
+ "619 Respiratory Rate Set \n",
+ "225949 NIV Mask NIV Mask \n",
+ "223840 ETT Re-taped ETT Re-taped \n",
+ "223838 ETT Location ETT Location \n",
+ "223837 ETT Size (ID) ETT Size (ID) \n",
+ "224373 Sputum Amount Sputum Amount \n",
+ "223836 Airway Type Airway Type \n",
+ "226815 Airway problems Airway problems \n",
+ "223835 Inspired O2 Fraction FiO2 \n",
+ "\n",
+ " linksto category unitname score \n",
+ "itemid \n",
+ "3603 chartevents 110.000000 \n",
+ "224688 chartevents Respiratory insp/min 110.000000 \n",
+ "226774 chartevents Scores - APACHE II insp/min 110.000000 \n",
+ "618 chartevents 110.000000 \n",
+ "224690 chartevents Respiratory insp/min 110.000000 \n",
+ "223875 chartevents Respiratory insp/min 110.000000 \n",
+ "224689 chartevents Respiratory insp/min 110.000000 \n",
+ "220210 chartevents Respiratory insp/min 110.000000 \n",
+ "224161 chartevents Alarms insp/min 110.000000 \n",
+ "227050 chartevents Scores - APACHE IV (2) insp/min 110.000000 \n",
+ "224162 chartevents Alarms insp/min 110.000000 \n",
+ "619 chartevents 102.666667 \n",
+ "225949 Respiratory 97.333333 \n",
+ "223840 Respiratory 97.333333 \n",
+ "223838 Respiratory 97.333333 \n",
+ "223837 Respiratory 97.333333 \n",
+ "224373 Respiratory 97.333333 \n",
+ "223836 Respiratory 97.333333 \n",
+ "226815 Respiratory 97.333333 \n",
+ "223835 chartevents Respiratory None 97.333333 "
+ ]
+ },
+ "execution_count": 66,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'respiratory rate',\n",
+ " 'resp rate',\n",
+ " 'insp/min',\n",
+ " 'breath/min'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 67,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "label = data_dict.labels.RESPIRATORY_RATE\n",
+ "keep_dict[label] = [220210,3603,618,8113,615,219]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Blood Pressure"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 68,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>224315</th>\n",
+ " <td>ABI Brachial BP L</td>\n",
+ " <td>ABI Brachial BP L</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227537</th>\n",
+ " <td>ART Blood Pressure Alarm - High</td>\n",
+ " <td>ART BP Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220181</th>\n",
+ " <td>Non Invasive Blood Pressure mean</td>\n",
+ " <td>NBPm</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220180</th>\n",
+ " <td>Non Invasive Blood Pressure diastolic</td>\n",
+ " <td>NBPd</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220179</th>\n",
+ " <td>Non Invasive Blood Pressure systolic</td>\n",
+ " <td>NBPs</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220074</th>\n",
+ " <td>Central Venous Pressure</td>\n",
+ " <td>CVP</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220073</th>\n",
+ " <td>Central Venous Pressure Alarm - Low</td>\n",
+ " <td>CVP Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220072</th>\n",
+ " <td>Central Venous Pressure Alarm - High</td>\n",
+ " <td>CVP Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220069</th>\n",
+ " <td>Left Artrial Pressure</td>\n",
+ " <td>LAP</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220066</th>\n",
+ " <td>Pulmonary Artery Pressure Alarm - Low</td>\n",
+ " <td>PAP Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220063</th>\n",
+ " <td>Pulmonary Artery Pressure Alarm - High</td>\n",
+ " <td>PAP Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220061</th>\n",
+ " <td>Pulmonary Artery Pressure mean</td>\n",
+ " <td>PAPm</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220060</th>\n",
+ " <td>Pulmonary Artery Pressure diastolic</td>\n",
+ " <td>PAPd</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220059</th>\n",
+ " <td>Pulmonary Artery Pressure systolic</td>\n",
+ " <td>PAPs</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220058</th>\n",
+ " <td>Arterial Blood Pressure Alarm - High</td>\n",
+ " <td>ABP Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227538</th>\n",
+ " <td>ART Blood Pressure Alarm - Low</td>\n",
+ " <td>ART BP Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226096</th>\n",
+ " <td>Orthostatic BPd standing</td>\n",
+ " <td>Orthostatic BPd standing</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224152</th>\n",
+ " <td>Return Pressure</td>\n",
+ " <td>Return Pressure</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Dialysis</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227066</th>\n",
+ " <td>Cerebral Perfusion Pressure</td>\n",
+ " <td>CPP</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226062</th>\n",
+ " <td>Venous CO2 Pressure</td>\n",
+ " <td>PCO2 (Venous)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation \\\n",
+ "itemid \n",
+ "224315 ABI Brachial BP L ABI Brachial BP L \n",
+ "227537 ART Blood Pressure Alarm - High ART BP Alarm - High \n",
+ "220181 Non Invasive Blood Pressure mean NBPm \n",
+ "220180 Non Invasive Blood Pressure diastolic NBPd \n",
+ "220179 Non Invasive Blood Pressure systolic NBPs \n",
+ "220074 Central Venous Pressure CVP \n",
+ "220073 Central Venous Pressure Alarm - Low CVP Alarm - Low \n",
+ "220072 Central Venous Pressure Alarm - High CVP Alarm - High \n",
+ "220069 Left Artrial Pressure LAP \n",
+ "220066 Pulmonary Artery Pressure Alarm - Low PAP Alarm - Low \n",
+ "220063 Pulmonary Artery Pressure Alarm - High PAP Alarm - High \n",
+ "220061 Pulmonary Artery Pressure mean PAPm \n",
+ "220060 Pulmonary Artery Pressure diastolic PAPd \n",
+ "220059 Pulmonary Artery Pressure systolic PAPs \n",
+ "220058 Arterial Blood Pressure Alarm - High ABP Alarm - High \n",
+ "227538 ART Blood Pressure Alarm - Low ART BP Alarm - Low \n",
+ "226096 Orthostatic BPd standing Orthostatic BPd standing \n",
+ "224152 Return Pressure Return Pressure \n",
+ "227066 Cerebral Perfusion Pressure CPP \n",
+ "226062 Venous CO2 Pressure PCO2 (Venous) \n",
+ "\n",
+ " linksto category unitname score \n",
+ "itemid \n",
+ "224315 chartevents IABP mmHg 110.0 \n",
+ "227537 chartevents Alarms mmHg 110.0 \n",
+ "220181 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "220180 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "220179 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "220074 chartevents Hemodynamics mmHg 110.0 \n",
+ "220073 chartevents Alarms mmHg 110.0 \n",
+ "220072 chartevents Alarms mmHg 110.0 \n",
+ "220069 chartevents Hemodynamics mmHg 110.0 \n",
+ "220066 chartevents Alarms mmHg 110.0 \n",
+ "220063 chartevents Alarms mmHg 110.0 \n",
+ "220061 chartevents Hemodynamics mmHg 110.0 \n",
+ "220060 chartevents Hemodynamics mmHg 110.0 \n",
+ "220059 chartevents Hemodynamics mmHg 110.0 \n",
+ "220058 chartevents Alarms mmHg 110.0 \n",
+ "227538 chartevents Alarms mmHg 110.0 \n",
+ "226096 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "224152 chartevents Dialysis mmHg 110.0 \n",
+ "227066 chartevents Hemodynamics mmHg 110.0 \n",
+ "226062 chartevents Labs mmHg 110.0 "
+ ]
+ },
+ "execution_count": 68,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'blood pressure',\n",
+ " 'systolic',\n",
+ " 'diastolic',\n",
+ " 'mmHg'\n",
+ " ])\n",
+ "out_df.iloc[0:20]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 69,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>226063</th>\n",
+ " <td>Venous O2 Pressure</td>\n",
+ " <td>PO2 (Venous)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225312</th>\n",
+ " <td>ART BP mean</td>\n",
+ " <td>ART BP mean</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225310</th>\n",
+ " <td>ART BP Diastolic</td>\n",
+ " <td>ART BP Diastolic</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225309</th>\n",
+ " <td>ART BP Systolic</td>\n",
+ " <td>ART BP Systolic</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223751</th>\n",
+ " <td>Non-Invasive Blood Pressure Alarm - High</td>\n",
+ " <td>NBP Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227516</th>\n",
+ " <td>PO2 (Mixed Venous)</td>\n",
+ " <td>PO2 (Mixed Venous)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224166</th>\n",
+ " <td>Doppler BP</td>\n",
+ " <td>Doppler BP</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224167</th>\n",
+ " <td>Manual Blood Pressure Systolic Left</td>\n",
+ " <td>Manual BPs L</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226737</th>\n",
+ " <td>AaDO2ApacheIIValue</td>\n",
+ " <td>AaDO2ApacheIIValue</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228148</th>\n",
+ " <td>ABI Ankle BP R (Impella)</td>\n",
+ " <td>ABI Ankle BP R (Impella)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Impella</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220224</th>\n",
+ " <td>Arterial O2 pressure</td>\n",
+ " <td>PO2 (Arterial)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220235</th>\n",
+ " <td>Arterial CO2 Pressure</td>\n",
+ " <td>PCO2 (Arterial)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223752</th>\n",
+ " <td>Non-Invasive Blood Pressure Alarm - Low</td>\n",
+ " <td>NBP Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223763</th>\n",
+ " <td>Bladder Pressure</td>\n",
+ " <td>Bladder Pressure</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224150</th>\n",
+ " <td>Filter Pressure</td>\n",
+ " <td>Filter Pressure</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Dialysis</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224149</th>\n",
+ " <td>Access Pressure</td>\n",
+ " <td>Access Pressure</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Dialysis</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227991</th>\n",
+ " <td>Intra Cranial Pressure #2 Alarm - Low</td>\n",
+ " <td>IC2 Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226094</th>\n",
+ " <td>Orthostatic BPd sitting</td>\n",
+ " <td>Orthostatic BPd sitting</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226092</th>\n",
+ " <td>Orthostatic BPd lying</td>\n",
+ " <td>Orthostatic BPd lying</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227990</th>\n",
+ " <td>Intra Cranial Pressure #2 Alarm - High</td>\n",
+ " <td>IC2 Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation \\\n",
+ "itemid \n",
+ "226063 Venous O2 Pressure PO2 (Venous) \n",
+ "225312 ART BP mean ART BP mean \n",
+ "225310 ART BP Diastolic ART BP Diastolic \n",
+ "225309 ART BP Systolic ART BP Systolic \n",
+ "223751 Non-Invasive Blood Pressure Alarm - High NBP Alarm - High \n",
+ "227516 PO2 (Mixed Venous) PO2 (Mixed Venous) \n",
+ "224166 Doppler BP Doppler BP \n",
+ "224167 Manual Blood Pressure Systolic Left Manual BPs L \n",
+ "226737 AaDO2ApacheIIValue AaDO2ApacheIIValue \n",
+ "228148 ABI Ankle BP R (Impella) ABI Ankle BP R (Impella) \n",
+ "220224 Arterial O2 pressure PO2 (Arterial) \n",
+ "220235 Arterial CO2 Pressure PCO2 (Arterial) \n",
+ "223752 Non-Invasive Blood Pressure Alarm - Low NBP Alarm - Low \n",
+ "223763 Bladder Pressure Bladder Pressure \n",
+ "224150 Filter Pressure Filter Pressure \n",
+ "224149 Access Pressure Access Pressure \n",
+ "227991 Intra Cranial Pressure #2 Alarm - Low IC2 Alarm - Low \n",
+ "226094 Orthostatic BPd sitting Orthostatic BPd sitting \n",
+ "226092 Orthostatic BPd lying Orthostatic BPd lying \n",
+ "227990 Intra Cranial Pressure #2 Alarm - High IC2 Alarm - High \n",
+ "\n",
+ " linksto category unitname score \n",
+ "itemid \n",
+ "226063 chartevents Labs mmHg 110.0 \n",
+ "225312 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "225310 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "225309 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "223751 chartevents Alarms mmHg 110.0 \n",
+ "227516 chartevents Labs mmHg 110.0 \n",
+ "224166 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "224167 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "226737 chartevents Scores - APACHE II mmHg 110.0 \n",
+ "228148 chartevents Impella mmHg 110.0 \n",
+ "220224 chartevents Labs mmHg 110.0 \n",
+ "220235 chartevents Labs mmHg 110.0 \n",
+ "223752 chartevents Alarms mmHg 110.0 \n",
+ "223763 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "224150 chartevents Dialysis mmHg 110.0 \n",
+ "224149 chartevents Dialysis mmHg 110.0 \n",
+ "227991 chartevents Alarms mmHg 110.0 \n",
+ "226094 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "226092 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "227990 chartevents Alarms mmHg 110.0 "
+ ]
+ },
+ "execution_count": 69,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC] = [220179]\n",
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_DIASTOLIC] = [220180]\n",
+ "out_df.iloc[20:40]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 70,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>227989</th>\n",
+ " <td>Intra Cranial Pressure #2</td>\n",
+ " <td>IC2</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220056</th>\n",
+ " <td>Arterial Blood Pressure Alarm - Low</td>\n",
+ " <td>ABP Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220052</th>\n",
+ " <td>Arterial Blood Pressure mean</td>\n",
+ " <td>ABPm</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220051</th>\n",
+ " <td>Arterial Blood Pressure diastolic</td>\n",
+ " <td>ABPd</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220050</th>\n",
+ " <td>Arterial Blood Pressure systolic</td>\n",
+ " <td>ABPs</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228145</th>\n",
+ " <td>ABI Ankle BP L</td>\n",
+ " <td>ABI Ankle BP L</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228146</th>\n",
+ " <td>ABI Brachial BP R</td>\n",
+ " <td>ABI Brachial BP R</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227039</th>\n",
+ " <td>PO2_ApacheIV</td>\n",
+ " <td>PO2_ApacheIV</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220765</th>\n",
+ " <td>Intra Cranial Pressure</td>\n",
+ " <td>ICP</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227023</th>\n",
+ " <td>MAP_ApacheIV</td>\n",
+ " <td>MAP_ApacheIV</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224309</th>\n",
+ " <td>Assisted Systole</td>\n",
+ " <td>SYS - Assisted</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224310</th>\n",
+ " <td>Augmented Diastole</td>\n",
+ " <td>AUG</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224311</th>\n",
+ " <td>BAEDP</td>\n",
+ " <td>DIA - Assisted</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224314</th>\n",
+ " <td>ABI Brachial BP R (Impella)</td>\n",
+ " <td>ABI Brachial BP R (Impella)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Impella</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224317</th>\n",
+ " <td>ABI Ankle BP R</td>\n",
+ " <td>ABI Ankle BP R</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224318</th>\n",
+ " <td>ABI Ankle BP L (Impella)</td>\n",
+ " <td>ABI Ankle BP L (Impella)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Impella</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224322</th>\n",
+ " <td>IABP Mean</td>\n",
+ " <td>MAP - Assisted</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223771</th>\n",
+ " <td>PCWP</td>\n",
+ " <td>PCWP</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223768</th>\n",
+ " <td>Intra Cranial Pressure Alarm - Low</td>\n",
+ " <td>ICP Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223767</th>\n",
+ " <td>Intra Cranial Pressure Alarm - High</td>\n",
+ " <td>ICP Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation \\\n",
+ "itemid \n",
+ "227989 Intra Cranial Pressure #2 IC2 \n",
+ "220056 Arterial Blood Pressure Alarm - Low ABP Alarm - Low \n",
+ "220052 Arterial Blood Pressure mean ABPm \n",
+ "220051 Arterial Blood Pressure diastolic ABPd \n",
+ "220050 Arterial Blood Pressure systolic ABPs \n",
+ "228145 ABI Ankle BP L ABI Ankle BP L \n",
+ "228146 ABI Brachial BP R ABI Brachial BP R \n",
+ "227039 PO2_ApacheIV PO2_ApacheIV \n",
+ "220765 Intra Cranial Pressure ICP \n",
+ "227023 MAP_ApacheIV MAP_ApacheIV \n",
+ "224309 Assisted Systole SYS - Assisted \n",
+ "224310 Augmented Diastole AUG \n",
+ "224311 BAEDP DIA - Assisted \n",
+ "224314 ABI Brachial BP R (Impella) ABI Brachial BP R (Impella) \n",
+ "224317 ABI Ankle BP R ABI Ankle BP R \n",
+ "224318 ABI Ankle BP L (Impella) ABI Ankle BP L (Impella) \n",
+ "224322 IABP Mean MAP - Assisted \n",
+ "223771 PCWP PCWP \n",
+ "223768 Intra Cranial Pressure Alarm - Low ICP Alarm - Low \n",
+ "223767 Intra Cranial Pressure Alarm - High ICP Alarm - High \n",
+ "\n",
+ " linksto category unitname score \n",
+ "itemid \n",
+ "227989 chartevents Hemodynamics mmHg 110.0 \n",
+ "220056 chartevents Alarms mmHg 110.0 \n",
+ "220052 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "220051 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "220050 chartevents Routine Vital Signs mmHg 110.0 \n",
+ "228145 chartevents IABP mmHg 110.0 \n",
+ "228146 chartevents IABP mmHg 110.0 \n",
+ "227039 chartevents Scores - APACHE IV (2) mmHg 110.0 \n",
+ "220765 chartevents Hemodynamics mmHg 110.0 \n",
+ "227023 chartevents Scores - APACHE IV (2) mmHg 110.0 \n",
+ "224309 chartevents IABP mmHg 110.0 \n",
+ "224310 chartevents IABP mmHg 110.0 \n",
+ "224311 chartevents IABP mmHg 110.0 \n",
+ "224314 chartevents Impella mmHg 110.0 \n",
+ "224317 chartevents IABP mmHg 110.0 \n",
+ "224318 chartevents Impella mmHg 110.0 \n",
+ "224322 chartevents IABP mmHg 110.0 \n",
+ "223771 chartevents Hemodynamics mmHg 110.0 \n",
+ "223768 chartevents Alarms mmHg 110.0 \n",
+ "223767 chartevents Alarms mmHg 110.0 "
+ ]
+ },
+ "execution_count": 70,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC] += [225309,224167]\n",
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_DIASTOLIC] += [225310,224643]\n",
+ "out_df.iloc[40:60]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 71,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>223766</th>\n",
+ " <td>Orthostatic BPs standing</td>\n",
+ " <td>Orthostatic BPs standing</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228149</th>\n",
+ " <td>ABI Brachial BP L (Impella)</td>\n",
+ " <td>ABI Brachial BP L (Impella)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Impella</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224151</th>\n",
+ " <td>Effluent Pressure</td>\n",
+ " <td>Effluent Pressure</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Dialysis</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224643</th>\n",
+ " <td>Manual Blood Pressure Diastolic Left</td>\n",
+ " <td>Manual BPd L</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224654</th>\n",
+ " <td>PAEDP</td>\n",
+ " <td>DIA - Unassisted</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226855</th>\n",
+ " <td>PCWP (mean) (PA Line)</td>\n",
+ " <td>PCWP (mean) (PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226857</th>\n",
+ " <td>PA mean pressure (PA Line)</td>\n",
+ " <td>PA mean pressure (PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224646</th>\n",
+ " <td>Orthostatic BPs sitting</td>\n",
+ " <td>Orthostatic BPs sitting</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227716</th>\n",
+ " <td>Cerebral Perfusion Pressure Alarm - High</td>\n",
+ " <td>CPP Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227717</th>\n",
+ " <td>Cerebral Perfusion Pressure Alarm - Low</td>\n",
+ " <td>CPP Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224645</th>\n",
+ " <td>Orthostatic BPs lying</td>\n",
+ " <td>Orthostatic BPs lying</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227242</th>\n",
+ " <td>Manual Blood Pressure Diastolic Right</td>\n",
+ " <td>Manual BPd R</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226766</th>\n",
+ " <td>MapApacheIIValue</td>\n",
+ " <td>MapApacheIIValue</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227243</th>\n",
+ " <td>Manual Blood Pressure Systolic Right</td>\n",
+ " <td>Manual BPs R</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226853</th>\n",
+ " <td>PA diastolic pressure(PA Line)</td>\n",
+ " <td>PA diastolic pressure(PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226849</th>\n",
+ " <td>RA (mean) pressure (PA Line)</td>\n",
+ " <td>RA (mean) pressure (PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226850</th>\n",
+ " <td>RV systolic pressure(PA Line)</td>\n",
+ " <td>RV systolic pressure(PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226851</th>\n",
+ " <td>RV diastolic pressure(PA Line)</td>\n",
+ " <td>RV diastolic pressure(PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224659</th>\n",
+ " <td>Vacuum Assist</td>\n",
+ " <td>Vacuum Assist</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226854</th>\n",
+ " <td>PCWP (v wave) (PA Line)</td>\n",
+ " <td>PCWP (v wave) (PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label \\\n",
+ "itemid \n",
+ "223766 Orthostatic BPs standing \n",
+ "228149 ABI Brachial BP L (Impella) \n",
+ "224151 Effluent Pressure \n",
+ "224643 Manual Blood Pressure Diastolic Left \n",
+ "224654 PAEDP \n",
+ "226855 PCWP (mean) (PA Line) \n",
+ "226857 PA mean pressure (PA Line) \n",
+ "224646 Orthostatic BPs sitting \n",
+ "227716 Cerebral Perfusion Pressure Alarm - High \n",
+ "227717 Cerebral Perfusion Pressure Alarm - Low \n",
+ "224645 Orthostatic BPs lying \n",
+ "227242 Manual Blood Pressure Diastolic Right \n",
+ "226766 MapApacheIIValue \n",
+ "227243 Manual Blood Pressure Systolic Right \n",
+ "226853 PA diastolic pressure(PA Line) \n",
+ "226849 RA (mean) pressure (PA Line) \n",
+ "226850 RV systolic pressure(PA Line) \n",
+ "226851 RV diastolic pressure(PA Line) \n",
+ "224659 Vacuum Assist \n",
+ "226854 PCWP (v wave) (PA Line) \n",
+ "\n",
+ " abbreviation linksto category \\\n",
+ "itemid \n",
+ "223766 Orthostatic BPs standing chartevents Routine Vital Signs \n",
+ "228149 ABI Brachial BP L (Impella) chartevents Impella \n",
+ "224151 Effluent Pressure chartevents Dialysis \n",
+ "224643 Manual BPd L chartevents Routine Vital Signs \n",
+ "224654 DIA - Unassisted chartevents IABP \n",
+ "226855 PCWP (mean) (PA Line) chartevents PA Line Insertion \n",
+ "226857 PA mean pressure (PA Line) chartevents PA Line Insertion \n",
+ "224646 Orthostatic BPs sitting chartevents Routine Vital Signs \n",
+ "227716 CPP Alarm - High chartevents Alarms \n",
+ "227717 CPP Alarm - Low chartevents Alarms \n",
+ "224645 Orthostatic BPs lying chartevents Routine Vital Signs \n",
+ "227242 Manual BPd R chartevents Routine Vital Signs \n",
+ "226766 MapApacheIIValue chartevents Scores - APACHE II \n",
+ "227243 Manual BPs R chartevents Routine Vital Signs \n",
+ "226853 PA diastolic pressure(PA Line) chartevents PA Line Insertion \n",
+ "226849 RA (mean) pressure (PA Line) chartevents PA Line Insertion \n",
+ "226850 RV systolic pressure(PA Line) chartevents PA Line Insertion \n",
+ "226851 RV diastolic pressure(PA Line) chartevents PA Line Insertion \n",
+ "224659 Vacuum Assist chartevents Hemodynamics \n",
+ "226854 PCWP (v wave) (PA Line) chartevents PA Line Insertion \n",
+ "\n",
+ " unitname score \n",
+ "itemid \n",
+ "223766 mmHg 110.0 \n",
+ "228149 mmHg 110.0 \n",
+ "224151 mmHg 110.0 \n",
+ "224643 mmHg 110.0 \n",
+ "224654 mmHg 110.0 \n",
+ "226855 mmHg 110.0 \n",
+ "226857 mmHg 110.0 \n",
+ "224646 mmHg 110.0 \n",
+ "227716 mmHg 110.0 \n",
+ "227717 mmHg 110.0 \n",
+ "224645 mmHg 110.0 \n",
+ "227242 mmHg 110.0 \n",
+ "226766 mmHg 110.0 \n",
+ "227243 mmHg 110.0 \n",
+ "226853 mmHg 110.0 \n",
+ "226849 mmHg 110.0 \n",
+ "226850 mmHg 110.0 \n",
+ "226851 mmHg 110.0 \n",
+ "224659 mmHg 110.0 \n",
+ "226854 mmHg 110.0 "
+ ]
+ },
+ "execution_count": 71,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC] += [220050]\n",
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_DIASTOLIC] += [220051]\n",
+ "out_df.iloc[60:80]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 72,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>228158</th>\n",
+ " <td>Purge Pressure</td>\n",
+ " <td>Purge Pressure</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Impella</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226852</th>\n",
+ " <td>PA systolic pressure(PA Line)</td>\n",
+ " <td>PA systolic pressure(PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224652</th>\n",
+ " <td>Unassisted Systole</td>\n",
+ " <td>SYS - Unassisted</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>IABP</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7643</th>\n",
+ " <td>RVSYSTOLIC</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>102.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8441</th>\n",
+ " <td>NBP [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8364</th>\n",
+ " <td>ABP [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8448</th>\n",
+ " <td>PAP [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>455</th>\n",
+ " <td>NBP [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>94.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>ABP [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>94.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>492</th>\n",
+ " <td>PAP [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>94.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8508</th>\n",
+ " <td>BP UAC [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>89.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8505</th>\n",
+ " <td>BP PAL [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>89.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3319</th>\n",
+ " <td>BP PAL [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3325</th>\n",
+ " <td>BP UAC [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8502</th>\n",
+ " <td>BP Cuff [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>87.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3313</th>\n",
+ " <td>BP Cuff [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>86.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>153</th>\n",
+ " <td>Diastolic Unloading</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>86.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227539</th>\n",
+ " <td>ART Blood Pressure Alarm Source</td>\n",
+ " <td>ART BP Alarm Source</td>\n",
+ " <td></td>\n",
+ " <td>Alarms</td>\n",
+ " <td></td>\n",
+ " <td>84.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8440</th>\n",
+ " <td>Manual BP [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>666</th>\n",
+ " <td>Systolic Unloading</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation \\\n",
+ "itemid \n",
+ "228158 Purge Pressure Purge Pressure \n",
+ "226852 PA systolic pressure(PA Line) PA systolic pressure(PA Line) \n",
+ "224652 Unassisted Systole SYS - Unassisted \n",
+ "7643 RVSYSTOLIC \n",
+ "8441 NBP [Diastolic] \n",
+ "8364 ABP [Diastolic] \n",
+ "8448 PAP [Diastolic] \n",
+ "455 NBP [Systolic] \n",
+ "6 ABP [Systolic] \n",
+ "492 PAP [Systolic] \n",
+ "8508 BP UAC [Diastolic] \n",
+ "8505 BP PAL [Diastolic] \n",
+ "3319 BP PAL [Systolic] \n",
+ "3325 BP UAC [Systolic] \n",
+ "8502 BP Cuff [Diastolic] \n",
+ "3313 BP Cuff [Systolic] \n",
+ "153 Diastolic Unloading \n",
+ "227539 ART Blood Pressure Alarm Source ART BP Alarm Source \n",
+ "8440 Manual BP [Diastolic] \n",
+ "666 Systolic Unloading \n",
+ "\n",
+ " linksto category unitname score \n",
+ "itemid \n",
+ "228158 chartevents Impella mmHg 110.000000 \n",
+ "226852 chartevents PA Line Insertion mmHg 110.000000 \n",
+ "224652 chartevents IABP mmHg 110.000000 \n",
+ "7643 chartevents 102.666667 \n",
+ "8441 chartevents 95.666667 \n",
+ "8364 chartevents 95.666667 \n",
+ "8448 chartevents 95.666667 \n",
+ "455 chartevents 94.333333 \n",
+ "6 chartevents 94.333333 \n",
+ "492 chartevents 94.333333 \n",
+ "8508 chartevents 89.666667 \n",
+ "8505 chartevents 89.666667 \n",
+ "3319 chartevents 88.000000 \n",
+ "3325 chartevents 88.000000 \n",
+ "8502 chartevents 87.666667 \n",
+ "3313 chartevents 86.333333 \n",
+ "153 chartevents 86.000000 \n",
+ "227539 Alarms 84.666667 \n",
+ "8440 chartevents 84.666667 \n",
+ "666 chartevents 84.666667 "
+ ]
+ },
+ "execution_count": 72,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC] += [227243]\n",
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_DIASTOLIC] += [227242]\n",
+ "out_df.iloc[80:100]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 73,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>6417</th>\n",
+ " <td>low pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7133</th>\n",
+ " <td>abd pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6944</th>\n",
+ " <td>LOW PRESSURE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2027</th>\n",
+ " <td>Low pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6107</th>\n",
+ " <td>Low Pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>442</th>\n",
+ " <td>Manual BP [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>83.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8503</th>\n",
+ " <td>BP Left Arm [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>82.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8504</th>\n",
+ " <td>BP Left Leg [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>82.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8368</th>\n",
+ " <td>Arterial BP [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>82.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8506</th>\n",
+ " <td>BP Right Arm [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8507</th>\n",
+ " <td>BP Right Leg [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51</th>\n",
+ " <td>Arterial BP [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>80.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3315</th>\n",
+ " <td>BP Left Arm [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>80.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3317</th>\n",
+ " <td>BP Left Leg [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>80.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3321</th>\n",
+ " <td>BP Right Arm [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>79.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3323</th>\n",
+ " <td>BP Right Leg [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>79.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8555</th>\n",
+ " <td>Arterial BP #2 [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>79.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>29</th>\n",
+ " <td>Access mmHg</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44560</th>\n",
+ " <td>blood</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>70015</th>\n",
+ " <td>BLOOD</td>\n",
+ " <td></td>\n",
+ " <td>microbiologyevents</td>\n",
+ " <td>SPECIMEN</td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto category \\\n",
+ "itemid \n",
+ "6417 low pressure chartevents \n",
+ "7133 abd pressure chartevents \n",
+ "6944 LOW PRESSURE chartevents \n",
+ "2027 Low pressure chartevents \n",
+ "6107 Low Pressure chartevents \n",
+ "442 Manual BP [Systolic] chartevents \n",
+ "8503 BP Left Arm [Diastolic] chartevents \n",
+ "8504 BP Left Leg [Diastolic] chartevents \n",
+ "8368 Arterial BP [Diastolic] chartevents \n",
+ "8506 BP Right Arm [Diastolic] chartevents \n",
+ "8507 BP Right Leg [Diastolic] chartevents \n",
+ "51 Arterial BP [Systolic] chartevents \n",
+ "3315 BP Left Arm [Systolic] chartevents \n",
+ "3317 BP Left Leg [Systolic] chartevents \n",
+ "3321 BP Right Arm [Systolic] chartevents \n",
+ "3323 BP Right Leg [Systolic] chartevents \n",
+ "8555 Arterial BP #2 [Diastolic] chartevents \n",
+ "29 Access mmHg chartevents \n",
+ "44560 blood inputevents_cv \n",
+ "70015 BLOOD microbiologyevents SPECIMEN \n",
+ "\n",
+ " unitname score \n",
+ "itemid \n",
+ "6417 84.333333 \n",
+ "7133 84.333333 \n",
+ "6944 84.333333 \n",
+ "2027 84.333333 \n",
+ "6107 84.333333 \n",
+ "442 83.000000 \n",
+ "8503 82.000000 \n",
+ "8504 82.000000 \n",
+ "8368 82.000000 \n",
+ "8506 81.000000 \n",
+ "8507 81.000000 \n",
+ "51 80.000000 \n",
+ "3315 80.000000 \n",
+ "3317 80.000000 \n",
+ "3321 79.000000 \n",
+ "3323 79.000000 \n",
+ "8555 79.000000 \n",
+ "29 78.666667 \n",
+ "44560 78.666667 \n",
+ "70015 78.666667 "
+ ]
+ },
+ "execution_count": 73,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC] += [455,6]\n",
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_DIASTOLIC] += [8441,8364]\n",
+ "out_df.iloc[100:120]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 74,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>51466</th>\n",
+ " <td>BLOOD</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6127</th>\n",
+ " <td>LO Press</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46780</th>\n",
+ " <td>Bladdar pressure</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>77.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1404</th>\n",
+ " <td>Bladder pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>77.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>993</th>\n",
+ " <td>bladder pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>77.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6701</th>\n",
+ " <td>Arterial BP #2 [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>77.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1411</th>\n",
+ " <td>Bladder Pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>77.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>996</th>\n",
+ " <td>BLADDER PRESSURE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>77.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44862</th>\n",
+ " <td>BLADDER PRESSURE</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>77.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>770</th>\n",
+ " <td>AST</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Enzymes</td>\n",
+ " <td></td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220587</th>\n",
+ " <td>AST</td>\n",
+ " <td>AST</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>None</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2347</th>\n",
+ " <td>BLADDER PRESSURE.</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>76.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6631</th>\n",
+ " <td>pressure low</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>75.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3108</th>\n",
+ " <td>PA PRESSURE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>75.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7504</th>\n",
+ " <td>Driv pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>75.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2779</th>\n",
+ " <td>bladder pressures</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>75.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43763</th>\n",
+ " <td>Bladder presure</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>74.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1509</th>\n",
+ " <td>bld pres</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>73.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6540</th>\n",
+ " <td>IntraABd pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>73.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8444</th>\n",
+ " <td>Orthostat BP sitting [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>73.333333</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "51466 BLOOD NaN labevents \n",
+ "6127 LO Press chartevents \n",
+ "46780 Bladdar pressure inputevents_cv \n",
+ "1404 Bladder pressure chartevents \n",
+ "993 bladder pressure chartevents \n",
+ "6701 Arterial BP #2 [Systolic] chartevents \n",
+ "1411 Bladder Pressure chartevents \n",
+ "996 BLADDER PRESSURE chartevents \n",
+ "44862 BLADDER PRESSURE inputevents_cv \n",
+ "770 AST chartevents \n",
+ "220587 AST AST chartevents \n",
+ "2347 BLADDER PRESSURE. chartevents \n",
+ "6631 pressure low chartevents \n",
+ "3108 PA PRESSURE chartevents \n",
+ "7504 Driv pressure chartevents \n",
+ "2779 bladder pressures chartevents \n",
+ "43763 Bladder presure inputevents_cv \n",
+ "1509 bld pres chartevents \n",
+ "6540 IntraABd pressure chartevents \n",
+ "8444 Orthostat BP sitting [Diastolic] chartevents \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "51466 HEMATOLOGY NaN 78.666667 \n",
+ "6127 78.000000 \n",
+ "46780 77.000000 \n",
+ "1404 77.000000 \n",
+ "993 77.000000 \n",
+ "6701 77.000000 \n",
+ "1411 77.000000 \n",
+ "996 77.000000 \n",
+ "44862 Free Form Intake 77.000000 \n",
+ "770 Enzymes 76.666667 \n",
+ "220587 Labs None 76.666667 \n",
+ "2347 76.000000 \n",
+ "6631 75.666667 \n",
+ "3108 75.333333 \n",
+ "7504 75.000000 \n",
+ "2779 75.000000 \n",
+ "43763 74.333333 \n",
+ "1509 73.666667 \n",
+ "6540 73.666667 \n",
+ "8444 73.333333 "
+ ]
+ },
+ "execution_count": 74,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC] += [3313]\n",
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_DIASTOLIC] += [8502,8440]\n",
+ "out_df.iloc[120:140]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 75,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>8446</th>\n",
+ " <td>Orthostatic BP lying [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>73.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8445</th>\n",
+ " <td>OrthostatBP standing [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>73.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6302</th>\n",
+ " <td>low press</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>72.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2562</th>\n",
+ " <td>INTRA ABD PRESSURE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>72.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45682</th>\n",
+ " <td>bladder pressure in</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>72.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7124</th>\n",
+ " <td>Low pressure Alarm</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>72.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43744</th>\n",
+ " <td>NS bladder pressure</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>72.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228151</th>\n",
+ " <td>Aortic Pressure Signal - Diastolic</td>\n",
+ " <td>Aortic Pressure Signal - Diastolic</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Impella</td>\n",
+ " <td>None</td>\n",
+ " <td>72.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42735</th>\n",
+ " <td>Intra-abd. Pressure</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>71.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>484</th>\n",
+ " <td>Orthostatic BP lying [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>482</th>\n",
+ " <td>OrthostatBP standing [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>480</th>\n",
+ " <td>Orthostat BP sitting [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44344</th>\n",
+ " <td>BLADDER PRESSURE FLD</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>71.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44187</th>\n",
+ " <td>Blood emesis</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>71.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3238</th>\n",
+ " <td>CSF PRESSURE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>71.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2965</th>\n",
+ " <td>INTRAABDOM. PRESSURE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>70.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228152</th>\n",
+ " <td>Aortic Pressure Signal - Systolic</td>\n",
+ " <td>Aortic Pressure Signal - Systolic</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Impella</td>\n",
+ " <td>None</td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50934</th>\n",
+ " <td>H</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>CHEMISTRY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7574</th>\n",
+ " <td>lumbar pressure</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>69.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2704</th>\n",
+ " <td>ABDOMINAL PRESSURE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>69.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label \\\n",
+ "itemid \n",
+ "8446 Orthostatic BP lying [Diastolic] \n",
+ "8445 OrthostatBP standing [Diastolic] \n",
+ "6302 low press \n",
+ "2562 INTRA ABD PRESSURE \n",
+ "45682 bladder pressure in \n",
+ "7124 Low pressure Alarm \n",
+ "43744 NS bladder pressure \n",
+ "228151 Aortic Pressure Signal - Diastolic \n",
+ "42735 Intra-abd. Pressure \n",
+ "484 Orthostatic BP lying [Systolic] \n",
+ "482 OrthostatBP standing [Systolic] \n",
+ "480 Orthostat BP sitting [Systolic] \n",
+ "44344 BLADDER PRESSURE FLD \n",
+ "44187 Blood emesis \n",
+ "3238 CSF PRESSURE \n",
+ "2965 INTRAABDOM. PRESSURE \n",
+ "228152 Aortic Pressure Signal - Systolic \n",
+ "50934 H \n",
+ "7574 lumbar pressure \n",
+ "2704 ABDOMINAL PRESSURE \n",
+ "\n",
+ " abbreviation linksto category \\\n",
+ "itemid \n",
+ "8446 chartevents \n",
+ "8445 chartevents \n",
+ "6302 chartevents \n",
+ "2562 chartevents \n",
+ "45682 inputevents_cv Free Form Intake \n",
+ "7124 chartevents \n",
+ "43744 inputevents_cv Free Form Intake \n",
+ "228151 Aortic Pressure Signal - Diastolic chartevents Impella \n",
+ "42735 inputevents_cv Free Form Intake \n",
+ "484 chartevents \n",
+ "482 chartevents \n",
+ "480 chartevents \n",
+ "44344 inputevents_cv Free Form Intake \n",
+ "44187 outputevents Free Form Intake \n",
+ "3238 chartevents \n",
+ "2965 chartevents \n",
+ "228152 Aortic Pressure Signal - Systolic chartevents Impella \n",
+ "50934 NaN labevents CHEMISTRY \n",
+ "7574 chartevents \n",
+ "2704 chartevents \n",
+ "\n",
+ " unitname score \n",
+ "itemid \n",
+ "8446 73.333333 \n",
+ "8445 73.333333 \n",
+ "6302 72.666667 \n",
+ "2562 72.333333 \n",
+ "45682 72.333333 \n",
+ "7124 72.333333 \n",
+ "43744 72.333333 \n",
+ "228151 None 72.000000 \n",
+ "42735 71.666667 \n",
+ "484 71.333333 \n",
+ "482 71.333333 \n",
+ "480 71.333333 \n",
+ "44344 71.000000 \n",
+ "44187 71.000000 \n",
+ "3238 71.000000 \n",
+ "2965 70.333333 \n",
+ "228152 None 70.000000 \n",
+ "50934 NaN 70.000000 \n",
+ "7574 69.666667 \n",
+ "2704 69.666667 "
+ ]
+ },
+ "execution_count": 75,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC] += [442,3315,51,3317]\n",
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_DIASTOLIC] += [8368,8503,8504,8507,8506]\n",
+ "out_df.iloc[140:160]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 76,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC] += [3321,3323]\n",
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_DIASTOLIC] += [8555]\n",
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_MEAN] = [220181,225312,220052]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC] += [6701]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 77,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>220179</th>\n",
+ " <td>Non Invasive Blood Pressure systolic</td>\n",
+ " <td>NBPs</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225309</th>\n",
+ " <td>ART BP Systolic</td>\n",
+ " <td>ART BP Systolic</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224167</th>\n",
+ " <td>Manual Blood Pressure Systolic Left</td>\n",
+ " <td>Manual BPs L</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220050</th>\n",
+ " <td>Arterial Blood Pressure systolic</td>\n",
+ " <td>ABPs</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227243</th>\n",
+ " <td>Manual Blood Pressure Systolic Right</td>\n",
+ " <td>Manual BPs R</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>455</th>\n",
+ " <td>NBP [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>94.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>ABP [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>94.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3313</th>\n",
+ " <td>BP Cuff [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>86.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>442</th>\n",
+ " <td>Manual BP [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>83.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3315</th>\n",
+ " <td>BP Left Arm [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>80.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51</th>\n",
+ " <td>Arterial BP [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>80.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3317</th>\n",
+ " <td>BP Left Leg [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>80.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3321</th>\n",
+ " <td>BP Right Arm [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>79.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3323</th>\n",
+ " <td>BP Right Leg [Systolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>79.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "220179 Non Invasive Blood Pressure systolic NBPs chartevents \n",
+ "225309 ART BP Systolic ART BP Systolic chartevents \n",
+ "224167 Manual Blood Pressure Systolic Left Manual BPs L chartevents \n",
+ "220050 Arterial Blood Pressure systolic ABPs chartevents \n",
+ "227243 Manual Blood Pressure Systolic Right Manual BPs R chartevents \n",
+ "455 NBP [Systolic] chartevents \n",
+ "6 ABP [Systolic] chartevents \n",
+ "3313 BP Cuff [Systolic] chartevents \n",
+ "442 Manual BP [Systolic] chartevents \n",
+ "3315 BP Left Arm [Systolic] chartevents \n",
+ "51 Arterial BP [Systolic] chartevents \n",
+ "3317 BP Left Leg [Systolic] chartevents \n",
+ "3321 BP Right Arm [Systolic] chartevents \n",
+ "3323 BP Right Leg [Systolic] chartevents \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "220179 Routine Vital Signs mmHg 110.000000 \n",
+ "225309 Routine Vital Signs mmHg 110.000000 \n",
+ "224167 Routine Vital Signs mmHg 110.000000 \n",
+ "220050 Routine Vital Signs mmHg 110.000000 \n",
+ "227243 Routine Vital Signs mmHg 110.000000 \n",
+ "455 94.333333 \n",
+ "6 94.333333 \n",
+ "3313 86.333333 \n",
+ "442 83.000000 \n",
+ "3315 80.000000 \n",
+ "51 80.000000 \n",
+ "3317 80.000000 \n",
+ "3321 79.000000 \n",
+ "3323 79.000000 "
+ ]
+ },
+ "execution_count": 77,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df.loc[keep_dict[data_dict.labels.BLOOD_PRESSURE_SYSTOLIC]]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 79,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>220180</th>\n",
+ " <td>Non Invasive Blood Pressure diastolic</td>\n",
+ " <td>NBPd</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225310</th>\n",
+ " <td>ART BP Diastolic</td>\n",
+ " <td>ART BP Diastolic</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224643</th>\n",
+ " <td>Manual Blood Pressure Diastolic Left</td>\n",
+ " <td>Manual BPd L</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220051</th>\n",
+ " <td>Arterial Blood Pressure diastolic</td>\n",
+ " <td>ABPd</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227242</th>\n",
+ " <td>Manual Blood Pressure Diastolic Right</td>\n",
+ " <td>Manual BPd R</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8441</th>\n",
+ " <td>NBP [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8364</th>\n",
+ " <td>ABP [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8502</th>\n",
+ " <td>BP Cuff [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>87.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8440</th>\n",
+ " <td>Manual BP [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8368</th>\n",
+ " <td>Arterial BP [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>82.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8503</th>\n",
+ " <td>BP Left Arm [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>82.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8504</th>\n",
+ " <td>BP Left Leg [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>82.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8507</th>\n",
+ " <td>BP Right Leg [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8506</th>\n",
+ " <td>BP Right Arm [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8555</th>\n",
+ " <td>Arterial BP #2 [Diastolic]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>79.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "220180 Non Invasive Blood Pressure diastolic NBPd chartevents \n",
+ "225310 ART BP Diastolic ART BP Diastolic chartevents \n",
+ "224643 Manual Blood Pressure Diastolic Left Manual BPd L chartevents \n",
+ "220051 Arterial Blood Pressure diastolic ABPd chartevents \n",
+ "227242 Manual Blood Pressure Diastolic Right Manual BPd R chartevents \n",
+ "8441 NBP [Diastolic] chartevents \n",
+ "8364 ABP [Diastolic] chartevents \n",
+ "8502 BP Cuff [Diastolic] chartevents \n",
+ "8440 Manual BP [Diastolic] chartevents \n",
+ "8368 Arterial BP [Diastolic] chartevents \n",
+ "8503 BP Left Arm [Diastolic] chartevents \n",
+ "8504 BP Left Leg [Diastolic] chartevents \n",
+ "8507 BP Right Leg [Diastolic] chartevents \n",
+ "8506 BP Right Arm [Diastolic] chartevents \n",
+ "8555 Arterial BP #2 [Diastolic] chartevents \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "220180 Routine Vital Signs mmHg 110.000000 \n",
+ "225310 Routine Vital Signs mmHg 110.000000 \n",
+ "224643 Routine Vital Signs mmHg 110.000000 \n",
+ "220051 Routine Vital Signs mmHg 110.000000 \n",
+ "227242 Routine Vital Signs mmHg 110.000000 \n",
+ "8441 95.666667 \n",
+ "8364 95.666667 \n",
+ "8502 87.666667 \n",
+ "8440 84.666667 \n",
+ "8368 82.000000 \n",
+ "8503 82.000000 \n",
+ "8504 82.000000 \n",
+ "8507 81.000000 \n",
+ "8506 81.000000 \n",
+ "8555 79.000000 "
+ ]
+ },
+ "execution_count": 79,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df.loc[keep_dict[data_dict.labels.BLOOD_PRESSURE_DIASTOLIC]]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### O2 Sat"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 80,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>50817</th>\n",
+ " <td>OXYGEN SATURATION</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220277</th>\n",
+ " <td>O2 saturation pulseoxymetry</td>\n",
+ " <td>SpO2</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>%</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>646</th>\n",
+ " <td>SpO2</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228232</th>\n",
+ " <td>PAR-Oxygen saturation</td>\n",
+ " <td>PAR-Oxygen saturation</td>\n",
+ " <td></td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td></td>\n",
+ " <td>102.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3785</th>\n",
+ " <td>PO2</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>ABG's</td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3837</th>\n",
+ " <td>pO2</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>ABG'S</td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50821</th>\n",
+ " <td>PO2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6719</th>\n",
+ " <td>SpO2-L</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1341</th>\n",
+ " <td>PULSE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1725</th>\n",
+ " <td>Pulse</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1332</th>\n",
+ " <td>pulse</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50816</th>\n",
+ " <td>OXYGEN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>78.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2955</th>\n",
+ " <td>JVO2 SAT</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2574</th>\n",
+ " <td>MVO2 SAT</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227873</th>\n",
+ " <td>Recovery O2 Sat - Aerobic Capacity</td>\n",
+ " <td>Recovery O2 Sat - Aerobic Capacity</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>OT Notes</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223772</th>\n",
+ " <td>SvO2</td>\n",
+ " <td>SvO2</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223769</th>\n",
+ " <td>O2 Saturation Pulseoxymetry Alarm - High</td>\n",
+ " <td>SpO2 Alarm - High</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227867</th>\n",
+ " <td>Activity O2 Sat - Aerobic Capacity</td>\n",
+ " <td>Activity O2 Sat - Aerobic Capacity</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>OT Notes</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223770</th>\n",
+ " <td>O2 Saturation Pulseoxymetry Alarm - Low</td>\n",
+ " <td>SpO2 Alarm - Low</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226861</th>\n",
+ " <td>ART %O2 saturation (PA Line)</td>\n",
+ " <td>ART %O2 saturation (PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225674</th>\n",
+ " <td>Mixed Venous O2% Sat</td>\n",
+ " <td>Mixed Venous O2% Sat</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226862</th>\n",
+ " <td>PA %O2 Saturation (PA Line)</td>\n",
+ " <td>PA %O2 Saturation (PA Line)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PA Line Insertion</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227686</th>\n",
+ " <td>Central Venous O2% Sat</td>\n",
+ " <td>Central Venous O2% Sat</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227546</th>\n",
+ " <td>SVV (Arterial)</td>\n",
+ " <td>SVV (Arterial)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227549</th>\n",
+ " <td>ScvO2 (Presep)</td>\n",
+ " <td>ScvO2 (Presep)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226993</th>\n",
+ " <td>ApacheIV_LOS</td>\n",
+ " <td>ApacheIV_LOS</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227008</th>\n",
+ " <td>Ejection Fraction</td>\n",
+ " <td>Ejection Fraction</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227010</th>\n",
+ " <td>FiO2_ApacheIV</td>\n",
+ " <td>FiO2_ApacheIV</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226272</th>\n",
+ " <td>EF (CCO)</td>\n",
+ " <td>EF (CCO)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hemodynamics</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228184</th>\n",
+ " <td>SVV (PiCCO)</td>\n",
+ " <td>SVV (PiCCO)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PiCCO</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227861</th>\n",
+ " <td>Rest O2 Sat - Aerobic Capacity</td>\n",
+ " <td>Rest O2 Sat - Aerobic Capacity</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>OT Notes</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226253</th>\n",
+ " <td>SpO2 Desat Limit</td>\n",
+ " <td>SpO2 Desat Limit</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Alarms</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224704</th>\n",
+ " <td>ATC %</td>\n",
+ " <td>ATC %</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Respiratory</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228378</th>\n",
+ " <td>TFCd (NICOM)</td>\n",
+ " <td>TFCd (NICOM)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>NICOM</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226745</th>\n",
+ " <td>APACHE II Predecited Death Rate</td>\n",
+ " <td>APACHE II PDR</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227919</th>\n",
+ " <td>Rest O2 Sat - Aerobic Activity Response</td>\n",
+ " <td>Rest O2 Sat - Aerobic Activity Response</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>OT Notes</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226744</th>\n",
+ " <td>APACHE II PDR - Adjusted</td>\n",
+ " <td>APACHE II PDR - Adjusted</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228377</th>\n",
+ " <td>SVI Change</td>\n",
+ " <td>SVI Change</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>NICOM</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226754</th>\n",
+ " <td>FiO2ApacheIIValue</td>\n",
+ " <td>FiO2ApacheIIValue</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228375</th>\n",
+ " <td>Stroke Volume Index (SVI NICOM)</td>\n",
+ " <td>Stroke Volume Index (SVI NICOM)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>NICOM</td>\n",
+ " <td>%</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label \\\n",
+ "itemid \n",
+ "50817 OXYGEN SATURATION \n",
+ "220277 O2 saturation pulseoxymetry \n",
+ "646 SpO2 \n",
+ "228232 PAR-Oxygen saturation \n",
+ "3785 PO2 \n",
+ "3837 pO2 \n",
+ "50821 PO2 \n",
+ "6719 SpO2-L \n",
+ "1341 PULSE \n",
+ "1725 Pulse \n",
+ "1332 pulse \n",
+ "50816 OXYGEN \n",
+ "2955 JVO2 SAT \n",
+ "2574 MVO2 SAT \n",
+ "227873 Recovery O2 Sat - Aerobic Capacity \n",
+ "223772 SvO2 \n",
+ "223769 O2 Saturation Pulseoxymetry Alarm - High \n",
+ "227867 Activity O2 Sat - Aerobic Capacity \n",
+ "223770 O2 Saturation Pulseoxymetry Alarm - Low \n",
+ "226861 ART %O2 saturation (PA Line) \n",
+ "225674 Mixed Venous O2% Sat \n",
+ "226862 PA %O2 Saturation (PA Line) \n",
+ "227686 Central Venous O2% Sat \n",
+ "227546 SVV (Arterial) \n",
+ "227549 ScvO2 (Presep) \n",
+ "226993 ApacheIV_LOS \n",
+ "227008 Ejection Fraction \n",
+ "227010 FiO2_ApacheIV \n",
+ "226272 EF (CCO) \n",
+ "228184 SVV (PiCCO) \n",
+ "227861 Rest O2 Sat - Aerobic Capacity \n",
+ "226253 SpO2 Desat Limit \n",
+ "224704 ATC % \n",
+ "228378 TFCd (NICOM) \n",
+ "226745 APACHE II Predecited Death Rate \n",
+ "227919 Rest O2 Sat - Aerobic Activity Response \n",
+ "226744 APACHE II PDR - Adjusted \n",
+ "228377 SVI Change \n",
+ "226754 FiO2ApacheIIValue \n",
+ "228375 Stroke Volume Index (SVI NICOM) \n",
+ "\n",
+ " abbreviation linksto \\\n",
+ "itemid \n",
+ "50817 NaN labevents \n",
+ "220277 SpO2 chartevents \n",
+ "646 chartevents \n",
+ "228232 PAR-Oxygen saturation \n",
+ "3785 chartevents \n",
+ "3837 chartevents \n",
+ "50821 NaN labevents \n",
+ "6719 chartevents \n",
+ "1341 chartevents \n",
+ "1725 chartevents \n",
+ "1332 chartevents \n",
+ "50816 NaN labevents \n",
+ "2955 chartevents \n",
+ "2574 chartevents \n",
+ "227873 Recovery O2 Sat - Aerobic Capacity chartevents \n",
+ "223772 SvO2 chartevents \n",
+ "223769 SpO2 Alarm - High chartevents \n",
+ "227867 Activity O2 Sat - Aerobic Capacity chartevents \n",
+ "223770 SpO2 Alarm - Low chartevents \n",
+ "226861 ART %O2 saturation (PA Line) chartevents \n",
+ "225674 Mixed Venous O2% Sat chartevents \n",
+ "226862 PA %O2 Saturation (PA Line) chartevents \n",
+ "227686 Central Venous O2% Sat chartevents \n",
+ "227546 SVV (Arterial) chartevents \n",
+ "227549 ScvO2 (Presep) chartevents \n",
+ "226993 ApacheIV_LOS chartevents \n",
+ "227008 Ejection Fraction chartevents \n",
+ "227010 FiO2_ApacheIV chartevents \n",
+ "226272 EF (CCO) chartevents \n",
+ "228184 SVV (PiCCO) chartevents \n",
+ "227861 Rest O2 Sat - Aerobic Capacity chartevents \n",
+ "226253 SpO2 Desat Limit chartevents \n",
+ "224704 ATC % chartevents \n",
+ "228378 TFCd (NICOM) chartevents \n",
+ "226745 APACHE II PDR chartevents \n",
+ "227919 Rest O2 Sat - Aerobic Activity Response chartevents \n",
+ "226744 APACHE II PDR - Adjusted chartevents \n",
+ "228377 SVI Change chartevents \n",
+ "226754 FiO2ApacheIIValue chartevents \n",
+ "228375 Stroke Volume Index (SVI NICOM) chartevents \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "50817 BLOOD GAS NaN 110.000000 \n",
+ "220277 Respiratory % 110.000000 \n",
+ "646 110.000000 \n",
+ "228232 Routine Vital Signs 102.666667 \n",
+ "3785 ABG's 100.666667 \n",
+ "3837 ABG'S 100.666667 \n",
+ "50821 BLOOD GAS NaN 100.666667 \n",
+ "6719 96.666667 \n",
+ "1341 78.666667 \n",
+ "1725 78.666667 \n",
+ "1332 78.666667 \n",
+ "50816 BLOOD GAS NaN 78.000000 \n",
+ "2955 78.000000 \n",
+ "2574 78.000000 \n",
+ "227873 OT Notes % 76.666667 \n",
+ "223772 Hemodynamics % 76.666667 \n",
+ "223769 Alarms % 76.666667 \n",
+ "227867 OT Notes % 76.666667 \n",
+ "223770 Alarms % 76.666667 \n",
+ "226861 PA Line Insertion % 76.666667 \n",
+ "225674 Labs % 76.666667 \n",
+ "226862 PA Line Insertion % 76.666667 \n",
+ "227686 Labs % 76.666667 \n",
+ "227546 Hemodynamics % 76.666667 \n",
+ "227549 Hemodynamics % 76.666667 \n",
+ "226993 Scores - APACHE IV (2) % 76.666667 \n",
+ "227008 Scores - APACHE IV (2) % 76.666667 \n",
+ "227010 Scores - APACHE IV (2) % 76.666667 \n",
+ "226272 Hemodynamics % 76.666667 \n",
+ "228184 PiCCO % 76.666667 \n",
+ "227861 OT Notes % 76.666667 \n",
+ "226253 Alarms % 76.666667 \n",
+ "224704 Respiratory % 76.666667 \n",
+ "228378 NICOM % 76.666667 \n",
+ "226745 Scores - APACHE II % 76.666667 \n",
+ "227919 OT Notes % 76.666667 \n",
+ "226744 Scores - APACHE II % 76.666667 \n",
+ "228377 NICOM % 76.666667 \n",
+ "226754 Scores - APACHE II % 76.666667 \n",
+ "228375 NICOM % 76.666667 "
+ ]
+ },
+ "execution_count": 80,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'oxygen saturation',\n",
+ " 'O2sat',\n",
+ " 'pulse oximetry',\n",
+ " '%',\n",
+ " 'spo2'\n",
+ " ])\n",
+ "out_df.head(40)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 81,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.OXYGEN_SATURATION_PULSE_OXIMETRY] = [646,220277,228232]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Body Temp"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 82,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>50825</th>\n",
+ " <td>TEMPERATURE</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226170</th>\n",
+ " <td>Head of Bead Measurement</td>\n",
+ " <td>HOB Measurement</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Treatments</td>\n",
+ " <td>Degree</td>\n",
+ " <td>104.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223762</th>\n",
+ " <td>Temperature Celsius</td>\n",
+ " <td>Temperature C</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>?C</td>\n",
+ " <td>104.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223761</th>\n",
+ " <td>Temperature Fahrenheit</td>\n",
+ " <td>Temperature F</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td>?F</td>\n",
+ " <td>104.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>678</th>\n",
+ " <td>Temperature F</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>104.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>676</th>\n",
+ " <td>Temperature C</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>104.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>591</th>\n",
+ " <td>RLE [Temperature]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>98.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>597</th>\n",
+ " <td>RUE [Temperature]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>98.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224027</th>\n",
+ " <td>Skin Temperature</td>\n",
+ " <td>Skin Temp</td>\n",
+ " <td></td>\n",
+ " <td>Skin - Assessment</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224642</th>\n",
+ " <td>Temperature Site</td>\n",
+ " <td>Temp Site</td>\n",
+ " <td></td>\n",
+ " <td>Routine Vital Signs</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>645</th>\n",
+ " <td>Skin [Temperature]</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>679</th>\n",
+ " <td>Temperature F (calc)</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>92.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>677</th>\n",
+ " <td>Temperature C (calc)</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>92.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227054</th>\n",
+ " <td>TemperatureF_ApacheIV</td>\n",
+ " <td>TemperatureF_ApacheIV</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>?F</td>\n",
+ " <td>89.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224769</th>\n",
+ " <td>LUE Temp</td>\n",
+ " <td>LUE Temp</td>\n",
+ " <td></td>\n",
+ " <td>Cardiovascular</td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224771</th>\n",
+ " <td>RLE Temp</td>\n",
+ " <td>RLE Temp</td>\n",
+ " <td></td>\n",
+ " <td>Cardiovascular</td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224773</th>\n",
+ " <td>LLE Temp</td>\n",
+ " <td>LLE Temp</td>\n",
+ " <td></td>\n",
+ " <td>Cardiovascular</td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2798</th>\n",
+ " <td>arm 90 degrees</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224674</th>\n",
+ " <td>Changes in Temperature</td>\n",
+ " <td>Changes in Temperature</td>\n",
+ " <td></td>\n",
+ " <td>Toxicology</td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224767</th>\n",
+ " <td>RUE Temp</td>\n",
+ " <td>RUE Temp</td>\n",
+ " <td></td>\n",
+ " <td>Cardiovascular</td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "50825 TEMPERATURE NaN labevents \n",
+ "226170 Head of Bead Measurement HOB Measurement chartevents \n",
+ "223762 Temperature Celsius Temperature C chartevents \n",
+ "223761 Temperature Fahrenheit Temperature F chartevents \n",
+ "678 Temperature F chartevents \n",
+ "676 Temperature C chartevents \n",
+ "591 RLE [Temperature] chartevents \n",
+ "597 RUE [Temperature] chartevents \n",
+ "224027 Skin Temperature Skin Temp \n",
+ "224642 Temperature Site Temp Site \n",
+ "645 Skin [Temperature] chartevents \n",
+ "679 Temperature F (calc) chartevents \n",
+ "677 Temperature C (calc) chartevents \n",
+ "227054 TemperatureF_ApacheIV TemperatureF_ApacheIV chartevents \n",
+ "224769 LUE Temp LUE Temp \n",
+ "224771 RLE Temp RLE Temp \n",
+ "224773 LLE Temp LLE Temp \n",
+ "2798 arm 90 degrees chartevents \n",
+ "224674 Changes in Temperature Changes in Temperature \n",
+ "224767 RUE Temp RUE Temp \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "50825 BLOOD GAS NaN 110.000000 \n",
+ "226170 Treatments Degree 104.666667 \n",
+ "223762 Routine Vital Signs ?C 104.666667 \n",
+ "223761 Routine Vital Signs ?F 104.666667 \n",
+ "678 104.666667 \n",
+ "676 104.666667 \n",
+ "591 98.000000 \n",
+ "597 98.000000 \n",
+ "224027 Skin - Assessment 97.333333 \n",
+ "224642 Routine Vital Signs 97.333333 \n",
+ "645 95.666667 \n",
+ "679 92.333333 \n",
+ "677 92.333333 \n",
+ "227054 Scores - APACHE IV (2) ?F 89.333333 \n",
+ "224769 Cardiovascular 88.000000 \n",
+ "224771 Cardiovascular 88.000000 \n",
+ "224773 Cardiovascular 88.000000 \n",
+ "2798 88.000000 \n",
+ "224674 Toxicology 88.000000 \n",
+ "224767 Cardiovascular 88.000000 "
+ ]
+ },
+ "execution_count": 82,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'temperature',\n",
+ " 'temp',\n",
+ " 'celcius',\n",
+ " 'farenheit',\n",
+ " 'degrees',\n",
+ " 'deg'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 83,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.TEMPERATURE_BODY] = [223761,678,223762,676]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Weight"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 97,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>763</th>\n",
+ " <td>Daily Weight</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226512</th>\n",
+ " <td>Admission Weight (Kg)</td>\n",
+ " <td>Admission Weight (Kg)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>General</td>\n",
+ " <td>kg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226846</th>\n",
+ " <td>Feeding Weight</td>\n",
+ " <td>Feeding Weight</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>General</td>\n",
+ " <td>kg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224639</th>\n",
+ " <td>Daily Weight</td>\n",
+ " <td>Daily Weight</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>General</td>\n",
+ " <td>kg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3693</th>\n",
+ " <td>Weight Kg</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>968</th>\n",
+ " <td>EKG</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225402</th>\n",
+ " <td>EKG</td>\n",
+ " <td>EKG</td>\n",
+ " <td>procedureevents_mv</td>\n",
+ " <td>4-Procedures</td>\n",
+ " <td>None</td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226184</th>\n",
+ " <td>Estimated Protein Needs/Kg</td>\n",
+ " <td>Estimated Protein Needs/Kg</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>General</td>\n",
+ " <td>g/kg</td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>733</th>\n",
+ " <td>Weight Change</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>85.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226707</th>\n",
+ " <td>Height</td>\n",
+ " <td>Height</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>General</td>\n",
+ " <td>Inch</td>\n",
+ " <td>83.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4183</th>\n",
+ " <td>Birthweight (kg)</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228179</th>\n",
+ " <td>ELWI (PiCCO)</td>\n",
+ " <td>ELWI (PiCCO)</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>PiCCO</td>\n",
+ " <td>ml/kg</td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>580</th>\n",
+ " <td>Previous Weight</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43622</th>\n",
+ " <td>cc/kg</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>581</th>\n",
+ " <td>Previous WeightF</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>80.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7000</th>\n",
+ " <td>ideal body weight</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45271</th>\n",
+ " <td>Chucks Pad Weight</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3723</th>\n",
+ " <td>Birth Weight (kg)</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>77.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3581</th>\n",
+ " <td>Present Weight (lb)</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>76.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3692</th>\n",
+ " <td>Weight Change (gms)</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>76.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation \\\n",
+ "itemid \n",
+ "763 Daily Weight \n",
+ "226512 Admission Weight (Kg) Admission Weight (Kg) \n",
+ "226846 Feeding Weight Feeding Weight \n",
+ "224639 Daily Weight Daily Weight \n",
+ "3693 Weight Kg \n",
+ "968 EKG \n",
+ "225402 EKG EKG \n",
+ "226184 Estimated Protein Needs/Kg Estimated Protein Needs/Kg \n",
+ "733 Weight Change \n",
+ "226707 Height Height \n",
+ "4183 Birthweight (kg) \n",
+ "228179 ELWI (PiCCO) ELWI (PiCCO) \n",
+ "580 Previous Weight \n",
+ "43622 cc/kg \n",
+ "581 Previous WeightF \n",
+ "7000 ideal body weight \n",
+ "45271 Chucks Pad Weight \n",
+ "3723 Birth Weight (kg) \n",
+ "3581 Present Weight (lb) \n",
+ "3692 Weight Change (gms) \n",
+ "\n",
+ " linksto category unitname score \n",
+ "itemid \n",
+ "763 chartevents 110.000000 \n",
+ "226512 chartevents General kg 110.000000 \n",
+ "226846 chartevents General kg 110.000000 \n",
+ "224639 chartevents General kg 110.000000 \n",
+ "3693 chartevents 96.666667 \n",
+ "968 chartevents 96.666667 \n",
+ "225402 procedureevents_mv 4-Procedures None 96.666667 \n",
+ "226184 chartevents General g/kg 88.000000 \n",
+ "733 chartevents 85.333333 \n",
+ "226707 chartevents General Inch 83.000000 \n",
+ "4183 chartevents 81.666667 \n",
+ "228179 chartevents PiCCO ml/kg 81.333333 \n",
+ "580 chartevents 81.333333 \n",
+ "43622 inputevents_cv 81.333333 \n",
+ "581 chartevents 80.000000 \n",
+ "7000 chartevents 78.000000 \n",
+ "45271 inputevents_cv 78.000000 \n",
+ "3723 chartevents 77.666667 \n",
+ "3581 chartevents 76.000000 \n",
+ "3692 chartevents 76.000000 "
+ ]
+ },
+ "execution_count": 97,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'weight',\n",
+ " 'daily weight',\n",
+ " 'kg' \n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 98,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.WEIGHT_BODY] =[763,224639,3693]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Urine Output"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 84,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>226560</th>\n",
+ " <td>Void</td>\n",
+ " <td>Void</td>\n",
+ " <td>outputevents</td>\n",
+ " <td>Output</td>\n",
+ " <td>mL</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43332</th>\n",
+ " <td>void</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7672</th>\n",
+ " <td>Foley</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3686</th>\n",
+ " <td>Void</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45967</th>\n",
+ " <td>foley</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43053</th>\n",
+ " <td>URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226559</th>\n",
+ " <td>Foley</td>\n",
+ " <td>Foley</td>\n",
+ " <td>outputevents</td>\n",
+ " <td>Output</td>\n",
+ " <td>mL</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44103</th>\n",
+ " <td>ER urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44834</th>\n",
+ " <td>er urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227519</th>\n",
+ " <td>Urine output_ApacheIV</td>\n",
+ " <td>Urine output</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>None</td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44706</th>\n",
+ " <td>urine output</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42892</th>\n",
+ " <td>EW URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45415</th>\n",
+ " <td>ED Urine OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43987</th>\n",
+ " <td>urine out or</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42666</th>\n",
+ " <td>E.R. URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44237</th>\n",
+ " <td>E.R. urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42592</th>\n",
+ " <td>VICU URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40069</th>\n",
+ " <td>Urine Out Void</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46423</th>\n",
+ " <td>ed foley</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>94.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43931</th>\n",
+ " <td>Floor urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "226560 Void Void outputevents \n",
+ "43332 void inputevents_cv \n",
+ "7672 Foley chartevents \n",
+ "3686 Void chartevents \n",
+ "45967 foley inputevents_cv \n",
+ "43053 URINE OUT outputevents \n",
+ "226559 Foley Foley outputevents \n",
+ "44103 ER urine out outputevents \n",
+ "44834 er urine out outputevents \n",
+ "227519 Urine output_ApacheIV Urine output chartevents \n",
+ "44706 urine output outputevents \n",
+ "42892 EW URINE OUT outputevents \n",
+ "45415 ED Urine OUT outputevents \n",
+ "43987 urine out or outputevents \n",
+ "42666 E.R. URINE OUT outputevents \n",
+ "44237 E.R. urine out outputevents \n",
+ "42592 VICU URINE OUT outputevents \n",
+ "40069 Urine Out Void outputevents \n",
+ "46423 ed foley inputevents_cv \n",
+ "43931 Floor urine out outputevents \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "226560 Output mL 110.000000 \n",
+ "43332 110.000000 \n",
+ "7672 110.000000 \n",
+ "3686 110.000000 \n",
+ "45967 110.000000 \n",
+ "43053 110.000000 \n",
+ "226559 Output mL 110.000000 \n",
+ "44103 100.666667 \n",
+ "44834 100.666667 \n",
+ "227519 Scores - APACHE IV (2) None 100.666667 \n",
+ "44706 100.666667 \n",
+ "42892 100.666667 \n",
+ "45415 100.666667 \n",
+ "43987 100.666667 \n",
+ "42666 96.666667 \n",
+ "44237 96.666667 \n",
+ "42592 95.333333 \n",
+ "40069 95.333333 \n",
+ "46423 94.666667 \n",
+ "43931 93.333333 "
+ ]
+ },
+ "execution_count": 84,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'urine out',\n",
+ " 'void',\n",
+ " 'foley'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 85,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>226560</th>\n",
+ " <td>Void</td>\n",
+ " <td>Void</td>\n",
+ " <td>outputevents</td>\n",
+ " <td>Output</td>\n",
+ " <td>mL</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43332</th>\n",
+ " <td>void</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7672</th>\n",
+ " <td>Foley</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3686</th>\n",
+ " <td>Void</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45967</th>\n",
+ " <td>foley</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43053</th>\n",
+ " <td>URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226559</th>\n",
+ " <td>Foley</td>\n",
+ " <td>Foley</td>\n",
+ " <td>outputevents</td>\n",
+ " <td>Output</td>\n",
+ " <td>mL</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44103</th>\n",
+ " <td>ER urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44834</th>\n",
+ " <td>er urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227519</th>\n",
+ " <td>Urine output_ApacheIV</td>\n",
+ " <td>Urine output</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>None</td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44706</th>\n",
+ " <td>urine output</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42892</th>\n",
+ " <td>EW URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45415</th>\n",
+ " <td>ED Urine OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43987</th>\n",
+ " <td>urine out or</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42666</th>\n",
+ " <td>E.R. URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44237</th>\n",
+ " <td>E.R. urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42592</th>\n",
+ " <td>VICU URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40069</th>\n",
+ " <td>Urine Out Void</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46423</th>\n",
+ " <td>ed foley</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>94.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43931</th>\n",
+ " <td>Floor urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43348</th>\n",
+ " <td>urine output/kg</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40405</th>\n",
+ " <td>Urine Out Other</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42810</th>\n",
+ " <td>angio urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46180</th>\n",
+ " <td>urine out-angio</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40055</th>\n",
+ " <td>Urine Out Foley</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44253</th>\n",
+ " <td>Urine out angio</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44325</th>\n",
+ " <td>ED URINE OUTPUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>41857</th>\n",
+ " <td>urine out in er</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44824</th>\n",
+ " <td>EW urine output</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45991</th>\n",
+ " <td>ew-urine output</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42042</th>\n",
+ " <td>ANGIO URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46177</th>\n",
+ " <td>URINE OUT-ANGIO</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44684</th>\n",
+ " <td>floor urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46658</th>\n",
+ " <td>ED Urine output</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46578</th>\n",
+ " <td>URINE OUTPUT-ER</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42765</th>\n",
+ " <td>FARR 6 URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>91.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>70081</th>\n",
+ " <td>URINE</td>\n",
+ " <td></td>\n",
+ " <td>microbiologyevents</td>\n",
+ " <td>SPECIMEN</td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3819</th>\n",
+ " <td>Urine Leukocytes</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Urine</td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>70079</th>\n",
+ " <td>URINE</td>\n",
+ " <td></td>\n",
+ " <td>microbiologyevents</td>\n",
+ " <td>SPECIMEN</td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43462</th>\n",
+ " <td>urine</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "226560 Void Void outputevents \n",
+ "43332 void inputevents_cv \n",
+ "7672 Foley chartevents \n",
+ "3686 Void chartevents \n",
+ "45967 foley inputevents_cv \n",
+ "43053 URINE OUT outputevents \n",
+ "226559 Foley Foley outputevents \n",
+ "44103 ER urine out outputevents \n",
+ "44834 er urine out outputevents \n",
+ "227519 Urine output_ApacheIV Urine output chartevents \n",
+ "44706 urine output outputevents \n",
+ "42892 EW URINE OUT outputevents \n",
+ "45415 ED Urine OUT outputevents \n",
+ "43987 urine out or outputevents \n",
+ "42666 E.R. URINE OUT outputevents \n",
+ "44237 E.R. urine out outputevents \n",
+ "42592 VICU URINE OUT outputevents \n",
+ "40069 Urine Out Void outputevents \n",
+ "46423 ed foley inputevents_cv \n",
+ "43931 Floor urine out outputevents \n",
+ "43348 urine output/kg outputevents \n",
+ "40405 Urine Out Other outputevents \n",
+ "42810 angio urine out outputevents \n",
+ "46180 urine out-angio outputevents \n",
+ "40055 Urine Out Foley outputevents \n",
+ "44253 Urine out angio outputevents \n",
+ "44325 ED URINE OUTPUT outputevents \n",
+ "41857 urine out in er outputevents \n",
+ "44824 EW urine output outputevents \n",
+ "45991 ew-urine output outputevents \n",
+ "42042 ANGIO URINE OUT outputevents \n",
+ "46177 URINE OUT-ANGIO outputevents \n",
+ "44684 floor urine out outputevents \n",
+ "46658 ED Urine output outputevents \n",
+ "46578 URINE OUTPUT-ER outputevents \n",
+ "42765 FARR 6 URINE OUT outputevents \n",
+ "70081 URINE microbiologyevents \n",
+ "3819 Urine Leukocytes chartevents \n",
+ "70079 URINE microbiologyevents \n",
+ "43462 urine outputevents \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "226560 Output mL 110.000000 \n",
+ "43332 110.000000 \n",
+ "7672 110.000000 \n",
+ "3686 110.000000 \n",
+ "45967 110.000000 \n",
+ "43053 110.000000 \n",
+ "226559 Output mL 110.000000 \n",
+ "44103 100.666667 \n",
+ "44834 100.666667 \n",
+ "227519 Scores - APACHE IV (2) None 100.666667 \n",
+ "44706 100.666667 \n",
+ "42892 100.666667 \n",
+ "45415 100.666667 \n",
+ "43987 100.666667 \n",
+ "42666 96.666667 \n",
+ "44237 96.666667 \n",
+ "42592 95.333333 \n",
+ "40069 95.333333 \n",
+ "46423 94.666667 \n",
+ "43931 93.333333 \n",
+ "43348 93.333333 \n",
+ "40405 93.333333 \n",
+ "42810 93.333333 \n",
+ "46180 93.333333 \n",
+ "40055 93.333333 \n",
+ "44253 93.333333 \n",
+ "44325 93.333333 \n",
+ "41857 93.333333 \n",
+ "44824 93.333333 \n",
+ "45991 93.333333 \n",
+ "42042 93.333333 \n",
+ "46177 93.333333 \n",
+ "44684 93.333333 \n",
+ "46658 93.333333 \n",
+ "46578 93.333333 \n",
+ "42765 91.333333 \n",
+ "70081 SPECIMEN 90.666667 \n",
+ "3819 Urine 90.666667 \n",
+ "70079 SPECIMEN 90.666667 \n",
+ "43462 90.666667 "
+ ]
+ },
+ "execution_count": 85,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df.head(40)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 86,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "out_df = out_df[out_df.linksto.isin(['outputevents','chartevents'])]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 87,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>226560</th>\n",
+ " <td>Void</td>\n",
+ " <td>Void</td>\n",
+ " <td>outputevents</td>\n",
+ " <td>Output</td>\n",
+ " <td>mL</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7672</th>\n",
+ " <td>Foley</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3686</th>\n",
+ " <td>Void</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43053</th>\n",
+ " <td>URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226559</th>\n",
+ " <td>Foley</td>\n",
+ " <td>Foley</td>\n",
+ " <td>outputevents</td>\n",
+ " <td>Output</td>\n",
+ " <td>mL</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44103</th>\n",
+ " <td>ER urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44834</th>\n",
+ " <td>er urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227519</th>\n",
+ " <td>Urine output_ApacheIV</td>\n",
+ " <td>Urine output</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>None</td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44706</th>\n",
+ " <td>urine output</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42892</th>\n",
+ " <td>EW URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45415</th>\n",
+ " <td>ED Urine OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43987</th>\n",
+ " <td>urine out or</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42666</th>\n",
+ " <td>E.R. URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44237</th>\n",
+ " <td>E.R. urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42592</th>\n",
+ " <td>VICU URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40069</th>\n",
+ " <td>Urine Out Void</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>95.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43931</th>\n",
+ " <td>Floor urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43348</th>\n",
+ " <td>urine output/kg</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40405</th>\n",
+ " <td>Urine Out Other</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42810</th>\n",
+ " <td>angio urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46180</th>\n",
+ " <td>urine out-angio</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40055</th>\n",
+ " <td>Urine Out Foley</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44253</th>\n",
+ " <td>Urine out angio</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44325</th>\n",
+ " <td>ED URINE OUTPUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>41857</th>\n",
+ " <td>urine out in er</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44824</th>\n",
+ " <td>EW urine output</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45991</th>\n",
+ " <td>ew-urine output</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42042</th>\n",
+ " <td>ANGIO URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46177</th>\n",
+ " <td>URINE OUT-ANGIO</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44684</th>\n",
+ " <td>floor urine out</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46658</th>\n",
+ " <td>ED Urine output</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46578</th>\n",
+ " <td>URINE OUTPUT-ER</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>93.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42765</th>\n",
+ " <td>FARR 6 URINE OUT</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>91.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3819</th>\n",
+ " <td>Urine Leukocytes</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Urine</td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43462</th>\n",
+ " <td>urine</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3816</th>\n",
+ " <td>Urine Glucose</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Urine</td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3817</th>\n",
+ " <td>Urine Heme</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Urine</td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3818</th>\n",
+ " <td>Urine Ketones</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Urine</td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3822</th>\n",
+ " <td>Urine Protein</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Urine</td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6298</th>\n",
+ " <td>foley d/c</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "226560 Void Void outputevents \n",
+ "7672 Foley chartevents \n",
+ "3686 Void chartevents \n",
+ "43053 URINE OUT outputevents \n",
+ "226559 Foley Foley outputevents \n",
+ "44103 ER urine out outputevents \n",
+ "44834 er urine out outputevents \n",
+ "227519 Urine output_ApacheIV Urine output chartevents \n",
+ "44706 urine output outputevents \n",
+ "42892 EW URINE OUT outputevents \n",
+ "45415 ED Urine OUT outputevents \n",
+ "43987 urine out or outputevents \n",
+ "42666 E.R. URINE OUT outputevents \n",
+ "44237 E.R. urine out outputevents \n",
+ "42592 VICU URINE OUT outputevents \n",
+ "40069 Urine Out Void outputevents \n",
+ "43931 Floor urine out outputevents \n",
+ "43348 urine output/kg outputevents \n",
+ "40405 Urine Out Other outputevents \n",
+ "42810 angio urine out outputevents \n",
+ "46180 urine out-angio outputevents \n",
+ "40055 Urine Out Foley outputevents \n",
+ "44253 Urine out angio outputevents \n",
+ "44325 ED URINE OUTPUT outputevents \n",
+ "41857 urine out in er outputevents \n",
+ "44824 EW urine output outputevents \n",
+ "45991 ew-urine output outputevents \n",
+ "42042 ANGIO URINE OUT outputevents \n",
+ "46177 URINE OUT-ANGIO outputevents \n",
+ "44684 floor urine out outputevents \n",
+ "46658 ED Urine output outputevents \n",
+ "46578 URINE OUTPUT-ER outputevents \n",
+ "42765 FARR 6 URINE OUT outputevents \n",
+ "3819 Urine Leukocytes chartevents \n",
+ "43462 urine outputevents \n",
+ "3816 Urine Glucose chartevents \n",
+ "3817 Urine Heme chartevents \n",
+ "3818 Urine Ketones chartevents \n",
+ "3822 Urine Protein chartevents \n",
+ "6298 foley d/c chartevents \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "226560 Output mL 110.000000 \n",
+ "7672 110.000000 \n",
+ "3686 110.000000 \n",
+ "43053 110.000000 \n",
+ "226559 Output mL 110.000000 \n",
+ "44103 100.666667 \n",
+ "44834 100.666667 \n",
+ "227519 Scores - APACHE IV (2) None 100.666667 \n",
+ "44706 100.666667 \n",
+ "42892 100.666667 \n",
+ "45415 100.666667 \n",
+ "43987 100.666667 \n",
+ "42666 96.666667 \n",
+ "44237 96.666667 \n",
+ "42592 95.333333 \n",
+ "40069 95.333333 \n",
+ "43931 93.333333 \n",
+ "43348 93.333333 \n",
+ "40405 93.333333 \n",
+ "42810 93.333333 \n",
+ "46180 93.333333 \n",
+ "40055 93.333333 \n",
+ "44253 93.333333 \n",
+ "44325 93.333333 \n",
+ "41857 93.333333 \n",
+ "44824 93.333333 \n",
+ "45991 93.333333 \n",
+ "42042 93.333333 \n",
+ "46177 93.333333 \n",
+ "44684 93.333333 \n",
+ "46658 93.333333 \n",
+ "46578 93.333333 \n",
+ "42765 91.333333 \n",
+ "3819 Urine 90.666667 \n",
+ "43462 90.666667 \n",
+ "3816 Urine 90.666667 \n",
+ "3817 Urine 90.666667 \n",
+ "3818 Urine 90.666667 \n",
+ "3822 Urine 90.666667 \n",
+ "6298 90.666667 "
+ ]
+ },
+ "execution_count": 87,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df.head(40)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 91,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": [
+ "out_df.drop(227519,axis=0,inplace=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 96,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.OUTPUT_URINE] = out_df.loc[:46578].index.unique().tolist()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "https://github.com/MIT-LCP/mimic-code/blob/travis/concepts/cookbook/uo.sql"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.OUTPUT_URINE] = keep_dict[data_dict.labels.OUTPUT_URINE]\n",
+ "to_add = [43175,40094,40715,40473,40085,40057,40056,40428,40086,40096,40651]\n",
+ "to_add += [227510,226561,226584,226563,226564,226565,226567,226557,226558 ]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Glasgow Coma Scale (GCS)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Eye Opening"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 99,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>184</th>\n",
+ " <td>Eye Opening</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220739</th>\n",
+ " <td>GCS - Eye Opening</td>\n",
+ " <td>Eye Opening</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>198</th>\n",
+ " <td>GCS Total</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>70033</th>\n",
+ " <td>EYE</td>\n",
+ " <td></td>\n",
+ " <td>microbiologyevents</td>\n",
+ " <td>SPECIMEN</td>\n",
+ " <td></td>\n",
+ " <td>72.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3742</th>\n",
+ " <td>Basos</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>CSF</td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3791</th>\n",
+ " <td>Polys</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>CSF</td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3779</th>\n",
+ " <td>Monos</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>CSF</td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2834</th>\n",
+ " <td>ICS</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227011</th>\n",
+ " <td>GCSEye_ApacheIV</td>\n",
+ " <td>GCSEye_ApacheIV</td>\n",
+ " <td></td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td></td>\n",
+ " <td>65.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226755</th>\n",
+ " <td>GcsApacheIIScore</td>\n",
+ " <td>GcsApacheIIScore</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td>None</td>\n",
+ " <td>64.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>41556</th>\n",
+ " <td>ng</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>64.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227012</th>\n",
+ " <td>GCSMotor_ApacheIV</td>\n",
+ " <td>GCSMotor_ApacheIV</td>\n",
+ " <td></td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td></td>\n",
+ " <td>63.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227013</th>\n",
+ " <td>GcsScore_ApacheIV</td>\n",
+ " <td>GcsScore_ApacheIV</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>None</td>\n",
+ " <td>63.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5700</th>\n",
+ " <td>Gent eye oint</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>63.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227014</th>\n",
+ " <td>GCSVerbal_ApacheIV</td>\n",
+ " <td>GCSVerbal_ApacheIV</td>\n",
+ " <td></td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td></td>\n",
+ " <td>62.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50931</th>\n",
+ " <td>GLUCOSE</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>CHEMISTRY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>62.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1529</th>\n",
+ " <td>Glucose</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Chemistry</td>\n",
+ " <td></td>\n",
+ " <td>62.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50809</th>\n",
+ " <td>GLUCOSE</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>62.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51478</th>\n",
+ " <td>GLUCOSE</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>62.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223901</th>\n",
+ " <td>GCS - Motor Response</td>\n",
+ " <td>Motor Response</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>61.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "184 Eye Opening chartevents \n",
+ "220739 GCS - Eye Opening Eye Opening \n",
+ "198 GCS Total chartevents \n",
+ "70033 EYE microbiologyevents \n",
+ "3742 Basos chartevents \n",
+ "3791 Polys chartevents \n",
+ "3779 Monos chartevents \n",
+ "2834 ICS chartevents \n",
+ "227011 GCSEye_ApacheIV GCSEye_ApacheIV \n",
+ "226755 GcsApacheIIScore GcsApacheIIScore chartevents \n",
+ "41556 ng inputevents_cv \n",
+ "227012 GCSMotor_ApacheIV GCSMotor_ApacheIV \n",
+ "227013 GcsScore_ApacheIV GcsScore_ApacheIV chartevents \n",
+ "5700 Gent eye oint chartevents \n",
+ "227014 GCSVerbal_ApacheIV GCSVerbal_ApacheIV \n",
+ "50931 GLUCOSE NaN labevents \n",
+ "1529 Glucose chartevents \n",
+ "50809 GLUCOSE NaN labevents \n",
+ "51478 GLUCOSE NaN labevents \n",
+ "223901 GCS - Motor Response Motor Response \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "184 110.000000 \n",
+ "220739 Neurological 110.000000 \n",
+ "198 76.666667 \n",
+ "70033 SPECIMEN 72.000000 \n",
+ "3742 CSF 71.333333 \n",
+ "3791 CSF 71.333333 \n",
+ "3779 CSF 71.333333 \n",
+ "2834 67.000000 \n",
+ "227011 Scores - APACHE IV (2) 65.333333 \n",
+ "226755 Scores - APACHE II None 64.666667 \n",
+ "41556 64.000000 \n",
+ "227012 Scores - APACHE IV (2) 63.333333 \n",
+ "227013 Scores - APACHE IV (2) None 63.333333 \n",
+ "5700 63.000000 \n",
+ "227014 Scores - APACHE IV (2) 62.666667 \n",
+ "50931 CHEMISTRY NaN 62.333333 \n",
+ "1529 Chemistry 62.333333 \n",
+ "50809 BLOOD GAS NaN 62.333333 \n",
+ "51478 HEMATOLOGY NaN 62.333333 \n",
+ "223901 Neurological 61.666667 "
+ ]
+ },
+ "execution_count": 99,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'glasgow come scale',\n",
+ " 'GCS',\n",
+ " 'eye opening'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 100,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.GLASGOW_COMA_SCALE_EYE_OPENING] = [184,220739]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Motor"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 101,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>228405</th>\n",
+ " <td>Motor L Leg</td>\n",
+ " <td>Motor L Leg</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>85.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228404</th>\n",
+ " <td>Motor L Arm</td>\n",
+ " <td>Motor L Arm</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>85.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228407</th>\n",
+ " <td>Motor R Leg</td>\n",
+ " <td>Motor R Leg</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>85.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228406</th>\n",
+ " <td>Motor R Arm</td>\n",
+ " <td>Motor R Arm</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>85.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227120</th>\n",
+ " <td>Motor Deficit</td>\n",
+ " <td>Motor Deficit</td>\n",
+ " <td></td>\n",
+ " <td>Pain/Sedation</td>\n",
+ " <td></td>\n",
+ " <td>80.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>453</th>\n",
+ " <td>Motor Deficits</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>454</th>\n",
+ " <td>Motor Response</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>223901</th>\n",
+ " <td>GCS - Motor Response</td>\n",
+ " <td>Motor Response</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>198</th>\n",
+ " <td>GCS Total</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227012</th>\n",
+ " <td>GCSMotor_ApacheIV</td>\n",
+ " <td>GCSMotor_ApacheIV</td>\n",
+ " <td></td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td></td>\n",
+ " <td>73.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3779</th>\n",
+ " <td>Monos</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>CSF</td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3742</th>\n",
+ " <td>Basos</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>CSF</td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3791</th>\n",
+ " <td>Polys</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>CSF</td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226757</th>\n",
+ " <td>GCSMotorApacheIIValue</td>\n",
+ " <td>GCSMotorApacheIIValue</td>\n",
+ " <td></td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td></td>\n",
+ " <td>68.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2834</th>\n",
+ " <td>ICS</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225472</th>\n",
+ " <td>Pneumothorax</td>\n",
+ " <td>Pneumothorax</td>\n",
+ " <td>procedureevents_mv</td>\n",
+ " <td>3-Significant Events</td>\n",
+ " <td>None</td>\n",
+ " <td>66.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227011</th>\n",
+ " <td>GCSEye_ApacheIV</td>\n",
+ " <td>GCSEye_ApacheIV</td>\n",
+ " <td></td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td></td>\n",
+ " <td>65.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226755</th>\n",
+ " <td>GcsApacheIIScore</td>\n",
+ " <td>GcsApacheIIScore</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td>None</td>\n",
+ " <td>64.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220739</th>\n",
+ " <td>GCS - Eye Opening</td>\n",
+ " <td>Eye Opening</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>64.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227013</th>\n",
+ " <td>GcsScore_ApacheIV</td>\n",
+ " <td>GcsScore_ApacheIV</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td>None</td>\n",
+ " <td>63.333333</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "228405 Motor L Leg Motor L Leg \n",
+ "228404 Motor L Arm Motor L Arm \n",
+ "228407 Motor R Leg Motor R Leg \n",
+ "228406 Motor R Arm Motor R Arm \n",
+ "227120 Motor Deficit Motor Deficit \n",
+ "453 Motor Deficits chartevents \n",
+ "454 Motor Response chartevents \n",
+ "223901 GCS - Motor Response Motor Response \n",
+ "198 GCS Total chartevents \n",
+ "227012 GCSMotor_ApacheIV GCSMotor_ApacheIV \n",
+ "3779 Monos chartevents \n",
+ "3742 Basos chartevents \n",
+ "3791 Polys chartevents \n",
+ "226757 GCSMotorApacheIIValue GCSMotorApacheIIValue \n",
+ "2834 ICS chartevents \n",
+ "225472 Pneumothorax Pneumothorax procedureevents_mv \n",
+ "227011 GCSEye_ApacheIV GCSEye_ApacheIV \n",
+ "226755 GcsApacheIIScore GcsApacheIIScore chartevents \n",
+ "220739 GCS - Eye Opening Eye Opening \n",
+ "227013 GcsScore_ApacheIV GcsScore_ApacheIV chartevents \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "228405 Neurological 85.333333 \n",
+ "228404 Neurological 85.333333 \n",
+ "228407 Neurological 85.333333 \n",
+ "228406 Neurological 85.333333 \n",
+ "227120 Pain/Sedation 80.666667 \n",
+ "453 78.666667 \n",
+ "454 78.666667 \n",
+ "223901 Neurological 78.666667 \n",
+ "198 76.666667 \n",
+ "227012 Scores - APACHE IV (2) 73.333333 \n",
+ "3779 CSF 71.333333 \n",
+ "3742 CSF 71.333333 \n",
+ "3791 CSF 71.333333 \n",
+ "226757 Scores - APACHE II 68.666667 \n",
+ "2834 67.000000 \n",
+ "225472 3-Significant Events None 66.000000 \n",
+ "227011 Scores - APACHE IV (2) 65.333333 \n",
+ "226755 Scores - APACHE II None 64.666667 \n",
+ "220739 Neurological 64.333333 \n",
+ "227013 Scores - APACHE IV (2) None 63.333333 "
+ ]
+ },
+ "execution_count": 101,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'glasgow come scale',\n",
+ " 'GCS',\n",
+ " 'motor',\n",
+ " 'motor response'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 102,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.GLASGOW_COMA_SCALE_MOTOR] = [454,223901]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Verbal"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 103,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>223900</th>\n",
+ " <td>GCS - Verbal Response</td>\n",
+ " <td>Verbal Response</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>723</th>\n",
+ " <td>Verbal Response</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224756</th>\n",
+ " <td>Response</td>\n",
+ " <td>Response</td>\n",
+ " <td></td>\n",
+ " <td>Neurological</td>\n",
+ " <td></td>\n",
+ " <td>90.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>41610</th>\n",
+ " <td>ER</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227014</th>\n",
+ " <td>GCSVerbal_ApacheIV</td>\n",
+ " <td>GCSVerbal_ApacheIV</td>\n",
+ " <td></td>\n",
+ " <td>Scores - APACHE IV (2)</td>\n",
+ " <td></td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44473</th>\n",
+ " <td>er</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>198</th>\n",
+ " <td>GCS Total</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226758</th>\n",
+ " <td>GCSVerbalApacheIIValue</td>\n",
+ " <td>GCSVerbalApacheIIValue</td>\n",
+ " <td></td>\n",
+ " <td>Scores - APACHE II</td>\n",
+ " <td></td>\n",
+ " <td>72.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3779</th>\n",
+ " <td>Monos</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>CSF</td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3742</th>\n",
+ " <td>Basos</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>CSF</td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3791</th>\n",
+ " <td>Polys</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>CSF</td>\n",
+ " <td></td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224413</th>\n",
+ " <td>TOF Response</td>\n",
+ " <td>TOF Response</td>\n",
+ " <td></td>\n",
+ " <td>Pain/Sedation</td>\n",
+ " <td></td>\n",
+ " <td>69.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>40450</th>\n",
+ " <td>EBL</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>41693</th>\n",
+ " <td>Verapamil</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>67.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1968</th>\n",
+ " <td>Verapamil</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42047</th>\n",
+ " <td>ebl</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>222318</th>\n",
+ " <td>Verapamil</td>\n",
+ " <td>Verapamil</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mg</td>\n",
+ " <td>67.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46484</th>\n",
+ " <td>verapamil</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>67.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2834</th>\n",
+ " <td>ICS</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>224409</th>\n",
+ " <td>Pain Level Response</td>\n",
+ " <td>Pain Level Response</td>\n",
+ " <td></td>\n",
+ " <td>Pain/Sedation</td>\n",
+ " <td></td>\n",
+ " <td>66.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "223900 GCS - Verbal Response Verbal Response \n",
+ "723 Verbal Response chartevents \n",
+ "224756 Response Response \n",
+ "41610 ER inputevents_cv \n",
+ "227014 GCSVerbal_ApacheIV GCSVerbal_ApacheIV \n",
+ "44473 er inputevents_cv \n",
+ "198 GCS Total chartevents \n",
+ "226758 GCSVerbalApacheIIValue GCSVerbalApacheIIValue \n",
+ "3779 Monos chartevents \n",
+ "3742 Basos chartevents \n",
+ "3791 Polys chartevents \n",
+ "224413 TOF Response TOF Response \n",
+ "40450 EBL inputevents_cv \n",
+ "41693 Verapamil inputevents_cv \n",
+ "1968 Verapamil chartevents \n",
+ "42047 ebl inputevents_cv \n",
+ "222318 Verapamil Verapamil inputevents_mv \n",
+ "46484 verapamil inputevents_cv \n",
+ "2834 ICS chartevents \n",
+ "224409 Pain Level Response Pain Level Response \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "223900 Neurological 110.000000 \n",
+ "723 110.000000 \n",
+ "224756 Neurological 90.000000 \n",
+ "41610 Free Form Intake 76.666667 \n",
+ "227014 Scores - APACHE IV (2) 76.666667 \n",
+ "44473 Free Form Intake 76.666667 \n",
+ "198 76.666667 \n",
+ "226758 Scores - APACHE II 72.000000 \n",
+ "3779 CSF 71.333333 \n",
+ "3742 CSF 71.333333 \n",
+ "3791 CSF 71.333333 \n",
+ "224413 Pain/Sedation 69.666667 \n",
+ "40450 67.000000 \n",
+ "41693 Free Form Intake 67.000000 \n",
+ "1968 67.000000 \n",
+ "42047 67.000000 \n",
+ "222318 Medications mg 67.000000 \n",
+ "46484 Free Form Intake 67.000000 \n",
+ "2834 67.000000 \n",
+ "224409 Pain/Sedation 66.000000 "
+ ]
+ },
+ "execution_count": 103,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'glasgow come scale',\n",
+ " 'GCS',\n",
+ " 'verbal',\n",
+ " 'verbal response'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 104,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.GLASGOW_COMA_SCALE_VERBAL] = [723,223900]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Labs\n",
+ "\n",
+ "### Lactate"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 105,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1531</th>\n",
+ " <td>Lactic Acid</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Chemistry</td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225668</th>\n",
+ " <td>Lactic Acid</td>\n",
+ " <td>Lactic Acid</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>None</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50813</th>\n",
+ " <td>LACTATE</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220228</th>\n",
+ " <td>Hemoglobin</td>\n",
+ " <td>Hemoglobin</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>g/dl</td>\n",
+ " <td>102.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2773</th>\n",
+ " <td>sjlactate</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>102.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225835</th>\n",
+ " <td>Na Phos</td>\n",
+ " <td>Na Phos</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mmol</td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225834</th>\n",
+ " <td>K Phos</td>\n",
+ " <td>K Phos</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mmol</td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227526</th>\n",
+ " <td>Citrate</td>\n",
+ " <td>Citrate</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mmol</td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225925</th>\n",
+ " <td>Potassium Phosphate</td>\n",
+ " <td>Potassium Phosphate</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Nutrition - Supplements</td>\n",
+ " <td>mmol</td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>818</th>\n",
+ " <td>Lactic Acid(0.5-2.0)</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Chemistry</td>\n",
+ " <td></td>\n",
+ " <td>91.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220955</th>\n",
+ " <td>Ringers Lactate</td>\n",
+ " <td>Ringers Lactate</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>86.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2638</th>\n",
+ " <td>CEREBRAL LACTATE</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1634</th>\n",
+ " <td>lactated ringers</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30021</th>\n",
+ " <td>Lactated Ringers</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1520</th>\n",
+ " <td>ACT</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Coags</td>\n",
+ " <td></td>\n",
+ " <td>83.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220507</th>\n",
+ " <td>Activated Clotting Time</td>\n",
+ " <td>ACT</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>None</td>\n",
+ " <td>83.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1671</th>\n",
+ " <td>act</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>83.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>221319</th>\n",
+ " <td>Alteplase (TPA)</td>\n",
+ " <td>Alteplase (TPA)</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mg</td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>221347</th>\n",
+ " <td>Amiodarone</td>\n",
+ " <td>Amiodarone</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mg</td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>221342</th>\n",
+ " <td>Aminophylline</td>\n",
+ " <td>Aminophylline</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mg</td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "1531 Lactic Acid chartevents \n",
+ "225668 Lactic Acid Lactic Acid chartevents \n",
+ "50813 LACTATE NaN labevents \n",
+ "220228 Hemoglobin Hemoglobin chartevents \n",
+ "2773 sjlactate chartevents \n",
+ "225835 Na Phos Na Phos inputevents_mv \n",
+ "225834 K Phos K Phos inputevents_mv \n",
+ "227526 Citrate Citrate inputevents_mv \n",
+ "225925 Potassium Phosphate Potassium Phosphate inputevents_mv \n",
+ "818 Lactic Acid(0.5-2.0) chartevents \n",
+ "220955 Ringers Lactate Ringers Lactate inputevents_mv \n",
+ "2638 CEREBRAL LACTATE chartevents \n",
+ "1634 lactated ringers chartevents \n",
+ "30021 Lactated Ringers inputevents_cv \n",
+ "1520 ACT chartevents \n",
+ "220507 Activated Clotting Time ACT chartevents \n",
+ "1671 act chartevents \n",
+ "221319 Alteplase (TPA) Alteplase (TPA) inputevents_mv \n",
+ "221347 Amiodarone Amiodarone inputevents_mv \n",
+ "221342 Aminophylline Aminophylline inputevents_mv \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "1531 Chemistry 110.000000 \n",
+ "225668 Labs None 110.000000 \n",
+ "50813 BLOOD GAS NaN 110.000000 \n",
+ "220228 Labs g/dl 102.666667 \n",
+ "2773 102.000000 \n",
+ "225835 Medications mmol 96.666667 \n",
+ "225834 Medications mmol 96.666667 \n",
+ "227526 Medications mmol 96.666667 \n",
+ "225925 Nutrition - Supplements mmol 96.666667 \n",
+ "818 Chemistry 91.333333 \n",
+ "220955 Fluids - Other (Not In Use) mL 86.000000 \n",
+ "2638 84.000000 \n",
+ "1634 84.000000 \n",
+ "30021 84.000000 \n",
+ "1520 Coags 83.333333 \n",
+ "220507 Labs None 83.333333 \n",
+ "1671 83.333333 \n",
+ "221319 Medications mg 81.333333 \n",
+ "221347 Medications mg 81.333333 \n",
+ "221342 Medications mg 81.333333 "
+ ]
+ },
+ "execution_count": 105,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'lactate',\n",
+ " 'lactic acid',\n",
+ " 'mmol/L',\n",
+ " 'mg/dL'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 106,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.LACTATE] = [1531,50813,225668,818]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Hemoglobin"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 107,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>51222</th>\n",
+ " <td>HEMOGLOBIN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220228</th>\n",
+ " <td>Hemoglobin</td>\n",
+ " <td>Hemoglobin</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>g/dl</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>814</th>\n",
+ " <td>Hemoglobin</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Hematology</td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1165</th>\n",
+ " <td>Hgb</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50811</th>\n",
+ " <td>HEMOGLOBIN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51225</th>\n",
+ " <td>HEMOGLOBIN F</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>104.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51224</th>\n",
+ " <td>HEMOGLOBIN C</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>104.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50814</th>\n",
+ " <td>METHEMOGLOBIN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>101.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51223</th>\n",
+ " <td>HEMOGLOBIN A2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>101.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7965</th>\n",
+ " <td>methhemoglobin</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>98.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50852</th>\n",
+ " <td>% HEMOGLOBIN A1C</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>CHEMISTRY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51212</th>\n",
+ " <td>FETAL HEMOGLOBIN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50805</th>\n",
+ " <td>CARBOXYHEMOGLOBIN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>92.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50855</th>\n",
+ " <td>ABSOLUTE HEMOGLOBIN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>CHEMISTRY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>89.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51226</th>\n",
+ " <td>HEMOGLOBLIN A</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51227</th>\n",
+ " <td>HEMOGLOBLIN S</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42232</th>\n",
+ " <td>THYMOGLOBLIN</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45486</th>\n",
+ " <td>Hemo</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42117</th>\n",
+ " <td>THYMOGLOBULIN</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>78.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50934</th>\n",
+ " <td>H</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>CHEMISTRY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>76.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto category \\\n",
+ "itemid \n",
+ "51222 HEMOGLOBIN NaN labevents HEMATOLOGY \n",
+ "220228 Hemoglobin Hemoglobin chartevents Labs \n",
+ "814 Hemoglobin chartevents Hematology \n",
+ "1165 Hgb chartevents \n",
+ "50811 HEMOGLOBIN NaN labevents BLOOD GAS \n",
+ "51225 HEMOGLOBIN F NaN labevents HEMATOLOGY \n",
+ "51224 HEMOGLOBIN C NaN labevents HEMATOLOGY \n",
+ "50814 METHEMOGLOBIN NaN labevents BLOOD GAS \n",
+ "51223 HEMOGLOBIN A2 NaN labevents HEMATOLOGY \n",
+ "7965 methhemoglobin chartevents \n",
+ "50852 % HEMOGLOBIN A1C NaN labevents CHEMISTRY \n",
+ "51212 FETAL HEMOGLOBIN NaN labevents HEMATOLOGY \n",
+ "50805 CARBOXYHEMOGLOBIN NaN labevents BLOOD GAS \n",
+ "50855 ABSOLUTE HEMOGLOBIN NaN labevents CHEMISTRY \n",
+ "51226 HEMOGLOBLIN A NaN labevents HEMATOLOGY \n",
+ "51227 HEMOGLOBLIN S NaN labevents HEMATOLOGY \n",
+ "42232 THYMOGLOBLIN inputevents_cv Free Form Intake \n",
+ "45486 Hemo inputevents_cv \n",
+ "42117 THYMOGLOBULIN inputevents_cv Free Form Intake \n",
+ "50934 H NaN labevents CHEMISTRY \n",
+ "\n",
+ " unitname score \n",
+ "itemid \n",
+ "51222 NaN 110.000000 \n",
+ "220228 g/dl 110.000000 \n",
+ "814 110.000000 \n",
+ "1165 110.000000 \n",
+ "50811 NaN 110.000000 \n",
+ "51225 NaN 104.000000 \n",
+ "51224 NaN 104.000000 \n",
+ "50814 NaN 101.333333 \n",
+ "51223 NaN 101.333333 \n",
+ "7965 98.666667 \n",
+ "50852 NaN 96.666667 \n",
+ "51212 NaN 94.666667 \n",
+ "50805 NaN 92.666667 \n",
+ "50855 NaN 89.333333 \n",
+ "51226 NaN 88.000000 \n",
+ "51227 NaN 88.000000 \n",
+ "42232 81.333333 \n",
+ "45486 81.333333 \n",
+ "42117 78.666667 \n",
+ "50934 NaN 76.666667 "
+ ]
+ },
+ "execution_count": 107,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'hgb',\n",
+ " 'hemoglobin',\n",
+ " 'g/dL'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 108,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.HEMOGLOBIN] = [51222,220228,814,1165,50811]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Fluids\n",
+ "\n",
+ "### Normal Saline"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 109,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>41913</th>\n",
+ " <td>NS</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6190</th>\n",
+ " <td>Normal saline</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30143</th>\n",
+ " <td>3% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>104.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30168</th>\n",
+ " <td>Normal Saline_GU</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>103.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30160</th>\n",
+ " <td>D5 Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>103.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30161</th>\n",
+ " <td>.3% normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>103.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30018</th>\n",
+ " <td>.9% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>103.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30020</th>\n",
+ " <td>.45% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>101.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30176</th>\n",
+ " <td>.25% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>101.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30352</th>\n",
+ " <td>0.9% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220962</th>\n",
+ " <td>Saline 3%</td>\n",
+ " <td>Saline 3%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>98.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30353</th>\n",
+ " <td>0.45% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>98.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44440</th>\n",
+ " <td>Normal Saline Bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44053</th>\n",
+ " <td>normal saline bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4647</th>\n",
+ " <td>normal saline bolus</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43354</th>\n",
+ " <td>normal saline flushs</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>96.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>221213</th>\n",
+ " <td>Saline 30%</td>\n",
+ " <td>Saline 30%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>95.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220959</th>\n",
+ " <td>Saline 0,3%</td>\n",
+ " <td>Saline 0,3%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>92.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220954</th>\n",
+ " <td>Saline 0,9%</td>\n",
+ " <td>Saline 0,9%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>92.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220960</th>\n",
+ " <td>Saline 0,45%</td>\n",
+ " <td>Saline 0,45%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>89.333333</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "41913 NS inputevents_cv \n",
+ "6190 Normal saline chartevents \n",
+ "30143 3% Normal Saline inputevents_cv \n",
+ "30168 Normal Saline_GU inputevents_cv \n",
+ "30160 D5 Normal Saline inputevents_cv \n",
+ "30161 .3% normal Saline inputevents_cv \n",
+ "30018 .9% Normal Saline inputevents_cv \n",
+ "30020 .45% Normal Saline inputevents_cv \n",
+ "30176 .25% Normal Saline inputevents_cv \n",
+ "30352 0.9% Normal Saline inputevents_cv \n",
+ "220962 Saline 3% Saline 3% inputevents_mv \n",
+ "30353 0.45% Normal Saline inputevents_cv \n",
+ "44440 Normal Saline Bolus inputevents_cv \n",
+ "44053 normal saline bolus inputevents_cv \n",
+ "4647 normal saline bolus chartevents \n",
+ "43354 normal saline flushs inputevents_cv \n",
+ "221213 Saline 30% Saline 30% inputevents_mv \n",
+ "220959 Saline 0,3% Saline 0,3% inputevents_mv \n",
+ "220954 Saline 0,9% Saline 0,9% inputevents_mv \n",
+ "220960 Saline 0,45% Saline 0,45% inputevents_mv \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "41913 Free Form Intake 110.000000 \n",
+ "6190 110.000000 \n",
+ "30143 104.333333 \n",
+ "30168 103.333333 \n",
+ "30160 103.333333 \n",
+ "30161 103.333333 \n",
+ "30018 103.333333 \n",
+ "30020 101.333333 \n",
+ "30176 101.333333 \n",
+ "30352 100.333333 \n",
+ "220962 Fluids - Other (Not In Use) mL 98.666667 \n",
+ "30353 98.333333 \n",
+ "44440 Free Form Intake 97.333333 \n",
+ "44053 Free Form Intake 97.333333 \n",
+ "4647 97.333333 \n",
+ "43354 Free Form Intake 96.000000 \n",
+ "221213 Fluids - Other (Not In Use) mL 95.000000 \n",
+ "220959 Fluids - Other (Not In Use) mL 92.000000 \n",
+ "220954 Fluids - Other (Not In Use) mL 92.000000 \n",
+ "220960 Fluids - Other (Not In Use) mL 89.333333 "
+ ]
+ },
+ "execution_count": 109,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'saline',\n",
+ " 'NS',\n",
+ " '0.9%',\n",
+ " 'normal saline'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 110,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.NORMAL_SALINE] = [41913,6190,20018,30252,44440,44053,4647,220954]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 111,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>41913</th>\n",
+ " <td>NS</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6190</th>\n",
+ " <td>Normal saline</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30143</th>\n",
+ " <td>3% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>104.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30168</th>\n",
+ " <td>Normal Saline_GU</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>103.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30160</th>\n",
+ " <td>D5 Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>103.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30161</th>\n",
+ " <td>.3% normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>103.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30018</th>\n",
+ " <td>.9% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>103.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30020</th>\n",
+ " <td>.45% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>101.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30176</th>\n",
+ " <td>.25% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>101.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30352</th>\n",
+ " <td>0.9% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>100.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220962</th>\n",
+ " <td>Saline 3%</td>\n",
+ " <td>Saline 3%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>98.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30353</th>\n",
+ " <td>0.45% Normal Saline</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>98.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44440</th>\n",
+ " <td>Normal Saline Bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44053</th>\n",
+ " <td>normal saline bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4647</th>\n",
+ " <td>normal saline bolus</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>43354</th>\n",
+ " <td>normal saline flushs</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>96.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>221213</th>\n",
+ " <td>Saline 30%</td>\n",
+ " <td>Saline 30%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>95.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220959</th>\n",
+ " <td>Saline 0,3%</td>\n",
+ " <td>Saline 0,3%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>92.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220954</th>\n",
+ " <td>Saline 0,9%</td>\n",
+ " <td>Saline 0,9%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>92.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220960</th>\n",
+ " <td>Saline 0,45%</td>\n",
+ " <td>Saline 0,45%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>89.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220961</th>\n",
+ " <td>Saline 0,65%</td>\n",
+ " <td>Saline 0,65%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>89.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>221212</th>\n",
+ " <td>Saline 0,18%</td>\n",
+ " <td>Saline 0,18%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>89.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>41392</th>\n",
+ " <td>ns b</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225825</th>\n",
+ " <td>D5NS</td>\n",
+ " <td>D5NS</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids/Intake</td>\n",
+ " <td>mL</td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5333</th>\n",
+ " <td>saline flush</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30060</th>\n",
+ " <td>D5NS</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>226401</th>\n",
+ " <td>GU Irrigant - Normal Saline</td>\n",
+ " <td>GU Irrigant - Normal Saline</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids/Intake</td>\n",
+ " <td>mL</td>\n",
+ " <td>87.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220958</th>\n",
+ " <td>Saline 0,255%</td>\n",
+ " <td>Saline 0,255%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>86.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2619</th>\n",
+ " <td>3% NS</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>227344</th>\n",
+ " <td>IV/Saline lock</td>\n",
+ " <td>IV/Saline lock</td>\n",
+ " <td></td>\n",
+ " <td>Restraint/Support Systems</td>\n",
+ " <td></td>\n",
+ " <td>83.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30190</th>\n",
+ " <td>NS .9%</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>82.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225158</th>\n",
+ " <td>NaCl 0.9%</td>\n",
+ " <td>NaCl 0.9%</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids/Intake</td>\n",
+ " <td>mL</td>\n",
+ " <td>82.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45298</th>\n",
+ " <td>ED NS</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2072</th>\n",
+ " <td>Pinsp</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2107</th>\n",
+ " <td>pinsp</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7092</th>\n",
+ " <td>Tinsp</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6384</th>\n",
+ " <td>PINSP</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44498</th>\n",
+ " <td>er ns</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3204</th>\n",
+ " <td>Pinsp.</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>79.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2404</th>\n",
+ " <td>.45%ns</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>79.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation \\\n",
+ "itemid \n",
+ "41913 NS \n",
+ "6190 Normal saline \n",
+ "30143 3% Normal Saline \n",
+ "30168 Normal Saline_GU \n",
+ "30160 D5 Normal Saline \n",
+ "30161 .3% normal Saline \n",
+ "30018 .9% Normal Saline \n",
+ "30020 .45% Normal Saline \n",
+ "30176 .25% Normal Saline \n",
+ "30352 0.9% Normal Saline \n",
+ "220962 Saline 3% Saline 3% \n",
+ "30353 0.45% Normal Saline \n",
+ "44440 Normal Saline Bolus \n",
+ "44053 normal saline bolus \n",
+ "4647 normal saline bolus \n",
+ "43354 normal saline flushs \n",
+ "221213 Saline 30% Saline 30% \n",
+ "220959 Saline 0,3% Saline 0,3% \n",
+ "220954 Saline 0,9% Saline 0,9% \n",
+ "220960 Saline 0,45% Saline 0,45% \n",
+ "220961 Saline 0,65% Saline 0,65% \n",
+ "221212 Saline 0,18% Saline 0,18% \n",
+ "41392 ns b \n",
+ "225825 D5NS D5NS \n",
+ "5333 saline flush \n",
+ "30060 D5NS \n",
+ "226401 GU Irrigant - Normal Saline GU Irrigant - Normal Saline \n",
+ "220958 Saline 0,255% Saline 0,255% \n",
+ "2619 3% NS \n",
+ "227344 IV/Saline lock IV/Saline lock \n",
+ "30190 NS .9% \n",
+ "225158 NaCl 0.9% NaCl 0.9% \n",
+ "45298 ED NS \n",
+ "2072 Pinsp \n",
+ "2107 pinsp \n",
+ "7092 Tinsp \n",
+ "6384 PINSP \n",
+ "44498 er ns \n",
+ "3204 Pinsp. \n",
+ "2404 .45%ns \n",
+ "\n",
+ " linksto category unitname score \n",
+ "itemid \n",
+ "41913 inputevents_cv Free Form Intake 110.000000 \n",
+ "6190 chartevents 110.000000 \n",
+ "30143 inputevents_cv 104.333333 \n",
+ "30168 inputevents_cv 103.333333 \n",
+ "30160 inputevents_cv 103.333333 \n",
+ "30161 inputevents_cv 103.333333 \n",
+ "30018 inputevents_cv 103.333333 \n",
+ "30020 inputevents_cv 101.333333 \n",
+ "30176 inputevents_cv 101.333333 \n",
+ "30352 inputevents_cv 100.333333 \n",
+ "220962 inputevents_mv Fluids - Other (Not In Use) mL 98.666667 \n",
+ "30353 inputevents_cv 98.333333 \n",
+ "44440 inputevents_cv Free Form Intake 97.333333 \n",
+ "44053 inputevents_cv Free Form Intake 97.333333 \n",
+ "4647 chartevents 97.333333 \n",
+ "43354 inputevents_cv Free Form Intake 96.000000 \n",
+ "221213 inputevents_mv Fluids - Other (Not In Use) mL 95.000000 \n",
+ "220959 inputevents_mv Fluids - Other (Not In Use) mL 92.000000 \n",
+ "220954 inputevents_mv Fluids - Other (Not In Use) mL 92.000000 \n",
+ "220960 inputevents_mv Fluids - Other (Not In Use) mL 89.333333 \n",
+ "220961 inputevents_mv Fluids - Other (Not In Use) mL 89.333333 \n",
+ "221212 inputevents_mv Fluids - Other (Not In Use) mL 89.333333 \n",
+ "41392 inputevents_cv Free Form Intake 88.000000 \n",
+ "225825 inputevents_mv Fluids/Intake mL 88.000000 \n",
+ "5333 chartevents 88.000000 \n",
+ "30060 inputevents_cv 88.000000 \n",
+ "226401 inputevents_mv Fluids/Intake mL 87.666667 \n",
+ "220958 inputevents_mv Fluids - Other (Not In Use) mL 86.666667 \n",
+ "2619 chartevents 84.666667 \n",
+ "227344 Restraint/Support Systems 83.333333 \n",
+ "30190 inputevents_cv 82.333333 \n",
+ "225158 inputevents_mv Fluids/Intake mL 82.333333 \n",
+ "45298 inputevents_cv Free Form Intake 81.333333 \n",
+ "2072 chartevents 81.333333 \n",
+ "2107 chartevents 81.333333 \n",
+ "7092 chartevents 81.333333 \n",
+ "6384 chartevents 81.333333 \n",
+ "44498 inputevents_cv Free Form Intake 81.333333 \n",
+ "3204 chartevents 79.000000 \n",
+ "2404 chartevents 79.000000 "
+ ]
+ },
+ "execution_count": 111,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df.head(40)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 112,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.NORMAL_SALINE] += [30190,225158]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Lactated Ringers"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 113,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>225828</th>\n",
+ " <td>LR</td>\n",
+ " <td>LR</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids/Intake</td>\n",
+ " <td>mL</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44367</th>\n",
+ " <td>LR</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2971</th>\n",
+ " <td>LR</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1634</th>\n",
+ " <td>lactated ringers</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30021</th>\n",
+ " <td>Lactated Ringers</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45532</th>\n",
+ " <td>IR Lactated ringers</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>104.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225943</th>\n",
+ " <td>Solution</td>\n",
+ " <td>Solution</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids/Intake</td>\n",
+ " <td>mL</td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225827</th>\n",
+ " <td>D5LR</td>\n",
+ " <td>D5LR</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids/Intake</td>\n",
+ " <td>mL</td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50813</th>\n",
+ " <td>LACTATE</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>84.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220953</th>\n",
+ " <td>Ringers</td>\n",
+ " <td>Ringers</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>84.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46207</th>\n",
+ " <td>OR LR</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44184</th>\n",
+ " <td>LR Bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44521</th>\n",
+ " <td>LR bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46781</th>\n",
+ " <td>lr bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44815</th>\n",
+ " <td>LR BOLUS</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44915</th>\n",
+ " <td>D5LR 40K</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46538</th>\n",
+ " <td>PD solution in</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>68.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44837</th>\n",
+ " <td>ED URINE</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>68.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8313</th>\n",
+ " <td>Nystatin solution</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30125</th>\n",
+ " <td>Milrinone</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.333333</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "225828 LR LR inputevents_mv \n",
+ "44367 LR inputevents_cv \n",
+ "2971 LR chartevents \n",
+ "1634 lactated ringers chartevents \n",
+ "30021 Lactated Ringers inputevents_cv \n",
+ "45532 IR Lactated ringers inputevents_cv \n",
+ "225943 Solution Solution inputevents_mv \n",
+ "225827 D5LR D5LR inputevents_mv \n",
+ "50813 LACTATE NaN labevents \n",
+ "220953 Ringers Ringers inputevents_mv \n",
+ "46207 OR LR inputevents_cv \n",
+ "44184 LR Bolus inputevents_cv \n",
+ "44521 LR bolus inputevents_cv \n",
+ "46781 lr bolus inputevents_cv \n",
+ "44815 LR BOLUS inputevents_cv \n",
+ "44915 D5LR 40K inputevents_cv \n",
+ "46538 PD solution in inputevents_cv \n",
+ "44837 ED URINE outputevents \n",
+ "8313 Nystatin solution chartevents \n",
+ "30125 Milrinone inputevents_cv \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "225828 Fluids/Intake mL 110.000000 \n",
+ "44367 Free Form Intake 110.000000 \n",
+ "2971 110.000000 \n",
+ "1634 110.000000 \n",
+ "30021 110.000000 \n",
+ "45532 Free Form Intake 104.000000 \n",
+ "225943 Fluids/Intake mL 88.000000 \n",
+ "225827 Fluids/Intake mL 88.000000 \n",
+ "50813 BLOOD GAS NaN 84.000000 \n",
+ "220953 Fluids - Other (Not In Use) mL 84.000000 \n",
+ "46207 Free Form Intake 81.333333 \n",
+ "44184 Free Form Intake 70.000000 \n",
+ "44521 Free Form Intake 70.000000 \n",
+ "46781 Free Form Intake 70.000000 \n",
+ "44815 Free Form Intake 70.000000 \n",
+ "44915 Free Form Intake 70.000000 \n",
+ "46538 Free Form Intake 68.333333 \n",
+ "44837 68.000000 \n",
+ "8313 67.666667 \n",
+ "30125 67.333333 "
+ ]
+ },
+ "execution_count": 113,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'LR',\n",
+ " 'ringers solution',\n",
+ " 'lactated ringers'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 114,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>225828</th>\n",
+ " <td>LR</td>\n",
+ " <td>LR</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids/Intake</td>\n",
+ " <td>mL</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44367</th>\n",
+ " <td>LR</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2971</th>\n",
+ " <td>LR</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1634</th>\n",
+ " <td>lactated ringers</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30021</th>\n",
+ " <td>Lactated Ringers</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45532</th>\n",
+ " <td>IR Lactated ringers</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>104.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225943</th>\n",
+ " <td>Solution</td>\n",
+ " <td>Solution</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids/Intake</td>\n",
+ " <td>mL</td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225827</th>\n",
+ " <td>D5LR</td>\n",
+ " <td>D5LR</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids/Intake</td>\n",
+ " <td>mL</td>\n",
+ " <td>88.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50813</th>\n",
+ " <td>LACTATE</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>84.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220953</th>\n",
+ " <td>Ringers</td>\n",
+ " <td>Ringers</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>84.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46207</th>\n",
+ " <td>OR LR</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>81.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44184</th>\n",
+ " <td>LR Bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44521</th>\n",
+ " <td>LR bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46781</th>\n",
+ " <td>lr bolus</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44815</th>\n",
+ " <td>LR BOLUS</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44915</th>\n",
+ " <td>D5LR 40K</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46538</th>\n",
+ " <td>PD solution in</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>68.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44837</th>\n",
+ " <td>ED URINE</td>\n",
+ " <td></td>\n",
+ " <td>outputevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>68.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8313</th>\n",
+ " <td>Nystatin solution</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30125</th>\n",
+ " <td>Milrinone</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>221986</th>\n",
+ " <td>Milrinone</td>\n",
+ " <td>Milrinone</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mg</td>\n",
+ " <td>67.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30159</th>\n",
+ " <td>D5 Ringers Lact.</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>67.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228159</th>\n",
+ " <td>Purge Solution Flow Rate</td>\n",
+ " <td>Purge Solution Flow Rate</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Impella</td>\n",
+ " <td>ml/hr</td>\n",
+ " <td>66.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225953</th>\n",
+ " <td>Solution (Peritoneal Dialysis)</td>\n",
+ " <td>Solution (PD)</td>\n",
+ " <td></td>\n",
+ " <td>Dialysis</td>\n",
+ " <td></td>\n",
+ " <td>66.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45983</th>\n",
+ " <td>Pitocin/LR</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>65.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42409</th>\n",
+ " <td>D5LR W/40K</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>65.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42978</th>\n",
+ " <td>D5LR 20KCL</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>65.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1189</th>\n",
+ " <td>finger stick</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>65.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5743</th>\n",
+ " <td>NT suction</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>64.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1520</th>\n",
+ " <td>ACT</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Coags</td>\n",
+ " <td></td>\n",
+ " <td>64.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220507</th>\n",
+ " <td>Activated Clotting Time</td>\n",
+ " <td>ACT</td>\n",
+ " <td>chartevents</td>\n",
+ " <td>Labs</td>\n",
+ " <td>None</td>\n",
+ " <td>64.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1671</th>\n",
+ " <td>act</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>64.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8339</th>\n",
+ " <td>Neo Opium Solution</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>64.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42288</th>\n",
+ " <td>LR w/40 kcl</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>64.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225072</th>\n",
+ " <td>Living situation</td>\n",
+ " <td>Living situation</td>\n",
+ " <td></td>\n",
+ " <td>Adm History/FHPA</td>\n",
+ " <td></td>\n",
+ " <td>63.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42345</th>\n",
+ " <td>LR w/ 40 mEq</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>63.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2773</th>\n",
+ " <td>sjlactate</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>63.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5088</th>\n",
+ " <td>fingers</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>63.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42265</th>\n",
+ " <td>LR W/ 20 KCL</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>63.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>220955</th>\n",
+ " <td>Ringers Lactate</td>\n",
+ " <td>Ringers Lactate</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Fluids - Other (Not In Use)</td>\n",
+ " <td>mL</td>\n",
+ " <td>63.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation \\\n",
+ "itemid \n",
+ "225828 LR LR \n",
+ "44367 LR \n",
+ "2971 LR \n",
+ "1634 lactated ringers \n",
+ "30021 Lactated Ringers \n",
+ "45532 IR Lactated ringers \n",
+ "225943 Solution Solution \n",
+ "225827 D5LR D5LR \n",
+ "50813 LACTATE NaN \n",
+ "220953 Ringers Ringers \n",
+ "46207 OR LR \n",
+ "44184 LR Bolus \n",
+ "44521 LR bolus \n",
+ "46781 lr bolus \n",
+ "44815 LR BOLUS \n",
+ "44915 D5LR 40K \n",
+ "46538 PD solution in \n",
+ "44837 ED URINE \n",
+ "8313 Nystatin solution \n",
+ "30125 Milrinone \n",
+ "221986 Milrinone Milrinone \n",
+ "30159 D5 Ringers Lact. \n",
+ "228159 Purge Solution Flow Rate Purge Solution Flow Rate \n",
+ "225953 Solution (Peritoneal Dialysis) Solution (PD) \n",
+ "45983 Pitocin/LR \n",
+ "42409 D5LR W/40K \n",
+ "42978 D5LR 20KCL \n",
+ "1189 finger stick \n",
+ "5743 NT suction \n",
+ "1520 ACT \n",
+ "220507 Activated Clotting Time ACT \n",
+ "1671 act \n",
+ "8339 Neo Opium Solution \n",
+ "42288 LR w/40 kcl \n",
+ "225072 Living situation Living situation \n",
+ "42345 LR w/ 40 mEq \n",
+ "2773 sjlactate \n",
+ "5088 fingers \n",
+ "42265 LR W/ 20 KCL \n",
+ "220955 Ringers Lactate Ringers Lactate \n",
+ "\n",
+ " linksto category unitname score \n",
+ "itemid \n",
+ "225828 inputevents_mv Fluids/Intake mL 110.000000 \n",
+ "44367 inputevents_cv Free Form Intake 110.000000 \n",
+ "2971 chartevents 110.000000 \n",
+ "1634 chartevents 110.000000 \n",
+ "30021 inputevents_cv 110.000000 \n",
+ "45532 inputevents_cv Free Form Intake 104.000000 \n",
+ "225943 inputevents_mv Fluids/Intake mL 88.000000 \n",
+ "225827 inputevents_mv Fluids/Intake mL 88.000000 \n",
+ "50813 labevents BLOOD GAS NaN 84.000000 \n",
+ "220953 inputevents_mv Fluids - Other (Not In Use) mL 84.000000 \n",
+ "46207 inputevents_cv Free Form Intake 81.333333 \n",
+ "44184 inputevents_cv Free Form Intake 70.000000 \n",
+ "44521 inputevents_cv Free Form Intake 70.000000 \n",
+ "46781 inputevents_cv Free Form Intake 70.000000 \n",
+ "44815 inputevents_cv Free Form Intake 70.000000 \n",
+ "44915 inputevents_cv Free Form Intake 70.000000 \n",
+ "46538 inputevents_cv Free Form Intake 68.333333 \n",
+ "44837 outputevents 68.000000 \n",
+ "8313 chartevents 67.666667 \n",
+ "30125 inputevents_cv 67.333333 \n",
+ "221986 inputevents_mv Medications mg 67.333333 \n",
+ "30159 inputevents_cv 67.333333 \n",
+ "228159 chartevents Impella ml/hr 66.666667 \n",
+ "225953 Dialysis 66.000000 \n",
+ "45983 inputevents_cv Free Form Intake 65.333333 \n",
+ "42409 inputevents_cv Free Form Intake 65.333333 \n",
+ "42978 inputevents_cv Free Form Intake 65.333333 \n",
+ "1189 chartevents 65.000000 \n",
+ "5743 chartevents 64.666667 \n",
+ "1520 chartevents Coags 64.666667 \n",
+ "220507 chartevents Labs None 64.666667 \n",
+ "1671 chartevents 64.666667 \n",
+ "8339 chartevents 64.333333 \n",
+ "42288 inputevents_cv Free Form Intake 64.000000 \n",
+ "225072 Adm History/FHPA 63.666667 \n",
+ "42345 inputevents_cv Free Form Intake 63.333333 \n",
+ "2773 chartevents 63.333333 \n",
+ "5088 chartevents 63.333333 \n",
+ "42265 inputevents_cv Free Form Intake 63.333333 \n",
+ "220955 inputevents_mv Fluids - Other (Not In Use) mL 63.000000 "
+ ]
+ },
+ "execution_count": 114,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df.head(40)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 115,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.LACTATED_RINGERS] = [225828,44367,2971,1634,30021,220953,46207,44184,44521,46781,44815]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Pressors"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Norepinephrine"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 117,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>30047</th>\n",
+ " <td>Levophed</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>221906</th>\n",
+ " <td>Norepinephrine</td>\n",
+ " <td>Norepinephrine</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mg</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30120</th>\n",
+ " <td>Levophed-k</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>102.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30044</th>\n",
+ " <td>Epinephrine</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>102.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>221289</th>\n",
+ " <td>Epinephrine</td>\n",
+ " <td>Epinephrine</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>mg</td>\n",
+ " <td>102.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5752</th>\n",
+ " <td>Epinephrin</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>98.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51201</th>\n",
+ " <td>EPINEPHERINE</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>88.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30119</th>\n",
+ " <td>Epinephrine-k</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>84.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30309</th>\n",
+ " <td>Epinephrine Drip</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>77.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30127</th>\n",
+ " <td>Neosynephrine</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>72.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>225922</th>\n",
+ " <td>Nephramine</td>\n",
+ " <td>Nephramine</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Nutrition - Supplements</td>\n",
+ " <td>mL</td>\n",
+ " <td>71.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3112</th>\n",
+ " <td>epinephrine mcg/min</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>71.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50820</th>\n",
+ " <td>PH</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51491</th>\n",
+ " <td>PH</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>HEMATOLOGY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>51094</th>\n",
+ " <td>PH</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>CHEMISTRY</td>\n",
+ " <td>NaN</td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50831</th>\n",
+ " <td>PH</td>\n",
+ " <td>NaN</td>\n",
+ " <td>labevents</td>\n",
+ " <td>BLOOD GAS</td>\n",
+ " <td>NaN</td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45183</th>\n",
+ " <td>ED</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7459</th>\n",
+ " <td>Ph</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1673</th>\n",
+ " <td>PH</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>70.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>30128</th>\n",
+ " <td>Neosynephrine-k</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>69.666667</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "30047 Levophed inputevents_cv \n",
+ "221906 Norepinephrine Norepinephrine inputevents_mv \n",
+ "30120 Levophed-k inputevents_cv \n",
+ "30044 Epinephrine inputevents_cv \n",
+ "221289 Epinephrine Epinephrine inputevents_mv \n",
+ "5752 Epinephrin chartevents \n",
+ "51201 EPINEPHERINE NaN labevents \n",
+ "30119 Epinephrine-k inputevents_cv \n",
+ "30309 Epinephrine Drip inputevents_cv \n",
+ "30127 Neosynephrine inputevents_cv \n",
+ "225922 Nephramine Nephramine inputevents_mv \n",
+ "3112 epinephrine mcg/min chartevents \n",
+ "50820 PH NaN labevents \n",
+ "51491 PH NaN labevents \n",
+ "51094 PH NaN labevents \n",
+ "50831 PH NaN labevents \n",
+ "45183 ED inputevents_cv \n",
+ "7459 Ph chartevents \n",
+ "1673 PH chartevents \n",
+ "30128 Neosynephrine-k inputevents_cv \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "30047 110.000000 \n",
+ "221906 Medications mg 110.000000 \n",
+ "30120 102.666667 \n",
+ "30044 102.000000 \n",
+ "221289 Medications mg 102.000000 \n",
+ "5752 98.666667 \n",
+ "51201 HEMATOLOGY NaN 88.666667 \n",
+ "30119 84.666667 \n",
+ "30309 77.333333 \n",
+ "30127 72.333333 \n",
+ "225922 Nutrition - Supplements mL 71.333333 \n",
+ "3112 71.000000 \n",
+ "50820 BLOOD GAS NaN 70.000000 \n",
+ "51491 HEMATOLOGY NaN 70.000000 \n",
+ "51094 CHEMISTRY NaN 70.000000 \n",
+ "50831 BLOOD GAS NaN 70.000000 \n",
+ "45183 Free Form Intake 70.000000 \n",
+ "7459 70.000000 \n",
+ "1673 70.000000 \n",
+ "30128 69.666667 "
+ ]
+ },
+ "execution_count": 117,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'levophed',\n",
+ " 'norepinephrine'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 118,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.NOREPINEPHRINE] = [30047,221906,30120]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Vasopressin"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 119,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>abbreviation</th>\n",
+ " <th>linksto</th>\n",
+ " <th>category</th>\n",
+ " <th>unitname</th>\n",
+ " <th>score</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>itemid</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>30051</th>\n",
+ " <td>Vasopressin</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2445</th>\n",
+ " <td>Vasopressin</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>222315</th>\n",
+ " <td>Vasopressin</td>\n",
+ " <td>Vasopressin</td>\n",
+ " <td>inputevents_mv</td>\n",
+ " <td>Medications</td>\n",
+ " <td>units</td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1136</th>\n",
+ " <td>vasopressin</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1222</th>\n",
+ " <td>VASOPRESSIN</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>110.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2334</th>\n",
+ " <td>vasopressin u/hr</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2561</th>\n",
+ " <td>VASOPRESSIN U/HR</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>97.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7341</th>\n",
+ " <td>Vasopressin u/hr</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>96.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46570</th>\n",
+ " <td>vassopressin</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>94.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42802</th>\n",
+ " <td>VASOPRESSIN CC/HR.</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>94.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6255</th>\n",
+ " <td>VAsopressin 0.04 s</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>92.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2765</th>\n",
+ " <td>VASOPRESSIN UNIT/R</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>92.333333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2248</th>\n",
+ " <td>VASOPRESSIN UNIT/MIN</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>42273</th>\n",
+ " <td>vasopressin unit/min</td>\n",
+ " <td></td>\n",
+ " <td>inputevents_cv</td>\n",
+ " <td>Free Form Intake</td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1327</th>\n",
+ " <td>vasopressin unit/min</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>90.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6269</th>\n",
+ " <td>Dressing</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>68.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>46</th>\n",
+ " <td>Angio Dressing #2</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>68.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6691</th>\n",
+ " <td>DRIV PRESS</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>68.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>45</th>\n",
+ " <td>Angio Dressing #1</td>\n",
+ " <td></td>\n",
+ " <td>chartevents</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>68.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>228448</th>\n",
+ " <td>Angio Dressing # 4</td>\n",
+ " <td>Angio Dressing # 4</td>\n",
+ " <td></td>\n",
+ " <td>Cardiovascular</td>\n",
+ " <td></td>\n",
+ " <td>67.333333</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label abbreviation linksto \\\n",
+ "itemid \n",
+ "30051 Vasopressin inputevents_cv \n",
+ "2445 Vasopressin chartevents \n",
+ "222315 Vasopressin Vasopressin inputevents_mv \n",
+ "1136 vasopressin chartevents \n",
+ "1222 VASOPRESSIN chartevents \n",
+ "2334 vasopressin u/hr chartevents \n",
+ "2561 VASOPRESSIN U/HR chartevents \n",
+ "7341 Vasopressin u/hr chartevents \n",
+ "46570 vassopressin inputevents_cv \n",
+ "42802 VASOPRESSIN CC/HR. inputevents_cv \n",
+ "6255 VAsopressin 0.04 s chartevents \n",
+ "2765 VASOPRESSIN UNIT/R chartevents \n",
+ "2248 VASOPRESSIN UNIT/MIN chartevents \n",
+ "42273 vasopressin unit/min inputevents_cv \n",
+ "1327 vasopressin unit/min chartevents \n",
+ "6269 Dressing chartevents \n",
+ "46 Angio Dressing #2 chartevents \n",
+ "6691 DRIV PRESS chartevents \n",
+ "45 Angio Dressing #1 chartevents \n",
+ "228448 Angio Dressing # 4 Angio Dressing # 4 \n",
+ "\n",
+ " category unitname score \n",
+ "itemid \n",
+ "30051 110.000000 \n",
+ "2445 110.000000 \n",
+ "222315 Medications units 110.000000 \n",
+ "1136 110.000000 \n",
+ "1222 110.000000 \n",
+ "2334 97.333333 \n",
+ "2561 97.333333 \n",
+ "7341 96.666667 \n",
+ "46570 Free Form Intake 94.333333 \n",
+ "42802 Free Form Intake 94.000000 \n",
+ "6255 92.333333 \n",
+ "2765 92.333333 \n",
+ "2248 90.666667 \n",
+ "42273 Free Form Intake 90.666667 \n",
+ "1327 90.666667 \n",
+ "6269 68.666667 \n",
+ "46 68.000000 \n",
+ "6691 68.000000 \n",
+ "45 68.000000 \n",
+ "228448 Cardiovascular 67.333333 "
+ ]
+ },
+ "execution_count": 119,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "out_df = explorer.search([\n",
+ " 'vasopressin',\n",
+ " 'argipressin',\n",
+ " 'arginine vasopressin'\n",
+ " ])\n",
+ "out_df.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 120,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "keep_dict[data_dict.labels.VASOPRESSIN] = out_df.loc[:1327].index.tolist()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Now build our mapping dataframe"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 124,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "from itertools import product"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 131,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": [
+ "tuples = []\n",
+ "\n",
+ "for label,items in keep_dict.iteritems():\n",
+ " tuples += list(product([label],items))\n",
+ "\n",
+ "item_map = pd.DataFrame(tuples,columns=['label','itemid'])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 132,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>glasgow coma scale eye opening</td>\n",
+ " <td>184</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>glasgow coma scale eye opening</td>\n",
+ " <td>220739</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>glasgow coma scale motor</td>\n",
+ " <td>454</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>glasgow coma scale motor</td>\n",
+ " <td>223901</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>blood pressure systolic</td>\n",
+ " <td>220179</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " label itemid\n",
+ "0 glasgow coma scale eye opening 184\n",
+ "1 glasgow coma scale eye opening 220739\n",
+ "2 glasgow coma scale motor 454\n",
+ "3 glasgow coma scale motor 223901\n",
+ "4 blood pressure systolic 220179"
+ ]
+ },
+ "execution_count": 132,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "item_map.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 133,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "item_map.to_csv('config/mimic_item_map.csv',index=False)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Extract MIMIC III data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import mimic\n",
+ "from constants import ALL\n",
+ "import icu_data_defs \n",
+ "import utils\n",
+ "import logger\n",
+ "import warnings\n",
+ "warnings.filterwarnings('ignore')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload(icu_data_defs)\n",
+ "reload(mimic)\n",
+ "reload(logger)\n",
+ "\n",
+ "def extract_labels(conn,labels,item_map_fname,hdf5_fname,hadm_ids=ALL):\n",
+ " logger.log('Start extracting {} labels'.format(len(labels)),new_level=True)\n",
+ " extractor = mimic.mimic_extractor(conn,item_map_fname)\n",
+ " for label in labels:\n",
+ " logger.log(label.upper(),new_level=True)\n",
+ " df = extractor.extract_label(label,hadm_ids)\n",
+ " if df is None: continue\n",
+ " utils.save_df(df,hdf5_fname,'extract/{}'.format(label))\n",
+ " display(df.head())\n",
+ " print df.shape\n",
+ " del df\n",
+ " logger.end_log()\n",
+ " return \n",
+ "\n",
+ "#connect to the mimic database\n",
+ "conn = mimic.connect()\n",
+ "\n",
+ "#these are the default config files we will be using\n",
+ "item_map_fname = 'config/mimic_item_map.csv'\n",
+ "mimic_data_sef_fname = 'config/data_definitions.xlsx'\n",
+ "\n",
+ "#get all labels\n",
+ "data_dict = icu_data_defs.data_dictionary(mimic_data_sef_fname)\n",
+ "simple_data = data_dict.get_panel_defintions(12) #12 is \"simple data\"\n",
+ "labels = simple_data.label.unique().tolist()\n",
+ "\n",
+ "#where we will be storing this extraction\n",
+ "hdf5_fname = 'data/mimic_data'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 03:26:58) Start extracting 5 labels\n",
+ "(2017-06-03 03:26:58)>> HEART RATE\n",
+ "(2017-06-03 03:26:59)>>>> Extracting 5 items from chartevents\n",
+ "(2017-06-03 03:26:59)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:26:59)>>>> Combine DF\n",
+ "(2017-06-03 03:26:59)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:26:59)>>>> Clean UOM\n",
+ "(2017-06-03 03:26:59)<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 00:00:00</td>\n",
+ " <td>62</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 00:30:00</td>\n",
+ " <td>67</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 01:00:00</td>\n",
+ " <td>67</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 01:20:00</td>\n",
+ " <td>63</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 01:25:00</td>\n",
+ " <td>63</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 143838 2129-07-14 00:00:00 62 beat/min 211\n",
+ "1 143838 2129-07-14 00:30:00 67 beat/min 211\n",
+ "2 143838 2129-07-14 01:00:00 67 beat/min 211\n",
+ "3 143838 2129-07-14 01:20:00 63 beat/min 211\n",
+ "4 143838 2129-07-14 01:25:00 63 beat/min 211"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(1649, 5)\n",
+ "(2017-06-03 03:27:01)<< DONE (3.0s)\n",
+ "(2017-06-03 03:27:01)>> BLOOD PRESSURE SYSTOLIC\n",
+ "(2017-06-03 03:27:01)>>>> Extracting 14 items from chartevents\n",
+ "(2017-06-03 03:27:02)<<<< DONE (1.0s)\n",
+ "(2017-06-03 03:27:02)>>>> Combine DF\n",
+ "(2017-06-03 03:27:02)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:27:02)>>>> Clean UOM\n",
+ "(2017-06-03 03:27:02)<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-13 22:40:00</td>\n",
+ " <td>145</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-13 23:00:00</td>\n",
+ " <td>136</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-13 23:30:00</td>\n",
+ " <td>179</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 00:00:00</td>\n",
+ " <td>131</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 00:30:00</td>\n",
+ " <td>146</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 143838 2129-07-13 22:40:00 145 mmHg 51\n",
+ "1 143838 2129-07-13 23:00:00 136 mmHg 51\n",
+ "2 143838 2129-07-13 23:30:00 179 mmHg 51\n",
+ "3 143838 2129-07-14 00:00:00 131 mmHg 51\n",
+ "4 143838 2129-07-14 00:30:00 146 mmHg 51"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(644, 5)\n",
+ "(2017-06-03 03:27:02)<< DONE (1.0s)\n",
+ "(2017-06-03 03:27:02)>> BLOOD PRESSURE DIASTOLIC\n",
+ "(2017-06-03 03:27:02)>>>> Extracting 15 items from chartevents\n",
+ "(2017-06-03 03:27:02)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:27:02)>>>> Combine DF\n",
+ "(2017-06-03 03:27:02)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:27:02)>>>> Clean UOM\n",
+ "(2017-06-03 03:27:02)<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 21:00:00</td>\n",
+ " <td>53</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 14:00:00</td>\n",
+ " <td>84</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 10:30:00</td>\n",
+ " <td>54</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 15:00:00</td>\n",
+ " <td>60</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 16:00:00</td>\n",
+ " <td>59</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 113540 2161-10-12 21:00:00 53 mmHg 220051\n",
+ "1 113540 2161-10-12 14:00:00 84 mmHg 220051\n",
+ "2 113540 2161-10-12 10:30:00 54 mmHg 220051\n",
+ "3 113540 2161-10-12 15:00:00 60 mmHg 220051\n",
+ "4 113540 2161-10-12 16:00:00 59 mmHg 220051"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(640, 5)\n",
+ "(2017-06-03 03:27:02)<< DONE (0.0s)\n",
+ "(2017-06-03 03:27:02)>> BLOOD PRESSURE MEAN\n",
+ "(2017-06-03 03:27:03)>>>> Extracting 3 items from chartevents\n",
+ "(2017-06-03 03:27:03)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:27:03)>>>> Combine DF\n",
+ "(2017-06-03 03:27:03)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:27:03)>>>> Clean UOM\n",
+ "(2017-06-03 03:27:03)<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 21:00:00</td>\n",
+ " <td>76</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 12:00:00</td>\n",
+ " <td>91</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 14:00:00</td>\n",
+ " <td>82</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 10:30:00</td>\n",
+ " <td>70</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>113540</td>\n",
+ " <td>2161-10-12 15:00:00</td>\n",
+ " <td>80</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 113540 2161-10-12 21:00:00 76 mmHg 220052\n",
+ "1 113540 2161-10-12 12:00:00 91 mmHg 220052\n",
+ "2 113540 2161-10-12 14:00:00 82 mmHg 220052\n",
+ "3 113540 2161-10-12 10:30:00 70 mmHg 220052\n",
+ "4 113540 2161-10-12 15:00:00 80 mmHg 220052"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(58, 5)\n",
+ "(2017-06-03 03:27:03)<< DONE (1.0s)\n",
+ "(2017-06-03 03:27:03)>> RESPIRATORY RATE\n",
+ "(2017-06-03 03:27:03)>>>> Extracting 4 items from chartevents\n",
+ "(2017-06-03 03:27:04)<<<< DONE (1.0s)\n",
+ "(2017-06-03 03:27:04)>>>> Combine DF\n",
+ "(2017-06-03 03:27:04)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:27:04)>>>> Clean UOM\n",
+ "(2017-06-03 03:27:04)<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-13 23:30:00</td>\n",
+ " <td>17</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 00:00:00</td>\n",
+ " <td>20</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 00:30:00</td>\n",
+ " <td>17</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 01:00:00</td>\n",
+ " <td>13</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>143838</td>\n",
+ " <td>2129-07-14 01:20:00</td>\n",
+ " <td>15</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 143838 2129-07-13 23:30:00 17 breath/min 618\n",
+ "1 143838 2129-07-14 00:00:00 20 breath/min 618\n",
+ "2 143838 2129-07-14 00:30:00 17 breath/min 618\n",
+ "3 143838 2129-07-14 01:00:00 13 breath/min 618\n",
+ "4 143838 2129-07-14 01:20:00 15 breath/min 618"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(1647, 5)\n",
+ "(2017-06-03 03:27:04)<< DONE (1.0s)\n",
+ "(2017-06-03 03:27:04) DONE (6.0s)\n"
+ ]
+ }
+ ],
+ "source": [
+ "hadm_ids = mimic.sample_hadm_ids(5,conn)\n",
+ "extract_labels(conn,labels[0:5],item_map_fname,hdf5_fname,hadm_ids)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 03:27:10) Start extracting 18 labels\n",
+ "(2017-06-03 03:27:10)>> HEART RATE\n",
+ "(2017-06-03 03:27:10)>>>> Extracting 5 items from chartevents\n",
+ "(2017-06-03 03:28:03)<<<< DONE (53.0s)\n",
+ "(2017-06-03 03:28:03)>>>> Combine DF\n",
+ "(2017-06-03 03:28:03)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:28:03)>>>> Clean UOM\n",
+ "(2017-06-03 03:28:07)<<<< DONE (4.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-26 03:00:00</td>\n",
+ " <td>79</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>106266.0</td>\n",
+ " <td>2114-12-02 06:00:00</td>\n",
+ " <td>116</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>106266.0</td>\n",
+ " <td>2114-12-02 07:00:00</td>\n",
+ " <td>116</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>106266.0</td>\n",
+ " <td>2114-12-02 08:00:00</td>\n",
+ " <td>144</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>106266.0</td>\n",
+ " <td>2114-12-03 08:00:00</td>\n",
+ " <td>144</td>\n",
+ " <td>beat/min</td>\n",
+ " <td>211</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-26 03:00:00 79 beat/min 211\n",
+ "1 106266.0 2114-12-02 06:00:00 116 beat/min 211\n",
+ "2 106266.0 2114-12-02 07:00:00 116 beat/min 211\n",
+ "3 106266.0 2114-12-02 08:00:00 144 beat/min 211\n",
+ "4 106266.0 2114-12-03 08:00:00 144 beat/min 211"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(7952939, 5)\n",
+ "(2017-06-03 03:28:20)<< DONE (70.0s)\n",
+ "(2017-06-03 03:28:20)>> BLOOD PRESSURE SYSTOLIC\n",
+ "(2017-06-03 03:28:21)>>>> Extracting 14 items from chartevents\n",
+ "(2017-06-03 03:29:45)<<<< DONE (84.0s)\n",
+ "(2017-06-03 03:29:45)>>>> Combine DF\n",
+ "(2017-06-03 03:29:45)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:29:45)>>>> Clean UOM\n",
+ "(2017-06-03 03:29:48)<<<< DONE (3.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>176203.0</td>\n",
+ " <td>2154-11-12 22:00:00</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>197569.0</td>\n",
+ " <td>2133-03-09 00:00:00</td>\n",
+ " <td>117</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>197569.0</td>\n",
+ " <td>2133-03-09 01:00:00</td>\n",
+ " <td>117</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>197569.0</td>\n",
+ " <td>2133-03-09 02:00:00</td>\n",
+ " <td>127</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>197569.0</td>\n",
+ " <td>2133-03-09 03:00:00</td>\n",
+ " <td>126</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 176203.0 2154-11-12 22:00:00 51\n",
+ "1 197569.0 2133-03-09 00:00:00 117 mmHg 51\n",
+ "2 197569.0 2133-03-09 01:00:00 117 mmHg 51\n",
+ "3 197569.0 2133-03-09 02:00:00 127 mmHg 51\n",
+ "4 197569.0 2133-03-09 03:00:00 126 mmHg 51"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(6374824, 5)\n",
+ "(2017-06-03 03:30:00)<< DONE (100.0s)\n",
+ "(2017-06-03 03:30:00)>> BLOOD PRESSURE DIASTOLIC\n",
+ "(2017-06-03 03:30:00)>>>> Extracting 15 items from chartevents\n",
+ "(2017-06-03 03:31:18)<<<< DONE (78.0s)\n",
+ "(2017-06-03 03:31:18)>>>> Combine DF\n",
+ "(2017-06-03 03:31:19)<<<< DONE (1.0s)\n",
+ "(2017-06-03 03:31:19)>>>> Clean UOM\n",
+ "(2017-06-03 03:31:22)<<<< DONE (3.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>124321.0</td>\n",
+ " <td>2157-10-21 12:15:00</td>\n",
+ " <td>74</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>124321.0</td>\n",
+ " <td>2157-10-21 13:00:00</td>\n",
+ " <td>67</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>124321.0</td>\n",
+ " <td>2157-10-21 14:00:00</td>\n",
+ " <td>64</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>124321.0</td>\n",
+ " <td>2157-10-21 15:00:00</td>\n",
+ " <td>76</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>124321.0</td>\n",
+ " <td>2157-10-21 16:17:00</td>\n",
+ " <td>80</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220051</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 124321.0 2157-10-21 12:15:00 74 mmHg 220051\n",
+ "1 124321.0 2157-10-21 13:00:00 67 mmHg 220051\n",
+ "2 124321.0 2157-10-21 14:00:00 64 mmHg 220051\n",
+ "3 124321.0 2157-10-21 15:00:00 76 mmHg 220051\n",
+ "4 124321.0 2157-10-21 16:17:00 80 mmHg 220051"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(6371249, 5)\n",
+ "(2017-06-03 03:31:34)<< DONE (94.0s)\n",
+ "(2017-06-03 03:31:34)>> BLOOD PRESSURE MEAN\n",
+ "(2017-06-03 03:31:34)>>>> Extracting 3 items from chartevents\n",
+ "(2017-06-03 03:32:13)<<<< DONE (39.0s)\n",
+ "(2017-06-03 03:32:13)>>>> Combine DF\n",
+ "(2017-06-03 03:32:13)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:32:13)>>>> Clean UOM\n",
+ "(2017-06-03 03:32:14)<<<< DONE (1.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>124321</td>\n",
+ " <td>2157-10-21 13:00:00</td>\n",
+ " <td>86</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>124321</td>\n",
+ " <td>2157-10-21 14:00:00</td>\n",
+ " <td>86</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>124321</td>\n",
+ " <td>2157-10-21 15:00:00</td>\n",
+ " <td>98</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>124321</td>\n",
+ " <td>2157-10-21 16:17:00</td>\n",
+ " <td>104</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>124321</td>\n",
+ " <td>2157-10-21 17:00:00</td>\n",
+ " <td>104</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>220052</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 124321 2157-10-21 13:00:00 86 mmHg 220052\n",
+ "1 124321 2157-10-21 14:00:00 86 mmHg 220052\n",
+ "2 124321 2157-10-21 15:00:00 98 mmHg 220052\n",
+ "3 124321 2157-10-21 16:17:00 104 mmHg 220052\n",
+ "4 124321 2157-10-21 17:00:00 104 mmHg 220052"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2536271, 5)\n",
+ "(2017-06-03 03:32:18)<< DONE (44.0s)\n",
+ "(2017-06-03 03:32:18)>> RESPIRATORY RATE\n",
+ "(2017-06-03 03:32:18)>>>> Extracting 4 items from chartevents\n",
+ "(2017-06-03 03:34:08)<<<< DONE (110.0s)\n",
+ "(2017-06-03 03:34:08)>>>> Combine DF\n",
+ "(2017-06-03 03:34:08)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:34:08)>>>> Clean UOM\n",
+ "(2017-06-03 03:34:13)<<<< DONE (5.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-25 00:00:00</td>\n",
+ " <td>20</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>122659.0</td>\n",
+ " <td>2131-05-22 14:00:00</td>\n",
+ " <td>29</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>188670.0</td>\n",
+ " <td>2183-08-23 19:00:00</td>\n",
+ " <td>24</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>188670.0</td>\n",
+ " <td>2183-08-23 20:00:00</td>\n",
+ " <td>24</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-10 13:30:00</td>\n",
+ " <td>22</td>\n",
+ " <td>breath/min</td>\n",
+ " <td>618</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-25 00:00:00 20 breath/min 618\n",
+ "1 122659.0 2131-05-22 14:00:00 29 breath/min 618\n",
+ "2 188670.0 2183-08-23 19:00:00 24 breath/min 618\n",
+ "3 188670.0 2183-08-23 20:00:00 24 breath/min 618\n",
+ "4 185910.0 2166-08-10 13:30:00 22 breath/min 618"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(7810019, 5)\n",
+ "(2017-06-03 03:34:27)<< DONE (129.0s)\n",
+ "(2017-06-03 03:34:27)>> TEMPERATURE BODY\n",
+ "(2017-06-03 03:34:27)>>>> Extracting 4 items from chartevents\n",
+ "(2017-06-03 03:35:01)<<<< DONE (34.0s)\n",
+ "(2017-06-03 03:35:01)>>>> Combine DF\n",
+ "(2017-06-03 03:35:01)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:35:01)>>>> Clean UOM\n",
+ "(2017-06-03 03:35:02)<<<< DONE (1.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-25 00:00:00</td>\n",
+ " <td>98.400001525878906</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>188670.0</td>\n",
+ " <td>2183-08-23 20:00:00</td>\n",
+ " <td>99.300003051757812</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-12 08:00:00</td>\n",
+ " <td>98.699996948242188</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-13 17:00:00</td>\n",
+ " <td>99.900001525878906</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>166707.0</td>\n",
+ " <td>2122-02-11 20:00:00</td>\n",
+ " <td>37.900001525878906</td>\n",
+ " <td>degC</td>\n",
+ " <td>676</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-25 00:00:00 98.400001525878906 degF 678\n",
+ "1 188670.0 2183-08-23 20:00:00 99.300003051757812 degF 678\n",
+ "2 185910.0 2166-08-12 08:00:00 98.699996948242188 degF 678\n",
+ "3 185910.0 2166-08-13 17:00:00 99.900001525878906 degF 678\n",
+ "4 166707.0 2122-02-11 20:00:00 37.900001525878906 degC 676"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(1751447, 5)\n",
+ "(2017-06-03 03:35:05)<< DONE (38.0s)\n",
+ "(2017-06-03 03:35:05)>> OXYGEN SATURATION PULSE OXIMETRY\n",
+ "(2017-06-03 03:35:06)>>>> Extracting 2 items from chartevents\n",
+ "(2017-06-03 03:35:59)<<<< DONE (53.0s)\n",
+ "(2017-06-03 03:35:59)>>>> Combine DF\n",
+ "(2017-06-03 03:35:59)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:35:59)>>>> Clean UOM\n",
+ "(2017-06-03 03:36:02)<<<< DONE (3.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-25 00:00:00</td>\n",
+ " <td>100</td>\n",
+ " <td>percent</td>\n",
+ " <td>646</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-25 00:15:00</td>\n",
+ " <td>100</td>\n",
+ " <td>percent</td>\n",
+ " <td>646</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>122659.0</td>\n",
+ " <td>2131-05-22 14:00:00</td>\n",
+ " <td>100</td>\n",
+ " <td>percent</td>\n",
+ " <td>646</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>188670.0</td>\n",
+ " <td>2183-08-23 19:00:00</td>\n",
+ " <td>97</td>\n",
+ " <td>percent</td>\n",
+ " <td>646</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>188670.0</td>\n",
+ " <td>2183-08-23 20:00:00</td>\n",
+ " <td>97</td>\n",
+ " <td>percent</td>\n",
+ " <td>646</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-25 00:00:00 100 percent 646\n",
+ "1 185910.0 2166-08-25 00:15:00 100 percent 646\n",
+ "2 122659.0 2131-05-22 14:00:00 100 percent 646\n",
+ "3 188670.0 2183-08-23 19:00:00 97 percent 646\n",
+ "4 188670.0 2183-08-23 20:00:00 97 percent 646"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(6099827, 5)\n",
+ "(2017-06-03 03:36:14)<< DONE (69.0s)\n",
+ "(2017-06-03 03:36:14)>> WEIGHT BODY\n",
+ "(2017-06-03 03:36:14)>>>> Extracting 3 items from chartevents\n",
+ "(2017-06-03 03:36:48)<<<< DONE (34.0s)\n",
+ "(2017-06-03 03:36:48)>>>> Combine DF\n",
+ "(2017-06-03 03:36:49)<<<< DONE (1.0s)\n",
+ "(2017-06-03 03:36:49)>>>> Clean UOM\n",
+ "(2017-06-03 03:36:49)<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-20 06:00:00</td>\n",
+ " <td>102.5</td>\n",
+ " <td>kg</td>\n",
+ " <td>763</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>166707.0</td>\n",
+ " <td>2122-02-15 07:00:00</td>\n",
+ " <td>99.400001525878906</td>\n",
+ " <td>kg</td>\n",
+ " <td>763</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>182104.0</td>\n",
+ " <td>2131-05-05 06:00:00</td>\n",
+ " <td>109.69999694824219</td>\n",
+ " <td>kg</td>\n",
+ " <td>763</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>157907.0</td>\n",
+ " <td>2129-06-10 05:00:00</td>\n",
+ " <td>103.19999694824219</td>\n",
+ " <td>kg</td>\n",
+ " <td>763</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>166707.0</td>\n",
+ " <td>2122-02-14 06:00:00</td>\n",
+ " <td>101.80000305175781</td>\n",
+ " <td>kg</td>\n",
+ " <td>763</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-20 06:00:00 102.5 kg 763\n",
+ "1 166707.0 2122-02-15 07:00:00 99.400001525878906 kg 763\n",
+ "2 182104.0 2131-05-05 06:00:00 109.69999694824219 kg 763\n",
+ "3 157907.0 2129-06-10 05:00:00 103.19999694824219 kg 763\n",
+ "4 166707.0 2122-02-14 06:00:00 101.80000305175781 kg 763"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(95425, 5)\n",
+ "(2017-06-03 03:36:49)<< DONE (35.0s)\n",
+ "(2017-06-03 03:36:49)>> OUTPUT URINE\n",
+ "(2017-06-03 03:36:49)>>>> Extracting 2 items from chartevents\n",
+ "(2017-06-03 03:37:28)<<<< DONE (39.0s)\n",
+ "(2017-06-03 03:37:28)>>>> Extracting 29 items from outputevents\n",
+ "(2017-06-03 03:37:59)<<<< DONE (31.0s)\n",
+ "(2017-06-03 03:37:59)>>>> Combine DF\n",
+ "(2017-06-03 03:37:59)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:37:59)>>>> Clean UOM\n",
+ "(2017-06-03 03:38:09)<<<< DONE (10.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>106266.0</td>\n",
+ " <td>2114-12-03 08:00:00</td>\n",
+ " <td>Voiding qs</td>\n",
+ " <td>ml</td>\n",
+ " <td>3686</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>106266.0</td>\n",
+ " <td>2114-12-09 09:00:00</td>\n",
+ " <td>Voiding qs</td>\n",
+ " <td>ml</td>\n",
+ " <td>3686</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>106266.0</td>\n",
+ " <td>2114-12-09 14:00:00</td>\n",
+ " <td>Voiding qs</td>\n",
+ " <td>ml</td>\n",
+ " <td>3686</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>106266.0</td>\n",
+ " <td>2114-12-05 21:30:00</td>\n",
+ " <td>Voiding qs</td>\n",
+ " <td>ml</td>\n",
+ " <td>3686</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>106266.0</td>\n",
+ " <td>2114-12-04 16:00:00</td>\n",
+ " <td>Voiding qs</td>\n",
+ " <td>ml</td>\n",
+ " <td>3686</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 106266.0 2114-12-03 08:00:00 Voiding qs ml 3686\n",
+ "1 106266.0 2114-12-09 09:00:00 Voiding qs ml 3686\n",
+ "2 106266.0 2114-12-09 14:00:00 Voiding qs ml 3686\n",
+ "3 106266.0 2114-12-05 21:30:00 Voiding qs ml 3686\n",
+ "4 106266.0 2114-12-04 16:00:00 Voiding qs ml 3686"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(3644639, 5)\n",
+ "(2017-06-03 03:38:15)<< DONE (86.0s)\n",
+ "(2017-06-03 03:38:15)>> GLASGOW COMA SCALE MOTOR\n",
+ "(2017-06-03 03:38:15)>>>> Extracting 1 items from chartevents\n",
+ "(2017-06-03 03:39:12)<<<< DONE (57.0s)\n",
+ "(2017-06-03 03:39:12)>>>> Combine DF\n",
+ "(2017-06-03 03:39:12)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:39:12)>>>> Clean UOM\n",
+ "(2017-06-03 03:39:12)<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-25 00:00:00</td>\n",
+ " <td>6 Obeys Commands</td>\n",
+ " <td></td>\n",
+ " <td>454</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>188670.0</td>\n",
+ " <td>2183-08-23 20:00:00</td>\n",
+ " <td>6 Obeys Commands</td>\n",
+ " <td></td>\n",
+ " <td>454</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-27 12:00:00</td>\n",
+ " <td>5 Localizes Pain</td>\n",
+ " <td></td>\n",
+ " <td>454</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-09-03 12:00:00</td>\n",
+ " <td>6 Obeys Commands</td>\n",
+ " <td></td>\n",
+ " <td>454</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>101757.0</td>\n",
+ " <td>2133-01-03 16:00:00</td>\n",
+ " <td>6 Obeys Commands</td>\n",
+ " <td></td>\n",
+ " <td>454</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-25 00:00:00 6 Obeys Commands 454\n",
+ "1 188670.0 2183-08-23 20:00:00 6 Obeys Commands 454\n",
+ "2 185910.0 2166-08-27 12:00:00 5 Localizes Pain 454\n",
+ "3 185910.0 2166-09-03 12:00:00 6 Obeys Commands 454\n",
+ "4 101757.0 2133-01-03 16:00:00 6 Obeys Commands 454"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(952565, 5)\n",
+ "(2017-06-03 03:39:13)<< DONE (58.0s)\n",
+ "(2017-06-03 03:39:13)>> GLASGOW COMA SCALE EYE OPENING\n",
+ "(2017-06-03 03:39:13)>>>> Extracting 1 items from chartevents\n",
+ "(2017-06-03 03:39:57)<<<< DONE (44.0s)\n",
+ "(2017-06-03 03:39:57)>>>> Combine DF\n",
+ "(2017-06-03 03:39:57)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:39:57)>>>> Clean UOM\n",
+ "(2017-06-03 03:39:57)<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>188670.0</td>\n",
+ " <td>2183-08-23 20:00:00</td>\n",
+ " <td>4 Spontaneously</td>\n",
+ " <td></td>\n",
+ " <td>184</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-15 20:00:00</td>\n",
+ " <td>4 Spontaneously</td>\n",
+ " <td></td>\n",
+ " <td>184</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-16 16:00:00</td>\n",
+ " <td>3 To speech</td>\n",
+ " <td></td>\n",
+ " <td>184</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-23 04:00:00</td>\n",
+ " <td>3 To speech</td>\n",
+ " <td></td>\n",
+ " <td>184</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-27 12:00:00</td>\n",
+ " <td>1 No Response</td>\n",
+ " <td></td>\n",
+ " <td>184</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 188670.0 2183-08-23 20:00:00 4 Spontaneously 184\n",
+ "1 185910.0 2166-08-15 20:00:00 4 Spontaneously 184\n",
+ "2 185910.0 2166-08-16 16:00:00 3 To speech 184\n",
+ "3 185910.0 2166-08-23 04:00:00 3 To speech 184\n",
+ "4 185910.0 2166-08-27 12:00:00 1 No Response 184"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(956672, 5)\n",
+ "(2017-06-03 03:39:58)<< DONE (45.0s)\n",
+ "(2017-06-03 03:39:58)>> GLASGOW COMA SCALE VERBAL\n",
+ "(2017-06-03 03:39:59)>>>> Extracting 1 items from chartevents\n",
+ "(2017-06-03 03:40:22)<<<< DONE (23.0s)\n",
+ "(2017-06-03 03:40:22)>>>> Combine DF\n",
+ "(2017-06-03 03:40:22)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:40:22)>>>> Clean UOM\n",
+ "(2017-06-03 03:40:22)<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-25 00:00:00</td>\n",
+ " <td>1.0 ET/Trach</td>\n",
+ " <td></td>\n",
+ " <td>723</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>188670.0</td>\n",
+ " <td>2183-08-23 20:00:00</td>\n",
+ " <td>4 Confused</td>\n",
+ " <td></td>\n",
+ " <td>723</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-12 08:00:00</td>\n",
+ " <td>1.0 ET/Trach</td>\n",
+ " <td></td>\n",
+ " <td>723</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-27 12:00:00</td>\n",
+ " <td>1.0 ET/Trach</td>\n",
+ " <td></td>\n",
+ " <td>723</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>166707.0</td>\n",
+ " <td>2122-02-11 20:00:00</td>\n",
+ " <td>5 Oriented</td>\n",
+ " <td></td>\n",
+ " <td>723</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-25 00:00:00 1.0 ET/Trach 723\n",
+ "1 188670.0 2183-08-23 20:00:00 4 Confused 723\n",
+ "2 185910.0 2166-08-12 08:00:00 1.0 ET/Trach 723\n",
+ "3 185910.0 2166-08-27 12:00:00 1.0 ET/Trach 723\n",
+ "4 166707.0 2122-02-11 20:00:00 5 Oriented 723"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(954700, 5)\n",
+ "(2017-06-03 03:40:24)<< DONE (26.0s)\n",
+ "(2017-06-03 03:40:24)>> NORMAL SALINE\n",
+ "(2017-06-03 03:40:24)>>>> Extracting 2 items from chartevents\n",
+ "(2017-06-03 03:40:24)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:40:24)>>>> Extracting 4 items from inputevents_cv\n",
+ "(2017-06-03 03:40:25)<<<< DONE (1.0s)\n",
+ "(2017-06-03 03:40:25)>>>> Extracting 2 items from inputevents_mv\n",
+ "(2017-06-03 03:40:43)<<<< DONE (18.0s)\n",
+ "(2017-06-03 03:40:43)>>>> Combine DF\n",
+ "(2017-06-03 03:40:43)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:40:43)>>>> Clean UOM\n",
+ "(2017-06-03 03:40:46)<<<< DONE (3.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>110468</td>\n",
+ " <td>2134-02-13 03:45:00</td>\n",
+ " <td>given</td>\n",
+ " <td>ml</td>\n",
+ " <td>4647</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>110468</td>\n",
+ " <td>2134-02-13 07:05:00</td>\n",
+ " <td>given</td>\n",
+ " <td>ml</td>\n",
+ " <td>4647</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>175419</td>\n",
+ " <td>2122-08-16 01:00:00</td>\n",
+ " <td>given</td>\n",
+ " <td>ml</td>\n",
+ " <td>4647</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>143494</td>\n",
+ " <td>2147-07-02 23:00:00</td>\n",
+ " <td>given</td>\n",
+ " <td>ml</td>\n",
+ " <td>4647</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>143494</td>\n",
+ " <td>2147-07-02 23:43:00</td>\n",
+ " <td>given</td>\n",
+ " <td>ml</td>\n",
+ " <td>4647</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 110468 2134-02-13 03:45:00 given ml 4647\n",
+ "1 110468 2134-02-13 07:05:00 given ml 4647\n",
+ "2 175419 2122-08-16 01:00:00 given ml 4647\n",
+ "3 143494 2147-07-02 23:00:00 given ml 4647\n",
+ "4 143494 2147-07-02 23:43:00 given ml 4647"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(817373, 5)\n",
+ "(2017-06-03 03:40:46)<< DONE (22.0s)\n",
+ "(2017-06-03 03:40:46)>> LACTATED RINGERS\n",
+ "(2017-06-03 03:40:46)>>>> Extracting 2 items from chartevents\n",
+ "(2017-06-03 03:40:46)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:40:46)>>>> Extracting 7 items from inputevents_cv\n",
+ "(2017-06-03 03:40:50)<<<< DONE (4.0s)\n",
+ "(2017-06-03 03:40:50)>>>> Extracting 2 items from inputevents_mv\n",
+ "(2017-06-03 03:40:51)<<<< DONE (1.0s)\n",
+ "(2017-06-03 03:40:51)>>>> Combine DF\n",
+ "(2017-06-03 03:40:51)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:40:51)>>>> Clean UOM\n",
+ "(2017-06-03 03:40:53)<<<< DONE (2.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>194762.0</td>\n",
+ " <td>2110-11-22 18:00:00</td>\n",
+ " <td>100</td>\n",
+ " <td>ml</td>\n",
+ " <td>1634</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>178769.0</td>\n",
+ " <td>2181-06-01 05:00:00</td>\n",
+ " <td>100</td>\n",
+ " <td>ml</td>\n",
+ " <td>2971</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>178769.0</td>\n",
+ " <td>2181-06-01 01:00:00</td>\n",
+ " <td>100</td>\n",
+ " <td>ml</td>\n",
+ " <td>2971</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>178769.0</td>\n",
+ " <td>2181-06-01 02:00:00</td>\n",
+ " <td>100</td>\n",
+ " <td>ml</td>\n",
+ " <td>2971</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>178769.0</td>\n",
+ " <td>2181-06-01 03:00:00</td>\n",
+ " <td>100</td>\n",
+ " <td>ml</td>\n",
+ " <td>2971</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 194762.0 2110-11-22 18:00:00 100 ml 1634\n",
+ "1 178769.0 2181-06-01 05:00:00 100 ml 2971\n",
+ "2 178769.0 2181-06-01 01:00:00 100 ml 2971\n",
+ "3 178769.0 2181-06-01 02:00:00 100 ml 2971\n",
+ "4 178769.0 2181-06-01 03:00:00 100 ml 2971"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(504306, 5)\n",
+ "(2017-06-03 03:40:53)<< DONE (7.0s)\n",
+ "(2017-06-03 03:40:53)>> NOREPINEPHRINE\n",
+ "(2017-06-03 03:40:53)>>>> Extracting 2 items from inputevents_cv\n",
+ "(2017-06-03 03:41:10)<<<< DONE (17.0s)\n",
+ "(2017-06-03 03:41:10)>>>> Extracting 1 items from inputevents_mv\n",
+ "(2017-06-03 03:41:12)<<<< DONE (2.0s)\n",
+ "(2017-06-03 03:41:12)>>>> Combine DF\n",
+ "(2017-06-03 03:41:12)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:41:12)>>>> Clean UOM\n",
+ "(2017-06-03 03:41:16)<<<< DONE (4.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>181516.0</td>\n",
+ " <td>2121-01-27 00:00:00</td>\n",
+ " <td>NaN</td>\n",
+ " <td>mg</td>\n",
+ " <td>30120</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>194502.0</td>\n",
+ " <td>2102-12-20 08:00:00</td>\n",
+ " <td>NaN</td>\n",
+ " <td>mg</td>\n",
+ " <td>30047</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>172260.0</td>\n",
+ " <td>2124-11-11 16:00:00</td>\n",
+ " <td>NaN</td>\n",
+ " <td>mg</td>\n",
+ " <td>30047</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>114829.0</td>\n",
+ " <td>2107-01-15 22:00:00</td>\n",
+ " <td>NaN</td>\n",
+ " <td>mg</td>\n",
+ " <td>30047</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>181516.0</td>\n",
+ " <td>2121-01-27 01:00:00</td>\n",
+ " <td>NaN</td>\n",
+ " <td>mg</td>\n",
+ " <td>30120</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 181516.0 2121-01-27 00:00:00 NaN mg 30120\n",
+ "1 194502.0 2102-12-20 08:00:00 NaN mg 30047\n",
+ "2 172260.0 2124-11-11 16:00:00 NaN mg 30047\n",
+ "3 114829.0 2107-01-15 22:00:00 NaN mg 30047\n",
+ "4 181516.0 2121-01-27 01:00:00 NaN mg 30120"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(1136938, 5)\n",
+ "(2017-06-03 03:41:16)<< DONE (23.0s)\n",
+ "(2017-06-03 03:41:16)>> VASOPRESSIN\n",
+ "(2017-06-03 03:41:16)>>>> Extracting 10 items from chartevents\n",
+ "(2017-06-03 03:41:17)<<<< DONE (1.0s)\n",
+ "(2017-06-03 03:41:17)>>>> Extracting 4 items from inputevents_cv\n",
+ "(2017-06-03 03:41:22)<<<< DONE (5.0s)\n",
+ "(2017-06-03 03:41:22)>>>> Extracting 1 items from inputevents_mv\n",
+ "(2017-06-03 03:41:23)<<<< DONE (1.0s)\n",
+ "(2017-06-03 03:41:23)>>>> Combine DF\n",
+ "(2017-06-03 03:41:23)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:41:23)>>>> Clean UOM\n",
+ "(2017-06-03 03:41:24)<<<< DONE (1.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>126005.0</td>\n",
+ " <td>2126-09-05 16:30:00</td>\n",
+ " <td></td>\n",
+ " <td>U</td>\n",
+ " <td>1136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>126005.0</td>\n",
+ " <td>2126-09-05 16:45:00</td>\n",
+ " <td></td>\n",
+ " <td>units/hour</td>\n",
+ " <td>1136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>115221.0</td>\n",
+ " <td>2194-12-09 05:00:00</td>\n",
+ " <td>3</td>\n",
+ " <td>U</td>\n",
+ " <td>1136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>115221.0</td>\n",
+ " <td>2194-12-09 06:00:00</td>\n",
+ " <td>3</td>\n",
+ " <td>units/hour</td>\n",
+ " <td>1136</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>115221.0</td>\n",
+ " <td>2194-12-09 04:00:00</td>\n",
+ " <td>3</td>\n",
+ " <td>units/hour</td>\n",
+ " <td>1136</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 126005.0 2126-09-05 16:30:00 U 1136\n",
+ "1 126005.0 2126-09-05 16:45:00 units/hour 1136\n",
+ "2 115221.0 2194-12-09 05:00:00 3 U 1136\n",
+ "3 115221.0 2194-12-09 06:00:00 3 units/hour 1136\n",
+ "4 115221.0 2194-12-09 04:00:00 3 units/hour 1136"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(339184, 5)\n",
+ "(2017-06-03 03:41:24)<< DONE (8.0s)\n",
+ "(2017-06-03 03:41:24)>> HEMOGLOBIN\n",
+ "(2017-06-03 03:41:24)>>>> Extracting 3 items from chartevents\n",
+ "(2017-06-03 03:43:00)<<<< DONE (96.0s)\n",
+ "(2017-06-03 03:43:00)>>>> Extracting 2 items from labevents\n",
+ "(2017-06-03 03:43:27)<<<< DONE (27.0s)\n",
+ "(2017-06-03 03:43:27)>>>> Combine DF\n",
+ "(2017-06-03 03:43:27)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:43:27)>>>> Clean UOM\n",
+ "(2017-06-03 03:43:30)<<<< DONE (3.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-13 01:53:00</td>\n",
+ " <td>9.5</td>\n",
+ " <td>gm/dl</td>\n",
+ " <td>814</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-22 02:14:00</td>\n",
+ " <td>10</td>\n",
+ " <td>gm/dl</td>\n",
+ " <td>814</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-18 03:46:00</td>\n",
+ " <td>10.100000381469727</td>\n",
+ " <td>gm/dl</td>\n",
+ " <td>814</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>157907.0</td>\n",
+ " <td>2129-06-11 02:00:00</td>\n",
+ " <td>9.8999996185302734</td>\n",
+ " <td>gm/dl</td>\n",
+ " <td>814</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-30 02:07:00</td>\n",
+ " <td>9</td>\n",
+ " <td>gm/dl</td>\n",
+ " <td>814</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-13 01:53:00 9.5 gm/dl 814\n",
+ "1 185910.0 2166-08-22 02:14:00 10 gm/dl 814\n",
+ "2 185910.0 2166-08-18 03:46:00 10.100000381469727 gm/dl 814\n",
+ "3 157907.0 2129-06-11 02:00:00 9.8999996185302734 gm/dl 814\n",
+ "4 185910.0 2166-08-30 02:07:00 9 gm/dl 814"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(1167921, 5)\n",
+ "(2017-06-03 03:43:31)<< DONE (127.0s)\n",
+ "(2017-06-03 03:43:31)>> LACTATE\n",
+ "(2017-06-03 03:43:31)>>>> Extracting 3 items from chartevents\n",
+ "(2017-06-03 03:44:30)<<<< DONE (59.0s)\n",
+ "(2017-06-03 03:44:30)>>>> Extracting 1 items from labevents\n",
+ "(2017-06-03 03:44:33)<<<< DONE (3.0s)\n",
+ "(2017-06-03 03:44:33)>>>> Combine DF\n",
+ "(2017-06-03 03:44:33)<<<< DONE (0.0s)\n",
+ "(2017-06-03 03:44:33)>>>> Clean UOM\n",
+ "(2017-06-03 03:44:34)<<<< DONE (1.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-11 21:20:00</td>\n",
+ " <td>1.5</td>\n",
+ " <td>mmol/L</td>\n",
+ " <td>818</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-11 21:20:00</td>\n",
+ " <td>1.5</td>\n",
+ " <td>mmol/L</td>\n",
+ " <td>1531</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>175413.0</td>\n",
+ " <td>2170-04-11 15:00:00</td>\n",
+ " <td></td>\n",
+ " <td>mmol/L</td>\n",
+ " <td>818</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>146828.0</td>\n",
+ " <td>2186-10-03 21:54:00</td>\n",
+ " <td>1.8</td>\n",
+ " <td>mmol/L</td>\n",
+ " <td>818</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>146828.0</td>\n",
+ " <td>2186-10-03 21:54:00</td>\n",
+ " <td>1.8</td>\n",
+ " <td>mmol/L</td>\n",
+ " <td>1531</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-11 21:20:00 1.5 mmol/L 818\n",
+ "1 185910.0 2166-08-11 21:20:00 1.5 mmol/L 1531\n",
+ "2 175413.0 2170-04-11 15:00:00 mmol/L 818\n",
+ "3 146828.0 2186-10-03 21:54:00 1.8 mmol/L 818\n",
+ "4 146828.0 2186-10-03 21:54:00 1.8 mmol/L 1531"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(393608, 5)\n",
+ "(2017-06-03 03:44:35)<< DONE (64.0s)\n",
+ "(2017-06-03 03:44:35) DONE (1045.0s)\n"
+ ]
+ }
+ ],
+ "source": [
+ "df_all = extract_labels(conn,labels,item_map_fname,hdf5_fname)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Transform (and \"Load\") MIMIC III Data"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 152,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "import icu_data_defs \n",
+ "import mimic\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "import logger\n",
+ "import pandas as pd\n",
+ "from constants import column_names\n",
+ "import utils\n",
+ "import warnings\n",
+ "warnings.filterwarnings('ignore')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 153,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload(utils)\n",
+ "reload(logger)\n",
+ "reload(mimic)\n",
+ "def transform_extracted_labels(labels,hdf5_fname):\n",
+ " \n",
+ " pipeline = Pipeline([\n",
+ " ('clean',mimic.clean_extract()),\n",
+ " ('unstack',mimic.unstacker()),\n",
+ " ('clean_uom',mimic.clean_uom())\n",
+ " ])\n",
+ " \n",
+ " for label in labels:\n",
+ " logger.log('Opening {}'.format(label.upper()))\n",
+ " df = utils.open_df(hdf5_fname,'extract/{}'.format(label))\n",
+ " logger.log('Transforming {} - {}'.format(label.upper(),df.shape))\n",
+ " df_transformed = pipeline.transform(df)\n",
+ " # Add label guess to column index\n",
+ " df = utils.add_same_val__index_level(df,label,'label',axis=1)\n",
+ " display(df_transformed.head())\n",
+ " utils.save_df(df_transformed,hdf5_fname,'transformed/{}'.format(label))\n",
+ " del df,df_transformed\n",
+ " logger.end_log_level()\n",
+ " \n",
+ " return\n",
+ " \n",
+ "mimic_data_sef_fname = 'config/data_definitions.xlsx'\n",
+ "hdf5_fname = 'data/mimic_data'\n",
+ "\n",
+ "#get all labels\n",
+ "data_dict = icu_data_defs.data_dictionary(mimic_data_sef_fname)\n",
+ "simple_data = data_dict.get_panel_defintions(12) #12 is \"simple data\"\n",
+ "labels = simple_data.label.unique().tolist()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-02 05:11:14) Opening HEART RATE\n",
+ "(2017-06-02 05:11:19) DONE (5.0s)\n",
+ "(2017-06-02 05:11:19) Transforming HEART RATE - (7952939, 5)\n"
+ ]
+ },
+ {
+ "ename": "KeyboardInterrupt",
+ "evalue": "",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[1;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m<ipython-input-3-4ff30e8e4bcc>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mtransform_extracted_labels\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabels\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mhdf5_fname\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[1;32m<ipython-input-2-7e9518f41127>\u001b[0m in \u001b[0;36mtransform_extracted_labels\u001b[1;34m(labels, hdf5_fname)\u001b[0m\n\u001b[0;32m 14\u001b[0m \u001b[0mdf\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mutils\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mopen_df\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mhdf5_fname\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'extract/{}'\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabel\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 15\u001b[0m \u001b[0mlogger\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlog\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'Transforming {} - {}'\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabel\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mupper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 16\u001b[1;33m \u001b[0mdf_transformed\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpipeline\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtransform\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 17\u001b[0m \u001b[0mdisplay\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf_transformed\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhead\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 18\u001b[0m \u001b[0mutils\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msave_df\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf_transformed\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mhdf5_fname\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'transformed/{}'\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlabel\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\sklearn\\pipeline.pyc\u001b[0m in \u001b[0;36m_transform\u001b[1;34m(self, X)\u001b[0m\n\u001b[0;32m 446\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtransform\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msteps\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 447\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mtransform\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 448\u001b[1;33m \u001b[0mXt\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mtransform\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtransform\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mXt\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 449\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mXt\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 450\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\icu_ml_project\\v5\\mimic.pyc\u001b[0m in \u001b[0;36mtransform\u001b[1;34m(self, df)\u001b[0m\n\u001b[0;32m 189\u001b[0m \u001b[0mFORMAT\u001b[0m \u001b[0mpre\u001b[0m\u001b[1;33m-\u001b[0m\u001b[0munstack\u001b[0m \u001b[0mcolumns\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 190\u001b[0m \"\"\"\n\u001b[1;32m--> 191\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreplace\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mto_replace\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m''\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnan\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minplace\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 192\u001b[0m \u001b[1;31m#drop NAN record_id, timestamps, or value\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 193\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdropna\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msubset\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mcolumn_names\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mID\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mcolumn_names\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mDATETIME\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mcolumn_names\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mVALUE\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mhow\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'any'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0minplace\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\generic.pyc\u001b[0m in \u001b[0;36mreplace\u001b[1;34m(self, to_replace, value, inplace, limit, regex, method, axis)\u001b[0m\n\u001b[0;32m 3538\u001b[0m new_data = self._data.replace(to_replace=to_replace,\n\u001b[0;32m 3539\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mvalue\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0minplace\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0minplace\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3540\u001b[1;33m regex=regex)\n\u001b[0m\u001b[0;32m 3541\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3542\u001b[0m msg = ('Invalid \"to_replace\" type: '\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\internals.pyc\u001b[0m in \u001b[0;36mreplace\u001b[1;34m(self, **kwargs)\u001b[0m\n\u001b[0;32m 3172\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3173\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mreplace\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3174\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mapply\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'replace'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3175\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3176\u001b[0m def replace_list(self, src_list, dest_list, inplace=False, regex=False,\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\internals.pyc\u001b[0m in \u001b[0;36mapply\u001b[1;34m(self, f, axes, filter, do_integrity_check, consolidate, **kwargs)\u001b[0m\n\u001b[0;32m 3033\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3034\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'mgr'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3035\u001b[1;33m \u001b[0mapplied\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mb\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 3036\u001b[0m \u001b[0mresult_blocks\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_extend_blocks\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mapplied\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresult_blocks\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3037\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\internals.pyc\u001b[0m in \u001b[0;36mreplace\u001b[1;34m(self, to_replace, value, inplace, filter, regex, convert, mgr)\u001b[0m\n\u001b[0;32m 1926\u001b[0m \u001b[0minplace\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0minplace\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1927\u001b[0m \u001b[0mfilter\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilter\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mregex\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mregex\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1928\u001b[1;33m convert=convert, mgr=mgr)\n\u001b[0m\u001b[0;32m 1929\u001b[0m \u001b[1;32melif\u001b[0m \u001b[0mboth_lists\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 1930\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mto_rep\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mv\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mzip\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mto_replace\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\internals.pyc\u001b[0m in \u001b[0;36mreplace\u001b[1;34m(self, to_replace, value, inplace, filter, regex, convert, mgr)\u001b[0m\n\u001b[0;32m 623\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 624\u001b[0m \u001b[0moriginal_to_replace\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mto_replace\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 625\u001b[1;33m \u001b[0mmask\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0misnull\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 626\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 627\u001b[0m \u001b[1;31m# try to replace, if we raise an error, convert to ObjectBlock and\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\types\\missing.pyc\u001b[0m in \u001b[0;36misnull\u001b[1;34m(obj)\u001b[0m\n\u001b[0;32m 43\u001b[0m \u001b[0mpandas\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnotnull\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mboolean\u001b[0m \u001b[0minverse\u001b[0m \u001b[0mof\u001b[0m \u001b[0mpandas\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0misnull\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 44\u001b[0m \"\"\"\n\u001b[1;32m---> 45\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0m_isnull\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 46\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 47\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\types\\missing.pyc\u001b[0m in \u001b[0;36m_isnull_new\u001b[1;34m(obj)\u001b[0m\n\u001b[0;32m 53\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mNotImplementedError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"isnull is not defined for MultiIndex\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 54\u001b[0m \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mABCSeries\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mndarray\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mABCIndexClass\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 55\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0m_isnull_ndarraylike\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 56\u001b[0m \u001b[1;32melif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mABCGeneric\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 57\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_constructor\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_data\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0misnull\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfunc\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0misnull\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\types\\missing.pyc\u001b[0m in \u001b[0;36m_isnull_ndarraylike\u001b[1;34m(obj)\u001b[0m\n\u001b[0;32m 139\u001b[0m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mempty\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mbool\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 140\u001b[0m \u001b[0mvec\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mlib\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0misnullobj\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mvalues\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mravel\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 141\u001b[1;33m \u001b[0mresult\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m.\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mvec\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 142\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 143\u001b[0m \u001b[1;32melif\u001b[0m \u001b[0mneeds_i8_conversion\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
+ ]
+ }
+ ],
+ "source": [
+ "transform_extracted_labels(labels,hdf5_fname)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": [
+ "store = pd.HDFStore(hdf5_fname)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<class 'pandas.io.pytables.HDFStore'>\n",
+ "File path: data/mimic_data\n",
+ "/extract/blood pressure diastolic frame (shape->[6371249,5])\n",
+ "/extract/blood pressure mean frame (shape->[2536271,5])\n",
+ "/extract/blood pressure systolic frame (shape->[6374824,5])\n",
+ "/extract/glasgow coma scale eye opening frame (shape->[956672,5]) \n",
+ "/extract/glasgow coma scale motor frame (shape->[952565,5]) \n",
+ "/extract/glasgow coma scale verbal frame (shape->[954700,5]) \n",
+ "/extract/heart rate frame (shape->[7952939,5])\n",
+ "/extract/hemoglobin frame (shape->[1167921,5])\n",
+ "/extract/lactate frame (shape->[393608,5]) \n",
+ "/extract/lactated ringers frame (shape->[504306,5]) \n",
+ "/extract/norepinephrine frame (shape->[1136938,5])\n",
+ "/extract/normal saline frame (shape->[817373,5]) \n",
+ "/extract/output urine frame (shape->[3644639,5])\n",
+ "/extract/oxygen saturation pulse oximetry frame (shape->[6099827,5])\n",
+ "/extract/respiratory rate frame (shape->[7810019,5])\n",
+ "/extract/temperature body frame (shape->[1751447,5])\n",
+ "/extract/vasopressin frame (shape->[339184,5]) \n",
+ "/extract/weight body frame (shape->[95425,5]) \n",
+ "/transformed/blood pressure diastolic frame \n",
+ "/transformed/blood pressure mean frame \n",
+ "/transformed/blood pressure systolic frame \n",
+ "/transformed/glasgow coma scale eye opening frame \n",
+ "/transformed/glasgow coma scale motor frame \n",
+ "/transformed/glasgow coma scale verbal frame \n",
+ "/transformed/heart rate frame \n",
+ "/transformed/hemoglobin frame \n",
+ "/transformed/lactate frame \n",
+ "/transformed/lactated ringers frame \n",
+ "/transformed/norepinephrine frame \n",
+ "/transformed/normal saline frame \n",
+ "/transformed/output urine frame \n",
+ "/transformed/oxygen saturation pulse oximetry frame \n",
+ "/transformed/respiratory rate frame \n",
+ "/transformed/temperature body frame \n",
+ "/transformed/vasopressin frame \n",
+ "/transformed/weight body frame "
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "store"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "store.close()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 116,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<module 'utils' from 'utils.py'>"
+ ]
+ },
+ "execution_count": 116,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "reload(utils)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Cleaners"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "Design decision: If a given column has both NUMERIC CATEGORICAL and QUANTITATIVE data, all NUMERIC CATEGORICAL data will actually be treated like QUANTITATIVE data, unfortunately."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "import transformers\n",
+ "import utils\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "from units import MedicalUreg\n",
+ "import icu_data_defs\n",
+ "import units\n",
+ "import pandas as pd"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload(transformers)\n",
+ "reload(utils)\n",
+ "mimic_data_sef_fname = 'config/data_definitions.xlsx'\n",
+ "hdf5_fname = 'data/mimic_data'\n",
+ "medical_units = 'config/medical_units.txt'\n",
+ "\n",
+ "#get all labels\n",
+ "data_dict = icu_data_defs.data_dictionary(mimic_data_sef_fname)\n",
+ "label = 'lactate'\n",
+ "\n",
+ "standard_pipeline = Pipeline([\n",
+ " ('aggregate_same_datetime',transformers.same_index_aggregator(agg_func=lambda x:x.iloc[0])),\n",
+ " ('split_dtype',transformers.split_dtype()),\n",
+ " ('format_columns',transformers.format_columns(data_dict,MedicalUreg(medical_units))),\n",
+ " ('drop_small_columns',transformers.remove_small_columns(threshold=50))\n",
+ " ])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "transformers.py:103: SettingWithCopyWarning: \n",
+ "A value is trying to be set on a copy of a slice from a DataFrame\n",
+ "\n",
+ "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
+ " df_out.dropna(how='all',inplace=True,axis=1)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/plain": [
+ "(113L, 0, '0.0%')"
+ ]
+ },
+ "execution_count": 3,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = utils.open_df('data/mimic_data','transformed/{}'.format(label))\n",
+ "df_cleaned = standard_pipeline.transform(df)\n",
+ "utils.data_loss(df,df_cleaned)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 216,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"6\" halign=\"left\">lactate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th colspan=\"4\" halign=\"left\">unknown</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">nom</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">mmol/L</th>\n",
+ " <th colspan=\"2\" halign=\"left\">no_units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">no_units</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>50813</th>\n",
+ " <th>225668</th>\n",
+ " <th>818</th>\n",
+ " <th>1531</th>\n",
+ " <th>50813(mmol/L)</th>\n",
+ " <th>818</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>100001</th>\n",
+ " <th>2117-09-11 09:32:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100003</th>\n",
+ " <th>2150-04-17 19:12:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100006</th>\n",
+ " <th>2108-04-08 10:58:00</th>\n",
+ " <td>4.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100007</th>\n",
+ " <th>2145-03-31 00:44:00</th>\n",
+ " <td>3.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2145-04-02 14:10:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100009</th>\n",
+ " <th>2162-05-17 13:19:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2162-05-17 17:14:00</th>\n",
+ " <td>1.5</td>\n",
+ " <td>1.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"4\" valign=\"top\">100010</th>\n",
+ " <th>2109-12-10 10:25:00</th>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 12:11:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 13:05:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 13:58:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100011</th>\n",
+ " <th>2177-08-29 04:44:00</th>\n",
+ " <td>3.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-08-29 06:55:00</th>\n",
+ " <td>2.3</td>\n",
+ " <td>2.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">100012</th>\n",
+ " <th>2177-03-14 07:38:00</th>\n",
+ " <td>2.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-14 11:42:00</th>\n",
+ " <td>2.5</td>\n",
+ " <td>2.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 08:05:00</th>\n",
+ " <td>2.1</td>\n",
+ " <td>2.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 14:01:00</th>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 21:42:00</th>\n",
+ " <td>1.8</td>\n",
+ " <td>1.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100016</th>\n",
+ " <th>2188-05-24 12:00:00</th>\n",
+ " <td>2.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100017</th>\n",
+ " <th>2103-03-11 05:10:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">100018</th>\n",
+ " <th>2176-08-29 15:29:00</th>\n",
+ " <td>1.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 09:23:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 10:19:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 11:29:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 12:40:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100020</th>\n",
+ " <th>2142-11-30 21:54:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2142-12-03 00:17:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">100024</th>\n",
+ " <th>2170-09-19 10:25:00</th>\n",
+ " <td>1.4</td>\n",
+ " <td>1.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2170-09-19 16:33:00</th>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2170-09-20 02:04:00</th>\n",
+ " <td>3.2</td>\n",
+ " <td>3.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">199976</th>\n",
+ " <th>2182-02-14 11:15:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-16 03:57:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-19 03:59:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-20 03:31:00</th>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-21 04:55:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199979</th>\n",
+ " <th>2182-02-06 09:17:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-06 14:16:00</th>\n",
+ " <td>3.8</td>\n",
+ " <td>3.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">199981</th>\n",
+ " <th>2110-09-24 16:34:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2110-09-24 20:09:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2110-09-25 06:10:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>199987</th>\n",
+ " <th>2175-05-19 16:30:00</th>\n",
+ " <td>2.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"6\" valign=\"top\">199988</th>\n",
+ " <th>2169-01-24 12:48:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 01:35:00</th>\n",
+ " <td>1.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 11:18:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 16:43:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 22:35:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-10 05:33:00</th>\n",
+ " <td>1.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199993</th>\n",
+ " <th>2161-11-12 23:14:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2161-11-13 03:46:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"4\" valign=\"top\">199994</th>\n",
+ " <th>2188-07-07 21:23:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 03:09:00</th>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 04:13:00</th>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 06:20:00</th>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">199998</th>\n",
+ " <th>2119-02-20 10:52:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 12:36:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 13:33:00</th>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 13:59:00</th>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 20:43:00</th>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199999</th>\n",
+ " <th>2136-04-04 20:55:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-06 15:29:00</th>\n",
+ " <td>1.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>177451 rows × 6 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label lactate \n",
+ "status known unknown \n",
+ "variable_type qn qn nom \n",
+ "units mmol/L no_units no_units \n",
+ "description 50813 225668 818 1531 50813(mmol/L) 818\n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 1.9 NaN NaN NaN NaN NaN\n",
+ "100003 2150-04-17 19:12:00 1.1 1.1 NaN NaN NaN NaN\n",
+ "100006 2108-04-08 10:58:00 4.5 NaN 4.5 NaN NaN NaN\n",
+ "100007 2145-03-31 00:44:00 3.1 NaN NaN NaN NaN NaN\n",
+ " 2145-04-02 14:10:00 1.9 NaN NaN NaN NaN NaN\n",
+ "100009 2162-05-17 13:19:00 1.1 1.1 NaN NaN NaN NaN\n",
+ " 2162-05-17 17:14:00 1.5 1.5 NaN NaN NaN NaN\n",
+ "100010 2109-12-10 10:25:00 0.6 NaN NaN NaN NaN NaN\n",
+ " 2109-12-10 12:11:00 0.9 NaN NaN NaN NaN NaN\n",
+ " 2109-12-10 13:05:00 1.0 NaN NaN NaN NaN NaN\n",
+ " 2109-12-10 13:58:00 0.8 NaN NaN NaN NaN NaN\n",
+ "100011 2177-08-29 04:44:00 3.8 NaN NaN NaN NaN NaN\n",
+ " 2177-08-29 06:55:00 2.3 2.3 NaN NaN NaN NaN\n",
+ "100012 2177-03-14 07:38:00 2.3 NaN NaN NaN NaN NaN\n",
+ " 2177-03-14 11:42:00 2.5 2.5 NaN NaN NaN NaN\n",
+ " 2177-03-15 08:05:00 2.1 2.1 NaN NaN NaN NaN\n",
+ " 2177-03-15 14:01:00 2.6 2.6 NaN NaN NaN NaN\n",
+ " 2177-03-15 21:42:00 1.8 1.8 NaN NaN NaN NaN\n",
+ "100016 2188-05-24 12:00:00 2.0 NaN NaN NaN NaN NaN\n",
+ "100017 2103-03-11 05:10:00 1.1 NaN 1.1 NaN NaN NaN\n",
+ "100018 2176-08-29 15:29:00 1.3 NaN NaN NaN NaN NaN\n",
+ " 2176-08-30 09:23:00 0.9 0.9 NaN NaN NaN NaN\n",
+ " 2176-08-30 10:19:00 1.0 1.0 NaN NaN NaN NaN\n",
+ " 2176-08-30 11:29:00 0.9 0.9 NaN NaN NaN NaN\n",
+ " 2176-08-30 12:40:00 1.1 1.1 NaN NaN NaN NaN\n",
+ "100020 2142-11-30 21:54:00 1.1 NaN NaN NaN NaN NaN\n",
+ " 2142-12-03 00:17:00 1.0 NaN NaN NaN NaN NaN\n",
+ "100024 2170-09-19 10:25:00 1.4 1.4 NaN NaN NaN NaN\n",
+ " 2170-09-19 16:33:00 2.6 2.6 NaN NaN NaN NaN\n",
+ " 2170-09-20 02:04:00 3.2 3.2 NaN NaN NaN NaN\n",
+ "... ... ... ... ... ... ...\n",
+ "199976 2182-02-14 11:15:00 0.8 NaN 0.8 NaN NaN NaN\n",
+ " 2182-02-16 03:57:00 0.8 NaN 0.8 NaN NaN NaN\n",
+ " 2182-02-19 03:59:00 0.8 NaN 0.8 NaN NaN NaN\n",
+ " 2182-02-20 03:31:00 0.7 NaN 0.7 NaN NaN NaN\n",
+ " 2182-02-21 04:55:00 0.9 NaN 0.9 NaN NaN NaN\n",
+ "199979 2182-02-06 09:17:00 1.0 NaN NaN NaN NaN NaN\n",
+ " 2182-02-06 14:16:00 3.8 3.8 NaN NaN NaN NaN\n",
+ "199981 2110-09-24 16:34:00 1.1 NaN 1.1 1.1 NaN NaN\n",
+ " 2110-09-24 20:09:00 1.0 NaN 1.0 1.0 NaN NaN\n",
+ " 2110-09-25 06:10:00 1.0 NaN 1.0 1.0 NaN NaN\n",
+ "199987 2175-05-19 16:30:00 2.3 NaN NaN NaN NaN NaN\n",
+ "199988 2169-01-24 12:48:00 1.0 NaN NaN NaN NaN NaN\n",
+ " 2169-02-07 01:35:00 1.6 NaN 1.6 NaN NaN NaN\n",
+ " 2169-02-07 11:18:00 1.0 NaN 1.0 NaN NaN NaN\n",
+ " 2169-02-07 16:43:00 1.0 NaN 1.0 NaN NaN NaN\n",
+ " 2169-02-07 22:35:00 1.1 NaN 1.1 NaN NaN NaN\n",
+ " 2169-02-10 05:33:00 1.4 NaN NaN NaN NaN NaN\n",
+ "199993 2161-11-12 23:14:00 0.9 NaN 0.9 NaN NaN NaN\n",
+ " 2161-11-13 03:46:00 0.9 NaN 0.9 NaN NaN NaN\n",
+ "199994 2188-07-07 21:23:00 1.0 NaN 1.0 NaN NaN NaN\n",
+ " 2188-07-08 03:09:00 0.7 NaN 0.7 NaN NaN NaN\n",
+ " 2188-07-08 04:13:00 0.6 NaN 0.6 NaN NaN NaN\n",
+ " 2188-07-08 06:20:00 0.7 NaN 0.7 NaN NaN NaN\n",
+ "199998 2119-02-20 10:52:00 1.1 1.1 1.1 1.1 NaN NaN\n",
+ " 2119-02-20 12:36:00 1.9 1.9 1.9 1.9 NaN NaN\n",
+ " 2119-02-20 13:33:00 2.0 2.0 2.0 2.0 NaN NaN\n",
+ " 2119-02-20 13:59:00 2.6 2.6 2.6 2.6 NaN NaN\n",
+ " 2119-02-20 20:43:00 1.3 1.3 1.3 1.3 NaN NaN\n",
+ "199999 2136-04-04 20:55:00 1.9 NaN NaN NaN NaN NaN\n",
+ " 2136-04-06 15:29:00 1.8 NaN NaN NaN NaN NaN\n",
+ "\n",
+ "[177451 rows x 6 columns]"
+ ]
+ },
+ "execution_count": 216,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_cleaned"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "df_invalid = df_cleaned.loc[:,df_cleaned.columns.get_level_values('status') == 'unknown']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "df_invalid.columns.set_labels([0]*df_invalid.columns.size,level='status',inplace=True)\n",
+ "df_invalid.columns.set_levels(['known'],level='status',inplace=True)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"10\" halign=\"left\">lactate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"6\" halign=\"left\">known</th>\n",
+ " <th colspan=\"4\" halign=\"left\">unknown</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">nom</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">nom</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">no_units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">no_units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">mmol/L</th>\n",
+ " <th colspan=\"2\" halign=\"left\">no_units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">no_units</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>818</th>\n",
+ " <th>1531</th>\n",
+ " <th>50813(mmol/L)</th>\n",
+ " <th>818</th>\n",
+ " <th>50813</th>\n",
+ " <th>225668</th>\n",
+ " <th>818</th>\n",
+ " <th>1531</th>\n",
+ " <th>50813(mmol/L)</th>\n",
+ " <th>818</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>100001</th>\n",
+ " <th>2117-09-11 09:32:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100003</th>\n",
+ " <th>2150-04-17 19:12:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100006</th>\n",
+ " <th>2108-04-08 10:58:00</th>\n",
+ " <td>4.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100007</th>\n",
+ " <th>2145-03-31 00:44:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>3.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2145-04-02 14:10:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100009</th>\n",
+ " <th>2162-05-17 13:19:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2162-05-17 17:14:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.5</td>\n",
+ " <td>1.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"4\" valign=\"top\">100010</th>\n",
+ " <th>2109-12-10 10:25:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 12:11:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 13:05:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 13:58:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100011</th>\n",
+ " <th>2177-08-29 04:44:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>3.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-08-29 06:55:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.3</td>\n",
+ " <td>2.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">100012</th>\n",
+ " <th>2177-03-14 07:38:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-14 11:42:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.5</td>\n",
+ " <td>2.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 08:05:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.1</td>\n",
+ " <td>2.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 14:01:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 21:42:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.8</td>\n",
+ " <td>1.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100016</th>\n",
+ " <th>2188-05-24 12:00:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100017</th>\n",
+ " <th>2103-03-11 05:10:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">100018</th>\n",
+ " <th>2176-08-29 15:29:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 09:23:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 10:19:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 11:29:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 12:40:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100020</th>\n",
+ " <th>2142-11-30 21:54:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2142-12-03 00:17:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">100024</th>\n",
+ " <th>2170-09-19 10:25:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.4</td>\n",
+ " <td>1.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2170-09-19 16:33:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2170-09-20 02:04:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>3.2</td>\n",
+ " <td>3.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">199976</th>\n",
+ " <th>2182-02-14 11:15:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-16 03:57:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-19 03:59:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-20 03:31:00</th>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-21 04:55:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199979</th>\n",
+ " <th>2182-02-06 09:17:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-06 14:16:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>3.8</td>\n",
+ " <td>3.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">199981</th>\n",
+ " <th>2110-09-24 16:34:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2110-09-24 20:09:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2110-09-25 06:10:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>199987</th>\n",
+ " <th>2175-05-19 16:30:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"6\" valign=\"top\">199988</th>\n",
+ " <th>2169-01-24 12:48:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 01:35:00</th>\n",
+ " <td>1.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 11:18:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 16:43:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 22:35:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-10 05:33:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199993</th>\n",
+ " <th>2161-11-12 23:14:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2161-11-13 03:46:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"4\" valign=\"top\">199994</th>\n",
+ " <th>2188-07-07 21:23:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 03:09:00</th>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 04:13:00</th>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 06:20:00</th>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">199998</th>\n",
+ " <th>2119-02-20 10:52:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 12:36:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 13:33:00</th>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 13:59:00</th>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 20:43:00</th>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199999</th>\n",
+ " <th>2136-04-04 20:55:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-06 15:29:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>177451 rows × 10 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label lactate \\\n",
+ "status known \n",
+ "variable_type qn nom qn \n",
+ "units no_units no_units mmol/L \n",
+ "description 818 1531 50813(mmol/L) 818 50813 225668 \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 NaN NaN NaN NaN 1.9 NaN \n",
+ "100003 2150-04-17 19:12:00 NaN NaN NaN NaN 1.1 1.1 \n",
+ "100006 2108-04-08 10:58:00 4.5 NaN NaN NaN 4.5 NaN \n",
+ "100007 2145-03-31 00:44:00 NaN NaN NaN NaN 3.1 NaN \n",
+ " 2145-04-02 14:10:00 NaN NaN NaN NaN 1.9 NaN \n",
+ "100009 2162-05-17 13:19:00 NaN NaN NaN NaN 1.1 1.1 \n",
+ " 2162-05-17 17:14:00 NaN NaN NaN NaN 1.5 1.5 \n",
+ "100010 2109-12-10 10:25:00 NaN NaN NaN NaN 0.6 NaN \n",
+ " 2109-12-10 12:11:00 NaN NaN NaN NaN 0.9 NaN \n",
+ " 2109-12-10 13:05:00 NaN NaN NaN NaN 1.0 NaN \n",
+ " 2109-12-10 13:58:00 NaN NaN NaN NaN 0.8 NaN \n",
+ "100011 2177-08-29 04:44:00 NaN NaN NaN NaN 3.8 NaN \n",
+ " 2177-08-29 06:55:00 NaN NaN NaN NaN 2.3 2.3 \n",
+ "100012 2177-03-14 07:38:00 NaN NaN NaN NaN 2.3 NaN \n",
+ " 2177-03-14 11:42:00 NaN NaN NaN NaN 2.5 2.5 \n",
+ " 2177-03-15 08:05:00 NaN NaN NaN NaN 2.1 2.1 \n",
+ " 2177-03-15 14:01:00 NaN NaN NaN NaN 2.6 2.6 \n",
+ " 2177-03-15 21:42:00 NaN NaN NaN NaN 1.8 1.8 \n",
+ "100016 2188-05-24 12:00:00 NaN NaN NaN NaN 2.0 NaN \n",
+ "100017 2103-03-11 05:10:00 1.1 NaN NaN NaN 1.1 NaN \n",
+ "100018 2176-08-29 15:29:00 NaN NaN NaN NaN 1.3 NaN \n",
+ " 2176-08-30 09:23:00 NaN NaN NaN NaN 0.9 0.9 \n",
+ " 2176-08-30 10:19:00 NaN NaN NaN NaN 1.0 1.0 \n",
+ " 2176-08-30 11:29:00 NaN NaN NaN NaN 0.9 0.9 \n",
+ " 2176-08-30 12:40:00 NaN NaN NaN NaN 1.1 1.1 \n",
+ "100020 2142-11-30 21:54:00 NaN NaN NaN NaN 1.1 NaN \n",
+ " 2142-12-03 00:17:00 NaN NaN NaN NaN 1.0 NaN \n",
+ "100024 2170-09-19 10:25:00 NaN NaN NaN NaN 1.4 1.4 \n",
+ " 2170-09-19 16:33:00 NaN NaN NaN NaN 2.6 2.6 \n",
+ " 2170-09-20 02:04:00 NaN NaN NaN NaN 3.2 3.2 \n",
+ "... ... ... ... ... ... ... \n",
+ "199976 2182-02-14 11:15:00 0.8 NaN NaN NaN 0.8 NaN \n",
+ " 2182-02-16 03:57:00 0.8 NaN NaN NaN 0.8 NaN \n",
+ " 2182-02-19 03:59:00 0.8 NaN NaN NaN 0.8 NaN \n",
+ " 2182-02-20 03:31:00 0.7 NaN NaN NaN 0.7 NaN \n",
+ " 2182-02-21 04:55:00 0.9 NaN NaN NaN 0.9 NaN \n",
+ "199979 2182-02-06 09:17:00 NaN NaN NaN NaN 1.0 NaN \n",
+ " 2182-02-06 14:16:00 NaN NaN NaN NaN 3.8 3.8 \n",
+ "199981 2110-09-24 16:34:00 1.1 1.1 NaN NaN 1.1 NaN \n",
+ " 2110-09-24 20:09:00 1.0 1.0 NaN NaN 1.0 NaN \n",
+ " 2110-09-25 06:10:00 1.0 1.0 NaN NaN 1.0 NaN \n",
+ "199987 2175-05-19 16:30:00 NaN NaN NaN NaN 2.3 NaN \n",
+ "199988 2169-01-24 12:48:00 NaN NaN NaN NaN 1.0 NaN \n",
+ " 2169-02-07 01:35:00 1.6 NaN NaN NaN 1.6 NaN \n",
+ " 2169-02-07 11:18:00 1.0 NaN NaN NaN 1.0 NaN \n",
+ " 2169-02-07 16:43:00 1.0 NaN NaN NaN 1.0 NaN \n",
+ " 2169-02-07 22:35:00 1.1 NaN NaN NaN 1.1 NaN \n",
+ " 2169-02-10 05:33:00 NaN NaN NaN NaN 1.4 NaN \n",
+ "199993 2161-11-12 23:14:00 0.9 NaN NaN NaN 0.9 NaN \n",
+ " 2161-11-13 03:46:00 0.9 NaN NaN NaN 0.9 NaN \n",
+ "199994 2188-07-07 21:23:00 1.0 NaN NaN NaN 1.0 NaN \n",
+ " 2188-07-08 03:09:00 0.7 NaN NaN NaN 0.7 NaN \n",
+ " 2188-07-08 04:13:00 0.6 NaN NaN NaN 0.6 NaN \n",
+ " 2188-07-08 06:20:00 0.7 NaN NaN NaN 0.7 NaN \n",
+ "199998 2119-02-20 10:52:00 1.1 1.1 NaN NaN 1.1 1.1 \n",
+ " 2119-02-20 12:36:00 1.9 1.9 NaN NaN 1.9 1.9 \n",
+ " 2119-02-20 13:33:00 2.0 2.0 NaN NaN 2.0 2.0 \n",
+ " 2119-02-20 13:59:00 2.6 2.6 NaN NaN 2.6 2.6 \n",
+ " 2119-02-20 20:43:00 1.3 1.3 NaN NaN 1.3 1.3 \n",
+ "199999 2136-04-04 20:55:00 NaN NaN NaN NaN 1.9 NaN \n",
+ " 2136-04-06 15:29:00 NaN NaN NaN NaN 1.8 NaN \n",
+ "\n",
+ "label \n",
+ "status unknown \n",
+ "variable_type qn nom \n",
+ "units no_units no_units \n",
+ "description 818 1531 50813(mmol/L) 818 \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 NaN NaN NaN NaN \n",
+ "100003 2150-04-17 19:12:00 NaN NaN NaN NaN \n",
+ "100006 2108-04-08 10:58:00 4.5 NaN NaN NaN \n",
+ "100007 2145-03-31 00:44:00 NaN NaN NaN NaN \n",
+ " 2145-04-02 14:10:00 NaN NaN NaN NaN \n",
+ "100009 2162-05-17 13:19:00 NaN NaN NaN NaN \n",
+ " 2162-05-17 17:14:00 NaN NaN NaN NaN \n",
+ "100010 2109-12-10 10:25:00 NaN NaN NaN NaN \n",
+ " 2109-12-10 12:11:00 NaN NaN NaN NaN \n",
+ " 2109-12-10 13:05:00 NaN NaN NaN NaN \n",
+ " 2109-12-10 13:58:00 NaN NaN NaN NaN \n",
+ "100011 2177-08-29 04:44:00 NaN NaN NaN NaN \n",
+ " 2177-08-29 06:55:00 NaN NaN NaN NaN \n",
+ "100012 2177-03-14 07:38:00 NaN NaN NaN NaN \n",
+ " 2177-03-14 11:42:00 NaN NaN NaN NaN \n",
+ " 2177-03-15 08:05:00 NaN NaN NaN NaN \n",
+ " 2177-03-15 14:01:00 NaN NaN NaN NaN \n",
+ " 2177-03-15 21:42:00 NaN NaN NaN NaN \n",
+ "100016 2188-05-24 12:00:00 NaN NaN NaN NaN \n",
+ "100017 2103-03-11 05:10:00 1.1 NaN NaN NaN \n",
+ "100018 2176-08-29 15:29:00 NaN NaN NaN NaN \n",
+ " 2176-08-30 09:23:00 NaN NaN NaN NaN \n",
+ " 2176-08-30 10:19:00 NaN NaN NaN NaN \n",
+ " 2176-08-30 11:29:00 NaN NaN NaN NaN \n",
+ " 2176-08-30 12:40:00 NaN NaN NaN NaN \n",
+ "100020 2142-11-30 21:54:00 NaN NaN NaN NaN \n",
+ " 2142-12-03 00:17:00 NaN NaN NaN NaN \n",
+ "100024 2170-09-19 10:25:00 NaN NaN NaN NaN \n",
+ " 2170-09-19 16:33:00 NaN NaN NaN NaN \n",
+ " 2170-09-20 02:04:00 NaN NaN NaN NaN \n",
+ "... ... ... ... ... \n",
+ "199976 2182-02-14 11:15:00 0.8 NaN NaN NaN \n",
+ " 2182-02-16 03:57:00 0.8 NaN NaN NaN \n",
+ " 2182-02-19 03:59:00 0.8 NaN NaN NaN \n",
+ " 2182-02-20 03:31:00 0.7 NaN NaN NaN \n",
+ " 2182-02-21 04:55:00 0.9 NaN NaN NaN \n",
+ "199979 2182-02-06 09:17:00 NaN NaN NaN NaN \n",
+ " 2182-02-06 14:16:00 NaN NaN NaN NaN \n",
+ "199981 2110-09-24 16:34:00 1.1 1.1 NaN NaN \n",
+ " 2110-09-24 20:09:00 1.0 1.0 NaN NaN \n",
+ " 2110-09-25 06:10:00 1.0 1.0 NaN NaN \n",
+ "199987 2175-05-19 16:30:00 NaN NaN NaN NaN \n",
+ "199988 2169-01-24 12:48:00 NaN NaN NaN NaN \n",
+ " 2169-02-07 01:35:00 1.6 NaN NaN NaN \n",
+ " 2169-02-07 11:18:00 1.0 NaN NaN NaN \n",
+ " 2169-02-07 16:43:00 1.0 NaN NaN NaN \n",
+ " 2169-02-07 22:35:00 1.1 NaN NaN NaN \n",
+ " 2169-02-10 05:33:00 NaN NaN NaN NaN \n",
+ "199993 2161-11-12 23:14:00 0.9 NaN NaN NaN \n",
+ " 2161-11-13 03:46:00 0.9 NaN NaN NaN \n",
+ "199994 2188-07-07 21:23:00 1.0 NaN NaN NaN \n",
+ " 2188-07-08 03:09:00 0.7 NaN NaN NaN \n",
+ " 2188-07-08 04:13:00 0.6 NaN NaN NaN \n",
+ " 2188-07-08 06:20:00 0.7 NaN NaN NaN \n",
+ "199998 2119-02-20 10:52:00 1.1 1.1 NaN NaN \n",
+ " 2119-02-20 12:36:00 1.9 1.9 NaN NaN \n",
+ " 2119-02-20 13:33:00 2.0 2.0 NaN NaN \n",
+ " 2119-02-20 13:59:00 2.6 2.6 NaN NaN \n",
+ " 2119-02-20 20:43:00 1.3 1.3 NaN NaN \n",
+ "199999 2136-04-04 20:55:00 NaN NaN NaN NaN \n",
+ " 2136-04-06 15:29:00 NaN NaN NaN NaN \n",
+ "\n",
+ "[177451 rows x 10 columns]"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_invalid.join(df_cleaned, how='outer')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 71,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "df = utils.open_df('data/mimic_data','transformed/{}'.format(label))\n",
+ "df_cleaned = pipeline.transform(df)\n",
+ "utils.data_loss(df,df_cleaned)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 72,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(113L, 0, '0.0%')"
+ ]
+ },
+ "execution_count": 72,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": []
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Secondary/optional transformation"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 99,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload (transformers)\n",
+ "pipeline1 = Pipeline([\n",
+ " ('combine_like_columns',transformers.combine_like_cols()),\n",
+ " ('quantitative_vales_only',transformers.quantitative_only()),\n",
+ " ('known_col_only',transformers.known_col_only())\n",
+ " ])\n",
+ "\n",
+ "pipeline2 = Pipeline([\n",
+ " ('combine_like_columns',transformers.combine_like_cols()),\n",
+ " ('max_col',transformers.max_col_only()),\n",
+ " ])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 74,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(205349L, 20, '0.0583%')"
+ ]
+ },
+ "execution_count": 74,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_final = pipeline1.transform(df_cleaned)\n",
+ "utils.data_loss(df,df_final)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 75,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "(205349L, 20, '0.0583%')"
+ ]
+ },
+ "execution_count": 75,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_final = pipeline2.transform(df_cleaned)\n",
+ "utils.data_loss(df,df_final)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "### Handle Categorical columns\n",
+ "\n",
+ "0. Standardize category lists\n",
+ "1. Make sure ordinal & nominal within category list?\n",
+ "2. Explode nominal\n",
+ "3. Ordinal to numeric"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def make_cat_dict(label,cat_codes):\n",
+ " df = utils.open_df(hdf5_fname, 'transformed/{}'.format(label))\n",
+ " mimic_cats = df.iloc[:,0].value_counts().sort_index().index.astype(str).tolist()\n",
+ " return dict(zip(mimic_cats,cat_codes))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "category_map={}"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>val_numeric</th>\n",
+ " <th>val_text</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>category_id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>1</td>\n",
+ " <td>No motor response</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>2</td>\n",
+ " <td>Extension to pain</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>3</td>\n",
+ " <td>Flexion to pain</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>4</td>\n",
+ " <td>Withdrawal from pain</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>5</td>\n",
+ " <td>Localizing pain</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>6</td>\n",
+ " <td>Obeys commands</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>1</td>\n",
+ " <td>No eye opening</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>2</td>\n",
+ " <td>Eye opening to pain</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>3</td>\n",
+ " <td>Eye opening to verbal command</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>4</td>\n",
+ " <td>Eyes open spontaneously</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>1</td>\n",
+ " <td>No verbal response (>2 yrs); no vocal response...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>2</td>\n",
+ " <td>Incomprehensible sounds</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>12</th>\n",
+ " <td>3</td>\n",
+ " <td>Inappropriate words</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13</th>\n",
+ " <td>4</td>\n",
+ " <td>Confused</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>14</th>\n",
+ " <td>5</td>\n",
+ " <td>Oriented</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " val_numeric val_text\n",
+ "category_id \n",
+ "0 1 No motor response \n",
+ "1 2 Extension to pain\n",
+ "2 3 Flexion to pain\n",
+ "3 4 Withdrawal from pain \n",
+ "4 5 Localizing pain\n",
+ "5 6 Obeys commands\n",
+ "6 1 No eye opening\n",
+ "7 2 Eye opening to pain\n",
+ "8 3 Eye opening to verbal command\n",
+ "9 4 Eyes open spontaneously\n",
+ "10 1 No verbal response (>2 yrs); no vocal response...\n",
+ "11 2 Incomprehensible sounds\n",
+ "12 3 Inappropriate words\n",
+ "13 4 Confused\n",
+ "14 5 Oriented"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data_dict.tables.categories"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 62,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "label = data_dict.labels.GLASGOW_COMA_SCALE_MOTOR\n",
+ "category_map[label] = make_cat_dict(label,range(0,6))\n",
+ "label = data_dict.labels.GLASGOW_COMA_SCALE_EYE_OPENING\n",
+ "category_map[label] = make_cat_dict(label,range(6,10))\n",
+ "label = data_dict.labels.GLASGOW_COMA_SCALE_VERBAL\n",
+ "category_map[label] = make_cat_dict(label,[10] + range(10,15))"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 63,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'glasgow coma scale eye opening': {'1 No Response': 6,\n",
+ " '2 To pain': 7,\n",
+ " '3 To speech': 8,\n",
+ " '4 Spontaneously': 9},\n",
+ " 'glasgow coma scale motor': {'1 No Response': 0,\n",
+ " '2 Abnorm extensn': 1,\n",
+ " '3 Abnorm flexion': 2,\n",
+ " '4 Flex-withdraws': 3,\n",
+ " '5 Localizes Pain': 4,\n",
+ " '6 Obeys Commands': 5},\n",
+ " 'glasgow coma scale verbal': {'1 No Response': 10,\n",
+ " '1.0 ET/Trach': 10,\n",
+ " '2 Incomp sounds': 11,\n",
+ " '3 Inapprop words': 12,\n",
+ " '4 Confused': 13,\n",
+ " '5 Oriented': 14}}"
+ ]
+ },
+ "execution_count": 63,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "category_map"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 57,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<module 'transformers' from 'transformers.pyc'>"
+ ]
+ },
+ "execution_count": 57,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "reload(utils)\n",
+ "reload(transformers)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 58,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>glasgow coma scale verbal</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>ord</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>no_units</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>723</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1.0 ET/Trach</th>\n",
+ " <td>444357</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5 Oriented</th>\n",
+ " <td>379668</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4 Confused</th>\n",
+ " <td>82434</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1 No Response</th>\n",
+ " <td>20836</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2 Incomp sounds</th>\n",
+ " <td>18007</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3 Inapprop words</th>\n",
+ " <td>5611</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label glasgow coma scale verbal\n",
+ "status known\n",
+ "variable_type ord\n",
+ "units no_units\n",
+ "description 723\n",
+ "1.0 ET/Trach 444357\n",
+ "5 Oriented 379668\n",
+ "4 Confused 82434\n",
+ "1 No Response 20836\n",
+ "2 Incomp sounds 18007\n",
+ "3 Inapprop words 5611"
+ ]
+ },
+ "execution_count": 58,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_gcs = utils.open_df(hdf5_fname, 'transformed/{}'.format(data_dict.labels.GLASGOW_COMA_SCALE_VERBAL))\n",
+ "df_gcs = standard_pipeline.transform(df_gcs)\n",
+ "df_gcs.apply(lambda x: x.value_counts())"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 59,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>glasgow coma scale verbal</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>ord</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>no_units</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>723</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>465193</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5 Oriented</th>\n",
+ " <td>379668</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>82434</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>18007</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>5611</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label glasgow coma scale verbal\n",
+ "status known\n",
+ "variable_type ord\n",
+ "units no_units\n",
+ "description 723\n",
+ "1 465193\n",
+ "5 Oriented 379668\n",
+ "4 82434\n",
+ "2 18007\n",
+ "3 5611"
+ ]
+ },
+ "execution_count": 59,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "transformer = transformers.standardize_categories(data_dict,category_map,use_numeric=True)\n",
+ "df_gcs = transformer.transform(df_gcs)\n",
+ "df_gcs.apply(lambda x: x.value_counts())"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 60,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"2\" halign=\"left\">glasgow coma scale verbal</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " <th>unknown</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>ord</th>\n",
+ " <th>nom</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>no_units</th>\n",
+ " <th>no_units</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>723</th>\n",
+ " <th>723</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>465193.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>18007.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>5611.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>82434.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5 Oriented</th>\n",
+ " <td>NaN</td>\n",
+ " <td>379668.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label glasgow coma scale verbal \n",
+ "status known unknown\n",
+ "variable_type ord nom\n",
+ "units no_units no_units\n",
+ "description 723 723\n",
+ "1 465193.0 NaN\n",
+ "2 18007.0 NaN\n",
+ "3 5611.0 NaN\n",
+ "4 82434.0 NaN\n",
+ "5 Oriented NaN 379668.0"
+ ]
+ },
+ "execution_count": 60,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "transformer2 = transformers.split_bad_categories(data_dict,use_numeric=True)\n",
+ "transformer2.transform(df_gcs).apply(lambda x: x.value_counts())"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Unified pipeline"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import icu_data_defs\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "import transformers\n",
+ "from units import MedicalUreg\n",
+ "from constants import variable_type\n",
+ "import utils\n",
+ "import mimic\n",
+ "import warnings\n",
+ "warnings.filterwarnings('ignore')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload(transformers)\n",
+ "reload(utils)\n",
+ "reload(mimic)\n",
+ "hdf5_fname = 'data/mimic_data'\n",
+ "\n",
+ "#get all labels\n",
+ "data_dict = icu_data_defs.data_dictionary('config/data_definitions.xlsx')\n",
+ "ureg = MedicalUreg('config/medical_units.txt')\n",
+ "\n",
+ "agg_func = lambda x:x.iloc[0]\n",
+ "var_types_to_keep = [variable_type.QUANTITATIVE,variable_type.ORDINAL]\n",
+ "category_map = {\n",
+ " data_dict.labels.GLASGOW_COMA_SCALE_EYE_OPENING: {\n",
+ " '1 No Response': 6,\n",
+ " '2 To pain': 7,\n",
+ " '3 To speech': 8,\n",
+ " '4 Spontaneously': 9\n",
+ " },\n",
+ " data_dict.labels.GLASGOW_COMA_SCALE_MOTOR: {\n",
+ " '1 No Response': 0,\n",
+ " '2 Abnorm extensn': 1,\n",
+ " '3 Abnorm flexion': 2,\n",
+ " '4 Flex-withdraws': 3,\n",
+ " '5 Localizes Pain': 4,\n",
+ " '6 Obeys Commands': 5\n",
+ " },\n",
+ " data_dict.labels.GLASGOW_COMA_SCALE_VERBAL: {\n",
+ " '1 No Response': 10,\n",
+ " '1.0 ET/Trach': 10,\n",
+ " '2 Incomp sounds': 11,\n",
+ " '3 Inapprop words': 12,\n",
+ " '4 Confused': 13,\n",
+ " '5 Oriented':14\n",
+ " }\n",
+ "}\n",
+ "\n",
+ "mimic_transform = Pipeline([\n",
+ " ('clean',mimic.clean_extract()),\n",
+ " ('unstack',mimic.unstacker()),\n",
+ " ('add_level',transformers.add_level(None,'label',axis=1)),\n",
+ "])\n",
+ "\n",
+ "standard_pipeline = Pipeline([\n",
+ " ('drop_small_columns',transformers.remove_small_columns(threshold=5)),\n",
+ " ('aggregate_same_datetime',transformers.same_index_aggregator(agg_func)),\n",
+ " ('split_dtype',transformers.split_dtype()),\n",
+ " ('standardize_columns',transformers.standardize_columns(data_dict,ureg)),\n",
+ " ('standardize_categories',transformers.standardize_categories(data_dict,category_map)),\n",
+ " ('split_bad_categories',transformers.split_bad_categories(data_dict))\n",
+ " ])\n",
+ "\n",
+ "cleaning_pipeline = Pipeline([\n",
+ " ('drop_small_columns',transformers.remove_small_columns(threshold=50)),\n",
+ " ('combine_like_columns',transformers.combine_like_cols()),\n",
+ " ('quantitative_only',transformers.filter_var_type(var_types_to_keep)),\n",
+ " ('known_col_only',transformers.known_col_only()),\n",
+ "# ('max_col',transformers.max_col_only()) \n",
+ " ])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>817373.000000</td>\n",
+ " <td>817373</td>\n",
+ " <td>771272.000000</td>\n",
+ " <td>817373</td>\n",
+ " <td>817373.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>unique</th>\n",
+ " <td>NaN</td>\n",
+ " <td>536890</td>\n",
+ " <td>446614.000000</td>\n",
+ " <td>6</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>top</th>\n",
+ " <td>NaN</td>\n",
+ " <td>2159-09-30 01:00:00</td>\n",
+ " <td>99.999996</td>\n",
+ " <td>mL/hour</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>freq</th>\n",
+ " <td>NaN</td>\n",
+ " <td>9</td>\n",
+ " <td>25385.000000</td>\n",
+ " <td>719922</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>first</th>\n",
+ " <td>NaN</td>\n",
+ " <td>2100-06-08 04:23:00</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>last</th>\n",
+ " <td>NaN</td>\n",
+ " <td>2209-08-07 14:27:00</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>150437.603989</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>222346.358593</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>28720.645234</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>23242.543767</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>100001.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4647.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>125824.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>225158.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>150715.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>225158.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>175466.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>225158.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>199984.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>225158.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units \\\n",
+ "count 817373.000000 817373 771272.000000 817373 \n",
+ "unique NaN 536890 446614.000000 6 \n",
+ "top NaN 2159-09-30 01:00:00 99.999996 mL/hour \n",
+ "freq NaN 9 25385.000000 719922 \n",
+ "first NaN 2100-06-08 04:23:00 NaN NaN \n",
+ "last NaN 2209-08-07 14:27:00 NaN NaN \n",
+ "mean 150437.603989 NaN NaN NaN \n",
+ "std 28720.645234 NaN NaN NaN \n",
+ "min 100001.000000 NaN NaN NaN \n",
+ "25% 125824.000000 NaN NaN NaN \n",
+ "50% 150715.000000 NaN NaN NaN \n",
+ "75% 175466.000000 NaN NaN NaN \n",
+ "max 199984.000000 NaN NaN NaN \n",
+ "\n",
+ " itemid \n",
+ "count 817373.000000 \n",
+ "unique NaN \n",
+ "top NaN \n",
+ "freq NaN \n",
+ "first NaN \n",
+ "last NaN \n",
+ "mean 222346.358593 \n",
+ "std 23242.543767 \n",
+ "min 4647.000000 \n",
+ "25% 225158.000000 \n",
+ "50% 225158.000000 \n",
+ "75% 225158.000000 \n",
+ "max 225158.000000 "
+ ]
+ },
+ "execution_count": 26,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "label = 'normal saline'\n",
+ "df = utils.open_df(hdf5_fname,'extract/{}'.format(label))\n",
+ "df.describe(include='all')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"17\" halign=\"left\">normal saline</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mL/hour</th>\n",
+ " <th>mL</th>\n",
+ " <th>ml</th>\n",
+ " <th>mL/hour</th>\n",
+ " <th>no_units</th>\n",
+ " <th>ml</th>\n",
+ " <th>mL</th>\n",
+ " <th>ml</th>\n",
+ " <th>mL/min</th>\n",
+ " <th>L</th>\n",
+ " <th colspan=\"2\" halign=\"left\">ml</th>\n",
+ " <th>no_units</th>\n",
+ " <th>ml</th>\n",
+ " <th>mL/hour</th>\n",
+ " <th>ml</th>\n",
+ " <th>mL/hour</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>225158</th>\n",
+ " <th>225158</th>\n",
+ " <th>30190</th>\n",
+ " <th>30190</th>\n",
+ " <th>30190</th>\n",
+ " <th>225158</th>\n",
+ " <th>30190</th>\n",
+ " <th>4647</th>\n",
+ " <th>225158</th>\n",
+ " <th>225158</th>\n",
+ " <th>6190</th>\n",
+ " <th>44053</th>\n",
+ " <th>44053</th>\n",
+ " <th>44440</th>\n",
+ " <th>44440</th>\n",
+ " <th>41913</th>\n",
+ " <th>41913</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>719400.000000</td>\n",
+ " <td>39402.0</td>\n",
+ " <td>5167.0</td>\n",
+ " <td>259.0</td>\n",
+ " <td>160.0</td>\n",
+ " <td>6730.000000</td>\n",
+ " <td>50.0</td>\n",
+ " <td>8</td>\n",
+ " <td>80.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1</td>\n",
+ " <td>3.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>5.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>unique</th>\n",
+ " <td>443511.000000</td>\n",
+ " <td>147.0</td>\n",
+ " <td>243.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>4233.000000</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1</td>\n",
+ " <td>6.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1</td>\n",
+ " <td>2.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>top</th>\n",
+ " <td>99.999996</td>\n",
+ " <td>500.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>49.999999</td>\n",
+ " <td>0.0</td>\n",
+ " <td>given</td>\n",
+ " <td>100.0</td>\n",
+ " <td>1000.0</td>\n",
+ " <td>given</td>\n",
+ " <td>17.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>37.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>20.0</td>\n",
+ " <td>0.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>freq</th>\n",
+ " <td>25193.000000</td>\n",
+ " <td>11589.0</td>\n",
+ " <td>651.0</td>\n",
+ " <td>259.0</td>\n",
+ " <td>160.0</td>\n",
+ " <td>352.000000</td>\n",
+ " <td>50.0</td>\n",
+ " <td>8</td>\n",
+ " <td>60.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1</td>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>3.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label normal saline \\\n",
+ "units mL/hour mL ml mL/hour no_units ml \n",
+ "description 225158 225158 30190 30190 30190 225158 \n",
+ "count 719400.000000 39402.0 5167.0 259.0 160.0 6730.000000 \n",
+ "unique 443511.000000 147.0 243.0 1.0 1.0 4233.000000 \n",
+ "top 99.999996 500.0 1.0 0.0 0.0 49.999999 \n",
+ "freq 25193.000000 11589.0 651.0 259.0 160.0 352.000000 \n",
+ "\n",
+ "label \\\n",
+ "units mL ml mL/min L ml no_units ml \n",
+ "description 30190 4647 225158 225158 6190 44053 44053 44440 \n",
+ "count 50.0 8 80.0 1.0 1 3.0 2.0 5.0 \n",
+ "unique 1.0 1 6.0 1.0 1 2.0 1.0 2.0 \n",
+ "top 0.0 given 100.0 1000.0 given 17.0 0.0 37.0 \n",
+ "freq 50.0 8 60.0 1.0 1 2.0 2.0 3.0 \n",
+ "\n",
+ "label \n",
+ "units mL/hour ml mL/hour \n",
+ "description 44440 41913 41913 \n",
+ "count 1.0 2.0 1.0 \n",
+ "unique 1.0 1.0 1.0 \n",
+ "top 0.0 20.0 0.0 \n",
+ "freq 1.0 2.0 1.0 "
+ ]
+ },
+ "execution_count": 27,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "mimic_transform.set_params(add_level__level_val=label)\n",
+ "df_tr = mimic_transform.transform(df)\n",
+ "df_tr.describe()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "((770238, 17), (504923, 9), 265320L, 4, '0.0202% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"9\" halign=\"left\">normal saline</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"4\" halign=\"left\">known</th>\n",
+ " <th>unknown</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th colspan=\"2\" halign=\"left\">unknown</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"4\" halign=\"left\">qn</th>\n",
+ " <th>qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>nom</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mL/hr</th>\n",
+ " <th colspan=\"2\" halign=\"left\">mL</th>\n",
+ " <th>mL/hr</th>\n",
+ " <th>no_units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">mL</th>\n",
+ " <th>mL/min</th>\n",
+ " <th>no_units</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>225158(mL/hour)</th>\n",
+ " <th>225158</th>\n",
+ " <th>30190(ml)</th>\n",
+ " <th>30190(mL/hour)</th>\n",
+ " <th>30190</th>\n",
+ " <th>225158(ml)</th>\n",
+ " <th>30190</th>\n",
+ " <th>225158</th>\n",
+ " <th>4647(ml)</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>456226.000000</td>\n",
+ " <td>39261.000000</td>\n",
+ " <td>5068.000000</td>\n",
+ " <td>258.0</td>\n",
+ " <td>157.0</td>\n",
+ " <td>4844.000000</td>\n",
+ " <td>50.0</td>\n",
+ " <td>80.000000</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>unique</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>top</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>given</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>freq</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>75.669716</td>\n",
+ " <td>471.560439</td>\n",
+ " <td>4.255024</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>128.094818</td>\n",
+ " <td>0.0</td>\n",
+ " <td>103.312500</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>217.566524</td>\n",
+ " <td>372.084861</td>\n",
+ " <td>8.418981</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>260.186534</td>\n",
+ " <td>0.0</td>\n",
+ " <td>55.885358</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>-906.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.500000</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>6.000000</td>\n",
+ " <td>200.000000</td>\n",
+ " <td>0.850000</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>9.310294</td>\n",
+ " <td>0.0</td>\n",
+ " <td>100.000000</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>15.000000</td>\n",
+ " <td>500.000000</td>\n",
+ " <td>1.100000</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>25.000000</td>\n",
+ " <td>0.0</td>\n",
+ " <td>100.000000</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>62.255889</td>\n",
+ " <td>500.000000</td>\n",
+ " <td>2.400000</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>100.000001</td>\n",
+ " <td>0.0</td>\n",
+ " <td>100.000000</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>51947.999400</td>\n",
+ " <td>11000.000000</td>\n",
+ " <td>117.000000</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>5000.000160</td>\n",
+ " <td>0.0</td>\n",
+ " <td>300.000000</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label normal saline \\\n",
+ "status known \n",
+ "variable_type qn \n",
+ "units mL/hr mL mL/hr \n",
+ "description 225158(mL/hour) 225158 30190(ml) 30190(mL/hour) \n",
+ "count 456226.000000 39261.000000 5068.000000 258.0 \n",
+ "unique NaN NaN NaN NaN \n",
+ "top NaN NaN NaN NaN \n",
+ "freq NaN NaN NaN NaN \n",
+ "mean 75.669716 471.560439 4.255024 0.0 \n",
+ "std 217.566524 372.084861 8.418981 0.0 \n",
+ "min -906.000000 0.000000 0.000000 0.0 \n",
+ "25% 6.000000 200.000000 0.850000 0.0 \n",
+ "50% 15.000000 500.000000 1.100000 0.0 \n",
+ "75% 62.255889 500.000000 2.400000 0.0 \n",
+ "max 51947.999400 11000.000000 117.000000 0.0 \n",
+ "\n",
+ "label \n",
+ "status unknown known unknown \n",
+ "variable_type qn qn qn nom \n",
+ "units no_units mL mL/min no_units \n",
+ "description 30190 225158(ml) 30190 225158 4647(ml) \n",
+ "count 157.0 4844.000000 50.0 80.000000 8 \n",
+ "unique NaN NaN NaN NaN 1 \n",
+ "top NaN NaN NaN NaN given \n",
+ "freq NaN NaN NaN NaN 8 \n",
+ "mean 0.0 128.094818 0.0 103.312500 NaN \n",
+ "std 0.0 260.186534 0.0 55.885358 NaN \n",
+ "min 0.0 0.000000 0.0 0.500000 NaN \n",
+ "25% 0.0 9.310294 0.0 100.000000 NaN \n",
+ "50% 0.0 25.000000 0.0 100.000000 NaN \n",
+ "75% 0.0 100.000001 0.0 100.000000 NaN \n",
+ "max 0.0 5000.000160 0.0 300.000000 NaN "
+ ]
+ },
+ "execution_count": 33,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_cln1 = standard_pipeline.transform(df_tr)\n",
+ "print utils.data_loss(df_tr,df_cln1)\n",
+ "df_cln1.describe(include='all')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "this step: ((504923, 9), (504874, 2), 295L, 1, '0.0051% records')\n",
+ "overall: ((770238, 17), (504874, 2), 265615L, 5, '0.0253% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"2\" halign=\"left\">normal saline</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mL</th>\n",
+ " <th>mL/hr</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>49173.000000</td>\n",
+ " <td>456484.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>389.563178</td>\n",
+ " <td>75.626948</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>380.287765</td>\n",
+ " <td>217.512467</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>-906.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>100.000000</td>\n",
+ " <td>6.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>250.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>500.000000</td>\n",
+ " <td>62.204886</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>11000.000000</td>\n",
+ " <td>51947.999400</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label normal saline \n",
+ "status known \n",
+ "variable_type qn \n",
+ "units mL mL/hr\n",
+ "count 49173.000000 456484.000000\n",
+ "mean 389.563178 75.626948\n",
+ "std 380.287765 217.512467\n",
+ "min 0.000000 -906.000000\n",
+ "25% 100.000000 6.000000\n",
+ "50% 250.000000 15.000000\n",
+ "75% 500.000000 62.204886\n",
+ "max 11000.000000 51947.999400"
+ ]
+ },
+ "execution_count": 36,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_cln2 = cleaning_pipeline.transform(df_cln1)\n",
+ "print 'this step:',utils.data_loss(df_cln1,df_cln2)\n",
+ "print 'overall:',utils.data_loss(df_tr,df_cln2)\n",
+ "df_cln2.describe(include='all')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 42,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "array([[<matplotlib.axes._subplots.AxesSubplot object at 0x0000000043A236D8>,\n",
+ " <matplotlib.axes._subplots.AxesSubplot object at 0x0000000029BE0C18>]], dtype=object)"
+ ]
+ },
+ "execution_count": 42,
+ "metadata": {},
+ "output_type": "execute_result"
+ },
+ {
+ "data": {
+ "image/png": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAFeCAYAAADzFKfgAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nCAAAAFjo/wOY67O5O3hY0wAAAABJRU5ErkJggg==\n",
+ "text/plain": [
+ "<matplotlib.figure.Figure at 0x43a236a0>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "import seaborn as sns\n",
+ "df_cln2.hist(normed=True)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Single pipeline"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "all_pipeline = Pipeline([\n",
+ " ('transform',mimic_transform),\n",
+ " ('format',standard_pipeline),\n",
+ " ('clean',cleaning_pipeline)\n",
+ " ])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>382993.000000</td>\n",
+ " <td>393608</td>\n",
+ " <td>393608</td>\n",
+ " <td>393608</td>\n",
+ " <td>393608.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>unique</th>\n",
+ " <td>NaN</td>\n",
+ " <td>187323</td>\n",
+ " <td>616</td>\n",
+ " <td>2</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>top</th>\n",
+ " <td>NaN</td>\n",
+ " <td>2140-07-14 03:59:00</td>\n",
+ " <td>1.2</td>\n",
+ " <td>mmol/L</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>freq</th>\n",
+ " <td>NaN</td>\n",
+ " <td>8</td>\n",
+ " <td>20704</td>\n",
+ " <td>393592</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>first</th>\n",
+ " <td>NaN</td>\n",
+ " <td>2096-08-25 16:32:00</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>last</th>\n",
+ " <td>NaN</td>\n",
+ " <td>2210-08-19 04:56:00</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>150112.612539</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>64364.242439</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>28874.716612</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>77900.842790</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>100001.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>818.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>125190.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1531.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>149789.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>50813.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>175567.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>50813.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>199999.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>225668.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "count 382993.000000 393608 393608 393608 393608.000000\n",
+ "unique NaN 187323 616 2 NaN\n",
+ "top NaN 2140-07-14 03:59:00 1.2 mmol/L NaN\n",
+ "freq NaN 8 20704 393592 NaN\n",
+ "first NaN 2096-08-25 16:32:00 NaN NaN NaN\n",
+ "last NaN 2210-08-19 04:56:00 NaN NaN NaN\n",
+ "mean 150112.612539 NaN NaN NaN 64364.242439\n",
+ "std 28874.716612 NaN NaN NaN 77900.842790\n",
+ "min 100001.000000 NaN NaN NaN 818.000000\n",
+ "25% 125190.000000 NaN NaN NaN 1531.000000\n",
+ "50% 149789.000000 NaN NaN NaN 50813.000000\n",
+ "75% 175567.000000 NaN NaN NaN 50813.000000\n",
+ "max 199999.000000 NaN NaN NaN 225668.000000"
+ ]
+ },
+ "execution_count": 4,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "label = 'lactate'\n",
+ "df = utils.open_df(hdf5_fname,'extract/{}'.format(label))\n",
+ "df.describe(include='all')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>lactate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th>mmol/L</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>100001</th>\n",
+ " <th>2117-09-11 09:32:00</th>\n",
+ " <td>1.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100003</th>\n",
+ " <th>2150-04-17 19:12:00</th>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100006</th>\n",
+ " <th>2108-04-08 10:58:00</th>\n",
+ " <td>4.5</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100007</th>\n",
+ " <th>2145-03-31 00:44:00</th>\n",
+ " <td>3.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2145-04-02 14:10:00</th>\n",
+ " <td>1.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100009</th>\n",
+ " <th>2162-05-17 13:19:00</th>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2162-05-17 17:14:00</th>\n",
+ " <td>1.5</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"4\" valign=\"top\">100010</th>\n",
+ " <th>2109-12-10 10:25:00</th>\n",
+ " <td>0.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 12:11:00</th>\n",
+ " <td>0.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 13:05:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 13:58:00</th>\n",
+ " <td>0.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100011</th>\n",
+ " <th>2177-08-29 04:44:00</th>\n",
+ " <td>3.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-08-29 06:55:00</th>\n",
+ " <td>2.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">100012</th>\n",
+ " <th>2177-03-14 07:38:00</th>\n",
+ " <td>2.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-14 11:42:00</th>\n",
+ " <td>2.5</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 08:05:00</th>\n",
+ " <td>2.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 14:01:00</th>\n",
+ " <td>2.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 21:42:00</th>\n",
+ " <td>1.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100016</th>\n",
+ " <th>2188-05-24 12:00:00</th>\n",
+ " <td>2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100017</th>\n",
+ " <th>2103-03-11 05:10:00</th>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">100018</th>\n",
+ " <th>2176-08-29 15:29:00</th>\n",
+ " <td>1.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 09:23:00</th>\n",
+ " <td>0.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 10:19:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 11:29:00</th>\n",
+ " <td>0.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 12:40:00</th>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100020</th>\n",
+ " <th>2142-11-30 21:54:00</th>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2142-12-03 00:17:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">100024</th>\n",
+ " <th>2170-09-19 10:25:00</th>\n",
+ " <td>1.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2170-09-19 16:33:00</th>\n",
+ " <td>2.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2170-09-20 02:04:00</th>\n",
+ " <td>3.2</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">199976</th>\n",
+ " <th>2182-02-14 11:15:00</th>\n",
+ " <td>0.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-16 03:57:00</th>\n",
+ " <td>0.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-19 03:59:00</th>\n",
+ " <td>0.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-20 03:31:00</th>\n",
+ " <td>0.7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-21 04:55:00</th>\n",
+ " <td>0.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199979</th>\n",
+ " <th>2182-02-06 09:17:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-06 14:16:00</th>\n",
+ " <td>3.8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">199981</th>\n",
+ " <th>2110-09-24 16:34:00</th>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2110-09-24 20:09:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2110-09-25 06:10:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>199987</th>\n",
+ " <th>2175-05-19 16:30:00</th>\n",
+ " <td>2.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"6\" valign=\"top\">199988</th>\n",
+ " <th>2169-01-24 12:48:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 01:35:00</th>\n",
+ " <td>1.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 11:18:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 16:43:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 22:35:00</th>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-10 05:33:00</th>\n",
+ " <td>1.4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199993</th>\n",
+ " <th>2161-11-12 23:14:00</th>\n",
+ " <td>0.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2161-11-13 03:46:00</th>\n",
+ " <td>0.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"4\" valign=\"top\">199994</th>\n",
+ " <th>2188-07-07 21:23:00</th>\n",
+ " <td>1.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 03:09:00</th>\n",
+ " <td>0.7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 04:13:00</th>\n",
+ " <td>0.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 06:20:00</th>\n",
+ " <td>0.7</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">199998</th>\n",
+ " <th>2119-02-20 10:52:00</th>\n",
+ " <td>1.1</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 12:36:00</th>\n",
+ " <td>1.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 13:33:00</th>\n",
+ " <td>2.0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 13:59:00</th>\n",
+ " <td>2.6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 20:43:00</th>\n",
+ " <td>1.3</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199999</th>\n",
+ " <th>2136-04-04 20:55:00</th>\n",
+ " <td>1.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-06 15:29:00</th>\n",
+ " <td>1.8</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>177439 rows × 1 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label lactate\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units mmol/L\n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 1.9\n",
+ "100003 2150-04-17 19:12:00 1.1\n",
+ "100006 2108-04-08 10:58:00 4.5\n",
+ "100007 2145-03-31 00:44:00 3.1\n",
+ " 2145-04-02 14:10:00 1.9\n",
+ "100009 2162-05-17 13:19:00 1.1\n",
+ " 2162-05-17 17:14:00 1.5\n",
+ "100010 2109-12-10 10:25:00 0.6\n",
+ " 2109-12-10 12:11:00 0.9\n",
+ " 2109-12-10 13:05:00 1.0\n",
+ " 2109-12-10 13:58:00 0.8\n",
+ "100011 2177-08-29 04:44:00 3.8\n",
+ " 2177-08-29 06:55:00 2.3\n",
+ "100012 2177-03-14 07:38:00 2.3\n",
+ " 2177-03-14 11:42:00 2.5\n",
+ " 2177-03-15 08:05:00 2.1\n",
+ " 2177-03-15 14:01:00 2.6\n",
+ " 2177-03-15 21:42:00 1.8\n",
+ "100016 2188-05-24 12:00:00 2.0\n",
+ "100017 2103-03-11 05:10:00 1.1\n",
+ "100018 2176-08-29 15:29:00 1.3\n",
+ " 2176-08-30 09:23:00 0.9\n",
+ " 2176-08-30 10:19:00 1.0\n",
+ " 2176-08-30 11:29:00 0.9\n",
+ " 2176-08-30 12:40:00 1.1\n",
+ "100020 2142-11-30 21:54:00 1.1\n",
+ " 2142-12-03 00:17:00 1.0\n",
+ "100024 2170-09-19 10:25:00 1.4\n",
+ " 2170-09-19 16:33:00 2.6\n",
+ " 2170-09-20 02:04:00 3.2\n",
+ "... ...\n",
+ "199976 2182-02-14 11:15:00 0.8\n",
+ " 2182-02-16 03:57:00 0.8\n",
+ " 2182-02-19 03:59:00 0.8\n",
+ " 2182-02-20 03:31:00 0.7\n",
+ " 2182-02-21 04:55:00 0.9\n",
+ "199979 2182-02-06 09:17:00 1.0\n",
+ " 2182-02-06 14:16:00 3.8\n",
+ "199981 2110-09-24 16:34:00 1.1\n",
+ " 2110-09-24 20:09:00 1.0\n",
+ " 2110-09-25 06:10:00 1.0\n",
+ "199987 2175-05-19 16:30:00 2.3\n",
+ "199988 2169-01-24 12:48:00 1.0\n",
+ " 2169-02-07 01:35:00 1.6\n",
+ " 2169-02-07 11:18:00 1.0\n",
+ " 2169-02-07 16:43:00 1.0\n",
+ " 2169-02-07 22:35:00 1.1\n",
+ " 2169-02-10 05:33:00 1.4\n",
+ "199993 2161-11-12 23:14:00 0.9\n",
+ " 2161-11-13 03:46:00 0.9\n",
+ "199994 2188-07-07 21:23:00 1.0\n",
+ " 2188-07-08 03:09:00 0.7\n",
+ " 2188-07-08 04:13:00 0.6\n",
+ " 2188-07-08 06:20:00 0.7\n",
+ "199998 2119-02-20 10:52:00 1.1\n",
+ " 2119-02-20 12:36:00 1.9\n",
+ " 2119-02-20 13:33:00 2.0\n",
+ " 2119-02-20 13:59:00 2.6\n",
+ " 2119-02-20 20:43:00 1.3\n",
+ "199999 2136-04-04 20:55:00 1.9\n",
+ " 2136-04-06 15:29:00 1.8\n",
+ "\n",
+ "[177439 rows x 1 columns]"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "all_pipeline.set_params(transform__add_level__level_val=label)\n",
+ "all_pipeline.transform(df)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Loop over everything"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import logger"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:18:23) heart rate\n",
+ "(2017-06-03 07:18:23)>> Open Extract\n",
+ "(2017-06-03 07:18:26)<< DONE (3.0s)\n",
+ "(2017-06-03 07:18:26)>> Run Pipeline\n",
+ "(2017-06-03 07:21:19)<< DONE (173.0s)\n",
+ "(2017-06-03 07:21:19)>> Analyze...\n",
+ "((7952939, 1), (7922961, 1), 29978L, 171, '0.3015% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>heart rate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>beats/min</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>7.922961e+06</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>1.026618e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>3.552932e+03</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>-8.800000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>7.700000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>9.200000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>1.190000e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>9.999999e+06</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label heart rate\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units beats/min\n",
+ "count 7.922961e+06\n",
+ "mean 1.026618e+02\n",
+ "std 3.552932e+03\n",
+ "min -8.800000e+01\n",
+ "25% 7.700000e+01\n",
+ "50% 9.200000e+01\n",
+ "75% 1.190000e+02\n",
+ "max 9.999999e+06"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:21:20)<< DONE (1.0s)\n",
+ "(2017-06-03 07:21:20)>> Joining!\n",
+ "(2017-06-03 07:21:20)<< DONE (0.0s)\n",
+ "(2017-06-03 07:21:20) DONE (177.0s)\n",
+ "(2017-06-03 07:21:20) blood pressure systolic\n",
+ "(2017-06-03 07:21:20)>> Open Extract\n",
+ "(2017-06-03 07:21:23)<< DONE (3.0s)\n",
+ "(2017-06-03 07:21:23)>> Run Pipeline\n",
+ "(2017-06-03 07:25:39)<< DONE (256.0s)\n",
+ "(2017-06-03 07:25:39)>> Analyze...\n",
+ "((6374824, 1), (5974186, 1), 548979L, 174, '0.307% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>blood pressure systolic</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mmHg</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>5.825845e+06</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>1.214682e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>1.311542e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>-6.900000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>1.040000e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>1.190000e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>1.370000e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>1.411460e+05</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label blood pressure systolic\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units mmHg\n",
+ "count 5.825845e+06\n",
+ "mean 1.214682e+02\n",
+ "std 1.311542e+02\n",
+ "min -6.900000e+01\n",
+ "25% 1.040000e+02\n",
+ "50% 1.190000e+02\n",
+ "75% 1.370000e+02\n",
+ "max 1.411460e+05"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:25:40)<< DONE (1.0s)\n",
+ "(2017-06-03 07:25:40)>> Joining!\n",
+ "(2017-06-03 07:26:28)<< DONE (48.0s)\n",
+ "(2017-06-03 07:26:28) DONE (308.0s)\n",
+ "(2017-06-03 07:26:28) blood pressure diastolic\n",
+ "(2017-06-03 07:26:28)>> Open Extract\n",
+ "(2017-06-03 07:26:31)<< DONE (3.0s)\n",
+ "(2017-06-03 07:26:31)>> Run Pipeline\n",
+ "(2017-06-03 07:30:32)<< DONE (241.0s)\n",
+ "(2017-06-03 07:30:32)>> Analyze...\n",
+ "((6371249, 1), (5976313, 1), 543269L, 170, '0.2999% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>blood pressure diastolic</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mmHg</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>5.827980e+06</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>6.115824e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>2.350768e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>-1.600000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>5.000000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>5.900000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>6.900000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>1.141090e+05</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label blood pressure diastolic\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units mmHg\n",
+ "count 5.827980e+06\n",
+ "mean 6.115824e+01\n",
+ "std 2.350768e+02\n",
+ "min -1.600000e+01\n",
+ "25% 5.000000e+01\n",
+ "50% 5.900000e+01\n",
+ "75% 6.900000e+01\n",
+ "max 1.141090e+05"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:30:34)<< DONE (2.0s)\n",
+ "(2017-06-03 07:30:34)>> Joining!\n",
+ "(2017-06-03 07:31:25)<< DONE (51.0s)\n",
+ "(2017-06-03 07:31:25) DONE (297.0s)\n",
+ "(2017-06-03 07:31:25) blood pressure mean\n",
+ "(2017-06-03 07:31:25)>> Open Extract\n",
+ "(2017-06-03 07:31:26)<< DONE (1.0s)\n",
+ "(2017-06-03 07:31:26)>> Run Pipeline\n",
+ "(2017-06-03 07:32:39)<< DONE (73.0s)\n",
+ "(2017-06-03 07:32:39)>> Analyze...\n",
+ "((2536271, 1), (2415995, 1), 120276L, 0, '0.0% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>blood pressure mean</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mmHg</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>2.415995e+06</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>7.879668e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>1.413279e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>-1.350000e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>6.700000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>7.700000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>8.800000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>1.201300e+05</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label blood pressure mean\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units mmHg\n",
+ "count 2.415995e+06\n",
+ "mean 7.879668e+01\n",
+ "std 1.413279e+02\n",
+ "min -1.350000e+02\n",
+ "25% 6.700000e+01\n",
+ "50% 7.700000e+01\n",
+ "75% 8.800000e+01\n",
+ "max 1.201300e+05"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:32:40)<< DONE (1.0s)\n",
+ "(2017-06-03 07:32:40)>> Joining!\n",
+ "(2017-06-03 07:33:20)<< DONE (40.0s)\n",
+ "(2017-06-03 07:33:20) DONE (115.0s)\n",
+ "(2017-06-03 07:33:20) respiratory rate\n",
+ "(2017-06-03 07:33:20)>> Open Extract\n",
+ "(2017-06-03 07:33:24)<< DONE (4.0s)\n",
+ "(2017-06-03 07:33:24)>> Run Pipeline\n",
+ "(2017-06-03 07:37:33)<< DONE (249.0s)\n",
+ "(2017-06-03 07:37:33)>> Analyze...\n",
+ "((7810019, 1), (7780015, 1), 5072936L, 172, '0.3035% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>respiratory rate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>insp/min</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>2.737083e+06</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>2.092347e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>1.423811e+03</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000e+00</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>1.600000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>2.000000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>2.400000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>2.355555e+06</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label respiratory rate\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units insp/min\n",
+ "count 2.737083e+06\n",
+ "mean 2.092347e+01\n",
+ "std 1.423811e+03\n",
+ "min 0.000000e+00\n",
+ "25% 1.600000e+01\n",
+ "50% 2.000000e+01\n",
+ "75% 2.400000e+01\n",
+ "max 2.355555e+06"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:37:35)<< DONE (2.0s)\n",
+ "(2017-06-03 07:37:35)>> Joining!\n",
+ "(2017-06-03 07:38:29)<< DONE (54.0s)\n",
+ "(2017-06-03 07:38:29) DONE (309.0s)\n",
+ "(2017-06-03 07:38:29) temperature body\n",
+ "(2017-06-03 07:38:29)>> Open Extract\n",
+ "(2017-06-03 07:38:31)<< DONE (2.0s)\n",
+ "(2017-06-03 07:38:31)>> Run Pipeline\n",
+ "(2017-06-03 07:39:35)<< DONE (64.0s)\n",
+ "(2017-06-03 07:39:35)>> Analyze...\n",
+ "((1751447, 1), (1731794, 1), 461152L, 156, '0.3189% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>temperature body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>degF</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>1.290295e+06</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>9.850479e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>9.563484e+00</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>-9.990000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>9.760000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>9.850000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>9.950000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>9.637000e+03</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label temperature body\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units degF\n",
+ "count 1.290295e+06\n",
+ "mean 9.850479e+01\n",
+ "std 9.563484e+00\n",
+ "min -9.990000e+01\n",
+ "25% 9.760000e+01\n",
+ "50% 9.850000e+01\n",
+ "75% 9.950000e+01\n",
+ "max 9.637000e+03"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:39:36)<< DONE (1.0s)\n",
+ "(2017-06-03 07:39:36)>> Joining!\n",
+ "(2017-06-03 07:40:14)<< DONE (38.0s)\n",
+ "(2017-06-03 07:40:14) DONE (105.0s)\n",
+ "(2017-06-03 07:40:14) oxygen saturation pulse oximetry\n",
+ "(2017-06-03 07:40:14)>> Open Extract\n",
+ "(2017-06-03 07:40:17)<< DONE (3.0s)\n",
+ "(2017-06-03 07:40:17)>> Run Pipeline\n",
+ "(2017-06-03 07:42:42)<< DONE (145.0s)\n",
+ "(2017-06-03 07:42:42)>> Analyze...\n",
+ "((6099827, 1), (6073019, 1), 26808L, 163, '0.3326% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>oxygen saturation pulse oximetry</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>percent</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>6.073019e+06</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>9.885942e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>2.942035e+03</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000e+00</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>9.600000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>9.800000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>9.900000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>6.363333e+06</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label oxygen saturation pulse oximetry\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units percent\n",
+ "count 6.073019e+06\n",
+ "mean 9.885942e+01\n",
+ "std 2.942035e+03\n",
+ "min 0.000000e+00\n",
+ "25% 9.600000e+01\n",
+ "50% 9.800000e+01\n",
+ "75% 9.900000e+01\n",
+ "max 6.363333e+06"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:42:43)<< DONE (1.0s)\n",
+ "(2017-06-03 07:42:43)>> Joining!\n",
+ "(2017-06-03 07:43:35)<< DONE (52.0s)\n",
+ "(2017-06-03 07:43:35) DONE (201.0s)\n",
+ "(2017-06-03 07:43:35) weight body\n",
+ "(2017-06-03 07:43:35)>> Open Extract\n",
+ "(2017-06-03 07:43:36)<< DONE (1.0s)\n",
+ "(2017-06-03 07:43:36)>> Run Pipeline\n",
+ "(2017-06-03 07:43:40)<< DONE (4.0s)\n",
+ "(2017-06-03 07:43:40)>> Analyze...\n",
+ "((95425, 1), (94457, 1), 1956L, 158, '0.4958% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>weight body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>kg</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>9.346900e+04</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>2.676828e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>3.908673e+04</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000e+00</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>6.980000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>8.340000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>9.890000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>8.654765e+06</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label weight body\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units kg\n",
+ "count 9.346900e+04\n",
+ "mean 2.676828e+02\n",
+ "std 3.908673e+04\n",
+ "min 0.000000e+00\n",
+ "25% 6.980000e+01\n",
+ "50% 8.340000e+01\n",
+ "75% 9.890000e+01\n",
+ "max 8.654765e+06"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:43:40)<< DONE (0.0s)\n",
+ "(2017-06-03 07:43:40)>> Joining!\n",
+ "(2017-06-03 07:44:15)<< DONE (35.0s)\n",
+ "(2017-06-03 07:44:15) DONE (40.0s)\n",
+ "(2017-06-03 07:44:15) output urine\n",
+ "(2017-06-03 07:44:15)>> Open Extract\n",
+ "(2017-06-03 07:44:16)<< DONE (1.0s)\n",
+ "(2017-06-03 07:44:16)>> Run Pipeline\n",
+ "(2017-06-03 07:47:57)<< DONE (221.0s)\n",
+ "(2017-06-03 07:47:57)>> Analyze...\n",
+ "((3644639, 1), (3624029, 1), 417242L, 92, '0.1758% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>output urine</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mL</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>3.216363e+06</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>1.265574e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>2.577291e+03</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>-1.500000e+03</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>4.200000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>8.000000e+01</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>1.600000e+02</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>4.555555e+06</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label output urine\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units mL\n",
+ "count 3.216363e+06\n",
+ "mean 1.265574e+02\n",
+ "std 2.577291e+03\n",
+ "min -1.500000e+03\n",
+ "25% 4.200000e+01\n",
+ "50% 8.000000e+01\n",
+ "75% 1.600000e+02\n",
+ "max 4.555555e+06"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:47:58)<< DONE (1.0s)\n",
+ "(2017-06-03 07:47:58)>> Joining!\n",
+ "(2017-06-03 07:48:43)<< DONE (45.0s)\n",
+ "(2017-06-03 07:48:43) DONE (268.0s)\n",
+ "(2017-06-03 07:48:43) glasgow coma scale motor\n",
+ "(2017-06-03 07:48:43)>> Open Extract\n",
+ "(2017-06-03 07:48:43)<< DONE (0.0s)\n",
+ "(2017-06-03 07:48:43)>> Run Pipeline\n",
+ "(2017-06-03 07:49:29)<< DONE (46.0s)\n",
+ "(2017-06-03 07:49:29)>> Analyze...\n",
+ "((952565, 1), (949198, 1), 3367L, 1, '0.0037% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>glasgow coma scale motor</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>ord</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>no_units</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>949198</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>unique</th>\n",
+ " <td>6</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>top</th>\n",
+ " <td>Obeys commands</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>freq</th>\n",
+ " <td>642879</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label glasgow coma scale motor\n",
+ "status known\n",
+ "variable_type ord\n",
+ "units no_units\n",
+ "count 949198\n",
+ "unique 6\n",
+ "top Obeys commands\n",
+ "freq 642879"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:49:29)<< DONE (0.0s)\n",
+ "(2017-06-03 07:49:29)>> Joining!\n",
+ "(2017-06-03 07:50:06)<< DONE (37.0s)\n",
+ "(2017-06-03 07:50:06) DONE (83.0s)\n",
+ "(2017-06-03 07:50:06) glasgow coma scale eye opening\n",
+ "(2017-06-03 07:50:06)>> Open Extract\n",
+ "(2017-06-03 07:50:07)<< DONE (1.0s)\n",
+ "(2017-06-03 07:50:07)>> Run Pipeline\n",
+ "(2017-06-03 07:50:50)<< DONE (43.0s)\n",
+ "(2017-06-03 07:50:50)>> Analyze...\n",
+ "((956672, 1), (953595, 1), 3077L, 1, '0.0037% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>glasgow coma scale eye opening</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>ord</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>no_units</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>953595</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>unique</th>\n",
+ " <td>4</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>top</th>\n",
+ " <td>Eyes open spontaneously</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>freq</th>\n",
+ " <td>588057</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label glasgow coma scale eye opening\n",
+ "status known\n",
+ "variable_type ord\n",
+ "units no_units\n",
+ "count 953595\n",
+ "unique 4\n",
+ "top Eyes open spontaneously\n",
+ "freq 588057"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:50:50)<< DONE (0.0s)\n",
+ "(2017-06-03 07:50:50)>> Joining!\n",
+ "(2017-06-03 07:51:28)<< DONE (38.0s)\n",
+ "(2017-06-03 07:51:28) DONE (82.0s)\n",
+ "(2017-06-03 07:51:28) glasgow coma scale verbal\n",
+ "(2017-06-03 07:51:28)>> Open Extract\n",
+ "(2017-06-03 07:51:29)<< DONE (1.0s)\n",
+ "(2017-06-03 07:51:29)>> Run Pipeline\n",
+ "(2017-06-03 07:52:14)<< DONE (45.0s)\n",
+ "(2017-06-03 07:52:14)>> Analyze...\n",
+ "((954700, 1), (950913, 1), 3787L, 2, '0.0074% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>glasgow coma scale verbal</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>ord</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>no_units</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>950913</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>unique</th>\n",
+ " <td>5</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>top</th>\n",
+ " <td>No verbal response (>2 yrs); no vocal response...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>freq</th>\n",
+ " <td>465193</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label glasgow coma scale verbal\n",
+ "status known\n",
+ "variable_type ord\n",
+ "units no_units\n",
+ "count 950913\n",
+ "unique 5\n",
+ "top No verbal response (>2 yrs); no vocal response...\n",
+ "freq 465193"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 07:52:14)<< DONE (0.0s)\n",
+ "(2017-06-03 07:52:14)>> Joining!\n",
+ "(2017-06-03 07:52:51)<< DONE (37.0s)\n",
+ "(2017-06-03 07:52:51) DONE (83.0s)\n",
+ "(2017-06-03 07:52:51) normal saline\n",
+ "(2017-06-03 07:52:51)>> Open Extract\n",
+ "(2017-06-03 07:52:51)<< DONE (0.0s)\n",
+ "(2017-06-03 07:52:51)>> Run Pipeline\n",
+ "(2017-06-03 08:01:38)<< DONE (527.0s)\n",
+ "(2017-06-03 08:01:38)>> Analyze...\n",
+ "((817373, 1), (504874, 2), 265615L, 8, '0.0405% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"2\" halign=\"left\">normal saline</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mL</th>\n",
+ " <th>mL/hr</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>49173.000000</td>\n",
+ " <td>456484.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>389.563178</td>\n",
+ " <td>75.626948</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>380.287765</td>\n",
+ " <td>217.512467</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>-906.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>100.000000</td>\n",
+ " <td>6.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>250.000000</td>\n",
+ " <td>15.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>500.000000</td>\n",
+ " <td>62.204886</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>11000.000000</td>\n",
+ " <td>51947.999400</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label normal saline \n",
+ "status known \n",
+ "variable_type qn \n",
+ "units mL mL/hr\n",
+ "count 49173.000000 456484.000000\n",
+ "mean 389.563178 75.626948\n",
+ "std 380.287765 217.512467\n",
+ "min 0.000000 -906.000000\n",
+ "25% 100.000000 6.000000\n",
+ "50% 250.000000 15.000000\n",
+ "75% 500.000000 62.204886\n",
+ "max 11000.000000 51947.999400"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 08:01:38)<< DONE (0.0s)\n",
+ "(2017-06-03 08:01:38)>> Joining!\n",
+ "(2017-06-03 08:02:15)<< DONE (37.0s)\n",
+ "(2017-06-03 08:02:15) DONE (564.0s)\n",
+ "(2017-06-03 08:02:15) lactated ringers\n",
+ "(2017-06-03 08:02:15)>> Open Extract\n",
+ "(2017-06-03 08:02:15)<< DONE (0.0s)\n",
+ "(2017-06-03 08:02:15)>> Run Pipeline\n",
+ "(2017-06-03 08:02:57)<< DONE (42.0s)\n",
+ "(2017-06-03 08:02:57)>> Analyze...\n",
+ "((504306, 1), (254175, 2), 19193L, 18, '0.1085% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"2\" halign=\"left\">lactated ringers</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mL</th>\n",
+ " <th>mL/hr</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>248510.000000</td>\n",
+ " <td>2161.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>204.109607</td>\n",
+ " <td>289.877760</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>338.277593</td>\n",
+ " <td>418.153805</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>15.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>100.000000</td>\n",
+ " <td>99.994818</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>200.000000</td>\n",
+ " <td>499.999980</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>60000.000000</td>\n",
+ " <td>3923.333176</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label lactated ringers \n",
+ "status known \n",
+ "variable_type qn \n",
+ "units mL mL/hr\n",
+ "count 248510.000000 2161.000000\n",
+ "mean 204.109607 289.877760\n",
+ "std 338.277593 418.153805\n",
+ "min 0.000000 0.000000\n",
+ "25% 15.000000 0.000000\n",
+ "50% 100.000000 99.994818\n",
+ "75% 200.000000 499.999980\n",
+ "max 60000.000000 3923.333176"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 08:02:57)<< DONE (0.0s)\n",
+ "(2017-06-03 08:02:57)>> Joining!\n",
+ "(2017-06-03 08:03:34)<< DONE (37.0s)\n",
+ "(2017-06-03 08:03:34) DONE (79.0s)\n",
+ "(2017-06-03 08:03:34) norepinephrine\n",
+ "(2017-06-03 08:03:34)>> Open Extract\n",
+ "(2017-06-03 08:03:34)<< DONE (0.0s)\n",
+ "(2017-06-03 08:03:34)>> Run Pipeline\n",
+ "(2017-06-03 08:05:19)<< DONE (105.0s)\n",
+ "(2017-06-03 08:05:19)>> Analyze...\n",
+ "((1136938, 1), (389986, 2), 331666L, 17, '0.231% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"2\" halign=\"left\">norepinephrine</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mcg/kg/min</th>\n",
+ " <th>mcg/min</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>286781.000000</td>\n",
+ " <td>14226.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>0.141207</td>\n",
+ " <td>9.687762</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>0.343212</td>\n",
+ " <td>14.889317</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>0.035000</td>\n",
+ " <td>2.666667</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>0.080000</td>\n",
+ " <td>6.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>0.180000</td>\n",
+ " <td>12.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>50.000000</td>\n",
+ " <td>250.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label norepinephrine \n",
+ "status known \n",
+ "variable_type qn \n",
+ "units mcg/kg/min mcg/min\n",
+ "count 286781.000000 14226.000000\n",
+ "mean 0.141207 9.687762\n",
+ "std 0.343212 14.889317\n",
+ "min 0.000000 0.000000\n",
+ "25% 0.035000 2.666667\n",
+ "50% 0.080000 6.000000\n",
+ "75% 0.180000 12.000000\n",
+ "max 50.000000 250.000000"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 08:05:20)<< DONE (1.0s)\n",
+ "(2017-06-03 08:05:20)>> Joining!\n",
+ "(2017-06-03 08:05:58)<< DONE (38.0s)\n",
+ "(2017-06-03 08:05:58) DONE (144.0s)\n",
+ "(2017-06-03 08:05:58) vasopressin\n",
+ "(2017-06-03 08:05:58)>> Open Extract\n",
+ "(2017-06-03 08:05:58)<< DONE (0.0s)\n",
+ "(2017-06-03 08:05:58)>> Run Pipeline\n",
+ "(2017-06-03 08:06:20)<< DONE (22.0s)\n",
+ "(2017-06-03 08:06:20)>> Analyze...\n",
+ "((339184, 1), (110333, 2), 16608L, 8, '0.3406% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"2\" halign=\"left\">vasopressin</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>units</th>\n",
+ " <th>units/min</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>57371.000000</td>\n",
+ " <td>98872.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>2.517366</td>\n",
+ " <td>0.992521</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>4.842854</td>\n",
+ " <td>1.291858</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>1.800000</td>\n",
+ " <td>0.040000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>2.400000</td>\n",
+ " <td>0.044000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>2.400000</td>\n",
+ " <td>2.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>722.400000</td>\n",
+ " <td>50.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label vasopressin \n",
+ "status known \n",
+ "variable_type qn \n",
+ "units units units/min\n",
+ "count 57371.000000 98872.000000\n",
+ "mean 2.517366 0.992521\n",
+ "std 4.842854 1.291858\n",
+ "min 0.000000 0.000000\n",
+ "25% 1.800000 0.040000\n",
+ "50% 2.400000 0.044000\n",
+ "75% 2.400000 2.400000\n",
+ "max 722.400000 50.000000"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 08:06:20)<< DONE (0.0s)\n",
+ "(2017-06-03 08:06:20)>> Joining!\n",
+ "(2017-06-03 08:06:56)<< DONE (36.0s)\n",
+ "(2017-06-03 08:06:56) DONE (58.0s)\n",
+ "(2017-06-03 08:06:56) hemoglobin\n",
+ "(2017-06-03 08:06:56)>> Open Extract\n",
+ "(2017-06-03 08:06:56)<< DONE (0.0s)\n",
+ "(2017-06-03 08:06:56)>> Run Pipeline\n",
+ "(2017-06-03 08:07:52)<< DONE (56.0s)\n",
+ "(2017-06-03 08:07:52)>> Analyze...\n",
+ "((1167921, 1), (671087, 1), 641393L, 7, '0.0123% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>hemoglobin</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>g/dL</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>526528.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>10.351784</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>1.980592</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>9.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>10.100000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>11.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>130.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label hemoglobin\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units g/dL\n",
+ "count 526528.000000\n",
+ "mean 10.351784\n",
+ "std 1.980592\n",
+ "min 0.000000\n",
+ "25% 9.000000\n",
+ "50% 10.100000\n",
+ "75% 11.400000\n",
+ "max 130.000000"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 08:07:52)<< DONE (0.0s)\n",
+ "(2017-06-03 08:07:52)>> Joining!\n",
+ "(2017-06-03 08:08:36)<< DONE (44.0s)\n",
+ "(2017-06-03 08:08:36) DONE (100.0s)\n",
+ "(2017-06-03 08:08:36) lactate\n",
+ "(2017-06-03 08:08:36)>> Open Extract\n",
+ "(2017-06-03 08:08:37)<< DONE (1.0s)\n",
+ "(2017-06-03 08:08:37)>> Run Pipeline\n",
+ "(2017-06-03 08:08:52)<< DONE (15.0s)\n",
+ "(2017-06-03 08:08:52)>> Analyze...\n",
+ "((393608, 1), (177439, 1), 216244L, 33, '0.0962% records')\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th>lactate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>mmol/L</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>177364.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>8.286749</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>2374.466306</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>1.200000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>1.800000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>2.900000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>999999.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label lactate\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units mmol/L\n",
+ "count 177364.000000\n",
+ "mean 8.286749\n",
+ "std 2374.466306\n",
+ "min 0.000000\n",
+ "25% 1.200000\n",
+ "50% 1.800000\n",
+ "75% 2.900000\n",
+ "max 999999.000000"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-03 08:08:52)<< DONE (0.0s)\n",
+ "(2017-06-03 08:08:52)>> Joining!\n",
+ "(2017-06-03 08:09:35)<< DONE (43.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>heart rate</th>\n",
+ " <th>blood pressure systolic</th>\n",
+ " <th>blood pressure diastolic</th>\n",
+ " <th>blood pressure mean</th>\n",
+ " <th>respiratory rate</th>\n",
+ " <th>temperature body</th>\n",
+ " <th>oxygen saturation pulse oximetry</th>\n",
+ " <th>weight body</th>\n",
+ " <th>output urine</th>\n",
+ " <th>glasgow coma scale motor</th>\n",
+ " <th>...</th>\n",
+ " <th colspan=\"2\" halign=\"left\">normal saline</th>\n",
+ " <th colspan=\"2\" halign=\"left\">lactated ringers</th>\n",
+ " <th colspan=\"2\" halign=\"left\">norepinephrine</th>\n",
+ " <th colspan=\"2\" halign=\"left\">vasopressin</th>\n",
+ " <th>hemoglobin</th>\n",
+ " <th>lactate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>...</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>ord</th>\n",
+ " <th>...</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th>beats/min</th>\n",
+ " <th>mmHg</th>\n",
+ " <th>mmHg</th>\n",
+ " <th>mmHg</th>\n",
+ " <th>insp/min</th>\n",
+ " <th>degF</th>\n",
+ " <th>percent</th>\n",
+ " <th>kg</th>\n",
+ " <th>mL</th>\n",
+ " <th>no_units</th>\n",
+ " <th>...</th>\n",
+ " <th>mL</th>\n",
+ " <th>mL/hr</th>\n",
+ " <th>mL</th>\n",
+ " <th>mL/hr</th>\n",
+ " <th>mcg/kg/min</th>\n",
+ " <th>mcg/min</th>\n",
+ " <th>units</th>\n",
+ " <th>units/min</th>\n",
+ " <th>g/dL</th>\n",
+ " <th>mmol/L</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"10\" valign=\"top\">100001</th>\n",
+ " <th>2117-09-11 09:22:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>13.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 09:32:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 12:50:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>5.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 12:55:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>6.996487</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 12:57:00</th>\n",
+ " <td>122.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>14.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:00:00</th>\n",
+ " <td>118.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>22.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:01:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>192.0</td>\n",
+ " <td>100.0</td>\n",
+ " <td>122.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:48:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>499.999980</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:49:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>300.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:50:00</th>\n",
+ " <td>118.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>22.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>10 rows × 22 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label heart rate blood pressure systolic \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units beats/min mmHg \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 122.0 NaN \n",
+ " 2117-09-11 13:00:00 118.0 NaN \n",
+ " 2117-09-11 13:01:00 NaN 192.0 \n",
+ " 2117-09-11 13:48:00 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 118.0 NaN \n",
+ "\n",
+ "label blood pressure diastolic blood pressure mean \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units mmHg mmHg \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN \n",
+ " 2117-09-11 13:01:00 100.0 122.0 \n",
+ " 2117-09-11 13:48:00 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN \n",
+ "\n",
+ "label respiratory rate temperature body \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units insp/min degF \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 14.0 NaN \n",
+ " 2117-09-11 13:00:00 22.0 NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN 98.0 \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 22.0 NaN \n",
+ "\n",
+ "label oxygen saturation pulse oximetry weight body \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units percent kg \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN \n",
+ "\n",
+ "label output urine glasgow coma scale motor ... \\\n",
+ "status known known ... \n",
+ "variable_type qn ord ... \n",
+ "units mL no_units ... \n",
+ "id datetime ... \n",
+ "100001 2117-09-11 09:22:00 NaN NaN ... \n",
+ " 2117-09-11 09:32:00 NaN NaN ... \n",
+ " 2117-09-11 12:50:00 NaN NaN ... \n",
+ " 2117-09-11 12:55:00 NaN NaN ... \n",
+ " 2117-09-11 12:57:00 NaN NaN ... \n",
+ " 2117-09-11 13:00:00 NaN NaN ... \n",
+ " 2117-09-11 13:01:00 NaN NaN ... \n",
+ " 2117-09-11 13:48:00 NaN NaN ... \n",
+ " 2117-09-11 13:49:00 300.0 NaN ... \n",
+ " 2117-09-11 13:50:00 NaN NaN ... \n",
+ "\n",
+ "label normal saline lactated ringers \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units mL mL/hr mL mL/hr \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN 5.000000 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN 6.996487 NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN 499.999980 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN NaN NaN \n",
+ "\n",
+ "label norepinephrine vasopressin \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units mcg/kg/min mcg/min units units/min \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN NaN NaN \n",
+ "\n",
+ "label hemoglobin lactate \n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units g/dL mmol/L \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 13.0 NaN \n",
+ " 2117-09-11 09:32:00 NaN 1.9 \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN \n",
+ "\n",
+ "[10 rows x 22 columns]"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "reload(logger)\n",
+ "simple_data = data_dict.get_panel_defintions(12) #12 is \"simple data\"\n",
+ "labels = simple_data.label.unique().tolist()\n",
+ "\n",
+ "df_final = None\n",
+ "for label in labels:\n",
+ " logger.log(label,new_level=True)\n",
+ " logger.log('Open Extract')\n",
+ " df_extract = utils.open_df(hdf5_fname,'extract/{}'.format(label))\n",
+ "\n",
+ " logger.log('Run Pipeline')\n",
+ " all_pipeline.set_params(transform__add_level__level_val=label)\n",
+ " df = all_pipeline.transform(df_extract)\n",
+ " \n",
+ " logger.log('Analyze...')\n",
+ " print utils.data_loss(df_extract.set_index('id').value.to_frame(),df)\n",
+ " display(df.describe())\n",
+ "\n",
+ " logger.log('Joining!')\n",
+ "\n",
+ " if df_final is None: df_final = df\n",
+ " else: \n",
+ " df_final = df_final.join(df,how='outer')\n",
+ " del df\n",
+ " logger.end_log_level()\n",
+ "\n",
+ "df_final.head(10)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 15,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>heart rate</th>\n",
+ " <th>blood pressure systolic</th>\n",
+ " <th>blood pressure diastolic</th>\n",
+ " <th>blood pressure mean</th>\n",
+ " <th>respiratory rate</th>\n",
+ " <th>temperature body</th>\n",
+ " <th>oxygen saturation pulse oximetry</th>\n",
+ " <th>weight body</th>\n",
+ " <th>output urine</th>\n",
+ " <th>glasgow coma scale motor</th>\n",
+ " <th>...</th>\n",
+ " <th colspan=\"2\" halign=\"left\">normal saline</th>\n",
+ " <th colspan=\"2\" halign=\"left\">lactated ringers</th>\n",
+ " <th colspan=\"2\" halign=\"left\">norepinephrine</th>\n",
+ " <th colspan=\"2\" halign=\"left\">vasopressin</th>\n",
+ " <th>hemoglobin</th>\n",
+ " <th>lactate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " <th>...</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th colspan=\"2\" halign=\"left\">known</th>\n",
+ " <th>known</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>ord</th>\n",
+ " <th>...</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"2\" halign=\"left\">qn</th>\n",
+ " <th>qn</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th>beats/min</th>\n",
+ " <th>mmHg</th>\n",
+ " <th>mmHg</th>\n",
+ " <th>mmHg</th>\n",
+ " <th>insp/min</th>\n",
+ " <th>degF</th>\n",
+ " <th>percent</th>\n",
+ " <th>kg</th>\n",
+ " <th>mL</th>\n",
+ " <th>no_units</th>\n",
+ " <th>...</th>\n",
+ " <th>mL</th>\n",
+ " <th>mL/hr</th>\n",
+ " <th>mL</th>\n",
+ " <th>mL/hr</th>\n",
+ " <th>mcg/kg/min</th>\n",
+ " <th>mcg/min</th>\n",
+ " <th>units</th>\n",
+ " <th>units/min</th>\n",
+ " <th>g/dL</th>\n",
+ " <th>mmol/L</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"30\" valign=\"top\">100001</th>\n",
+ " <th>2117-09-11 09:22:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>13.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 09:32:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 12:50:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>5.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 12:55:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>6.996487</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 12:57:00</th>\n",
+ " <td>122.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>14.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:00:00</th>\n",
+ " <td>118.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>22.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:01:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>192.0</td>\n",
+ " <td>100.0</td>\n",
+ " <td>122.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:48:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>499.999980</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:49:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>300.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 13:50:00</th>\n",
+ " <td>118.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>22.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 14:00:00</th>\n",
+ " <td>118.0</td>\n",
+ " <td>165.0</td>\n",
+ " <td>85.0</td>\n",
+ " <td>103.0</td>\n",
+ " <td>15.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>8.990600</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 15:00:00</th>\n",
+ " <td>110.0</td>\n",
+ " <td>119.0</td>\n",
+ " <td>64.0</td>\n",
+ " <td>76.0</td>\n",
+ " <td>15.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 15:48:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>999.999960</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 15:59:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>199.999998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 16:00:00</th>\n",
+ " <td>104.0</td>\n",
+ " <td>169.0</td>\n",
+ " <td>84.0</td>\n",
+ " <td>105.0</td>\n",
+ " <td>16.0</td>\n",
+ " <td>97.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 16:02:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 16:11:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>40.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 16:12:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4.992476</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 17:00:00</th>\n",
+ " <td>101.0</td>\n",
+ " <td>110.0</td>\n",
+ " <td>62.0</td>\n",
+ " <td>75.0</td>\n",
+ " <td>15.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 18:00:00</th>\n",
+ " <td>112.0</td>\n",
+ " <td>170.0</td>\n",
+ " <td>86.0</td>\n",
+ " <td>106.0</td>\n",
+ " <td>16.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 18:34:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>400.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 19:00:00</th>\n",
+ " <td>108.0</td>\n",
+ " <td>179.0</td>\n",
+ " <td>88.0</td>\n",
+ " <td>110.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 19:31:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>11.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 20:00:00</th>\n",
+ " <td>116.0</td>\n",
+ " <td>183.0</td>\n",
+ " <td>91.0</td>\n",
+ " <td>114.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 21:00:00</th>\n",
+ " <td>117.0</td>\n",
+ " <td>189.0</td>\n",
+ " <td>98.0</td>\n",
+ " <td>121.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 21:12:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>3.396080</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 21:16:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>5.012718</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 22:00:00</th>\n",
+ " <td>124.0</td>\n",
+ " <td>180.0</td>\n",
+ " <td>88.0</td>\n",
+ " <td>110.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>200.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 22:10:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 22:25:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>500.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"30\" valign=\"top\">199999</th>\n",
+ " <th>2136-04-09 09:00:00</th>\n",
+ " <td>79.0</td>\n",
+ " <td>130.0</td>\n",
+ " <td>48.0</td>\n",
+ " <td>69.0</td>\n",
+ " <td>25.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>350.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 10:00:00</th>\n",
+ " <td>81.0</td>\n",
+ " <td>123.0</td>\n",
+ " <td>64.0</td>\n",
+ " <td>80.0</td>\n",
+ " <td>24.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 11:00:00</th>\n",
+ " <td>89.0</td>\n",
+ " <td>115.0</td>\n",
+ " <td>57.0</td>\n",
+ " <td>70.0</td>\n",
+ " <td>16.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 12:00:00</th>\n",
+ " <td>72.0</td>\n",
+ " <td>119.0</td>\n",
+ " <td>45.0</td>\n",
+ " <td>65.0</td>\n",
+ " <td>24.0</td>\n",
+ " <td>98.3</td>\n",
+ " <td>93.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 13:00:00</th>\n",
+ " <td>82.0</td>\n",
+ " <td>156.0</td>\n",
+ " <td>58.0</td>\n",
+ " <td>78.0</td>\n",
+ " <td>22.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 14:00:00</th>\n",
+ " <td>74.0</td>\n",
+ " <td>128.0</td>\n",
+ " <td>53.0</td>\n",
+ " <td>72.0</td>\n",
+ " <td>28.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>93.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 15:00:00</th>\n",
+ " <td>69.0</td>\n",
+ " <td>129.0</td>\n",
+ " <td>49.0</td>\n",
+ " <td>69.0</td>\n",
+ " <td>26.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>93.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 16:00:00</th>\n",
+ " <td>71.0</td>\n",
+ " <td>133.0</td>\n",
+ " <td>46.0</td>\n",
+ " <td>70.0</td>\n",
+ " <td>27.0</td>\n",
+ " <td>98.0</td>\n",
+ " <td>94.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>400.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 17:00:00</th>\n",
+ " <td>68.0</td>\n",
+ " <td>150.0</td>\n",
+ " <td>55.0</td>\n",
+ " <td>79.0</td>\n",
+ " <td>24.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 18:00:00</th>\n",
+ " <td>90.0</td>\n",
+ " <td>146.0</td>\n",
+ " <td>53.0</td>\n",
+ " <td>79.0</td>\n",
+ " <td>24.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>93.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 19:00:00</th>\n",
+ " <td>78.0</td>\n",
+ " <td>134.0</td>\n",
+ " <td>50.0</td>\n",
+ " <td>72.0</td>\n",
+ " <td>26.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>93.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 20:00:00</th>\n",
+ " <td>82.0</td>\n",
+ " <td>142.0</td>\n",
+ " <td>52.0</td>\n",
+ " <td>75.0</td>\n",
+ " <td>23.0</td>\n",
+ " <td>97.4</td>\n",
+ " <td>95.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>480.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 21:00:00</th>\n",
+ " <td>81.0</td>\n",
+ " <td>132.0</td>\n",
+ " <td>50.0</td>\n",
+ " <td>70.0</td>\n",
+ " <td>29.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>93.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 22:00:00</th>\n",
+ " <td>72.0</td>\n",
+ " <td>112.0</td>\n",
+ " <td>48.0</td>\n",
+ " <td>62.0</td>\n",
+ " <td>25.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 23:00:00</th>\n",
+ " <td>65.0</td>\n",
+ " <td>129.0</td>\n",
+ " <td>42.0</td>\n",
+ " <td>66.0</td>\n",
+ " <td>24.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 00:00:00</th>\n",
+ " <td>80.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>25.0</td>\n",
+ " <td>97.4</td>\n",
+ " <td>94.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 00:01:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>128.0</td>\n",
+ " <td>59.0</td>\n",
+ " <td>75.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 01:00:00</th>\n",
+ " <td>80.0</td>\n",
+ " <td>124.0</td>\n",
+ " <td>59.0</td>\n",
+ " <td>75.0</td>\n",
+ " <td>26.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 02:00:00</th>\n",
+ " <td>76.0</td>\n",
+ " <td>130.0</td>\n",
+ " <td>49.0</td>\n",
+ " <td>68.0</td>\n",
+ " <td>26.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>93.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>350.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 02:28:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>12.6</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 03:00:00</th>\n",
+ " <td>72.0</td>\n",
+ " <td>126.0</td>\n",
+ " <td>37.0</td>\n",
+ " <td>61.0</td>\n",
+ " <td>27.0</td>\n",
+ " <td>97.4</td>\n",
+ " <td>91.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 04:00:00</th>\n",
+ " <td>66.0</td>\n",
+ " <td>126.0</td>\n",
+ " <td>31.0</td>\n",
+ " <td>52.0</td>\n",
+ " <td>26.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 05:00:00</th>\n",
+ " <td>66.0</td>\n",
+ " <td>129.0</td>\n",
+ " <td>39.0</td>\n",
+ " <td>63.0</td>\n",
+ " <td>27.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>330.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 06:00:00</th>\n",
+ " <td>65.0</td>\n",
+ " <td>143.0</td>\n",
+ " <td>47.0</td>\n",
+ " <td>71.0</td>\n",
+ " <td>19.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>92.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 07:00:00</th>\n",
+ " <td>79.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>28.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>92.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 08:00:00</th>\n",
+ " <td>69.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>24.0</td>\n",
+ " <td>98.1</td>\n",
+ " <td>96.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>200.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 09:00:00</th>\n",
+ " <td>79.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>24.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>93.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 09:10:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>128.0</td>\n",
+ " <td>81.0</td>\n",
+ " <td>89.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 10:00:00</th>\n",
+ " <td>72.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>26.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>200.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 11:00:00</th>\n",
+ " <td>72.0</td>\n",
+ " <td>144.0</td>\n",
+ " <td>123.0</td>\n",
+ " <td>128.0</td>\n",
+ " <td>24.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>...</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>10071464 rows × 22 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label heart rate blood pressure systolic \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units beats/min mmHg \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 122.0 NaN \n",
+ " 2117-09-11 13:00:00 118.0 NaN \n",
+ " 2117-09-11 13:01:00 NaN 192.0 \n",
+ " 2117-09-11 13:48:00 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 118.0 NaN \n",
+ " 2117-09-11 14:00:00 118.0 165.0 \n",
+ " 2117-09-11 15:00:00 110.0 119.0 \n",
+ " 2117-09-11 15:48:00 NaN NaN \n",
+ " 2117-09-11 15:59:00 NaN NaN \n",
+ " 2117-09-11 16:00:00 104.0 169.0 \n",
+ " 2117-09-11 16:02:00 NaN NaN \n",
+ " 2117-09-11 16:11:00 NaN NaN \n",
+ " 2117-09-11 16:12:00 NaN NaN \n",
+ " 2117-09-11 17:00:00 101.0 110.0 \n",
+ " 2117-09-11 18:00:00 112.0 170.0 \n",
+ " 2117-09-11 18:34:00 NaN NaN \n",
+ " 2117-09-11 19:00:00 108.0 179.0 \n",
+ " 2117-09-11 19:31:00 NaN NaN \n",
+ " 2117-09-11 20:00:00 116.0 183.0 \n",
+ " 2117-09-11 21:00:00 117.0 189.0 \n",
+ " 2117-09-11 21:12:00 NaN NaN \n",
+ " 2117-09-11 21:16:00 NaN NaN \n",
+ " 2117-09-11 22:00:00 124.0 180.0 \n",
+ " 2117-09-11 22:10:00 NaN NaN \n",
+ " 2117-09-11 22:25:00 NaN NaN \n",
+ "... ... ... \n",
+ "199999 2136-04-09 09:00:00 79.0 130.0 \n",
+ " 2136-04-09 10:00:00 81.0 123.0 \n",
+ " 2136-04-09 11:00:00 89.0 115.0 \n",
+ " 2136-04-09 12:00:00 72.0 119.0 \n",
+ " 2136-04-09 13:00:00 82.0 156.0 \n",
+ " 2136-04-09 14:00:00 74.0 128.0 \n",
+ " 2136-04-09 15:00:00 69.0 129.0 \n",
+ " 2136-04-09 16:00:00 71.0 133.0 \n",
+ " 2136-04-09 17:00:00 68.0 150.0 \n",
+ " 2136-04-09 18:00:00 90.0 146.0 \n",
+ " 2136-04-09 19:00:00 78.0 134.0 \n",
+ " 2136-04-09 20:00:00 82.0 142.0 \n",
+ " 2136-04-09 21:00:00 81.0 132.0 \n",
+ " 2136-04-09 22:00:00 72.0 112.0 \n",
+ " 2136-04-09 23:00:00 65.0 129.0 \n",
+ " 2136-04-10 00:00:00 80.0 NaN \n",
+ " 2136-04-10 00:01:00 NaN 128.0 \n",
+ " 2136-04-10 01:00:00 80.0 124.0 \n",
+ " 2136-04-10 02:00:00 76.0 130.0 \n",
+ " 2136-04-10 02:28:00 NaN NaN \n",
+ " 2136-04-10 03:00:00 72.0 126.0 \n",
+ " 2136-04-10 04:00:00 66.0 126.0 \n",
+ " 2136-04-10 05:00:00 66.0 129.0 \n",
+ " 2136-04-10 06:00:00 65.0 143.0 \n",
+ " 2136-04-10 07:00:00 79.0 NaN \n",
+ " 2136-04-10 08:00:00 69.0 NaN \n",
+ " 2136-04-10 09:00:00 79.0 NaN \n",
+ " 2136-04-10 09:10:00 NaN 128.0 \n",
+ " 2136-04-10 10:00:00 72.0 NaN \n",
+ " 2136-04-10 11:00:00 72.0 144.0 \n",
+ "\n",
+ "label blood pressure diastolic blood pressure mean \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units mmHg mmHg \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN \n",
+ " 2117-09-11 13:01:00 100.0 122.0 \n",
+ " 2117-09-11 13:48:00 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN \n",
+ " 2117-09-11 14:00:00 85.0 103.0 \n",
+ " 2117-09-11 15:00:00 64.0 76.0 \n",
+ " 2117-09-11 15:48:00 NaN NaN \n",
+ " 2117-09-11 15:59:00 NaN NaN \n",
+ " 2117-09-11 16:00:00 84.0 105.0 \n",
+ " 2117-09-11 16:02:00 NaN NaN \n",
+ " 2117-09-11 16:11:00 NaN NaN \n",
+ " 2117-09-11 16:12:00 NaN NaN \n",
+ " 2117-09-11 17:00:00 62.0 75.0 \n",
+ " 2117-09-11 18:00:00 86.0 106.0 \n",
+ " 2117-09-11 18:34:00 NaN NaN \n",
+ " 2117-09-11 19:00:00 88.0 110.0 \n",
+ " 2117-09-11 19:31:00 NaN NaN \n",
+ " 2117-09-11 20:00:00 91.0 114.0 \n",
+ " 2117-09-11 21:00:00 98.0 121.0 \n",
+ " 2117-09-11 21:12:00 NaN NaN \n",
+ " 2117-09-11 21:16:00 NaN NaN \n",
+ " 2117-09-11 22:00:00 88.0 110.0 \n",
+ " 2117-09-11 22:10:00 NaN NaN \n",
+ " 2117-09-11 22:25:00 NaN NaN \n",
+ "... ... ... \n",
+ "199999 2136-04-09 09:00:00 48.0 69.0 \n",
+ " 2136-04-09 10:00:00 64.0 80.0 \n",
+ " 2136-04-09 11:00:00 57.0 70.0 \n",
+ " 2136-04-09 12:00:00 45.0 65.0 \n",
+ " 2136-04-09 13:00:00 58.0 78.0 \n",
+ " 2136-04-09 14:00:00 53.0 72.0 \n",
+ " 2136-04-09 15:00:00 49.0 69.0 \n",
+ " 2136-04-09 16:00:00 46.0 70.0 \n",
+ " 2136-04-09 17:00:00 55.0 79.0 \n",
+ " 2136-04-09 18:00:00 53.0 79.0 \n",
+ " 2136-04-09 19:00:00 50.0 72.0 \n",
+ " 2136-04-09 20:00:00 52.0 75.0 \n",
+ " 2136-04-09 21:00:00 50.0 70.0 \n",
+ " 2136-04-09 22:00:00 48.0 62.0 \n",
+ " 2136-04-09 23:00:00 42.0 66.0 \n",
+ " 2136-04-10 00:00:00 NaN NaN \n",
+ " 2136-04-10 00:01:00 59.0 75.0 \n",
+ " 2136-04-10 01:00:00 59.0 75.0 \n",
+ " 2136-04-10 02:00:00 49.0 68.0 \n",
+ " 2136-04-10 02:28:00 NaN NaN \n",
+ " 2136-04-10 03:00:00 37.0 61.0 \n",
+ " 2136-04-10 04:00:00 31.0 52.0 \n",
+ " 2136-04-10 05:00:00 39.0 63.0 \n",
+ " 2136-04-10 06:00:00 47.0 71.0 \n",
+ " 2136-04-10 07:00:00 NaN NaN \n",
+ " 2136-04-10 08:00:00 NaN NaN \n",
+ " 2136-04-10 09:00:00 NaN NaN \n",
+ " 2136-04-10 09:10:00 81.0 89.0 \n",
+ " 2136-04-10 10:00:00 NaN NaN \n",
+ " 2136-04-10 11:00:00 123.0 128.0 \n",
+ "\n",
+ "label respiratory rate temperature body \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units insp/min degF \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 14.0 NaN \n",
+ " 2117-09-11 13:00:00 22.0 NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN 98.0 \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 22.0 NaN \n",
+ " 2117-09-11 14:00:00 15.0 NaN \n",
+ " 2117-09-11 15:00:00 15.0 NaN \n",
+ " 2117-09-11 15:48:00 NaN NaN \n",
+ " 2117-09-11 15:59:00 NaN NaN \n",
+ " 2117-09-11 16:00:00 16.0 97.9 \n",
+ " 2117-09-11 16:02:00 NaN NaN \n",
+ " 2117-09-11 16:11:00 NaN NaN \n",
+ " 2117-09-11 16:12:00 NaN NaN \n",
+ " 2117-09-11 17:00:00 15.0 NaN \n",
+ " 2117-09-11 18:00:00 16.0 NaN \n",
+ " 2117-09-11 18:34:00 NaN NaN \n",
+ " 2117-09-11 19:00:00 NaN 99.5 \n",
+ " 2117-09-11 19:31:00 NaN NaN \n",
+ " 2117-09-11 20:00:00 NaN NaN \n",
+ " 2117-09-11 21:00:00 NaN NaN \n",
+ " 2117-09-11 21:12:00 NaN NaN \n",
+ " 2117-09-11 21:16:00 NaN NaN \n",
+ " 2117-09-11 22:00:00 NaN 100.0 \n",
+ " 2117-09-11 22:10:00 NaN NaN \n",
+ " 2117-09-11 22:25:00 NaN NaN \n",
+ "... ... ... \n",
+ "199999 2136-04-09 09:00:00 25.0 NaN \n",
+ " 2136-04-09 10:00:00 24.0 NaN \n",
+ " 2136-04-09 11:00:00 16.0 NaN \n",
+ " 2136-04-09 12:00:00 24.0 98.3 \n",
+ " 2136-04-09 13:00:00 22.0 NaN \n",
+ " 2136-04-09 14:00:00 28.0 NaN \n",
+ " 2136-04-09 15:00:00 26.0 NaN \n",
+ " 2136-04-09 16:00:00 27.0 98.0 \n",
+ " 2136-04-09 17:00:00 24.0 NaN \n",
+ " 2136-04-09 18:00:00 24.0 NaN \n",
+ " 2136-04-09 19:00:00 26.0 NaN \n",
+ " 2136-04-09 20:00:00 23.0 97.4 \n",
+ " 2136-04-09 21:00:00 29.0 NaN \n",
+ " 2136-04-09 22:00:00 25.0 NaN \n",
+ " 2136-04-09 23:00:00 24.0 NaN \n",
+ " 2136-04-10 00:00:00 25.0 97.4 \n",
+ " 2136-04-10 00:01:00 NaN NaN \n",
+ " 2136-04-10 01:00:00 26.0 NaN \n",
+ " 2136-04-10 02:00:00 26.0 NaN \n",
+ " 2136-04-10 02:28:00 NaN NaN \n",
+ " 2136-04-10 03:00:00 27.0 97.4 \n",
+ " 2136-04-10 04:00:00 26.0 NaN \n",
+ " 2136-04-10 05:00:00 27.0 NaN \n",
+ " 2136-04-10 06:00:00 19.0 NaN \n",
+ " 2136-04-10 07:00:00 28.0 NaN \n",
+ " 2136-04-10 08:00:00 24.0 98.1 \n",
+ " 2136-04-10 09:00:00 24.0 NaN \n",
+ " 2136-04-10 09:10:00 NaN NaN \n",
+ " 2136-04-10 10:00:00 26.0 NaN \n",
+ " 2136-04-10 11:00:00 24.0 NaN \n",
+ "\n",
+ "label oxygen saturation pulse oximetry weight body \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units percent kg \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN \n",
+ " 2117-09-11 14:00:00 NaN NaN \n",
+ " 2117-09-11 15:00:00 NaN NaN \n",
+ " 2117-09-11 15:48:00 NaN NaN \n",
+ " 2117-09-11 15:59:00 NaN NaN \n",
+ " 2117-09-11 16:00:00 NaN NaN \n",
+ " 2117-09-11 16:02:00 100.0 NaN \n",
+ " 2117-09-11 16:11:00 NaN NaN \n",
+ " 2117-09-11 16:12:00 NaN NaN \n",
+ " 2117-09-11 17:00:00 97.0 NaN \n",
+ " 2117-09-11 18:00:00 98.0 NaN \n",
+ " 2117-09-11 18:34:00 NaN NaN \n",
+ " 2117-09-11 19:00:00 NaN NaN \n",
+ " 2117-09-11 19:31:00 NaN NaN \n",
+ " 2117-09-11 20:00:00 97.0 NaN \n",
+ " 2117-09-11 21:00:00 NaN NaN \n",
+ " 2117-09-11 21:12:00 NaN NaN \n",
+ " 2117-09-11 21:16:00 NaN NaN \n",
+ " 2117-09-11 22:00:00 NaN NaN \n",
+ " 2117-09-11 22:10:00 97.0 NaN \n",
+ " 2117-09-11 22:25:00 NaN NaN \n",
+ "... ... ... \n",
+ "199999 2136-04-09 09:00:00 95.0 NaN \n",
+ " 2136-04-09 10:00:00 94.0 NaN \n",
+ " 2136-04-09 11:00:00 94.0 NaN \n",
+ " 2136-04-09 12:00:00 93.0 NaN \n",
+ " 2136-04-09 13:00:00 94.0 NaN \n",
+ " 2136-04-09 14:00:00 93.0 NaN \n",
+ " 2136-04-09 15:00:00 93.0 NaN \n",
+ " 2136-04-09 16:00:00 94.0 NaN \n",
+ " 2136-04-09 17:00:00 94.0 NaN \n",
+ " 2136-04-09 18:00:00 93.0 NaN \n",
+ " 2136-04-09 19:00:00 93.0 NaN \n",
+ " 2136-04-09 20:00:00 95.0 NaN \n",
+ " 2136-04-09 21:00:00 93.0 NaN \n",
+ " 2136-04-09 22:00:00 97.0 NaN \n",
+ " 2136-04-09 23:00:00 96.0 NaN \n",
+ " 2136-04-10 00:00:00 94.0 NaN \n",
+ " 2136-04-10 00:01:00 NaN NaN \n",
+ " 2136-04-10 01:00:00 95.0 NaN \n",
+ " 2136-04-10 02:00:00 93.0 NaN \n",
+ " 2136-04-10 02:28:00 NaN NaN \n",
+ " 2136-04-10 03:00:00 91.0 NaN \n",
+ " 2136-04-10 04:00:00 95.0 NaN \n",
+ " 2136-04-10 05:00:00 96.0 NaN \n",
+ " 2136-04-10 06:00:00 92.0 NaN \n",
+ " 2136-04-10 07:00:00 92.0 NaN \n",
+ " 2136-04-10 08:00:00 96.0 NaN \n",
+ " 2136-04-10 09:00:00 93.0 NaN \n",
+ " 2136-04-10 09:10:00 NaN NaN \n",
+ " 2136-04-10 10:00:00 97.0 NaN \n",
+ " 2136-04-10 11:00:00 96.0 NaN \n",
+ "\n",
+ "label output urine glasgow coma scale motor ... \\\n",
+ "status known known ... \n",
+ "variable_type qn ord ... \n",
+ "units mL no_units ... \n",
+ "id datetime ... \n",
+ "100001 2117-09-11 09:22:00 NaN NaN ... \n",
+ " 2117-09-11 09:32:00 NaN NaN ... \n",
+ " 2117-09-11 12:50:00 NaN NaN ... \n",
+ " 2117-09-11 12:55:00 NaN NaN ... \n",
+ " 2117-09-11 12:57:00 NaN NaN ... \n",
+ " 2117-09-11 13:00:00 NaN NaN ... \n",
+ " 2117-09-11 13:01:00 NaN NaN ... \n",
+ " 2117-09-11 13:48:00 NaN NaN ... \n",
+ " 2117-09-11 13:49:00 300.0 NaN ... \n",
+ " 2117-09-11 13:50:00 NaN NaN ... \n",
+ " 2117-09-11 14:00:00 NaN NaN ... \n",
+ " 2117-09-11 15:00:00 NaN NaN ... \n",
+ " 2117-09-11 15:48:00 NaN NaN ... \n",
+ " 2117-09-11 15:59:00 NaN NaN ... \n",
+ " 2117-09-11 16:00:00 NaN NaN ... \n",
+ " 2117-09-11 16:02:00 NaN NaN ... \n",
+ " 2117-09-11 16:11:00 NaN NaN ... \n",
+ " 2117-09-11 16:12:00 NaN NaN ... \n",
+ " 2117-09-11 17:00:00 NaN NaN ... \n",
+ " 2117-09-11 18:00:00 NaN NaN ... \n",
+ " 2117-09-11 18:34:00 400.0 NaN ... \n",
+ " 2117-09-11 19:00:00 NaN NaN ... \n",
+ " 2117-09-11 19:31:00 NaN NaN ... \n",
+ " 2117-09-11 20:00:00 NaN NaN ... \n",
+ " 2117-09-11 21:00:00 NaN NaN ... \n",
+ " 2117-09-11 21:12:00 NaN NaN ... \n",
+ " 2117-09-11 21:16:00 NaN NaN ... \n",
+ " 2117-09-11 22:00:00 200.0 NaN ... \n",
+ " 2117-09-11 22:10:00 NaN NaN ... \n",
+ " 2117-09-11 22:25:00 NaN NaN ... \n",
+ "... ... ... ... \n",
+ "199999 2136-04-09 09:00:00 350.0 NaN ... \n",
+ " 2136-04-09 10:00:00 NaN NaN ... \n",
+ " 2136-04-09 11:00:00 NaN NaN ... \n",
+ " 2136-04-09 12:00:00 NaN NaN ... \n",
+ " 2136-04-09 13:00:00 NaN NaN ... \n",
+ " 2136-04-09 14:00:00 NaN NaN ... \n",
+ " 2136-04-09 15:00:00 NaN NaN ... \n",
+ " 2136-04-09 16:00:00 400.0 NaN ... \n",
+ " 2136-04-09 17:00:00 NaN NaN ... \n",
+ " 2136-04-09 18:00:00 NaN NaN ... \n",
+ " 2136-04-09 19:00:00 NaN NaN ... \n",
+ " 2136-04-09 20:00:00 480.0 NaN ... \n",
+ " 2136-04-09 21:00:00 NaN NaN ... \n",
+ " 2136-04-09 22:00:00 NaN NaN ... \n",
+ " 2136-04-09 23:00:00 NaN NaN ... \n",
+ " 2136-04-10 00:00:00 NaN NaN ... \n",
+ " 2136-04-10 00:01:00 NaN NaN ... \n",
+ " 2136-04-10 01:00:00 NaN NaN ... \n",
+ " 2136-04-10 02:00:00 350.0 NaN ... \n",
+ " 2136-04-10 02:28:00 NaN NaN ... \n",
+ " 2136-04-10 03:00:00 NaN NaN ... \n",
+ " 2136-04-10 04:00:00 NaN NaN ... \n",
+ " 2136-04-10 05:00:00 330.0 NaN ... \n",
+ " 2136-04-10 06:00:00 NaN NaN ... \n",
+ " 2136-04-10 07:00:00 NaN NaN ... \n",
+ " 2136-04-10 08:00:00 200.0 NaN ... \n",
+ " 2136-04-10 09:00:00 NaN NaN ... \n",
+ " 2136-04-10 09:10:00 NaN NaN ... \n",
+ " 2136-04-10 10:00:00 200.0 NaN ... \n",
+ " 2136-04-10 11:00:00 NaN NaN ... \n",
+ "\n",
+ "label normal saline lactated ringers \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units mL mL/hr mL mL/hr \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN 5.000000 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN 6.996487 NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN 499.999980 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 14:00:00 NaN 8.990600 NaN NaN \n",
+ " 2117-09-11 15:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 15:48:00 NaN 999.999960 NaN NaN \n",
+ " 2117-09-11 15:59:00 NaN 199.999998 NaN NaN \n",
+ " 2117-09-11 16:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 16:02:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 16:11:00 NaN 40.000000 NaN NaN \n",
+ " 2117-09-11 16:12:00 NaN 4.992476 NaN NaN \n",
+ " 2117-09-11 17:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 18:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 18:34:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 19:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 19:31:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 20:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 21:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 21:12:00 NaN 3.396080 NaN NaN \n",
+ " 2117-09-11 21:16:00 NaN 5.012718 NaN NaN \n",
+ " 2117-09-11 22:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 22:10:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 22:25:00 500.0 NaN NaN NaN \n",
+ "... ... ... ... ... \n",
+ "199999 2136-04-09 09:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 10:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 11:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 12:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 13:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 14:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 15:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 16:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 17:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 18:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 19:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 20:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 21:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 22:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 23:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 00:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 00:01:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 01:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 02:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 02:28:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 03:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 04:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 05:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 06:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 07:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 08:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 09:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 09:10:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 10:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 11:00:00 NaN NaN NaN NaN \n",
+ "\n",
+ "label norepinephrine vasopressin \\\n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units mcg/kg/min mcg/min units units/min \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 09:32:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 12:50:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 14:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 15:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 15:48:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 15:59:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 16:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 16:02:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 16:11:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 16:12:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 17:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 18:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 18:34:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 19:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 19:31:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 20:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 21:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 21:12:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 21:16:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 22:00:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 22:10:00 NaN NaN NaN NaN \n",
+ " 2117-09-11 22:25:00 NaN NaN NaN NaN \n",
+ "... ... ... ... ... \n",
+ "199999 2136-04-09 09:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 10:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 11:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 12:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 13:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 14:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 15:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 16:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 17:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 18:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 19:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 20:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 21:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 22:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-09 23:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 00:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 00:01:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 01:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 02:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 02:28:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 03:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 04:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 05:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 06:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 07:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 08:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 09:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 09:10:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 10:00:00 NaN NaN NaN NaN \n",
+ " 2136-04-10 11:00:00 NaN NaN NaN NaN \n",
+ "\n",
+ "label hemoglobin lactate \n",
+ "status known known \n",
+ "variable_type qn qn \n",
+ "units g/dL mmol/L \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:22:00 13.0 NaN \n",
+ " 2117-09-11 09:32:00 NaN 1.9 \n",
+ " 2117-09-11 12:50:00 NaN NaN \n",
+ " 2117-09-11 12:55:00 NaN NaN \n",
+ " 2117-09-11 12:57:00 NaN NaN \n",
+ " 2117-09-11 13:00:00 NaN NaN \n",
+ " 2117-09-11 13:01:00 NaN NaN \n",
+ " 2117-09-11 13:48:00 NaN NaN \n",
+ " 2117-09-11 13:49:00 NaN NaN \n",
+ " 2117-09-11 13:50:00 NaN NaN \n",
+ " 2117-09-11 14:00:00 NaN NaN \n",
+ " 2117-09-11 15:00:00 NaN NaN \n",
+ " 2117-09-11 15:48:00 NaN NaN \n",
+ " 2117-09-11 15:59:00 NaN NaN \n",
+ " 2117-09-11 16:00:00 NaN NaN \n",
+ " 2117-09-11 16:02:00 NaN NaN \n",
+ " 2117-09-11 16:11:00 NaN NaN \n",
+ " 2117-09-11 16:12:00 NaN NaN \n",
+ " 2117-09-11 17:00:00 NaN NaN \n",
+ " 2117-09-11 18:00:00 NaN NaN \n",
+ " 2117-09-11 18:34:00 NaN NaN \n",
+ " 2117-09-11 19:00:00 NaN NaN \n",
+ " 2117-09-11 19:31:00 11.0 NaN \n",
+ " 2117-09-11 20:00:00 NaN NaN \n",
+ " 2117-09-11 21:00:00 NaN NaN \n",
+ " 2117-09-11 21:12:00 NaN NaN \n",
+ " 2117-09-11 21:16:00 NaN NaN \n",
+ " 2117-09-11 22:00:00 NaN NaN \n",
+ " 2117-09-11 22:10:00 NaN NaN \n",
+ " 2117-09-11 22:25:00 NaN NaN \n",
+ "... ... ... \n",
+ "199999 2136-04-09 09:00:00 NaN NaN \n",
+ " 2136-04-09 10:00:00 NaN NaN \n",
+ " 2136-04-09 11:00:00 NaN NaN \n",
+ " 2136-04-09 12:00:00 NaN NaN \n",
+ " 2136-04-09 13:00:00 NaN NaN \n",
+ " 2136-04-09 14:00:00 NaN NaN \n",
+ " 2136-04-09 15:00:00 NaN NaN \n",
+ " 2136-04-09 16:00:00 NaN NaN \n",
+ " 2136-04-09 17:00:00 NaN NaN \n",
+ " 2136-04-09 18:00:00 NaN NaN \n",
+ " 2136-04-09 19:00:00 NaN NaN \n",
+ " 2136-04-09 20:00:00 NaN NaN \n",
+ " 2136-04-09 21:00:00 NaN NaN \n",
+ " 2136-04-09 22:00:00 NaN NaN \n",
+ " 2136-04-09 23:00:00 NaN NaN \n",
+ " 2136-04-10 00:00:00 NaN NaN \n",
+ " 2136-04-10 00:01:00 NaN NaN \n",
+ " 2136-04-10 01:00:00 NaN NaN \n",
+ " 2136-04-10 02:00:00 NaN NaN \n",
+ " 2136-04-10 02:28:00 12.6 NaN \n",
+ " 2136-04-10 03:00:00 NaN NaN \n",
+ " 2136-04-10 04:00:00 NaN NaN \n",
+ " 2136-04-10 05:00:00 NaN NaN \n",
+ " 2136-04-10 06:00:00 NaN NaN \n",
+ " 2136-04-10 07:00:00 NaN NaN \n",
+ " 2136-04-10 08:00:00 NaN NaN \n",
+ " 2136-04-10 09:00:00 NaN NaN \n",
+ " 2136-04-10 09:10:00 NaN NaN \n",
+ " 2136-04-10 10:00:00 NaN NaN \n",
+ " 2136-04-10 11:00:00 NaN NaN \n",
+ "\n",
+ "[10071464 rows x 22 columns]"
+ ]
+ },
+ "execution_count": 15,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "utils.save_df(df_final,hdf5_fname,'cleaned/test1')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Prepare for ML\n",
+ "\n",
+ "\n",
+ "1. All categories to numeric representations\n",
+ "2. Segment, add to index\n",
+ "3. Transform into features (FeatureUnion)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 16,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "intro_pipeline = Pipeline([\n",
+ " ('transform',mimic_transform),\n",
+ " ('format',standard_pipeline),\n",
+ " ])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 17,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"8\" halign=\"left\">lactate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"4\" halign=\"left\">known</th>\n",
+ " <th colspan=\"4\" halign=\"left\">unknown</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"4\" halign=\"left\">qn</th>\n",
+ " <th>qn</th>\n",
+ " <th colspan=\"3\" halign=\"left\">nom</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"4\" halign=\"left\">mmol/L</th>\n",
+ " <th>no_units</th>\n",
+ " <th colspan=\"3\" halign=\"left\">no_units</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>50813</th>\n",
+ " <th>225668</th>\n",
+ " <th>818</th>\n",
+ " <th>1531</th>\n",
+ " <th>225668</th>\n",
+ " <th>50813(mmol/L)</th>\n",
+ " <th>818(mmol/L)</th>\n",
+ " <th>1531(mmol/L)</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>100001</th>\n",
+ " <th>2117-09-11 09:32:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100003</th>\n",
+ " <th>2150-04-17 19:12:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100006</th>\n",
+ " <th>2108-04-08 10:58:00</th>\n",
+ " <td>4.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100007</th>\n",
+ " <th>2145-03-31 00:44:00</th>\n",
+ " <td>3.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2145-04-02 14:10:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label lactate \\\n",
+ "status known unknown \n",
+ "variable_type qn qn nom \n",
+ "units mmol/L no_units no_units \n",
+ "description 50813 225668 818 1531 225668 50813(mmol/L) \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 1.9 NaN NaN NaN NaN NaN \n",
+ "100003 2150-04-17 19:12:00 1.1 1.1 NaN NaN NaN NaN \n",
+ "100006 2108-04-08 10:58:00 4.5 NaN 4.5 NaN NaN NaN \n",
+ "100007 2145-03-31 00:44:00 3.1 NaN NaN NaN NaN NaN \n",
+ " 2145-04-02 14:10:00 1.9 NaN NaN NaN NaN NaN \n",
+ "\n",
+ "label \n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 818(mmol/L) 1531(mmol/L) \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 NaN NaN \n",
+ "100003 2150-04-17 19:12:00 NaN NaN \n",
+ "100006 2108-04-08 10:58:00 NaN NaN \n",
+ "100007 2145-03-31 00:44:00 NaN NaN \n",
+ " 2145-04-02 14:10:00 NaN NaN "
+ ]
+ },
+ "execution_count": 17,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "label = 'lactate'\n",
+ "df_extract = utils.open_df(hdf5_fname,'extract/{}'.format(label))\n",
+ "df_cleaned = intro_pipeline.transform(df_extract)\n",
+ "df_cleaned.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 18,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"8\" halign=\"left\">lactate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"4\" halign=\"left\">known</th>\n",
+ " <th colspan=\"4\" halign=\"left\">unknown</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"4\" halign=\"left\">qn</th>\n",
+ " <th>qn</th>\n",
+ " <th colspan=\"3\" halign=\"left\">nom</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"4\" halign=\"left\">mmol/L</th>\n",
+ " <th>no_units</th>\n",
+ " <th colspan=\"3\" halign=\"left\">no_units</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>50813</th>\n",
+ " <th>225668</th>\n",
+ " <th>818</th>\n",
+ " <th>1531</th>\n",
+ " <th>225668</th>\n",
+ " <th>50813(mmol/L)</th>\n",
+ " <th>818(mmol/L)</th>\n",
+ " <th>1531(mmol/L)</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>176767.000000</td>\n",
+ " <td>69402.000000</td>\n",
+ " <td>72916.000000</td>\n",
+ " <td>63134.000000</td>\n",
+ " <td>14.000000</td>\n",
+ " <td>57</td>\n",
+ " <td>57</td>\n",
+ " <td>23</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>unique</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>34</td>\n",
+ " <td>14</td>\n",
+ " <td>8</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>top</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>ERROR</td>\n",
+ " <td>no data</td>\n",
+ " <td>no data</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>freq</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>18</td>\n",
+ " <td>37</td>\n",
+ " <td>9</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>2.635120</td>\n",
+ " <td>16.943607</td>\n",
+ " <td>2.849300</td>\n",
+ " <td>2.780338</td>\n",
+ " <td>52.835714</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>2.590268</td>\n",
+ " <td>3795.881233</td>\n",
+ " <td>3.152031</td>\n",
+ " <td>3.045527</td>\n",
+ " <td>82.567153</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.050000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>1.200000</td>\n",
+ " <td>1.200000</td>\n",
+ " <td>1.200000</td>\n",
+ " <td>1.200000</td>\n",
+ " <td>1.175000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>1.800000</td>\n",
+ " <td>1.800000</td>\n",
+ " <td>1.800000</td>\n",
+ " <td>1.800000</td>\n",
+ " <td>3.400000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>2.900000</td>\n",
+ " <td>2.900000</td>\n",
+ " <td>3.100000</td>\n",
+ " <td>3.000000</td>\n",
+ " <td>115.400000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>36.000000</td>\n",
+ " <td>999999.000000</td>\n",
+ " <td>153.000000</td>\n",
+ " <td>153.000000</td>\n",
+ " <td>203.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label lactate \\\n",
+ "status known \n",
+ "variable_type qn \n",
+ "units mmol/L \n",
+ "description 50813 225668 818 1531 \n",
+ "count 176767.000000 69402.000000 72916.000000 63134.000000 \n",
+ "unique NaN NaN NaN NaN \n",
+ "top NaN NaN NaN NaN \n",
+ "freq NaN NaN NaN NaN \n",
+ "mean 2.635120 16.943607 2.849300 2.780338 \n",
+ "std 2.590268 3795.881233 3.152031 3.045527 \n",
+ "min 0.000000 0.050000 0.000000 0.000000 \n",
+ "25% 1.200000 1.200000 1.200000 1.200000 \n",
+ "50% 1.800000 1.800000 1.800000 1.800000 \n",
+ "75% 2.900000 2.900000 3.100000 3.000000 \n",
+ "max 36.000000 999999.000000 153.000000 153.000000 \n",
+ "\n",
+ "label \n",
+ "status unknown \n",
+ "variable_type qn nom \n",
+ "units no_units no_units \n",
+ "description 225668 50813(mmol/L) 818(mmol/L) 1531(mmol/L) \n",
+ "count 14.000000 57 57 23 \n",
+ "unique NaN 34 14 8 \n",
+ "top NaN ERROR no data no data \n",
+ "freq NaN 18 37 9 \n",
+ "mean 52.835714 NaN NaN NaN \n",
+ "std 82.567153 NaN NaN NaN \n",
+ "min 0.000000 NaN NaN NaN \n",
+ "25% 1.175000 NaN NaN NaN \n",
+ "50% 3.400000 NaN NaN NaN \n",
+ "75% 115.400000 NaN NaN NaN \n",
+ "max 203.000000 NaN NaN NaN "
+ ]
+ },
+ "execution_count": 18,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_cleaned.describe(include='all')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"21\" halign=\"left\">lactate</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"4\" halign=\"left\">known</th>\n",
+ " <th colspan=\"17\" halign=\"left\">unknown</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"4\" halign=\"left\">qn</th>\n",
+ " <th>qn</th>\n",
+ " <th colspan=\"16\" halign=\"left\">nom</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"4\" halign=\"left\">mmol/L</th>\n",
+ " <th>no_units</th>\n",
+ " <th colspan=\"16\" halign=\"left\">no_units</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>50813</th>\n",
+ " <th>225668</th>\n",
+ " <th>818</th>\n",
+ " <th>1531</th>\n",
+ " <th>225668</th>\n",
+ " <th>50813(mmol/L)_.</th>\n",
+ " <th>50813(mmol/L)_5,0</th>\n",
+ " <th>50813(mmol/L)_>30</th>\n",
+ " <th>50813(mmol/L)_>30.0</th>\n",
+ " <th>50813(mmol/L)_CLOTTED</th>\n",
+ " <th>...</th>\n",
+ " <th>818(mmol/L)_VOIDED</th>\n",
+ " <th>818(mmol/L)_no data</th>\n",
+ " <th>1531(mmol/L)_.</th>\n",
+ " <th>1531(mmol/L)_5,0</th>\n",
+ " <th>1531(mmol/L)_>30</th>\n",
+ " <th>1531(mmol/L)_>30.0</th>\n",
+ " <th>1531(mmol/L)_CLOTTED</th>\n",
+ " <th>1531(mmol/L)_ERROR</th>\n",
+ " <th>1531(mmol/L)_VOIDED</th>\n",
+ " <th>1531(mmol/L)_no data</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>100001</th>\n",
+ " <th>2117-09-11 09:32:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100003</th>\n",
+ " <th>2150-04-17 19:12:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100006</th>\n",
+ " <th>2108-04-08 10:58:00</th>\n",
+ " <td>4.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100007</th>\n",
+ " <th>2145-03-31 00:44:00</th>\n",
+ " <td>3.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2145-04-02 14:10:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100009</th>\n",
+ " <th>2162-05-17 13:19:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2162-05-17 17:14:00</th>\n",
+ " <td>1.5</td>\n",
+ " <td>1.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"4\" valign=\"top\">100010</th>\n",
+ " <th>2109-12-10 10:25:00</th>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 12:11:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 13:05:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-10 13:58:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100011</th>\n",
+ " <th>2177-08-29 04:44:00</th>\n",
+ " <td>3.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-08-29 06:55:00</th>\n",
+ " <td>2.3</td>\n",
+ " <td>2.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">100012</th>\n",
+ " <th>2177-03-14 07:38:00</th>\n",
+ " <td>2.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-14 11:42:00</th>\n",
+ " <td>2.5</td>\n",
+ " <td>2.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 08:05:00</th>\n",
+ " <td>2.1</td>\n",
+ " <td>2.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 14:01:00</th>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-03-15 21:42:00</th>\n",
+ " <td>1.8</td>\n",
+ " <td>1.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100016</th>\n",
+ " <th>2188-05-24 12:00:00</th>\n",
+ " <td>2.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100017</th>\n",
+ " <th>2103-03-11 05:10:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">100018</th>\n",
+ " <th>2176-08-29 15:29:00</th>\n",
+ " <td>1.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 09:23:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 10:19:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 11:29:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2176-08-30 12:40:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100020</th>\n",
+ " <th>2142-11-30 21:54:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2142-12-03 00:17:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">100024</th>\n",
+ " <th>2170-09-19 10:25:00</th>\n",
+ " <td>1.4</td>\n",
+ " <td>1.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2170-09-19 16:33:00</th>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2170-09-20 02:04:00</th>\n",
+ " <td>3.2</td>\n",
+ " <td>3.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">199976</th>\n",
+ " <th>2182-02-14 11:15:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-16 03:57:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-19 03:59:00</th>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-20 03:31:00</th>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-21 04:55:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199979</th>\n",
+ " <th>2182-02-06 09:17:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2182-02-06 14:16:00</th>\n",
+ " <td>3.8</td>\n",
+ " <td>3.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">199981</th>\n",
+ " <th>2110-09-24 16:34:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2110-09-24 20:09:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2110-09-25 06:10:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>199987</th>\n",
+ " <th>2175-05-19 16:30:00</th>\n",
+ " <td>2.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"6\" valign=\"top\">199988</th>\n",
+ " <th>2169-01-24 12:48:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 01:35:00</th>\n",
+ " <td>1.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 11:18:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 16:43:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-07 22:35:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2169-02-10 05:33:00</th>\n",
+ " <td>1.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199993</th>\n",
+ " <th>2161-11-12 23:14:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2161-11-13 03:46:00</th>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"4\" valign=\"top\">199994</th>\n",
+ " <th>2188-07-07 21:23:00</th>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 03:09:00</th>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 04:13:00</th>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2188-07-08 06:20:00</th>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"5\" valign=\"top\">199998</th>\n",
+ " <th>2119-02-20 10:52:00</th>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>1.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 12:36:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 13:33:00</th>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 13:59:00</th>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>2.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 20:43:00</th>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>1.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">199999</th>\n",
+ " <th>2136-04-04 20:55:00</th>\n",
+ " <td>1.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-06 15:29:00</th>\n",
+ " <td>1.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>...</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>177450 rows × 29 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label lactate \\\n",
+ "status known unknown \n",
+ "variable_type qn qn nom \n",
+ "units mmol/L no_units no_units \n",
+ "description 50813 225668 818 1531 225668 50813(mmol/L)_. \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 1.9 NaN NaN NaN NaN 0 \n",
+ "100003 2150-04-17 19:12:00 1.1 1.1 NaN NaN NaN 0 \n",
+ "100006 2108-04-08 10:58:00 4.5 NaN 4.5 NaN NaN 0 \n",
+ "100007 2145-03-31 00:44:00 3.1 NaN NaN NaN NaN 0 \n",
+ " 2145-04-02 14:10:00 1.9 NaN NaN NaN NaN 0 \n",
+ "100009 2162-05-17 13:19:00 1.1 1.1 NaN NaN NaN 0 \n",
+ " 2162-05-17 17:14:00 1.5 1.5 NaN NaN NaN 0 \n",
+ "100010 2109-12-10 10:25:00 0.6 NaN NaN NaN NaN 0 \n",
+ " 2109-12-10 12:11:00 0.9 NaN NaN NaN NaN 0 \n",
+ " 2109-12-10 13:05:00 1.0 NaN NaN NaN NaN 0 \n",
+ " 2109-12-10 13:58:00 0.8 NaN NaN NaN NaN 0 \n",
+ "100011 2177-08-29 04:44:00 3.8 NaN NaN NaN NaN 0 \n",
+ " 2177-08-29 06:55:00 2.3 2.3 NaN NaN NaN 0 \n",
+ "100012 2177-03-14 07:38:00 2.3 NaN NaN NaN NaN 0 \n",
+ " 2177-03-14 11:42:00 2.5 2.5 NaN NaN NaN 0 \n",
+ " 2177-03-15 08:05:00 2.1 2.1 NaN NaN NaN 0 \n",
+ " 2177-03-15 14:01:00 2.6 2.6 NaN NaN NaN 0 \n",
+ " 2177-03-15 21:42:00 1.8 1.8 NaN NaN NaN 0 \n",
+ "100016 2188-05-24 12:00:00 2.0 NaN NaN NaN NaN 0 \n",
+ "100017 2103-03-11 05:10:00 1.1 NaN 1.1 NaN NaN 0 \n",
+ "100018 2176-08-29 15:29:00 1.3 NaN NaN NaN NaN 0 \n",
+ " 2176-08-30 09:23:00 0.9 0.9 NaN NaN NaN 0 \n",
+ " 2176-08-30 10:19:00 1.0 1.0 NaN NaN NaN 0 \n",
+ " 2176-08-30 11:29:00 0.9 0.9 NaN NaN NaN 0 \n",
+ " 2176-08-30 12:40:00 1.1 1.1 NaN NaN NaN 0 \n",
+ "100020 2142-11-30 21:54:00 1.1 NaN NaN NaN NaN 0 \n",
+ " 2142-12-03 00:17:00 1.0 NaN NaN NaN NaN 0 \n",
+ "100024 2170-09-19 10:25:00 1.4 1.4 NaN NaN NaN 0 \n",
+ " 2170-09-19 16:33:00 2.6 2.6 NaN NaN NaN 0 \n",
+ " 2170-09-20 02:04:00 3.2 3.2 NaN NaN NaN 0 \n",
+ "... ... ... ... ... ... ... \n",
+ "199976 2182-02-14 11:15:00 0.8 NaN 0.8 NaN NaN 0 \n",
+ " 2182-02-16 03:57:00 0.8 NaN 0.8 NaN NaN 0 \n",
+ " 2182-02-19 03:59:00 0.8 NaN 0.8 NaN NaN 0 \n",
+ " 2182-02-20 03:31:00 0.7 NaN 0.7 NaN NaN 0 \n",
+ " 2182-02-21 04:55:00 0.9 NaN 0.9 NaN NaN 0 \n",
+ "199979 2182-02-06 09:17:00 1.0 NaN NaN NaN NaN 0 \n",
+ " 2182-02-06 14:16:00 3.8 3.8 NaN NaN NaN 0 \n",
+ "199981 2110-09-24 16:34:00 1.1 NaN 1.1 1.1 NaN 0 \n",
+ " 2110-09-24 20:09:00 1.0 NaN 1.0 1.0 NaN 0 \n",
+ " 2110-09-25 06:10:00 1.0 NaN 1.0 1.0 NaN 0 \n",
+ "199987 2175-05-19 16:30:00 2.3 NaN NaN NaN NaN 0 \n",
+ "199988 2169-01-24 12:48:00 1.0 NaN NaN NaN NaN 0 \n",
+ " 2169-02-07 01:35:00 1.6 NaN 1.6 NaN NaN 0 \n",
+ " 2169-02-07 11:18:00 1.0 NaN 1.0 NaN NaN 0 \n",
+ " 2169-02-07 16:43:00 1.0 NaN 1.0 NaN NaN 0 \n",
+ " 2169-02-07 22:35:00 1.1 NaN 1.1 NaN NaN 0 \n",
+ " 2169-02-10 05:33:00 1.4 NaN NaN NaN NaN 0 \n",
+ "199993 2161-11-12 23:14:00 0.9 NaN 0.9 NaN NaN 0 \n",
+ " 2161-11-13 03:46:00 0.9 NaN 0.9 NaN NaN 0 \n",
+ "199994 2188-07-07 21:23:00 1.0 NaN 1.0 NaN NaN 0 \n",
+ " 2188-07-08 03:09:00 0.7 NaN 0.7 NaN NaN 0 \n",
+ " 2188-07-08 04:13:00 0.6 NaN 0.6 NaN NaN 0 \n",
+ " 2188-07-08 06:20:00 0.7 NaN 0.7 NaN NaN 0 \n",
+ "199998 2119-02-20 10:52:00 1.1 1.1 1.1 1.1 NaN 0 \n",
+ " 2119-02-20 12:36:00 1.9 1.9 1.9 1.9 NaN 0 \n",
+ " 2119-02-20 13:33:00 2.0 2.0 2.0 2.0 NaN 0 \n",
+ " 2119-02-20 13:59:00 2.6 2.6 2.6 2.6 NaN 0 \n",
+ " 2119-02-20 20:43:00 1.3 1.3 1.3 1.3 NaN 0 \n",
+ "199999 2136-04-04 20:55:00 1.9 NaN NaN NaN NaN 0 \n",
+ " 2136-04-06 15:29:00 1.8 NaN NaN NaN NaN 0 \n",
+ "\n",
+ "label \\\n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 50813(mmol/L)_5,0 50813(mmol/L)_>30 \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 0 0 \n",
+ "100003 2150-04-17 19:12:00 0 0 \n",
+ "100006 2108-04-08 10:58:00 0 0 \n",
+ "100007 2145-03-31 00:44:00 0 0 \n",
+ " 2145-04-02 14:10:00 0 0 \n",
+ "100009 2162-05-17 13:19:00 0 0 \n",
+ " 2162-05-17 17:14:00 0 0 \n",
+ "100010 2109-12-10 10:25:00 0 0 \n",
+ " 2109-12-10 12:11:00 0 0 \n",
+ " 2109-12-10 13:05:00 0 0 \n",
+ " 2109-12-10 13:58:00 0 0 \n",
+ "100011 2177-08-29 04:44:00 0 0 \n",
+ " 2177-08-29 06:55:00 0 0 \n",
+ "100012 2177-03-14 07:38:00 0 0 \n",
+ " 2177-03-14 11:42:00 0 0 \n",
+ " 2177-03-15 08:05:00 0 0 \n",
+ " 2177-03-15 14:01:00 0 0 \n",
+ " 2177-03-15 21:42:00 0 0 \n",
+ "100016 2188-05-24 12:00:00 0 0 \n",
+ "100017 2103-03-11 05:10:00 0 0 \n",
+ "100018 2176-08-29 15:29:00 0 0 \n",
+ " 2176-08-30 09:23:00 0 0 \n",
+ " 2176-08-30 10:19:00 0 0 \n",
+ " 2176-08-30 11:29:00 0 0 \n",
+ " 2176-08-30 12:40:00 0 0 \n",
+ "100020 2142-11-30 21:54:00 0 0 \n",
+ " 2142-12-03 00:17:00 0 0 \n",
+ "100024 2170-09-19 10:25:00 0 0 \n",
+ " 2170-09-19 16:33:00 0 0 \n",
+ " 2170-09-20 02:04:00 0 0 \n",
+ "... ... ... \n",
+ "199976 2182-02-14 11:15:00 0 0 \n",
+ " 2182-02-16 03:57:00 0 0 \n",
+ " 2182-02-19 03:59:00 0 0 \n",
+ " 2182-02-20 03:31:00 0 0 \n",
+ " 2182-02-21 04:55:00 0 0 \n",
+ "199979 2182-02-06 09:17:00 0 0 \n",
+ " 2182-02-06 14:16:00 0 0 \n",
+ "199981 2110-09-24 16:34:00 0 0 \n",
+ " 2110-09-24 20:09:00 0 0 \n",
+ " 2110-09-25 06:10:00 0 0 \n",
+ "199987 2175-05-19 16:30:00 0 0 \n",
+ "199988 2169-01-24 12:48:00 0 0 \n",
+ " 2169-02-07 01:35:00 0 0 \n",
+ " 2169-02-07 11:18:00 0 0 \n",
+ " 2169-02-07 16:43:00 0 0 \n",
+ " 2169-02-07 22:35:00 0 0 \n",
+ " 2169-02-10 05:33:00 0 0 \n",
+ "199993 2161-11-12 23:14:00 0 0 \n",
+ " 2161-11-13 03:46:00 0 0 \n",
+ "199994 2188-07-07 21:23:00 0 0 \n",
+ " 2188-07-08 03:09:00 0 0 \n",
+ " 2188-07-08 04:13:00 0 0 \n",
+ " 2188-07-08 06:20:00 0 0 \n",
+ "199998 2119-02-20 10:52:00 0 0 \n",
+ " 2119-02-20 12:36:00 0 0 \n",
+ " 2119-02-20 13:33:00 0 0 \n",
+ " 2119-02-20 13:59:00 0 0 \n",
+ " 2119-02-20 20:43:00 0 0 \n",
+ "199999 2136-04-04 20:55:00 0 0 \n",
+ " 2136-04-06 15:29:00 0 0 \n",
+ "\n",
+ "label \\\n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 50813(mmol/L)_>30.0 50813(mmol/L)_CLOTTED \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 0 0 \n",
+ "100003 2150-04-17 19:12:00 0 0 \n",
+ "100006 2108-04-08 10:58:00 0 0 \n",
+ "100007 2145-03-31 00:44:00 0 0 \n",
+ " 2145-04-02 14:10:00 0 0 \n",
+ "100009 2162-05-17 13:19:00 0 0 \n",
+ " 2162-05-17 17:14:00 0 0 \n",
+ "100010 2109-12-10 10:25:00 0 0 \n",
+ " 2109-12-10 12:11:00 0 0 \n",
+ " 2109-12-10 13:05:00 0 0 \n",
+ " 2109-12-10 13:58:00 0 0 \n",
+ "100011 2177-08-29 04:44:00 0 0 \n",
+ " 2177-08-29 06:55:00 0 0 \n",
+ "100012 2177-03-14 07:38:00 0 0 \n",
+ " 2177-03-14 11:42:00 0 0 \n",
+ " 2177-03-15 08:05:00 0 0 \n",
+ " 2177-03-15 14:01:00 0 0 \n",
+ " 2177-03-15 21:42:00 0 0 \n",
+ "100016 2188-05-24 12:00:00 0 0 \n",
+ "100017 2103-03-11 05:10:00 0 0 \n",
+ "100018 2176-08-29 15:29:00 0 0 \n",
+ " 2176-08-30 09:23:00 0 0 \n",
+ " 2176-08-30 10:19:00 0 0 \n",
+ " 2176-08-30 11:29:00 0 0 \n",
+ " 2176-08-30 12:40:00 0 0 \n",
+ "100020 2142-11-30 21:54:00 0 0 \n",
+ " 2142-12-03 00:17:00 0 0 \n",
+ "100024 2170-09-19 10:25:00 0 0 \n",
+ " 2170-09-19 16:33:00 0 0 \n",
+ " 2170-09-20 02:04:00 0 0 \n",
+ "... ... ... \n",
+ "199976 2182-02-14 11:15:00 0 0 \n",
+ " 2182-02-16 03:57:00 0 0 \n",
+ " 2182-02-19 03:59:00 0 0 \n",
+ " 2182-02-20 03:31:00 0 0 \n",
+ " 2182-02-21 04:55:00 0 0 \n",
+ "199979 2182-02-06 09:17:00 0 0 \n",
+ " 2182-02-06 14:16:00 0 0 \n",
+ "199981 2110-09-24 16:34:00 0 0 \n",
+ " 2110-09-24 20:09:00 0 0 \n",
+ " 2110-09-25 06:10:00 0 0 \n",
+ "199987 2175-05-19 16:30:00 0 0 \n",
+ "199988 2169-01-24 12:48:00 0 0 \n",
+ " 2169-02-07 01:35:00 0 0 \n",
+ " 2169-02-07 11:18:00 0 0 \n",
+ " 2169-02-07 16:43:00 0 0 \n",
+ " 2169-02-07 22:35:00 0 0 \n",
+ " 2169-02-10 05:33:00 0 0 \n",
+ "199993 2161-11-12 23:14:00 0 0 \n",
+ " 2161-11-13 03:46:00 0 0 \n",
+ "199994 2188-07-07 21:23:00 0 0 \n",
+ " 2188-07-08 03:09:00 0 0 \n",
+ " 2188-07-08 04:13:00 0 0 \n",
+ " 2188-07-08 06:20:00 0 0 \n",
+ "199998 2119-02-20 10:52:00 0 0 \n",
+ " 2119-02-20 12:36:00 0 0 \n",
+ " 2119-02-20 13:33:00 0 0 \n",
+ " 2119-02-20 13:59:00 0 0 \n",
+ " 2119-02-20 20:43:00 0 0 \n",
+ "199999 2136-04-04 20:55:00 0 0 \n",
+ " 2136-04-06 15:29:00 0 0 \n",
+ "\n",
+ "label ... \\\n",
+ "status ... \n",
+ "variable_type ... \n",
+ "units ... \n",
+ "description ... 818(mmol/L)_VOIDED \n",
+ "id datetime ... \n",
+ "100001 2117-09-11 09:32:00 ... 0 \n",
+ "100003 2150-04-17 19:12:00 ... 0 \n",
+ "100006 2108-04-08 10:58:00 ... 0 \n",
+ "100007 2145-03-31 00:44:00 ... 0 \n",
+ " 2145-04-02 14:10:00 ... 0 \n",
+ "100009 2162-05-17 13:19:00 ... 0 \n",
+ " 2162-05-17 17:14:00 ... 0 \n",
+ "100010 2109-12-10 10:25:00 ... 0 \n",
+ " 2109-12-10 12:11:00 ... 0 \n",
+ " 2109-12-10 13:05:00 ... 0 \n",
+ " 2109-12-10 13:58:00 ... 0 \n",
+ "100011 2177-08-29 04:44:00 ... 0 \n",
+ " 2177-08-29 06:55:00 ... 0 \n",
+ "100012 2177-03-14 07:38:00 ... 0 \n",
+ " 2177-03-14 11:42:00 ... 0 \n",
+ " 2177-03-15 08:05:00 ... 0 \n",
+ " 2177-03-15 14:01:00 ... 0 \n",
+ " 2177-03-15 21:42:00 ... 0 \n",
+ "100016 2188-05-24 12:00:00 ... 0 \n",
+ "100017 2103-03-11 05:10:00 ... 0 \n",
+ "100018 2176-08-29 15:29:00 ... 0 \n",
+ " 2176-08-30 09:23:00 ... 0 \n",
+ " 2176-08-30 10:19:00 ... 0 \n",
+ " 2176-08-30 11:29:00 ... 0 \n",
+ " 2176-08-30 12:40:00 ... 0 \n",
+ "100020 2142-11-30 21:54:00 ... 0 \n",
+ " 2142-12-03 00:17:00 ... 0 \n",
+ "100024 2170-09-19 10:25:00 ... 0 \n",
+ " 2170-09-19 16:33:00 ... 0 \n",
+ " 2170-09-20 02:04:00 ... 0 \n",
+ "... ... ... \n",
+ "199976 2182-02-14 11:15:00 ... 0 \n",
+ " 2182-02-16 03:57:00 ... 0 \n",
+ " 2182-02-19 03:59:00 ... 0 \n",
+ " 2182-02-20 03:31:00 ... 0 \n",
+ " 2182-02-21 04:55:00 ... 0 \n",
+ "199979 2182-02-06 09:17:00 ... 0 \n",
+ " 2182-02-06 14:16:00 ... 0 \n",
+ "199981 2110-09-24 16:34:00 ... 0 \n",
+ " 2110-09-24 20:09:00 ... 0 \n",
+ " 2110-09-25 06:10:00 ... 0 \n",
+ "199987 2175-05-19 16:30:00 ... 0 \n",
+ "199988 2169-01-24 12:48:00 ... 0 \n",
+ " 2169-02-07 01:35:00 ... 0 \n",
+ " 2169-02-07 11:18:00 ... 0 \n",
+ " 2169-02-07 16:43:00 ... 0 \n",
+ " 2169-02-07 22:35:00 ... 0 \n",
+ " 2169-02-10 05:33:00 ... 0 \n",
+ "199993 2161-11-12 23:14:00 ... 0 \n",
+ " 2161-11-13 03:46:00 ... 0 \n",
+ "199994 2188-07-07 21:23:00 ... 0 \n",
+ " 2188-07-08 03:09:00 ... 0 \n",
+ " 2188-07-08 04:13:00 ... 0 \n",
+ " 2188-07-08 06:20:00 ... 0 \n",
+ "199998 2119-02-20 10:52:00 ... 0 \n",
+ " 2119-02-20 12:36:00 ... 0 \n",
+ " 2119-02-20 13:33:00 ... 0 \n",
+ " 2119-02-20 13:59:00 ... 0 \n",
+ " 2119-02-20 20:43:00 ... 0 \n",
+ "199999 2136-04-04 20:55:00 ... 0 \n",
+ " 2136-04-06 15:29:00 ... 0 \n",
+ "\n",
+ "label \\\n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 818(mmol/L)_no data 1531(mmol/L)_. \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 0 0 \n",
+ "100003 2150-04-17 19:12:00 0 0 \n",
+ "100006 2108-04-08 10:58:00 0 0 \n",
+ "100007 2145-03-31 00:44:00 0 0 \n",
+ " 2145-04-02 14:10:00 0 0 \n",
+ "100009 2162-05-17 13:19:00 0 0 \n",
+ " 2162-05-17 17:14:00 0 0 \n",
+ "100010 2109-12-10 10:25:00 0 0 \n",
+ " 2109-12-10 12:11:00 0 0 \n",
+ " 2109-12-10 13:05:00 0 0 \n",
+ " 2109-12-10 13:58:00 0 0 \n",
+ "100011 2177-08-29 04:44:00 0 0 \n",
+ " 2177-08-29 06:55:00 0 0 \n",
+ "100012 2177-03-14 07:38:00 0 0 \n",
+ " 2177-03-14 11:42:00 0 0 \n",
+ " 2177-03-15 08:05:00 0 0 \n",
+ " 2177-03-15 14:01:00 0 0 \n",
+ " 2177-03-15 21:42:00 0 0 \n",
+ "100016 2188-05-24 12:00:00 0 0 \n",
+ "100017 2103-03-11 05:10:00 0 0 \n",
+ "100018 2176-08-29 15:29:00 0 0 \n",
+ " 2176-08-30 09:23:00 0 0 \n",
+ " 2176-08-30 10:19:00 0 0 \n",
+ " 2176-08-30 11:29:00 0 0 \n",
+ " 2176-08-30 12:40:00 0 0 \n",
+ "100020 2142-11-30 21:54:00 0 0 \n",
+ " 2142-12-03 00:17:00 0 0 \n",
+ "100024 2170-09-19 10:25:00 0 0 \n",
+ " 2170-09-19 16:33:00 0 0 \n",
+ " 2170-09-20 02:04:00 0 0 \n",
+ "... ... ... \n",
+ "199976 2182-02-14 11:15:00 0 0 \n",
+ " 2182-02-16 03:57:00 0 0 \n",
+ " 2182-02-19 03:59:00 0 0 \n",
+ " 2182-02-20 03:31:00 0 0 \n",
+ " 2182-02-21 04:55:00 0 0 \n",
+ "199979 2182-02-06 09:17:00 0 0 \n",
+ " 2182-02-06 14:16:00 0 0 \n",
+ "199981 2110-09-24 16:34:00 0 0 \n",
+ " 2110-09-24 20:09:00 0 0 \n",
+ " 2110-09-25 06:10:00 0 0 \n",
+ "199987 2175-05-19 16:30:00 0 0 \n",
+ "199988 2169-01-24 12:48:00 0 0 \n",
+ " 2169-02-07 01:35:00 0 0 \n",
+ " 2169-02-07 11:18:00 0 0 \n",
+ " 2169-02-07 16:43:00 0 0 \n",
+ " 2169-02-07 22:35:00 0 0 \n",
+ " 2169-02-10 05:33:00 0 0 \n",
+ "199993 2161-11-12 23:14:00 0 0 \n",
+ " 2161-11-13 03:46:00 0 0 \n",
+ "199994 2188-07-07 21:23:00 0 0 \n",
+ " 2188-07-08 03:09:00 0 0 \n",
+ " 2188-07-08 04:13:00 0 0 \n",
+ " 2188-07-08 06:20:00 0 0 \n",
+ "199998 2119-02-20 10:52:00 0 0 \n",
+ " 2119-02-20 12:36:00 0 0 \n",
+ " 2119-02-20 13:33:00 0 0 \n",
+ " 2119-02-20 13:59:00 0 0 \n",
+ " 2119-02-20 20:43:00 0 0 \n",
+ "199999 2136-04-04 20:55:00 0 0 \n",
+ " 2136-04-06 15:29:00 0 0 \n",
+ "\n",
+ "label \\\n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 1531(mmol/L)_5,0 1531(mmol/L)_>30 \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 0 0 \n",
+ "100003 2150-04-17 19:12:00 0 0 \n",
+ "100006 2108-04-08 10:58:00 0 0 \n",
+ "100007 2145-03-31 00:44:00 0 0 \n",
+ " 2145-04-02 14:10:00 0 0 \n",
+ "100009 2162-05-17 13:19:00 0 0 \n",
+ " 2162-05-17 17:14:00 0 0 \n",
+ "100010 2109-12-10 10:25:00 0 0 \n",
+ " 2109-12-10 12:11:00 0 0 \n",
+ " 2109-12-10 13:05:00 0 0 \n",
+ " 2109-12-10 13:58:00 0 0 \n",
+ "100011 2177-08-29 04:44:00 0 0 \n",
+ " 2177-08-29 06:55:00 0 0 \n",
+ "100012 2177-03-14 07:38:00 0 0 \n",
+ " 2177-03-14 11:42:00 0 0 \n",
+ " 2177-03-15 08:05:00 0 0 \n",
+ " 2177-03-15 14:01:00 0 0 \n",
+ " 2177-03-15 21:42:00 0 0 \n",
+ "100016 2188-05-24 12:00:00 0 0 \n",
+ "100017 2103-03-11 05:10:00 0 0 \n",
+ "100018 2176-08-29 15:29:00 0 0 \n",
+ " 2176-08-30 09:23:00 0 0 \n",
+ " 2176-08-30 10:19:00 0 0 \n",
+ " 2176-08-30 11:29:00 0 0 \n",
+ " 2176-08-30 12:40:00 0 0 \n",
+ "100020 2142-11-30 21:54:00 0 0 \n",
+ " 2142-12-03 00:17:00 0 0 \n",
+ "100024 2170-09-19 10:25:00 0 0 \n",
+ " 2170-09-19 16:33:00 0 0 \n",
+ " 2170-09-20 02:04:00 0 0 \n",
+ "... ... ... \n",
+ "199976 2182-02-14 11:15:00 0 0 \n",
+ " 2182-02-16 03:57:00 0 0 \n",
+ " 2182-02-19 03:59:00 0 0 \n",
+ " 2182-02-20 03:31:00 0 0 \n",
+ " 2182-02-21 04:55:00 0 0 \n",
+ "199979 2182-02-06 09:17:00 0 0 \n",
+ " 2182-02-06 14:16:00 0 0 \n",
+ "199981 2110-09-24 16:34:00 0 0 \n",
+ " 2110-09-24 20:09:00 0 0 \n",
+ " 2110-09-25 06:10:00 0 0 \n",
+ "199987 2175-05-19 16:30:00 0 0 \n",
+ "199988 2169-01-24 12:48:00 0 0 \n",
+ " 2169-02-07 01:35:00 0 0 \n",
+ " 2169-02-07 11:18:00 0 0 \n",
+ " 2169-02-07 16:43:00 0 0 \n",
+ " 2169-02-07 22:35:00 0 0 \n",
+ " 2169-02-10 05:33:00 0 0 \n",
+ "199993 2161-11-12 23:14:00 0 0 \n",
+ " 2161-11-13 03:46:00 0 0 \n",
+ "199994 2188-07-07 21:23:00 0 0 \n",
+ " 2188-07-08 03:09:00 0 0 \n",
+ " 2188-07-08 04:13:00 0 0 \n",
+ " 2188-07-08 06:20:00 0 0 \n",
+ "199998 2119-02-20 10:52:00 0 0 \n",
+ " 2119-02-20 12:36:00 0 0 \n",
+ " 2119-02-20 13:33:00 0 0 \n",
+ " 2119-02-20 13:59:00 0 0 \n",
+ " 2119-02-20 20:43:00 0 0 \n",
+ "199999 2136-04-04 20:55:00 0 0 \n",
+ " 2136-04-06 15:29:00 0 0 \n",
+ "\n",
+ "label \\\n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 1531(mmol/L)_>30.0 1531(mmol/L)_CLOTTED \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 0 0 \n",
+ "100003 2150-04-17 19:12:00 0 0 \n",
+ "100006 2108-04-08 10:58:00 0 0 \n",
+ "100007 2145-03-31 00:44:00 0 0 \n",
+ " 2145-04-02 14:10:00 0 0 \n",
+ "100009 2162-05-17 13:19:00 0 0 \n",
+ " 2162-05-17 17:14:00 0 0 \n",
+ "100010 2109-12-10 10:25:00 0 0 \n",
+ " 2109-12-10 12:11:00 0 0 \n",
+ " 2109-12-10 13:05:00 0 0 \n",
+ " 2109-12-10 13:58:00 0 0 \n",
+ "100011 2177-08-29 04:44:00 0 0 \n",
+ " 2177-08-29 06:55:00 0 0 \n",
+ "100012 2177-03-14 07:38:00 0 0 \n",
+ " 2177-03-14 11:42:00 0 0 \n",
+ " 2177-03-15 08:05:00 0 0 \n",
+ " 2177-03-15 14:01:00 0 0 \n",
+ " 2177-03-15 21:42:00 0 0 \n",
+ "100016 2188-05-24 12:00:00 0 0 \n",
+ "100017 2103-03-11 05:10:00 0 0 \n",
+ "100018 2176-08-29 15:29:00 0 0 \n",
+ " 2176-08-30 09:23:00 0 0 \n",
+ " 2176-08-30 10:19:00 0 0 \n",
+ " 2176-08-30 11:29:00 0 0 \n",
+ " 2176-08-30 12:40:00 0 0 \n",
+ "100020 2142-11-30 21:54:00 0 0 \n",
+ " 2142-12-03 00:17:00 0 0 \n",
+ "100024 2170-09-19 10:25:00 0 0 \n",
+ " 2170-09-19 16:33:00 0 0 \n",
+ " 2170-09-20 02:04:00 0 0 \n",
+ "... ... ... \n",
+ "199976 2182-02-14 11:15:00 0 0 \n",
+ " 2182-02-16 03:57:00 0 0 \n",
+ " 2182-02-19 03:59:00 0 0 \n",
+ " 2182-02-20 03:31:00 0 0 \n",
+ " 2182-02-21 04:55:00 0 0 \n",
+ "199979 2182-02-06 09:17:00 0 0 \n",
+ " 2182-02-06 14:16:00 0 0 \n",
+ "199981 2110-09-24 16:34:00 0 0 \n",
+ " 2110-09-24 20:09:00 0 0 \n",
+ " 2110-09-25 06:10:00 0 0 \n",
+ "199987 2175-05-19 16:30:00 0 0 \n",
+ "199988 2169-01-24 12:48:00 0 0 \n",
+ " 2169-02-07 01:35:00 0 0 \n",
+ " 2169-02-07 11:18:00 0 0 \n",
+ " 2169-02-07 16:43:00 0 0 \n",
+ " 2169-02-07 22:35:00 0 0 \n",
+ " 2169-02-10 05:33:00 0 0 \n",
+ "199993 2161-11-12 23:14:00 0 0 \n",
+ " 2161-11-13 03:46:00 0 0 \n",
+ "199994 2188-07-07 21:23:00 0 0 \n",
+ " 2188-07-08 03:09:00 0 0 \n",
+ " 2188-07-08 04:13:00 0 0 \n",
+ " 2188-07-08 06:20:00 0 0 \n",
+ "199998 2119-02-20 10:52:00 0 0 \n",
+ " 2119-02-20 12:36:00 0 0 \n",
+ " 2119-02-20 13:33:00 0 0 \n",
+ " 2119-02-20 13:59:00 0 0 \n",
+ " 2119-02-20 20:43:00 0 0 \n",
+ "199999 2136-04-04 20:55:00 0 0 \n",
+ " 2136-04-06 15:29:00 0 0 \n",
+ "\n",
+ "label \\\n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 1531(mmol/L)_ERROR 1531(mmol/L)_VOIDED \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 0 0 \n",
+ "100003 2150-04-17 19:12:00 0 0 \n",
+ "100006 2108-04-08 10:58:00 0 0 \n",
+ "100007 2145-03-31 00:44:00 0 0 \n",
+ " 2145-04-02 14:10:00 0 0 \n",
+ "100009 2162-05-17 13:19:00 0 0 \n",
+ " 2162-05-17 17:14:00 0 0 \n",
+ "100010 2109-12-10 10:25:00 0 0 \n",
+ " 2109-12-10 12:11:00 0 0 \n",
+ " 2109-12-10 13:05:00 0 0 \n",
+ " 2109-12-10 13:58:00 0 0 \n",
+ "100011 2177-08-29 04:44:00 0 0 \n",
+ " 2177-08-29 06:55:00 0 0 \n",
+ "100012 2177-03-14 07:38:00 0 0 \n",
+ " 2177-03-14 11:42:00 0 0 \n",
+ " 2177-03-15 08:05:00 0 0 \n",
+ " 2177-03-15 14:01:00 0 0 \n",
+ " 2177-03-15 21:42:00 0 0 \n",
+ "100016 2188-05-24 12:00:00 0 0 \n",
+ "100017 2103-03-11 05:10:00 0 0 \n",
+ "100018 2176-08-29 15:29:00 0 0 \n",
+ " 2176-08-30 09:23:00 0 0 \n",
+ " 2176-08-30 10:19:00 0 0 \n",
+ " 2176-08-30 11:29:00 0 0 \n",
+ " 2176-08-30 12:40:00 0 0 \n",
+ "100020 2142-11-30 21:54:00 0 0 \n",
+ " 2142-12-03 00:17:00 0 0 \n",
+ "100024 2170-09-19 10:25:00 0 0 \n",
+ " 2170-09-19 16:33:00 0 0 \n",
+ " 2170-09-20 02:04:00 0 0 \n",
+ "... ... ... \n",
+ "199976 2182-02-14 11:15:00 0 0 \n",
+ " 2182-02-16 03:57:00 0 0 \n",
+ " 2182-02-19 03:59:00 0 0 \n",
+ " 2182-02-20 03:31:00 0 0 \n",
+ " 2182-02-21 04:55:00 0 0 \n",
+ "199979 2182-02-06 09:17:00 0 0 \n",
+ " 2182-02-06 14:16:00 0 0 \n",
+ "199981 2110-09-24 16:34:00 0 0 \n",
+ " 2110-09-24 20:09:00 0 0 \n",
+ " 2110-09-25 06:10:00 0 0 \n",
+ "199987 2175-05-19 16:30:00 0 0 \n",
+ "199988 2169-01-24 12:48:00 0 0 \n",
+ " 2169-02-07 01:35:00 0 0 \n",
+ " 2169-02-07 11:18:00 0 0 \n",
+ " 2169-02-07 16:43:00 0 0 \n",
+ " 2169-02-07 22:35:00 0 0 \n",
+ " 2169-02-10 05:33:00 0 0 \n",
+ "199993 2161-11-12 23:14:00 0 0 \n",
+ " 2161-11-13 03:46:00 0 0 \n",
+ "199994 2188-07-07 21:23:00 0 0 \n",
+ " 2188-07-08 03:09:00 0 0 \n",
+ " 2188-07-08 04:13:00 0 0 \n",
+ " 2188-07-08 06:20:00 0 0 \n",
+ "199998 2119-02-20 10:52:00 0 0 \n",
+ " 2119-02-20 12:36:00 0 0 \n",
+ " 2119-02-20 13:33:00 0 0 \n",
+ " 2119-02-20 13:59:00 0 0 \n",
+ " 2119-02-20 20:43:00 0 0 \n",
+ "199999 2136-04-04 20:55:00 0 0 \n",
+ " 2136-04-06 15:29:00 0 0 \n",
+ "\n",
+ "label \n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 1531(mmol/L)_no data \n",
+ "id datetime \n",
+ "100001 2117-09-11 09:32:00 0 \n",
+ "100003 2150-04-17 19:12:00 0 \n",
+ "100006 2108-04-08 10:58:00 0 \n",
+ "100007 2145-03-31 00:44:00 0 \n",
+ " 2145-04-02 14:10:00 0 \n",
+ "100009 2162-05-17 13:19:00 0 \n",
+ " 2162-05-17 17:14:00 0 \n",
+ "100010 2109-12-10 10:25:00 0 \n",
+ " 2109-12-10 12:11:00 0 \n",
+ " 2109-12-10 13:05:00 0 \n",
+ " 2109-12-10 13:58:00 0 \n",
+ "100011 2177-08-29 04:44:00 0 \n",
+ " 2177-08-29 06:55:00 0 \n",
+ "100012 2177-03-14 07:38:00 0 \n",
+ " 2177-03-14 11:42:00 0 \n",
+ " 2177-03-15 08:05:00 0 \n",
+ " 2177-03-15 14:01:00 0 \n",
+ " 2177-03-15 21:42:00 0 \n",
+ "100016 2188-05-24 12:00:00 0 \n",
+ "100017 2103-03-11 05:10:00 0 \n",
+ "100018 2176-08-29 15:29:00 0 \n",
+ " 2176-08-30 09:23:00 0 \n",
+ " 2176-08-30 10:19:00 0 \n",
+ " 2176-08-30 11:29:00 0 \n",
+ " 2176-08-30 12:40:00 0 \n",
+ "100020 2142-11-30 21:54:00 0 \n",
+ " 2142-12-03 00:17:00 0 \n",
+ "100024 2170-09-19 10:25:00 0 \n",
+ " 2170-09-19 16:33:00 0 \n",
+ " 2170-09-20 02:04:00 0 \n",
+ "... ... \n",
+ "199976 2182-02-14 11:15:00 0 \n",
+ " 2182-02-16 03:57:00 0 \n",
+ " 2182-02-19 03:59:00 0 \n",
+ " 2182-02-20 03:31:00 0 \n",
+ " 2182-02-21 04:55:00 0 \n",
+ "199979 2182-02-06 09:17:00 0 \n",
+ " 2182-02-06 14:16:00 0 \n",
+ "199981 2110-09-24 16:34:00 0 \n",
+ " 2110-09-24 20:09:00 0 \n",
+ " 2110-09-25 06:10:00 0 \n",
+ "199987 2175-05-19 16:30:00 0 \n",
+ "199988 2169-01-24 12:48:00 0 \n",
+ " 2169-02-07 01:35:00 0 \n",
+ " 2169-02-07 11:18:00 0 \n",
+ " 2169-02-07 16:43:00 0 \n",
+ " 2169-02-07 22:35:00 0 \n",
+ " 2169-02-10 05:33:00 0 \n",
+ "199993 2161-11-12 23:14:00 0 \n",
+ " 2161-11-13 03:46:00 0 \n",
+ "199994 2188-07-07 21:23:00 0 \n",
+ " 2188-07-08 03:09:00 0 \n",
+ " 2188-07-08 04:13:00 0 \n",
+ " 2188-07-08 06:20:00 0 \n",
+ "199998 2119-02-20 10:52:00 0 \n",
+ " 2119-02-20 12:36:00 0 \n",
+ " 2119-02-20 13:33:00 0 \n",
+ " 2119-02-20 13:59:00 0 \n",
+ " 2119-02-20 20:43:00 0 \n",
+ "199999 2136-04-04 20:55:00 0 \n",
+ " 2136-04-06 15:29:00 0 \n",
+ "\n",
+ "[177450 rows x 29 columns]"
+ ]
+ },
+ "execution_count": 28,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "nominal_cols = df_cleaned.columns.get_level_values('variable_type') == variable_type.NOMINAL\n",
+ "\n",
+ "for col_name in df_cleaned.loc[:,nominal_cols]:\n",
+ " column = df_cleaned[col_nam]\n",
+ " df_dummies = pd.get_dummies(column)\n",
+ " dummy_col_names = [col_name[:-1] + ('{}_{}'.format(col_name[-1],text),) for text in df_dummies.columns]\n",
+ " df_dummies.columns = pd.MultiIndex.from_tuples(dummy_col_names,names=df_cleaned.columns.names)\n",
+ " \n",
+ " df_cleaned.drop(col_name,axis=1,inplace=True)\n",
+ " df_cleaned = df_cleaned.join(df_dummies,how='outer')\n",
+ "\n",
+ "df_cleaned"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Possible additional cleaning:\n",
+ "\n",
+ "1. Infer UOM \n",
+ "2. Remove extreme values [DONE]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "import utils\n",
+ "import mimic\n",
+ "import transformers\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "import icu_data_defs\n",
+ "import units"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "df_temp = utils.open_df('data/mimic_data','extract/temperature body')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload(mimic)\n",
+ "pipeline = mimic.transform_pipeline('temperature body')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-25 00:00:00</td>\n",
+ " <td>98.400001525878906</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>188670.0</td>\n",
+ " <td>2183-08-23 20:00:00</td>\n",
+ " <td>99.300003051757812</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-12 08:00:00</td>\n",
+ " <td>98.699996948242188</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-13 17:00:00</td>\n",
+ " <td>99.900001525878906</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>166707.0</td>\n",
+ " <td>2122-02-11 20:00:00</td>\n",
+ " <td>37.900001525878906</td>\n",
+ " <td>degC</td>\n",
+ " <td>676</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>166707.0</td>\n",
+ " <td>2122-02-13 00:00:00</td>\n",
+ " <td>97.800003051757812</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-11 21:00:00</td>\n",
+ " <td>99.099998474121094</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-24 04:00:00</td>\n",
+ " <td>98.900001525878906</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>176176.0</td>\n",
+ " <td>2116-12-24 16:00:00</td>\n",
+ " <td>99.099998474121094</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-13 03:00:00</td>\n",
+ " <td>99.199996948242188</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-30 18:00:00</td>\n",
+ " <td>98.800003051757812</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>181750.0</td>\n",
+ " <td>2192-11-24 08:00:00</td>\n",
+ " <td>98.5</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>12</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-14 12:00:00</td>\n",
+ " <td>100.40000152587891</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-14 13:00:00</td>\n",
+ " <td>100.69999694824219</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>14</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-15 22:00:00</td>\n",
+ " <td>99.800003051757812</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>15</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-16 21:00:00</td>\n",
+ " <td>100.59999847412109</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>16</th>\n",
+ " <td>185910.0</td>\n",
+ " <td>2166-08-23 08:00:00</td>\n",
+ " <td>98</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>17</th>\n",
+ " <td>190797.0</td>\n",
+ " <td>2191-01-10 08:00:00</td>\n",
+ " <td>97.900001525878906</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18</th>\n",
+ " <td>157907.0</td>\n",
+ " <td>2129-06-10 23:00:00</td>\n",
+ " <td>100.09999847412109</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>19</th>\n",
+ " <td>157907.0</td>\n",
+ " <td>2129-06-11 04:30:00</td>\n",
+ " <td>98.800003051757812</td>\n",
+ " <td>degF</td>\n",
+ " <td>678</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 185910.0 2166-08-25 00:00:00 98.400001525878906 degF 678\n",
+ "1 188670.0 2183-08-23 20:00:00 99.300003051757812 degF 678\n",
+ "2 185910.0 2166-08-12 08:00:00 98.699996948242188 degF 678\n",
+ "3 185910.0 2166-08-13 17:00:00 99.900001525878906 degF 678\n",
+ "4 166707.0 2122-02-11 20:00:00 37.900001525878906 degC 676\n",
+ "5 166707.0 2122-02-13 00:00:00 97.800003051757812 degF 678\n",
+ "6 185910.0 2166-08-11 21:00:00 99.099998474121094 degF 678\n",
+ "7 185910.0 2166-08-24 04:00:00 98.900001525878906 degF 678\n",
+ "8 176176.0 2116-12-24 16:00:00 99.099998474121094 degF 678\n",
+ "9 185910.0 2166-08-13 03:00:00 99.199996948242188 degF 678\n",
+ "10 185910.0 2166-08-30 18:00:00 98.800003051757812 degF 678\n",
+ "11 181750.0 2192-11-24 08:00:00 98.5 degF 678\n",
+ "12 185910.0 2166-08-14 12:00:00 100.40000152587891 degF 678\n",
+ "13 185910.0 2166-08-14 13:00:00 100.69999694824219 degF 678\n",
+ "14 185910.0 2166-08-15 22:00:00 99.800003051757812 degF 678\n",
+ "15 185910.0 2166-08-16 21:00:00 100.59999847412109 degF 678\n",
+ "16 185910.0 2166-08-23 08:00:00 98 degF 678\n",
+ "17 190797.0 2191-01-10 08:00:00 97.900001525878906 degF 678\n",
+ "18 157907.0 2129-06-10 23:00:00 100.09999847412109 degF 678\n",
+ "19 157907.0 2129-06-11 04:30:00 98.800003051757812 degF 678"
+ ]
+ },
+ "execution_count": 5,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_temp.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "df_temp_tr = pipeline.transform(df_temp)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"4\" halign=\"left\">temperature body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">degF</th>\n",
+ " <th colspan=\"2\" halign=\"left\">degC</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>223761</th>\n",
+ " <th>678</th>\n",
+ " <th>223762</th>\n",
+ " <th>676</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"20\" valign=\"top\">100001</th>\n",
+ " <th>2117-09-11 13:48:00</th>\n",
+ " <td>98</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 16:00:00</th>\n",
+ " <td>97.9</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 19:00:00</th>\n",
+ " <td>99.5</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 22:00:00</th>\n",
+ " <td>100</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 01:00:00</th>\n",
+ " <td>99.9</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 04:00:00</th>\n",
+ " <td>97.7</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 08:00:00</th>\n",
+ " <td>97.8</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 12:00:00</th>\n",
+ " <td>97.5</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 19:00:00</th>\n",
+ " <td>99.8</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 00:00:00</th>\n",
+ " <td>99.7</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 04:00:00</th>\n",
+ " <td>99.3</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 08:00:00</th>\n",
+ " <td>99.4</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 12:00:00</th>\n",
+ " <td>98.8</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 16:00:00</th>\n",
+ " <td>99.3</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 22:00:00</th>\n",
+ " <td>99.9</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 00:00:00</th>\n",
+ " <td>99.4</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 04:00:00</th>\n",
+ " <td>99.6</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 08:00:00</th>\n",
+ " <td>99</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 13:00:00</th>\n",
+ " <td>98</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 19:00:00</th>\n",
+ " <td>99.5</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label temperature body \n",
+ "units degF degC \n",
+ "description 223761 678 223762 676 \n",
+ "id datetime \n",
+ "100001 2117-09-11 13:48:00 98 None None None\n",
+ " 2117-09-11 16:00:00 97.9 None None None\n",
+ " 2117-09-11 19:00:00 99.5 None None None\n",
+ " 2117-09-11 22:00:00 100 None None None\n",
+ " 2117-09-12 01:00:00 99.9 None None None\n",
+ " 2117-09-12 04:00:00 97.7 None None None\n",
+ " 2117-09-12 08:00:00 97.8 None None None\n",
+ " 2117-09-12 12:00:00 97.5 None None None\n",
+ " 2117-09-12 19:00:00 99.8 None None None\n",
+ " 2117-09-13 00:00:00 99.7 None None None\n",
+ " 2117-09-13 04:00:00 99.3 None None None\n",
+ " 2117-09-13 08:00:00 99.4 None None None\n",
+ " 2117-09-13 12:00:00 98.8 None None None\n",
+ " 2117-09-13 16:00:00 99.3 None None None\n",
+ " 2117-09-13 22:00:00 99.9 None None None\n",
+ " 2117-09-14 00:00:00 99.4 None None None\n",
+ " 2117-09-14 04:00:00 99.6 None None None\n",
+ " 2117-09-14 08:00:00 99 None None None\n",
+ " 2117-09-14 13:00:00 98 None None None\n",
+ " 2117-09-14 19:00:00 99.5 None None None"
+ ]
+ },
+ "execution_count": 7,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_temp_tr.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 26,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload(transformers)\n",
+ "reload(units)\n",
+ "reload(icu_data_defs)\n",
+ "data_dict = icu_data_defs.data_dictionary('config/data_definitions.xlsx')\n",
+ "agg_func = lambda x:x.iloc[0]\n",
+ "ureg = units.MedicalUreg()\n",
+ "standard_pipeline = Pipeline([\n",
+ " ('drop_small_columns',transformers.remove_small_columns(threshold=5)),\n",
+ " ('aggregate_same_datetime',transformers.same_index_aggregator(agg_func)),\n",
+ " ('split_dtype',transformers.split_dtype())\n",
+ " ])\n",
+ "\n",
+ "stnd_cols = transformers.column_standardizer(data_dict,ureg)\n",
+ "drop_oob = transformers.oob_value_remover(data_dict)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "df_temp_cl = standard_pipeline.transform(df_temp_tr)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"4\" halign=\"left\">temperature body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">degF</th>\n",
+ " <th colspan=\"2\" halign=\"left\">degC</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>223761</th>\n",
+ " <th>678</th>\n",
+ " <th>223762</th>\n",
+ " <th>676</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"20\" valign=\"top\">100001</th>\n",
+ " <th>2117-09-11 13:48:00</th>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 16:00:00</th>\n",
+ " <td>97.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 19:00:00</th>\n",
+ " <td>99.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 22:00:00</th>\n",
+ " <td>100.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 01:00:00</th>\n",
+ " <td>99.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 04:00:00</th>\n",
+ " <td>97.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 08:00:00</th>\n",
+ " <td>97.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 12:00:00</th>\n",
+ " <td>97.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 19:00:00</th>\n",
+ " <td>99.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 00:00:00</th>\n",
+ " <td>99.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 04:00:00</th>\n",
+ " <td>99.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 08:00:00</th>\n",
+ " <td>99.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 12:00:00</th>\n",
+ " <td>98.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 16:00:00</th>\n",
+ " <td>99.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 22:00:00</th>\n",
+ " <td>99.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 00:00:00</th>\n",
+ " <td>99.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 04:00:00</th>\n",
+ " <td>99.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 08:00:00</th>\n",
+ " <td>99.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 13:00:00</th>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 19:00:00</th>\n",
+ " <td>99.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label temperature body \n",
+ "units degF degC \n",
+ "description 223761 678 223762 676 \n",
+ "id datetime \n",
+ "100001 2117-09-11 13:48:00 98.0 NaN NaN NaN\n",
+ " 2117-09-11 16:00:00 97.9 NaN NaN NaN\n",
+ " 2117-09-11 19:00:00 99.5 NaN NaN NaN\n",
+ " 2117-09-11 22:00:00 100.0 NaN NaN NaN\n",
+ " 2117-09-12 01:00:00 99.9 NaN NaN NaN\n",
+ " 2117-09-12 04:00:00 97.7 NaN NaN NaN\n",
+ " 2117-09-12 08:00:00 97.8 NaN NaN NaN\n",
+ " 2117-09-12 12:00:00 97.5 NaN NaN NaN\n",
+ " 2117-09-12 19:00:00 99.8 NaN NaN NaN\n",
+ " 2117-09-13 00:00:00 99.7 NaN NaN NaN\n",
+ " 2117-09-13 04:00:00 99.3 NaN NaN NaN\n",
+ " 2117-09-13 08:00:00 99.4 NaN NaN NaN\n",
+ " 2117-09-13 12:00:00 98.8 NaN NaN NaN\n",
+ " 2117-09-13 16:00:00 99.3 NaN NaN NaN\n",
+ " 2117-09-13 22:00:00 99.9 NaN NaN NaN\n",
+ " 2117-09-14 00:00:00 99.4 NaN NaN NaN\n",
+ " 2117-09-14 04:00:00 99.6 NaN NaN NaN\n",
+ " 2117-09-14 08:00:00 99.0 NaN NaN NaN\n",
+ " 2117-09-14 13:00:00 98.0 NaN NaN NaN\n",
+ " 2117-09-14 19:00:00 99.5 NaN NaN NaN"
+ ]
+ },
+ "execution_count": 10,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_temp_cl.head(20)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [],
+ "source": [
+ "df_temp_conv = stnd_cols.transform(df_temp_cl)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"4\" halign=\"left\">temperature body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"4\" halign=\"left\">known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"4\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"4\" halign=\"left\">degF</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>223761</th>\n",
+ " <th>678</th>\n",
+ " <th>223762(degC)</th>\n",
+ " <th>676(degC)</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>522143.000000</td>\n",
+ " <td>768158.000000</td>\n",
+ " <td>74144.000000</td>\n",
+ " <td>370309.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>98.407970</td>\n",
+ " <td>98.570606</td>\n",
+ " <td>99.193821</td>\n",
+ " <td>98.765740</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>14.681127</td>\n",
+ " <td>2.666614</td>\n",
+ " <td>9.735224</td>\n",
+ " <td>2.608901</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>-99.900000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>26.600000</td>\n",
+ " <td>32.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>97.500000</td>\n",
+ " <td>97.599998</td>\n",
+ " <td>97.520000</td>\n",
+ " <td>97.879998</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>98.300000</td>\n",
+ " <td>98.599998</td>\n",
+ " <td>98.600000</td>\n",
+ " <td>98.960002</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>99.300000</td>\n",
+ " <td>99.599998</td>\n",
+ " <td>99.680000</td>\n",
+ " <td>99.860002</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>9637.000000</td>\n",
+ " <td>109.000000</td>\n",
+ " <td>709.700000</td>\n",
+ " <td>115.700000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label temperature body \n",
+ "status known \n",
+ "variable_type qn \n",
+ "units degF \n",
+ "description 223761 678 223762(degC) 676(degC)\n",
+ "count 522143.000000 768158.000000 74144.000000 370309.000000\n",
+ "mean 98.407970 98.570606 99.193821 98.765740\n",
+ "std 14.681127 2.666614 9.735224 2.608901\n",
+ "min -99.900000 0.000000 26.600000 32.000000\n",
+ "25% 97.500000 97.599998 97.520000 97.879998\n",
+ "50% 98.300000 98.599998 98.600000 98.960002\n",
+ "75% 99.300000 99.599998 99.680000 99.860002\n",
+ "max 9637.000000 109.000000 709.700000 115.700000"
+ ]
+ },
+ "execution_count": 12,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_temp_conv.describe()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "df_temp_no_oob = drop_oob.transform(df_temp_conv)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"4\" halign=\"left\">temperature body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"4\" halign=\"left\">known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"4\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"4\" halign=\"left\">degF</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>223761</th>\n",
+ " <th>678</th>\n",
+ " <th>223762(degC)</th>\n",
+ " <th>676(degC)</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>522116.000000</td>\n",
+ " <td>768158.000000</td>\n",
+ " <td>73638.000000</td>\n",
+ " <td>370309.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>98.352642</td>\n",
+ " <td>98.570606</td>\n",
+ " <td>98.430646</td>\n",
+ " <td>98.765740</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>2.825922</td>\n",
+ " <td>2.666614</td>\n",
+ " <td>2.467125</td>\n",
+ " <td>2.608901</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>26.600000</td>\n",
+ " <td>32.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>97.500000</td>\n",
+ " <td>97.599998</td>\n",
+ " <td>97.340000</td>\n",
+ " <td>97.879998</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>98.300000</td>\n",
+ " <td>98.599998</td>\n",
+ " <td>98.600000</td>\n",
+ " <td>98.960002</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>99.300000</td>\n",
+ " <td>99.599998</td>\n",
+ " <td>99.680000</td>\n",
+ " <td>99.860002</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>129.000000</td>\n",
+ " <td>109.000000</td>\n",
+ " <td>113.000000</td>\n",
+ " <td>115.700000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label temperature body \n",
+ "status known \n",
+ "variable_type qn \n",
+ "units degF \n",
+ "description 223761 678 223762(degC) 676(degC)\n",
+ "count 522116.000000 768158.000000 73638.000000 370309.000000\n",
+ "mean 98.352642 98.570606 98.430646 98.765740\n",
+ "std 2.825922 2.666614 2.467125 2.608901\n",
+ "min 0.000000 0.000000 26.600000 32.000000\n",
+ "25% 97.500000 97.599998 97.340000 97.879998\n",
+ "50% 98.300000 98.599998 98.600000 98.960002\n",
+ "75% 99.300000 99.599998 99.680000 99.860002\n",
+ "max 129.000000 109.000000 113.000000 115.700000"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_temp_no_oob.describe()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 27,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "combine_like = transformers.combine_like_cols()\n",
+ "df_temp_combined = combine_like.transform(df_temp_no_oob)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 28,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th>temperature body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th>known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th>qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th>degF</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>all</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"24\" valign=\"top\">100001</th>\n",
+ " <th>2117-09-11 13:48:00</th>\n",
+ " <td>98.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 16:00:00</th>\n",
+ " <td>97.900000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 19:00:00</th>\n",
+ " <td>99.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 22:00:00</th>\n",
+ " <td>100.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 01:00:00</th>\n",
+ " <td>99.900000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 04:00:00</th>\n",
+ " <td>97.700000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 08:00:00</th>\n",
+ " <td>97.800000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 12:00:00</th>\n",
+ " <td>97.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 19:00:00</th>\n",
+ " <td>99.800000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 00:00:00</th>\n",
+ " <td>99.700000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 04:00:00</th>\n",
+ " <td>99.300000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 08:00:00</th>\n",
+ " <td>99.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 12:00:00</th>\n",
+ " <td>98.800000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 16:00:00</th>\n",
+ " <td>99.300000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 22:00:00</th>\n",
+ " <td>99.900000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 00:00:00</th>\n",
+ " <td>99.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 04:00:00</th>\n",
+ " <td>99.600000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 08:00:00</th>\n",
+ " <td>99.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 13:00:00</th>\n",
+ " <td>98.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 19:00:00</th>\n",
+ " <td>99.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-15 00:00:00</th>\n",
+ " <td>99.600000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-15 08:00:00</th>\n",
+ " <td>98.300000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-15 12:00:00</th>\n",
+ " <td>97.800000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-15 16:00:00</th>\n",
+ " <td>98.600000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"6\" valign=\"top\">100003</th>\n",
+ " <th>2150-04-17 20:31:00</th>\n",
+ " <td>95.900000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-17 22:00:00</th>\n",
+ " <td>98.200000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-18 00:00:00</th>\n",
+ " <td>97.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-18 04:00:00</th>\n",
+ " <td>98.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-18 08:00:00</th>\n",
+ " <td>97.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-18 11:18:00</th>\n",
+ " <td>96.300000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"7\" valign=\"top\">199998</th>\n",
+ " <th>2119-02-21 02:00:00</th>\n",
+ " <td>100.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-21 03:00:00</th>\n",
+ " <td>100.220003</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-21 04:00:00</th>\n",
+ " <td>99.860002</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-21 05:00:00</th>\n",
+ " <td>100.220003</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-21 06:00:00</th>\n",
+ " <td>100.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-21 07:00:00</th>\n",
+ " <td>100.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-21 08:00:00</th>\n",
+ " <td>100.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"23\" valign=\"top\">199999</th>\n",
+ " <th>2136-04-06 16:07:00</th>\n",
+ " <td>97.800000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-06 20:00:00</th>\n",
+ " <td>97.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 00:00:00</th>\n",
+ " <td>97.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 02:00:00</th>\n",
+ " <td>101.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 05:00:00</th>\n",
+ " <td>100.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 08:00:00</th>\n",
+ " <td>99.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 12:00:00</th>\n",
+ " <td>99.800000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 15:00:00</th>\n",
+ " <td>100.700000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 18:00:00</th>\n",
+ " <td>97.600000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 22:00:00</th>\n",
+ " <td>98.600000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-08 04:00:00</th>\n",
+ " <td>98.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-08 09:00:00</th>\n",
+ " <td>97.800000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-08 16:00:00</th>\n",
+ " <td>97.700000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-08 20:00:00</th>\n",
+ " <td>99.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 00:00:00</th>\n",
+ " <td>99.600000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 05:00:00</th>\n",
+ " <td>99.100000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 08:00:00</th>\n",
+ " <td>97.800000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 12:00:00</th>\n",
+ " <td>98.300000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 16:00:00</th>\n",
+ " <td>98.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 20:00:00</th>\n",
+ " <td>97.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 00:00:00</th>\n",
+ " <td>97.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 03:00:00</th>\n",
+ " <td>97.400000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-10 08:00:00</th>\n",
+ " <td>98.100000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>1731503 rows × 1 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label temperature body\n",
+ "status known\n",
+ "variable_type qn\n",
+ "units degF\n",
+ "description all\n",
+ "id datetime \n",
+ "100001 2117-09-11 13:48:00 98.000000\n",
+ " 2117-09-11 16:00:00 97.900000\n",
+ " 2117-09-11 19:00:00 99.500000\n",
+ " 2117-09-11 22:00:00 100.000000\n",
+ " 2117-09-12 01:00:00 99.900000\n",
+ " 2117-09-12 04:00:00 97.700000\n",
+ " 2117-09-12 08:00:00 97.800000\n",
+ " 2117-09-12 12:00:00 97.500000\n",
+ " 2117-09-12 19:00:00 99.800000\n",
+ " 2117-09-13 00:00:00 99.700000\n",
+ " 2117-09-13 04:00:00 99.300000\n",
+ " 2117-09-13 08:00:00 99.400000\n",
+ " 2117-09-13 12:00:00 98.800000\n",
+ " 2117-09-13 16:00:00 99.300000\n",
+ " 2117-09-13 22:00:00 99.900000\n",
+ " 2117-09-14 00:00:00 99.400000\n",
+ " 2117-09-14 04:00:00 99.600000\n",
+ " 2117-09-14 08:00:00 99.000000\n",
+ " 2117-09-14 13:00:00 98.000000\n",
+ " 2117-09-14 19:00:00 99.500000\n",
+ " 2117-09-15 00:00:00 99.600000\n",
+ " 2117-09-15 08:00:00 98.300000\n",
+ " 2117-09-15 12:00:00 97.800000\n",
+ " 2117-09-15 16:00:00 98.600000\n",
+ "100003 2150-04-17 20:31:00 95.900000\n",
+ " 2150-04-17 22:00:00 98.200000\n",
+ " 2150-04-18 00:00:00 97.400000\n",
+ " 2150-04-18 04:00:00 98.000000\n",
+ " 2150-04-18 08:00:00 97.400000\n",
+ " 2150-04-18 11:18:00 96.300000\n",
+ "... ...\n",
+ "199998 2119-02-21 02:00:00 100.400000\n",
+ " 2119-02-21 03:00:00 100.220003\n",
+ " 2119-02-21 04:00:00 99.860002\n",
+ " 2119-02-21 05:00:00 100.220003\n",
+ " 2119-02-21 06:00:00 100.400000\n",
+ " 2119-02-21 07:00:00 100.400000\n",
+ " 2119-02-21 08:00:00 100.400000\n",
+ "199999 2136-04-06 16:07:00 97.800000\n",
+ " 2136-04-06 20:00:00 97.500000\n",
+ " 2136-04-07 00:00:00 97.400000\n",
+ " 2136-04-07 02:00:00 101.000000\n",
+ " 2136-04-07 05:00:00 100.500000\n",
+ " 2136-04-07 08:00:00 99.000000\n",
+ " 2136-04-07 12:00:00 99.800000\n",
+ " 2136-04-07 15:00:00 100.700000\n",
+ " 2136-04-07 18:00:00 97.600000\n",
+ " 2136-04-07 22:00:00 98.600000\n",
+ " 2136-04-08 04:00:00 98.500000\n",
+ " 2136-04-08 09:00:00 97.800000\n",
+ " 2136-04-08 16:00:00 97.700000\n",
+ " 2136-04-08 20:00:00 99.000000\n",
+ " 2136-04-09 00:00:00 99.600000\n",
+ " 2136-04-09 05:00:00 99.100000\n",
+ " 2136-04-09 08:00:00 97.800000\n",
+ " 2136-04-09 12:00:00 98.300000\n",
+ " 2136-04-09 16:00:00 98.000000\n",
+ " 2136-04-09 20:00:00 97.400000\n",
+ " 2136-04-10 00:00:00 97.400000\n",
+ " 2136-04-10 03:00:00 97.400000\n",
+ " 2136-04-10 08:00:00 98.100000\n",
+ "\n",
+ "[1731503 rows x 1 columns]"
+ ]
+ },
+ "execution_count": 28,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_temp_combined"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Segmenting"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 29,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import segmenting"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 30,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "df_context = utils.open_df('data/mimic_data','context')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 31,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>pt_id</th>\n",
+ " <th>id</th>\n",
+ " <th>start_dt</th>\n",
+ " <th>end_dt</th>\n",
+ " <th>lang</th>\n",
+ " <th>religion</th>\n",
+ " <th>marital_status</th>\n",
+ " <th>ethnicity</th>\n",
+ " <th>dx_info</th>\n",
+ " <th>admission_location</th>\n",
+ " <th>...</th>\n",
+ " <th>dod</th>\n",
+ " <th>icd_codes</th>\n",
+ " <th>age</th>\n",
+ " <th>icustay_id</th>\n",
+ " <th>dbsource</th>\n",
+ " <th>first_icu</th>\n",
+ " <th>last_icu</th>\n",
+ " <th>intime</th>\n",
+ " <th>outtime</th>\n",
+ " <th>los</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>87</td>\n",
+ " <td>190659</td>\n",
+ " <td>2191-02-25 20:30:00</td>\n",
+ " <td>2191-04-25 15:18:00</td>\n",
+ " <td></td>\n",
+ " <td>UNOBTAINABLE</td>\n",
+ " <td></td>\n",
+ " <td>UNKNOWN/NOT SPECIFIED</td>\n",
+ " <td>NEWBORN</td>\n",
+ " <td>PHYS REFERRAL/NORMAL DELI</td>\n",
+ " <td>...</td>\n",
+ " <td>None</td>\n",
+ " <td>[V3101, 76515, 76524, 769, 7707, 7775, 7742, 7...</td>\n",
+ " <td>0 days 20:30:00</td>\n",
+ " <td>277633.0</td>\n",
+ " <td>carevue</td>\n",
+ " <td>NICU</td>\n",
+ " <td>NICU</td>\n",
+ " <td>2191-02-25 21:09:05</td>\n",
+ " <td>2191-04-25 15:38:56</td>\n",
+ " <td>58.7707</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>88</td>\n",
+ " <td>123010</td>\n",
+ " <td>2111-08-29 03:03:00</td>\n",
+ " <td>2111-09-03 14:24:00</td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td></td>\n",
+ " <td>BLACK/AFRICAN AMERICAN</td>\n",
+ " <td>S/P MOTOR VEHICLE ACCIDENT-STABBING</td>\n",
+ " <td>EMERGENCY ROOM ADMIT</td>\n",
+ " <td>...</td>\n",
+ " <td>None</td>\n",
+ " <td>[86113, 5119, 4239, E966]</td>\n",
+ " <td>10467 days 03:03:00</td>\n",
+ " <td>297289.0</td>\n",
+ " <td>carevue</td>\n",
+ " <td>TSICU</td>\n",
+ " <td>TSICU</td>\n",
+ " <td>2111-08-29 03:04:42</td>\n",
+ " <td>2111-08-30 21:08:09</td>\n",
+ " <td>1.7524</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>89</td>\n",
+ " <td>188646</td>\n",
+ " <td>2185-06-17 05:22:00</td>\n",
+ " <td>2185-06-21 11:15:00</td>\n",
+ " <td></td>\n",
+ " <td>UNOBTAINABLE</td>\n",
+ " <td></td>\n",
+ " <td>UNKNOWN/NOT SPECIFIED</td>\n",
+ " <td>NEWBORN</td>\n",
+ " <td>PHYS REFERRAL/NORMAL DELI</td>\n",
+ " <td>...</td>\n",
+ " <td>None</td>\n",
+ " <td>[V3101, 7742, 76516, 76527, 22801, V290]</td>\n",
+ " <td>0 days 05:22:00</td>\n",
+ " <td>249786.0</td>\n",
+ " <td>carevue</td>\n",
+ " <td>NICU</td>\n",
+ " <td>NICU</td>\n",
+ " <td>2185-06-17 05:46:00</td>\n",
+ " <td>2185-06-21 12:00:41</td>\n",
+ " <td>4.2602</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>91</td>\n",
+ " <td>121205</td>\n",
+ " <td>2177-04-23 00:08:00</td>\n",
+ " <td>2177-05-10 15:16:00</td>\n",
+ " <td></td>\n",
+ " <td>JEWISH</td>\n",
+ " <td>MARRIED</td>\n",
+ " <td>WHITE</td>\n",
+ " <td>FEVER</td>\n",
+ " <td>EMERGENCY ROOM ADMIT</td>\n",
+ " <td>...</td>\n",
+ " <td>2177-05-10 00:00:00</td>\n",
+ " <td>[20008, 2765, 5559, 99812, 51881, 4470, 135, 5...</td>\n",
+ " <td>29794 days 00:08:00</td>\n",
+ " <td>218528.0</td>\n",
+ " <td>carevue</td>\n",
+ " <td>CSRU</td>\n",
+ " <td>CSRU</td>\n",
+ " <td>2177-04-27 02:08:00</td>\n",
+ " <td>2177-04-27 14:03:00</td>\n",
+ " <td>0.4965</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>91</td>\n",
+ " <td>121205</td>\n",
+ " <td>2177-04-23 00:08:00</td>\n",
+ " <td>2177-05-10 15:16:00</td>\n",
+ " <td></td>\n",
+ " <td>JEWISH</td>\n",
+ " <td>MARRIED</td>\n",
+ " <td>WHITE</td>\n",
+ " <td>FEVER</td>\n",
+ " <td>EMERGENCY ROOM ADMIT</td>\n",
+ " <td>...</td>\n",
+ " <td>2177-05-10 00:00:00</td>\n",
+ " <td>[20008, 2765, 5559, 99812, 51881, 4470, 135, 5...</td>\n",
+ " <td>29794 days 00:08:00</td>\n",
+ " <td>256972.0</td>\n",
+ " <td>carevue</td>\n",
+ " <td>MICU</td>\n",
+ " <td>MICU</td>\n",
+ " <td>2177-05-07 03:52:00</td>\n",
+ " <td>2177-05-10 15:16:00</td>\n",
+ " <td>3.4750</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>5 rows × 22 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " pt_id id start_dt end_dt lang religion \\\n",
+ "0 87 190659 2191-02-25 20:30:00 2191-04-25 15:18:00 UNOBTAINABLE \n",
+ "1 88 123010 2111-08-29 03:03:00 2111-09-03 14:24:00 \n",
+ "2 89 188646 2185-06-17 05:22:00 2185-06-21 11:15:00 UNOBTAINABLE \n",
+ "3 91 121205 2177-04-23 00:08:00 2177-05-10 15:16:00 JEWISH \n",
+ "4 91 121205 2177-04-23 00:08:00 2177-05-10 15:16:00 JEWISH \n",
+ "\n",
+ " marital_status ethnicity dx_info \\\n",
+ "0 UNKNOWN/NOT SPECIFIED NEWBORN \n",
+ "1 BLACK/AFRICAN AMERICAN S/P MOTOR VEHICLE ACCIDENT-STABBING \n",
+ "2 UNKNOWN/NOT SPECIFIED NEWBORN \n",
+ "3 MARRIED WHITE FEVER \n",
+ "4 MARRIED WHITE FEVER \n",
+ "\n",
+ " admission_location ... dod \\\n",
+ "0 PHYS REFERRAL/NORMAL DELI ... None \n",
+ "1 EMERGENCY ROOM ADMIT ... None \n",
+ "2 PHYS REFERRAL/NORMAL DELI ... None \n",
+ "3 EMERGENCY ROOM ADMIT ... 2177-05-10 00:00:00 \n",
+ "4 EMERGENCY ROOM ADMIT ... 2177-05-10 00:00:00 \n",
+ "\n",
+ " icd_codes age \\\n",
+ "0 [V3101, 76515, 76524, 769, 7707, 7775, 7742, 7... 0 days 20:30:00 \n",
+ "1 [86113, 5119, 4239, E966] 10467 days 03:03:00 \n",
+ "2 [V3101, 7742, 76516, 76527, 22801, V290] 0 days 05:22:00 \n",
+ "3 [20008, 2765, 5559, 99812, 51881, 4470, 135, 5... 29794 days 00:08:00 \n",
+ "4 [20008, 2765, 5559, 99812, 51881, 4470, 135, 5... 29794 days 00:08:00 \n",
+ "\n",
+ " icustay_id dbsource first_icu last_icu intime \\\n",
+ "0 277633.0 carevue NICU NICU 2191-02-25 21:09:05 \n",
+ "1 297289.0 carevue TSICU TSICU 2111-08-29 03:04:42 \n",
+ "2 249786.0 carevue NICU NICU 2185-06-17 05:46:00 \n",
+ "3 218528.0 carevue CSRU CSRU 2177-04-27 02:08:00 \n",
+ "4 256972.0 carevue MICU MICU 2177-05-07 03:52:00 \n",
+ "\n",
+ " outtime los \n",
+ "0 2191-04-25 15:38:56 58.7707 \n",
+ "1 2111-08-30 21:08:09 1.7524 \n",
+ "2 2185-06-21 12:00:41 4.2602 \n",
+ "3 2177-04-27 14:03:00 0.4965 \n",
+ "4 2177-05-10 15:16:00 3.4750 \n",
+ "\n",
+ "[5 rows x 22 columns]"
+ ]
+ },
+ "execution_count": 31,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_context.head()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 33,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "end_dt = df_temp_combined.iloc[:,0].groupby(level='id').apply(lambda x:x.sample(1))\n",
+ "end_dt = end_dt.reset_index(level=0,drop=True).reset_index(level=1,drop=False).iloc[:,0]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 34,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload(segmenting)\n",
+ "reload(utils)\n",
+ "all_before = segmenting.all_before(end_dt,df_context)\n",
+ "n_hrs_before = segmenting.n_hrs_before(end_dt,10)\n",
+ "periodic = segmenting.periodic(10,df_context)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 138,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "C:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\tools\\merge.py:480: UserWarning: merging between different levels can give an unintended result (3 levels on the left, 1 on the right)\n",
+ " warnings.warn(msg, UserWarning)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"4\" halign=\"left\">temperature body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"2\" halign=\"left\">degF</th>\n",
+ " <th colspan=\"2\" halign=\"left\">degC</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>223761</th>\n",
+ " <th>678</th>\n",
+ " <th>223762</th>\n",
+ " <th>676</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>seg_id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"8\" valign=\"top\">100001</th>\n",
+ " <th>2117-09-11 13:48:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 16:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 19:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 22:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>100.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 01:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 04:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 08:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 12:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">100003</th>\n",
+ " <th>2150-04-17 20:31:00</th>\n",
+ " <th>0</th>\n",
+ " <td>95.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-17 22:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-18 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"19\" valign=\"top\">100006</th>\n",
+ " <th>2108-04-06 16:30:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-06 20:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-07 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-07 04:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-07 08:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-07 12:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-07 20:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-08 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.599998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-08 04:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-08 08:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.199997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-08 12:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-08 16:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-08 20:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-09 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.199997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-09 04:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-09 08:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-09 12:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.300003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-09 20:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.599998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2108-04-10 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"10\" valign=\"top\">199998</th>\n",
+ " <th>2119-02-20 17:15:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.299999</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 17:30:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 17:45:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.599998</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 18:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.900002</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 18:30:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.200001</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 19:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.599998</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 20:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.799999</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 21:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.799999</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 22:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.799999</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2119-02-20 23:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.700001</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"20\" valign=\"top\">199999</th>\n",
+ " <th>2136-04-06 16:07:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-06 20:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 02:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>101.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 05:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>100.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 08:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 12:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 15:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>100.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 18:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-07 22:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-08 04:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-08 09:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-08 16:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-08 20:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 05:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 08:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 12:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 16:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2136-04-09 20:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>839877 rows × 4 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label temperature body \\\n",
+ "units degF degC \n",
+ "description 223761 678 223762 \n",
+ "id datetime seg_id \n",
+ "100001 2117-09-11 13:48:00 0 98.0 NaN NaN \n",
+ " 2117-09-11 16:00:00 0 97.9 NaN NaN \n",
+ " 2117-09-11 19:00:00 0 99.5 NaN NaN \n",
+ " 2117-09-11 22:00:00 0 100.0 NaN NaN \n",
+ " 2117-09-12 01:00:00 0 99.9 NaN NaN \n",
+ " 2117-09-12 04:00:00 0 97.7 NaN NaN \n",
+ " 2117-09-12 08:00:00 0 97.8 NaN NaN \n",
+ " 2117-09-12 12:00:00 0 97.5 NaN NaN \n",
+ "100003 2150-04-17 20:31:00 0 95.9 NaN NaN \n",
+ " 2150-04-17 22:00:00 0 98.2 NaN NaN \n",
+ " 2150-04-18 00:00:00 0 97.4 NaN NaN \n",
+ "100006 2108-04-06 16:30:00 0 NaN 97.000000 NaN \n",
+ " 2108-04-06 20:00:00 0 NaN 97.400002 NaN \n",
+ " 2108-04-07 00:00:00 0 NaN 97.800003 NaN \n",
+ " 2108-04-07 04:00:00 0 NaN 97.000000 NaN \n",
+ " 2108-04-07 08:00:00 0 NaN 97.099998 NaN \n",
+ " 2108-04-07 12:00:00 0 NaN 97.000000 NaN \n",
+ " 2108-04-07 20:00:00 0 NaN 98.800003 NaN \n",
+ " 2108-04-08 00:00:00 0 NaN 98.599998 NaN \n",
+ " 2108-04-08 04:00:00 0 NaN 98.000000 NaN \n",
+ " 2108-04-08 08:00:00 0 NaN 97.199997 NaN \n",
+ " 2108-04-08 12:00:00 0 NaN 97.000000 NaN \n",
+ " 2108-04-08 16:00:00 0 NaN 98.000000 NaN \n",
+ " 2108-04-08 20:00:00 0 NaN 98.800003 NaN \n",
+ " 2108-04-09 00:00:00 0 NaN 97.199997 NaN \n",
+ " 2108-04-09 04:00:00 0 NaN 97.400002 NaN \n",
+ " 2108-04-09 08:00:00 0 NaN 97.099998 NaN \n",
+ " 2108-04-09 12:00:00 0 NaN 97.300003 NaN \n",
+ " 2108-04-09 20:00:00 0 NaN 97.599998 NaN \n",
+ " 2108-04-10 00:00:00 0 NaN 97.000000 NaN \n",
+ "... ... ... ... \n",
+ "199998 2119-02-20 17:15:00 0 NaN NaN NaN \n",
+ " 2119-02-20 17:30:00 0 NaN NaN NaN \n",
+ " 2119-02-20 17:45:00 0 NaN NaN NaN \n",
+ " 2119-02-20 18:00:00 0 NaN NaN NaN \n",
+ " 2119-02-20 18:30:00 0 NaN NaN NaN \n",
+ " 2119-02-20 19:00:00 0 NaN NaN NaN \n",
+ " 2119-02-20 20:00:00 0 NaN NaN NaN \n",
+ " 2119-02-20 21:00:00 0 NaN NaN NaN \n",
+ " 2119-02-20 22:00:00 0 NaN NaN NaN \n",
+ " 2119-02-20 23:00:00 0 NaN NaN NaN \n",
+ "199999 2136-04-06 16:07:00 0 97.8 NaN NaN \n",
+ " 2136-04-06 20:00:00 0 97.5 NaN NaN \n",
+ " 2136-04-07 00:00:00 0 97.4 NaN NaN \n",
+ " 2136-04-07 02:00:00 0 101.0 NaN NaN \n",
+ " 2136-04-07 05:00:00 0 100.5 NaN NaN \n",
+ " 2136-04-07 08:00:00 0 99.0 NaN NaN \n",
+ " 2136-04-07 12:00:00 0 99.8 NaN NaN \n",
+ " 2136-04-07 15:00:00 0 100.7 NaN NaN \n",
+ " 2136-04-07 18:00:00 0 97.6 NaN NaN \n",
+ " 2136-04-07 22:00:00 0 98.6 NaN NaN \n",
+ " 2136-04-08 04:00:00 0 98.5 NaN NaN \n",
+ " 2136-04-08 09:00:00 0 97.8 NaN NaN \n",
+ " 2136-04-08 16:00:00 0 97.7 NaN NaN \n",
+ " 2136-04-08 20:00:00 0 99.0 NaN NaN \n",
+ " 2136-04-09 00:00:00 0 99.6 NaN NaN \n",
+ " 2136-04-09 05:00:00 0 99.1 NaN NaN \n",
+ " 2136-04-09 08:00:00 0 97.8 NaN NaN \n",
+ " 2136-04-09 12:00:00 0 98.3 NaN NaN \n",
+ " 2136-04-09 16:00:00 0 98.0 NaN NaN \n",
+ " 2136-04-09 20:00:00 0 97.4 NaN NaN \n",
+ "\n",
+ "label \n",
+ "units \n",
+ "description 676 \n",
+ "id datetime seg_id \n",
+ "100001 2117-09-11 13:48:00 0 NaN \n",
+ " 2117-09-11 16:00:00 0 NaN \n",
+ " 2117-09-11 19:00:00 0 NaN \n",
+ " 2117-09-11 22:00:00 0 NaN \n",
+ " 2117-09-12 01:00:00 0 NaN \n",
+ " 2117-09-12 04:00:00 0 NaN \n",
+ " 2117-09-12 08:00:00 0 NaN \n",
+ " 2117-09-12 12:00:00 0 NaN \n",
+ "100003 2150-04-17 20:31:00 0 NaN \n",
+ " 2150-04-17 22:00:00 0 NaN \n",
+ " 2150-04-18 00:00:00 0 NaN \n",
+ "100006 2108-04-06 16:30:00 0 NaN \n",
+ " 2108-04-06 20:00:00 0 NaN \n",
+ " 2108-04-07 00:00:00 0 NaN \n",
+ " 2108-04-07 04:00:00 0 NaN \n",
+ " 2108-04-07 08:00:00 0 NaN \n",
+ " 2108-04-07 12:00:00 0 NaN \n",
+ " 2108-04-07 20:00:00 0 NaN \n",
+ " 2108-04-08 00:00:00 0 NaN \n",
+ " 2108-04-08 04:00:00 0 NaN \n",
+ " 2108-04-08 08:00:00 0 NaN \n",
+ " 2108-04-08 12:00:00 0 NaN \n",
+ " 2108-04-08 16:00:00 0 NaN \n",
+ " 2108-04-08 20:00:00 0 NaN \n",
+ " 2108-04-09 00:00:00 0 NaN \n",
+ " 2108-04-09 04:00:00 0 NaN \n",
+ " 2108-04-09 08:00:00 0 NaN \n",
+ " 2108-04-09 12:00:00 0 NaN \n",
+ " 2108-04-09 20:00:00 0 NaN \n",
+ " 2108-04-10 00:00:00 0 NaN \n",
+ "... ... \n",
+ "199998 2119-02-20 17:15:00 0 36.299999 \n",
+ " 2119-02-20 17:30:00 0 36.500000 \n",
+ " 2119-02-20 17:45:00 0 36.599998 \n",
+ " 2119-02-20 18:00:00 0 36.900002 \n",
+ " 2119-02-20 18:30:00 0 37.200001 \n",
+ " 2119-02-20 19:00:00 0 37.599998 \n",
+ " 2119-02-20 20:00:00 0 37.799999 \n",
+ " 2119-02-20 21:00:00 0 37.799999 \n",
+ " 2119-02-20 22:00:00 0 37.799999 \n",
+ " 2119-02-20 23:00:00 0 37.700001 \n",
+ "199999 2136-04-06 16:07:00 0 NaN \n",
+ " 2136-04-06 20:00:00 0 NaN \n",
+ " 2136-04-07 00:00:00 0 NaN \n",
+ " 2136-04-07 02:00:00 0 NaN \n",
+ " 2136-04-07 05:00:00 0 NaN \n",
+ " 2136-04-07 08:00:00 0 NaN \n",
+ " 2136-04-07 12:00:00 0 NaN \n",
+ " 2136-04-07 15:00:00 0 NaN \n",
+ " 2136-04-07 18:00:00 0 NaN \n",
+ " 2136-04-07 22:00:00 0 NaN \n",
+ " 2136-04-08 04:00:00 0 NaN \n",
+ " 2136-04-08 09:00:00 0 NaN \n",
+ " 2136-04-08 16:00:00 0 NaN \n",
+ " 2136-04-08 20:00:00 0 NaN \n",
+ " 2136-04-09 00:00:00 0 NaN \n",
+ " 2136-04-09 05:00:00 0 NaN \n",
+ " 2136-04-09 08:00:00 0 NaN \n",
+ " 2136-04-09 12:00:00 0 NaN \n",
+ " 2136-04-09 16:00:00 0 NaN \n",
+ " 2136-04-09 20:00:00 0 NaN \n",
+ "\n",
+ "[839877 rows x 4 columns]"
+ ]
+ },
+ "execution_count": 138,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_temp_all_before = all_before.transform(df_temp_cl)\n",
+ "df_temp_all_before[df_temp_all_before.index.get_level_values('seg_id') > -1]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 262,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ " seg_id\n",
+ "id datetime \n",
+ "100001 2117-09-11 22:00:00 0\n",
+ " 2117-09-12 01:00:00 0\n",
+ " 2117-09-12 04:00:00 0\n",
+ "100006 2108-04-07 20:00:00 0\n",
+ "100007 2145-04-04 00:00:00 0\n",
+ " 2145-04-04 04:00:00 0\n",
+ "100009 2162-05-19 03:00:00 0\n",
+ "100010 2109-12-10 22:47:00 0\n",
+ " 2109-12-11 00:00:00 0\n",
+ "100011 2177-09-07 09:00:00 0\n",
+ " 2177-09-07 13:00:00 0\n",
+ " 2177-09-07 17:00:00 0\n",
+ "label temperature body \n",
+ "status known \n",
+ "variable_type qn \n",
+ "units degF \n",
+ "description 223761 678 223762(degC) 676(degC)\n",
+ "id datetime seg_id \n",
+ "100001 2117-09-11 13:48:00 -1 98.0 NaN NaN NaN\n",
+ " 2117-09-11 16:00:00 -1 97.9 NaN NaN NaN\n",
+ " 2117-09-11 19:00:00 -1 99.5 NaN NaN NaN\n",
+ " 2117-09-11 22:00:00 0 100.0 NaN NaN NaN\n",
+ " 2117-09-12 01:00:00 0 99.9 NaN NaN NaN\n",
+ " 2117-09-12 04:00:00 0 97.7 NaN NaN NaN\n",
+ " 2117-09-12 08:00:00 -1 97.8 NaN NaN NaN\n",
+ " 2117-09-12 12:00:00 -1 97.5 NaN NaN NaN\n",
+ " 2117-09-12 19:00:00 -1 99.8 NaN NaN NaN\n",
+ " 2117-09-13 00:00:00 -1 99.7 NaN NaN NaN\n",
+ " 2117-09-13 04:00:00 -1 99.3 NaN NaN NaN\n",
+ " 2117-09-13 08:00:00 -1 99.4 NaN NaN NaN\n",
+ " 2117-09-13 12:00:00 -1 98.8 NaN NaN NaN\n",
+ " 2117-09-13 16:00:00 -1 99.3 NaN NaN NaN\n",
+ " 2117-09-13 22:00:00 -1 99.9 NaN NaN NaN\n",
+ " 2117-09-14 00:00:00 -1 99.4 NaN NaN NaN\n",
+ " 2117-09-14 04:00:00 -1 99.6 NaN NaN NaN\n",
+ " 2117-09-14 08:00:00 -1 99.0 NaN NaN NaN\n",
+ " 2117-09-14 13:00:00 -1 98.0 NaN NaN NaN\n",
+ " 2117-09-14 19:00:00 -1 99.5 NaN NaN NaN\n",
+ " 2117-09-15 00:00:00 -1 99.6 NaN NaN NaN\n",
+ " 2117-09-15 08:00:00 -1 98.3 NaN NaN NaN\n",
+ " 2117-09-15 12:00:00 -1 97.8 NaN NaN NaN\n",
+ " 2117-09-15 16:00:00 -1 98.6 NaN NaN NaN\n",
+ "100003 2150-04-17 20:31:00 -1 95.9 NaN NaN NaN\n",
+ " 2150-04-17 22:00:00 -1 98.2 NaN NaN NaN\n",
+ " 2150-04-18 00:00:00 -1 97.4 NaN NaN NaN\n",
+ " 2150-04-18 04:00:00 -1 98.0 NaN NaN NaN\n",
+ " 2150-04-18 08:00:00 -1 97.4 NaN NaN NaN\n",
+ " 2150-04-18 11:18:00 -1 96.3 NaN NaN NaN\n",
+ "... ... .. ... ...\n",
+ "100011 2177-09-04 19:00:00 -1 101.0 NaN NaN NaN\n",
+ " 2177-09-04 20:00:00 -1 101.2 NaN NaN NaN\n",
+ " 2177-09-04 22:00:00 -1 102.1 NaN NaN NaN\n",
+ " 2177-09-05 00:00:00 -1 101.8 NaN NaN NaN\n",
+ " 2177-09-05 02:00:00 -1 100.8 NaN NaN NaN\n",
+ " 2177-09-05 04:00:00 -1 100.1 NaN NaN NaN\n",
+ " 2177-09-05 06:00:00 -1 100.1 NaN NaN NaN\n",
+ " 2177-09-05 08:00:00 -1 99.5 NaN NaN NaN\n",
+ " 2177-09-05 10:00:00 -1 101.4 NaN NaN NaN\n",
+ " 2177-09-05 12:00:00 -1 101.1 NaN NaN NaN\n",
+ " 2177-09-05 14:00:00 -1 99.8 NaN NaN NaN\n",
+ " 2177-09-05 16:00:00 -1 97.5 NaN NaN NaN\n",
+ " 2177-09-05 20:00:00 -1 102.0 NaN NaN NaN\n",
+ " 2177-09-05 23:00:00 -1 100.8 NaN NaN NaN\n",
+ " 2177-09-06 02:00:00 -1 101.0 NaN NaN NaN\n",
+ " 2177-09-06 04:00:00 -1 101.2 NaN NaN NaN\n",
+ " 2177-09-06 08:00:00 -1 100.1 NaN NaN NaN\n",
+ " 2177-09-06 12:00:00 -1 100.1 NaN NaN NaN\n",
+ " 2177-09-06 16:00:00 -1 102.7 NaN NaN NaN\n",
+ " 2177-09-06 18:00:00 -1 102.0 NaN NaN NaN\n",
+ " 2177-09-06 20:00:00 -1 101.3 NaN NaN NaN\n",
+ " 2177-09-06 23:00:00 -1 101.9 NaN NaN NaN\n",
+ " 2177-09-07 00:00:00 -1 99.9 NaN NaN NaN\n",
+ " 2177-09-07 04:00:00 -1 100.5 NaN NaN NaN\n",
+ " 2177-09-07 09:00:00 0 99.5 NaN NaN NaN\n",
+ " 2177-09-07 13:00:00 0 99.1 NaN NaN NaN\n",
+ " 2177-09-07 17:00:00 0 99.2 NaN NaN NaN\n",
+ " 2177-09-07 19:00:00 -1 99.9 NaN NaN NaN\n",
+ " 2177-09-08 00:00:00 -1 99.8 NaN NaN NaN\n",
+ " 2177-09-08 04:00:00 -1 99.5 NaN NaN NaN\n",
+ "\n",
+ "[200 rows x 4 columns]\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"4\" halign=\"left\">temperature body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"4\" halign=\"left\">known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"4\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"4\" halign=\"left\">degF</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>223761</th>\n",
+ " <th>678</th>\n",
+ " <th>223762(degC)</th>\n",
+ " <th>676(degC)</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>seg_id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">100001</th>\n",
+ " <th>2117-09-11 22:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>100.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 01:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 04:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100006</th>\n",
+ " <th>2108-04-07 20:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100007</th>\n",
+ " <th>2145-04-04 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.699997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2145-04-04 04:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100009</th>\n",
+ " <th>2162-05-19 03:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100010</th>\n",
+ " <th>2109-12-10 22:47:00</th>\n",
+ " <th>0</th>\n",
+ " <td>100.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2109-12-11 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">100011</th>\n",
+ " <th>2177-09-07 09:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-09-07 13:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2177-09-07 17:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label temperature body \\\n",
+ "status known \n",
+ "variable_type qn \n",
+ "units degF \n",
+ "description 223761 678 223762(degC) \n",
+ "id datetime seg_id \n",
+ "100001 2117-09-11 22:00:00 0 100.0 NaN NaN \n",
+ " 2117-09-12 01:00:00 0 99.9 NaN NaN \n",
+ " 2117-09-12 04:00:00 0 97.7 NaN NaN \n",
+ "100006 2108-04-07 20:00:00 0 NaN 98.800003 NaN \n",
+ "100007 2145-04-04 00:00:00 0 NaN 98.699997 NaN \n",
+ " 2145-04-04 04:00:00 0 NaN 97.400002 NaN \n",
+ "100009 2162-05-19 03:00:00 0 98.6 NaN NaN \n",
+ "100010 2109-12-10 22:47:00 0 100.2 NaN NaN \n",
+ " 2109-12-11 00:00:00 0 98.8 NaN NaN \n",
+ "100011 2177-09-07 09:00:00 0 99.5 NaN NaN \n",
+ " 2177-09-07 13:00:00 0 99.1 NaN NaN \n",
+ " 2177-09-07 17:00:00 0 99.2 NaN NaN \n",
+ "\n",
+ "label \n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 676(degC) \n",
+ "id datetime seg_id \n",
+ "100001 2117-09-11 22:00:00 0 NaN \n",
+ " 2117-09-12 01:00:00 0 NaN \n",
+ " 2117-09-12 04:00:00 0 NaN \n",
+ "100006 2108-04-07 20:00:00 0 NaN \n",
+ "100007 2145-04-04 00:00:00 0 NaN \n",
+ " 2145-04-04 04:00:00 0 NaN \n",
+ "100009 2162-05-19 03:00:00 0 NaN \n",
+ "100010 2109-12-10 22:47:00 0 NaN \n",
+ " 2109-12-11 00:00:00 0 NaN \n",
+ "100011 2177-09-07 09:00:00 0 NaN \n",
+ " 2177-09-07 13:00:00 0 NaN \n",
+ " 2177-09-07 17:00:00 0 NaN "
+ ]
+ },
+ "execution_count": 262,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_temp_Nhr_before = n_hrs_before.transform(df_temp_combined.head(200))\n",
+ "df_temp_Nhr_before[df_temp_Nhr_before.index.get_level_values('seg_id') > -1]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 266,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>label</th>\n",
+ " <th colspan=\"4\" halign=\"left\">temperature body</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"4\" halign=\"left\">known</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"4\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"4\" halign=\"left\">degF</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>223761</th>\n",
+ " <th>678</th>\n",
+ " <th>223762(degC)</th>\n",
+ " <th>676(degC)</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>seg_id</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"24\" valign=\"top\">100001</th>\n",
+ " <th>2117-09-11 13:48:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 16:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 19:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-11 22:00:00</th>\n",
+ " <th>1</th>\n",
+ " <td>100.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 01:00:00</th>\n",
+ " <th>1</th>\n",
+ " <td>99.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 04:00:00</th>\n",
+ " <th>1</th>\n",
+ " <td>97.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 08:00:00</th>\n",
+ " <th>2</th>\n",
+ " <td>97.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 12:00:00</th>\n",
+ " <th>2</th>\n",
+ " <td>97.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-12 19:00:00</th>\n",
+ " <th>3</th>\n",
+ " <td>99.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 00:00:00</th>\n",
+ " <th>3</th>\n",
+ " <td>99.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 04:00:00</th>\n",
+ " <th>4</th>\n",
+ " <td>99.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 08:00:00</th>\n",
+ " <th>4</th>\n",
+ " <td>99.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 12:00:00</th>\n",
+ " <th>4</th>\n",
+ " <td>98.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 16:00:00</th>\n",
+ " <th>5</th>\n",
+ " <td>99.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-13 22:00:00</th>\n",
+ " <th>5</th>\n",
+ " <td>99.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 00:00:00</th>\n",
+ " <th>6</th>\n",
+ " <td>99.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 04:00:00</th>\n",
+ " <th>6</th>\n",
+ " <td>99.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 08:00:00</th>\n",
+ " <th>6</th>\n",
+ " <td>99.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 13:00:00</th>\n",
+ " <th>7</th>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-14 19:00:00</th>\n",
+ " <th>7</th>\n",
+ " <td>99.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-15 00:00:00</th>\n",
+ " <th>8</th>\n",
+ " <td>99.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-15 08:00:00</th>\n",
+ " <th>9</th>\n",
+ " <td>98.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-15 12:00:00</th>\n",
+ " <th>9</th>\n",
+ " <td>97.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2117-09-15 16:00:00</th>\n",
+ " <th>10</th>\n",
+ " <td>98.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"6\" valign=\"top\">100003</th>\n",
+ " <th>2150-04-17 20:31:00</th>\n",
+ " <th>0</th>\n",
+ " <td>95.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-17 22:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-18 00:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>97.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-18 04:00:00</th>\n",
+ " <th>1</th>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-18 08:00:00</th>\n",
+ " <th>1</th>\n",
+ " <td>97.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2150-04-18 11:18:00</th>\n",
+ " <th>1</th>\n",
+ " <td>96.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"16\" valign=\"top\">100114</th>\n",
+ " <th>2157-09-19 18:15:00</th>\n",
+ " <th>3</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-19 18:30:00</th>\n",
+ " <th>3</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.300003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-19 20:00:00</th>\n",
+ " <th>3</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-19 23:00:00</th>\n",
+ " <th>3</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 00:00:00</th>\n",
+ " <th>3</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.599998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 01:00:00</th>\n",
+ " <th>3</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 01:15:00</th>\n",
+ " <th>4</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.199997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 02:00:00</th>\n",
+ " <th>4</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 06:00:00</th>\n",
+ " <th>4</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 08:00:00</th>\n",
+ " <th>4</th>\n",
+ " <td>NaN</td>\n",
+ " <td>96.699997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 09:15:00</th>\n",
+ " <th>4</th>\n",
+ " <td>NaN</td>\n",
+ " <td>96.900002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 09:30:00</th>\n",
+ " <th>4</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 10:00:00</th>\n",
+ " <th>4</th>\n",
+ " <td>NaN</td>\n",
+ " <td>96.900002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 12:00:00</th>\n",
+ " <th>5</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.199997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 15:00:00</th>\n",
+ " <th>5</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2157-09-20 18:00:00</th>\n",
+ " <th>5</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"13\" valign=\"top\">100116</th>\n",
+ " <th>2173-07-27 05:13:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-27 08:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>100.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-27 09:30:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-27 11:00:00</th>\n",
+ " <th>0</th>\n",
+ " <td>98.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-27 14:25:00</th>\n",
+ " <th>0</th>\n",
+ " <td>100.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-27 16:30:00</th>\n",
+ " <th>1</th>\n",
+ " <td>100.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-27 18:00:00</th>\n",
+ " <th>1</th>\n",
+ " <td>99.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-27 20:00:00</th>\n",
+ " <th>1</th>\n",
+ " <td>100.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-28 00:00:00</th>\n",
+ " <th>1</th>\n",
+ " <td>99.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-28 04:00:00</th>\n",
+ " <th>2</th>\n",
+ " <td>98.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-28 08:00:00</th>\n",
+ " <th>2</th>\n",
+ " <td>99.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-28 12:00:00</th>\n",
+ " <th>3</th>\n",
+ " <td>98.5</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2173-07-28 16:00:00</th>\n",
+ " <th>3</th>\n",
+ " <td>99.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>100117</th>\n",
+ " <th>2166-04-30 21:39:00</th>\n",
+ " <th>0</th>\n",
+ " <td>99.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>2000 rows × 4 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "label temperature body \\\n",
+ "status known \n",
+ "variable_type qn \n",
+ "units degF \n",
+ "description 223761 678 223762(degC) \n",
+ "id datetime seg_id \n",
+ "100001 2117-09-11 13:48:00 0 98.0 NaN NaN \n",
+ " 2117-09-11 16:00:00 0 97.9 NaN NaN \n",
+ " 2117-09-11 19:00:00 0 99.5 NaN NaN \n",
+ " 2117-09-11 22:00:00 1 100.0 NaN NaN \n",
+ " 2117-09-12 01:00:00 1 99.9 NaN NaN \n",
+ " 2117-09-12 04:00:00 1 97.7 NaN NaN \n",
+ " 2117-09-12 08:00:00 2 97.8 NaN NaN \n",
+ " 2117-09-12 12:00:00 2 97.5 NaN NaN \n",
+ " 2117-09-12 19:00:00 3 99.8 NaN NaN \n",
+ " 2117-09-13 00:00:00 3 99.7 NaN NaN \n",
+ " 2117-09-13 04:00:00 4 99.3 NaN NaN \n",
+ " 2117-09-13 08:00:00 4 99.4 NaN NaN \n",
+ " 2117-09-13 12:00:00 4 98.8 NaN NaN \n",
+ " 2117-09-13 16:00:00 5 99.3 NaN NaN \n",
+ " 2117-09-13 22:00:00 5 99.9 NaN NaN \n",
+ " 2117-09-14 00:00:00 6 99.4 NaN NaN \n",
+ " 2117-09-14 04:00:00 6 99.6 NaN NaN \n",
+ " 2117-09-14 08:00:00 6 99.0 NaN NaN \n",
+ " 2117-09-14 13:00:00 7 98.0 NaN NaN \n",
+ " 2117-09-14 19:00:00 7 99.5 NaN NaN \n",
+ " 2117-09-15 00:00:00 8 99.6 NaN NaN \n",
+ " 2117-09-15 08:00:00 9 98.3 NaN NaN \n",
+ " 2117-09-15 12:00:00 9 97.8 NaN NaN \n",
+ " 2117-09-15 16:00:00 10 98.6 NaN NaN \n",
+ "100003 2150-04-17 20:31:00 0 95.9 NaN NaN \n",
+ " 2150-04-17 22:00:00 0 98.2 NaN NaN \n",
+ " 2150-04-18 00:00:00 0 97.4 NaN NaN \n",
+ " 2150-04-18 04:00:00 1 98.0 NaN NaN \n",
+ " 2150-04-18 08:00:00 1 97.4 NaN NaN \n",
+ " 2150-04-18 11:18:00 1 96.3 NaN NaN \n",
+ "... ... ... ... \n",
+ "100114 2157-09-19 18:15:00 3 NaN 98.400002 NaN \n",
+ " 2157-09-19 18:30:00 3 NaN 98.300003 NaN \n",
+ " 2157-09-19 20:00:00 3 NaN 98.400002 NaN \n",
+ " 2157-09-19 23:00:00 3 NaN 98.400002 NaN \n",
+ " 2157-09-20 00:00:00 3 NaN 98.599998 NaN \n",
+ " 2157-09-20 01:00:00 3 NaN 98.000000 NaN \n",
+ " 2157-09-20 01:15:00 4 NaN 98.199997 NaN \n",
+ " 2157-09-20 02:00:00 4 NaN 97.099998 NaN \n",
+ " 2157-09-20 06:00:00 4 NaN 98.000000 NaN \n",
+ " 2157-09-20 08:00:00 4 NaN 96.699997 NaN \n",
+ " 2157-09-20 09:15:00 4 NaN 96.900002 NaN \n",
+ " 2157-09-20 09:30:00 4 NaN 97.000000 NaN \n",
+ " 2157-09-20 10:00:00 4 NaN 96.900002 NaN \n",
+ " 2157-09-20 12:00:00 5 NaN 97.199997 NaN \n",
+ " 2157-09-20 15:00:00 5 NaN 98.400002 NaN \n",
+ " 2157-09-20 18:00:00 5 NaN 97.800003 NaN \n",
+ "100116 2173-07-27 05:13:00 0 98.9 NaN NaN \n",
+ " 2173-07-27 08:00:00 0 100.0 NaN NaN \n",
+ " 2173-07-27 09:30:00 0 99.7 NaN NaN \n",
+ " 2173-07-27 11:00:00 0 98.7 NaN NaN \n",
+ " 2173-07-27 14:25:00 0 100.4 NaN NaN \n",
+ " 2173-07-27 16:30:00 1 100.3 NaN NaN \n",
+ " 2173-07-27 18:00:00 1 99.9 NaN NaN \n",
+ " 2173-07-27 20:00:00 1 100.3 NaN NaN \n",
+ " 2173-07-28 00:00:00 1 99.7 NaN NaN \n",
+ " 2173-07-28 04:00:00 2 98.5 NaN NaN \n",
+ " 2173-07-28 08:00:00 2 99.4 NaN NaN \n",
+ " 2173-07-28 12:00:00 3 98.5 NaN NaN \n",
+ " 2173-07-28 16:00:00 3 99.4 NaN NaN \n",
+ "100117 2166-04-30 21:39:00 0 99.7 NaN NaN \n",
+ "\n",
+ "label \n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 676(degC) \n",
+ "id datetime seg_id \n",
+ "100001 2117-09-11 13:48:00 0 NaN \n",
+ " 2117-09-11 16:00:00 0 NaN \n",
+ " 2117-09-11 19:00:00 0 NaN \n",
+ " 2117-09-11 22:00:00 1 NaN \n",
+ " 2117-09-12 01:00:00 1 NaN \n",
+ " 2117-09-12 04:00:00 1 NaN \n",
+ " 2117-09-12 08:00:00 2 NaN \n",
+ " 2117-09-12 12:00:00 2 NaN \n",
+ " 2117-09-12 19:00:00 3 NaN \n",
+ " 2117-09-13 00:00:00 3 NaN \n",
+ " 2117-09-13 04:00:00 4 NaN \n",
+ " 2117-09-13 08:00:00 4 NaN \n",
+ " 2117-09-13 12:00:00 4 NaN \n",
+ " 2117-09-13 16:00:00 5 NaN \n",
+ " 2117-09-13 22:00:00 5 NaN \n",
+ " 2117-09-14 00:00:00 6 NaN \n",
+ " 2117-09-14 04:00:00 6 NaN \n",
+ " 2117-09-14 08:00:00 6 NaN \n",
+ " 2117-09-14 13:00:00 7 NaN \n",
+ " 2117-09-14 19:00:00 7 NaN \n",
+ " 2117-09-15 00:00:00 8 NaN \n",
+ " 2117-09-15 08:00:00 9 NaN \n",
+ " 2117-09-15 12:00:00 9 NaN \n",
+ " 2117-09-15 16:00:00 10 NaN \n",
+ "100003 2150-04-17 20:31:00 0 NaN \n",
+ " 2150-04-17 22:00:00 0 NaN \n",
+ " 2150-04-18 00:00:00 0 NaN \n",
+ " 2150-04-18 04:00:00 1 NaN \n",
+ " 2150-04-18 08:00:00 1 NaN \n",
+ " 2150-04-18 11:18:00 1 NaN \n",
+ "... ... \n",
+ "100114 2157-09-19 18:15:00 3 NaN \n",
+ " 2157-09-19 18:30:00 3 NaN \n",
+ " 2157-09-19 20:00:00 3 NaN \n",
+ " 2157-09-19 23:00:00 3 NaN \n",
+ " 2157-09-20 00:00:00 3 NaN \n",
+ " 2157-09-20 01:00:00 3 NaN \n",
+ " 2157-09-20 01:15:00 4 NaN \n",
+ " 2157-09-20 02:00:00 4 NaN \n",
+ " 2157-09-20 06:00:00 4 NaN \n",
+ " 2157-09-20 08:00:00 4 NaN \n",
+ " 2157-09-20 09:15:00 4 NaN \n",
+ " 2157-09-20 09:30:00 4 NaN \n",
+ " 2157-09-20 10:00:00 4 NaN \n",
+ " 2157-09-20 12:00:00 5 NaN \n",
+ " 2157-09-20 15:00:00 5 NaN \n",
+ " 2157-09-20 18:00:00 5 NaN \n",
+ "100116 2173-07-27 05:13:00 0 NaN \n",
+ " 2173-07-27 08:00:00 0 NaN \n",
+ " 2173-07-27 09:30:00 0 NaN \n",
+ " 2173-07-27 11:00:00 0 NaN \n",
+ " 2173-07-27 14:25:00 0 NaN \n",
+ " 2173-07-27 16:30:00 1 NaN \n",
+ " 2173-07-27 18:00:00 1 NaN \n",
+ " 2173-07-27 20:00:00 1 NaN \n",
+ " 2173-07-28 00:00:00 1 NaN \n",
+ " 2173-07-28 04:00:00 2 NaN \n",
+ " 2173-07-28 08:00:00 2 NaN \n",
+ " 2173-07-28 12:00:00 3 NaN \n",
+ " 2173-07-28 16:00:00 3 NaN \n",
+ "100117 2166-04-30 21:39:00 0 NaN \n",
+ "\n",
+ "[2000 rows x 4 columns]"
+ ]
+ },
+ "execution_count": 266,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df_temp_periodic = periodic.transform(df_temp_combined.head(2000))\n",
+ "df_temp_periodic[df_temp_periodic.index.get_level_values('seg_id') > -1]"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 252,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import utils\n",
+ "import mimic\n",
+ "import transformers\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "import icu_data_defs\n",
+ "import units\n",
+ "import segmenting\n",
+ "from sklearn_pandas import DataFrameMapper\n",
+ "import constants\n",
+ "import features"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 251,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "hdf5_fname = 'data/mimic_data'\n",
+ "data_dict = icu_data_defs.data_dictionary('config/data_definitions.xlsx')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "df_cleaned"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 249,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "end_dt = df_temp_combined.iloc[:,0].groupby(level='id').apply(lambda x:x.sample(1))\n",
+ "end_dt = end_dt.reset_index(level=0,drop=True).reset_index(level=1,drop=False).iloc[:,0]\n",
+ "all_before = segmenting.all_before(end_dt,df_context)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Feature creation"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 247,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "import utils\n",
+ "import transformers\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "import units\n",
+ "from sklearn_pandas import DataFrameMapper\n",
+ "import constants\n",
+ "import features"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 248,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "ename": "ImportError",
+ "evalue": "cannot import name CUSTOM_FILTER",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[1;31mImportError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m<ipython-input-248-bae7a29e5c29>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mreload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[0mreload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mutils\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0mreload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0munits\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0mreload\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mconstants\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\icu_ml_project\\v5\\features.pyc\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbase\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mTransformerMixin\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mBaseEstimator\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0msklearn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpipeline\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mFeatureUnion\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 3\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mconstants\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mcolumn_names\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mSEG_ID\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mNO_SEGMENT\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mALL\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mCUSTOM_FILTER\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 4\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mnp\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0msklearn_pandas\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mDataFrameMapper\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;31mImportError\u001b[0m: cannot import name CUSTOM_FILTER"
+ ]
+ }
+ ],
+ "source": [
+ "reload(features)\n",
+ "reload(utils)\n",
+ "reload(units)\n",
+ "reload(constants)\n",
+ "\n",
+ "df = df_temp_all_before\n",
+ "ureg = units.MedicalUreg()\n",
+ "\n",
+ "\n",
+ "\n",
+ "def summable_filter(df):\n",
+ " filter_func= lambda x: (ureg.is_volume(str(x[-2])) or ureg.is_mass(str(x[-2]))) and (x[0] != 'weight body')\n",
+ " return df.loc[:,df.columns.map(filter_func)]\n",
+ "\n",
+ "feature_tuples = [\n",
+ " ('MEAN',features.segment_mean(),ALL),\n",
+ " ('STD',features.segment_std(),ALL),\n",
+ " ('COUNT',features.segment_count(),ALL),\n",
+ " ('LAST',features.segment_last(),ALL),\n",
+ " ('SUM',features.segment_sum(),{constants.CUSTOM_FILTER:summable_filter})\n",
+ "]\n",
+ "\n",
+ "mapped_ft = features.make_mapper(feature_tuples,df)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 232,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "feature_df = mapped_ft.transform(df)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 233,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>temperature body_degF_223761_MEAN</th>\n",
+ " <th>temperature body_degF_678_MEAN</th>\n",
+ " <th>temperature body_degC_223762_MEAN</th>\n",
+ " <th>temperature body_degC_676_MEAN</th>\n",
+ " <th>temperature body_degF_223761_STD</th>\n",
+ " <th>temperature body_degF_678_STD</th>\n",
+ " <th>temperature body_degC_223762_STD</th>\n",
+ " <th>temperature body_degC_676_STD</th>\n",
+ " <th>temperature body_degF_223761_COUNT</th>\n",
+ " <th>temperature body_degF_678_COUNT</th>\n",
+ " <th>temperature body_degC_223762_COUNT</th>\n",
+ " <th>temperature body_degC_676_COUNT</th>\n",
+ " <th>temperature body_degF_223761_LAST</th>\n",
+ " <th>temperature body_degF_678_LAST</th>\n",
+ " <th>temperature body_degC_223762_LAST</th>\n",
+ " <th>temperature body_degC_676_LAST</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>98.537500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.064945</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>8.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>98.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>97.166667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.167619</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>3.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>95.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.533334</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.607729</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>21.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.591667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.466263</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>12.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.699997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>98.100000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.458258</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>3.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>98.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>98.550000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.036822</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>6.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>100.2</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>98.380000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.511765</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.641872</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.790767</td>\n",
+ " <td>NaN</td>\n",
+ " <td>5.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>34.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>34.5</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>NaN</td>\n",
+ " <td>100.649998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.777816</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>101.199997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>97.975000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.875032</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>12.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>97.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>96.050000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.777817</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>96.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.536364</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.492489</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>11.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.500000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.378571</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.260705</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>14.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.6</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>12</th>\n",
+ " <td>99.466667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.495650</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>12.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>98.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13</th>\n",
+ " <td>NaN</td>\n",
+ " <td>99.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.766037</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.374646</td>\n",
+ " <td>0.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>106.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.599998</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>14</th>\n",
+ " <td>NaN</td>\n",
+ " <td>95.300003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.300003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>15</th>\n",
+ " <td>98.500000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.141421</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>98.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>16</th>\n",
+ " <td>100.772222</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.719512</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.075287</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.281265</td>\n",
+ " <td>NaN</td>\n",
+ " <td>18.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>41.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.5</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>17</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.193750</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.401560</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>32.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.799999</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18</th>\n",
+ " <td>99.345455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.864975</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>33.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>98.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>19</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>20</th>\n",
+ " <td>98.312500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.022986</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>16.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>97.6</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>21</th>\n",
+ " <td>97.760000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.585662</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>5.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>97.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>22</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.445455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.849254</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>22.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>23</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>34.990909</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4.190574</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>11.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>28.4</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>24</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.799999</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.799999</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.320000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.277491</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>5.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.199997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26</th>\n",
+ " <td>NaN</td>\n",
+ " <td>96.700000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.754119</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>24.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>27</th>\n",
+ " <td>NaN</td>\n",
+ " <td>96.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.787487</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>10.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>28</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.847368</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.300681</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>19.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.200001</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>29</th>\n",
+ " <td>96.525000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.450000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>96.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44216</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.302703</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.021739</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.047082</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.997311</td>\n",
+ " <td>0.0</td>\n",
+ " <td>37.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>46.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44217</th>\n",
+ " <td>98.475000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.081280</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>4.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>97.1</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44218</th>\n",
+ " <td>96.275000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.420034</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>8.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>96.3</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44219</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44220</th>\n",
+ " <td>NaN</td>\n",
+ " <td>95.740001</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.021275</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>5.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44221</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.672309</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>5.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44222</th>\n",
+ " <td>99.240000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.512835</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>5.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>99.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44223</th>\n",
+ " <td>98.450000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.070711</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>2.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>98.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44224</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.130000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.531351</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>10.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44225</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.900002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.199997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>4.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44226</th>\n",
+ " <td>99.753333</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.765195</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>15.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>98.7</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44227</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.071875</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.449181</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.944674</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.920982</td>\n",
+ " <td>0.0</td>\n",
+ " <td>32.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>61.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>34.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44228</th>\n",
+ " <td>NaN</td>\n",
+ " <td>100.526316</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.175605</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>19.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44229</th>\n",
+ " <td>97.580000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.740570</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>10.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>96.9</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44230</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.443518</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.332443</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>108.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.299999</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44231</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.071429</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.239964</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>14.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>35.599998</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44232</th>\n",
+ " <td>98.484375</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.070456</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>32.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>100.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44233</th>\n",
+ " <td>NaN</td>\n",
+ " <td>100.278462</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.300803</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>130.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.900002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44234</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.173333</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.688131</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>15.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>35.0</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44235</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.074999</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.056330</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>4.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.599998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44236</th>\n",
+ " <td>97.977778</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.032930</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>9.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>98.4</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44237</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.485713</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.977118</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>7.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.900002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44238</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.264285</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.759157</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>14.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.599998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44239</th>\n",
+ " <td>NaN</td>\n",
+ " <td>95.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.565688</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.000000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44240</th>\n",
+ " <td>95.800000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>34.800000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>1.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>34.8</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44241</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.670000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>37.420725</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.668415</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.378023</td>\n",
+ " <td>0.0</td>\n",
+ " <td>10.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>193.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.699997</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44242</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.980953</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.933605</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.0</td>\n",
+ " <td>21.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44243</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>35.750000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>0.919241</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>2.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>35.099998</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44244</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>36.176191</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.159700</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>21.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>34.700001</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44245</th>\n",
+ " <td>98.655000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>1.147297</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>20.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>0.0</td>\n",
+ " <td>97.8</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>44246 rows × 16 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " temperature body_degF_223761_MEAN temperature body_degF_678_MEAN \\\n",
+ "0 98.537500 NaN \n",
+ "1 97.166667 NaN \n",
+ "2 NaN 97.533334 \n",
+ "3 NaN 98.591667 \n",
+ "4 98.100000 NaN \n",
+ "5 98.550000 NaN \n",
+ "6 98.380000 NaN \n",
+ "7 NaN 100.649998 \n",
+ "8 97.975000 NaN \n",
+ "9 96.050000 NaN \n",
+ "10 NaN 98.536364 \n",
+ "11 NaN NaN \n",
+ "12 99.466667 NaN \n",
+ "13 NaN 99.099998 \n",
+ "14 NaN 95.300003 \n",
+ "15 98.500000 NaN \n",
+ "16 100.772222 NaN \n",
+ "17 NaN NaN \n",
+ "18 99.345455 NaN \n",
+ "19 NaN 98.800003 \n",
+ "20 98.312500 NaN \n",
+ "21 97.760000 NaN \n",
+ "22 NaN 98.445455 \n",
+ "23 NaN NaN \n",
+ "24 NaN NaN \n",
+ "25 NaN 97.320000 \n",
+ "26 NaN 96.700000 \n",
+ "27 NaN 96.920000 \n",
+ "28 NaN NaN \n",
+ "29 96.525000 NaN \n",
+ "... ... ... \n",
+ "44216 NaN 98.302703 \n",
+ "44217 98.475000 NaN \n",
+ "44218 96.275000 NaN \n",
+ "44219 NaN 97.800003 \n",
+ "44220 NaN 95.740001 \n",
+ "44221 NaN 97.920000 \n",
+ "44222 99.240000 NaN \n",
+ "44223 98.450000 NaN \n",
+ "44224 NaN 98.130000 \n",
+ "44225 NaN 97.900002 \n",
+ "44226 99.753333 NaN \n",
+ "44227 NaN 98.071875 \n",
+ "44228 NaN 100.526316 \n",
+ "44229 97.580000 NaN \n",
+ "44230 NaN NaN \n",
+ "44231 NaN NaN \n",
+ "44232 98.484375 NaN \n",
+ "44233 NaN 100.278462 \n",
+ "44234 NaN NaN \n",
+ "44235 NaN 97.074999 \n",
+ "44236 97.977778 NaN \n",
+ "44237 NaN 97.485713 \n",
+ "44238 NaN 97.264285 \n",
+ "44239 NaN 95.400002 \n",
+ "44240 95.800000 NaN \n",
+ "44241 NaN 97.670000 \n",
+ "44242 NaN 98.980953 \n",
+ "44243 NaN NaN \n",
+ "44244 NaN NaN \n",
+ "44245 98.655000 NaN \n",
+ "\n",
+ " temperature body_degC_223762_MEAN temperature body_degC_676_MEAN \\\n",
+ "0 NaN NaN \n",
+ "1 NaN NaN \n",
+ "2 NaN NaN \n",
+ "3 NaN NaN \n",
+ "4 NaN NaN \n",
+ "5 NaN NaN \n",
+ "6 36.511765 NaN \n",
+ "7 NaN NaN \n",
+ "8 NaN NaN \n",
+ "9 NaN NaN \n",
+ "10 NaN NaN \n",
+ "11 36.378571 NaN \n",
+ "12 NaN NaN \n",
+ "13 NaN 36.766037 \n",
+ "14 NaN NaN \n",
+ "15 NaN NaN \n",
+ "16 37.719512 NaN \n",
+ "17 NaN 37.193750 \n",
+ "18 NaN NaN \n",
+ "19 NaN NaN \n",
+ "20 NaN NaN \n",
+ "21 NaN NaN \n",
+ "22 NaN NaN \n",
+ "23 34.990909 NaN \n",
+ "24 NaN 36.799999 \n",
+ "25 NaN NaN \n",
+ "26 NaN NaN \n",
+ "27 NaN NaN \n",
+ "28 NaN 36.847368 \n",
+ "29 NaN NaN \n",
+ "... ... ... \n",
+ "44216 NaN 37.021739 \n",
+ "44217 NaN NaN \n",
+ "44218 NaN NaN \n",
+ "44219 NaN NaN \n",
+ "44220 NaN NaN \n",
+ "44221 NaN NaN \n",
+ "44222 NaN NaN \n",
+ "44223 NaN NaN \n",
+ "44224 NaN NaN \n",
+ "44225 NaN NaN \n",
+ "44226 NaN NaN \n",
+ "44227 NaN 37.449181 \n",
+ "44228 NaN NaN \n",
+ "44229 NaN NaN \n",
+ "44230 NaN 37.443518 \n",
+ "44231 NaN 36.071429 \n",
+ "44232 NaN NaN \n",
+ "44233 NaN NaN \n",
+ "44234 36.173333 NaN \n",
+ "44235 NaN NaN \n",
+ "44236 NaN NaN \n",
+ "44237 NaN NaN \n",
+ "44238 NaN NaN \n",
+ "44239 NaN NaN \n",
+ "44240 34.800000 NaN \n",
+ "44241 NaN 37.420725 \n",
+ "44242 NaN NaN \n",
+ "44243 NaN 35.750000 \n",
+ "44244 NaN 36.176191 \n",
+ "44245 NaN NaN \n",
+ "\n",
+ " temperature body_degF_223761_STD temperature body_degF_678_STD \\\n",
+ "0 1.064945 NaN \n",
+ "1 1.167619 NaN \n",
+ "2 NaN 0.607729 \n",
+ "3 NaN 1.466263 \n",
+ "4 0.458258 NaN \n",
+ "5 1.036822 NaN \n",
+ "6 0.641872 NaN \n",
+ "7 NaN 0.777816 \n",
+ "8 0.875032 NaN \n",
+ "9 0.777817 NaN \n",
+ "10 NaN 0.492489 \n",
+ "11 NaN NaN \n",
+ "12 1.495650 NaN \n",
+ "13 NaN NaN \n",
+ "14 NaN NaN \n",
+ "15 0.141421 NaN \n",
+ "16 1.075287 NaN \n",
+ "17 NaN NaN \n",
+ "18 0.864975 NaN \n",
+ "19 NaN NaN \n",
+ "20 1.022986 NaN \n",
+ "21 0.585662 NaN \n",
+ "22 NaN 1.849254 \n",
+ "23 NaN NaN \n",
+ "24 NaN NaN \n",
+ "25 NaN 0.277491 \n",
+ "26 NaN 0.754119 \n",
+ "27 NaN 1.787487 \n",
+ "28 NaN NaN \n",
+ "29 0.450000 NaN \n",
+ "... ... ... \n",
+ "44216 NaN 1.047082 \n",
+ "44217 1.081280 NaN \n",
+ "44218 0.420034 NaN \n",
+ "44219 NaN NaN \n",
+ "44220 NaN 1.021275 \n",
+ "44221 NaN 0.672309 \n",
+ "44222 0.512835 NaN \n",
+ "44223 0.070711 NaN \n",
+ "44224 NaN 0.531351 \n",
+ "44225 NaN 0.199997 \n",
+ "44226 0.765195 NaN \n",
+ "44227 NaN 0.944674 \n",
+ "44228 NaN 1.175605 \n",
+ "44229 0.740570 NaN \n",
+ "44230 NaN NaN \n",
+ "44231 NaN NaN \n",
+ "44232 1.070456 NaN \n",
+ "44233 NaN 1.300803 \n",
+ "44234 NaN NaN \n",
+ "44235 NaN 1.056330 \n",
+ "44236 1.032930 NaN \n",
+ "44237 NaN 0.977118 \n",
+ "44238 NaN 0.759157 \n",
+ "44239 NaN 0.565688 \n",
+ "44240 NaN NaN \n",
+ "44241 NaN 0.668415 \n",
+ "44242 NaN 0.933605 \n",
+ "44243 NaN NaN \n",
+ "44244 NaN NaN \n",
+ "44245 1.147297 NaN \n",
+ "\n",
+ " temperature body_degC_223762_STD temperature body_degC_676_STD \\\n",
+ "0 NaN NaN \n",
+ "1 NaN NaN \n",
+ "2 NaN NaN \n",
+ "3 NaN NaN \n",
+ "4 NaN NaN \n",
+ "5 NaN NaN \n",
+ "6 0.790767 NaN \n",
+ "7 NaN NaN \n",
+ "8 NaN NaN \n",
+ "9 NaN NaN \n",
+ "10 NaN NaN \n",
+ "11 0.260705 NaN \n",
+ "12 NaN NaN \n",
+ "13 NaN 0.374646 \n",
+ "14 NaN NaN \n",
+ "15 NaN NaN \n",
+ "16 0.281265 NaN \n",
+ "17 NaN 0.401560 \n",
+ "18 NaN NaN \n",
+ "19 NaN NaN \n",
+ "20 NaN NaN \n",
+ "21 NaN NaN \n",
+ "22 NaN NaN \n",
+ "23 4.190574 NaN \n",
+ "24 NaN NaN \n",
+ "25 NaN NaN \n",
+ "26 NaN NaN \n",
+ "27 NaN NaN \n",
+ "28 NaN 0.300681 \n",
+ "29 NaN NaN \n",
+ "... ... ... \n",
+ "44216 NaN 0.997311 \n",
+ "44217 NaN NaN \n",
+ "44218 NaN NaN \n",
+ "44219 NaN NaN \n",
+ "44220 NaN NaN \n",
+ "44221 NaN NaN \n",
+ "44222 NaN NaN \n",
+ "44223 NaN NaN \n",
+ "44224 NaN NaN \n",
+ "44225 NaN NaN \n",
+ "44226 NaN NaN \n",
+ "44227 NaN 0.920982 \n",
+ "44228 NaN NaN \n",
+ "44229 NaN NaN \n",
+ "44230 NaN 0.332443 \n",
+ "44231 NaN 0.239964 \n",
+ "44232 NaN NaN \n",
+ "44233 NaN NaN \n",
+ "44234 0.688131 NaN \n",
+ "44235 NaN NaN \n",
+ "44236 NaN NaN \n",
+ "44237 NaN NaN \n",
+ "44238 NaN NaN \n",
+ "44239 NaN NaN \n",
+ "44240 NaN NaN \n",
+ "44241 NaN 0.378023 \n",
+ "44242 NaN NaN \n",
+ "44243 NaN 0.919241 \n",
+ "44244 NaN 1.159700 \n",
+ "44245 NaN NaN \n",
+ "\n",
+ " temperature body_degF_223761_COUNT temperature body_degF_678_COUNT \\\n",
+ "0 8.0 0.0 \n",
+ "1 3.0 0.0 \n",
+ "2 0.0 21.0 \n",
+ "3 0.0 12.0 \n",
+ "4 3.0 0.0 \n",
+ "5 6.0 0.0 \n",
+ "6 5.0 0.0 \n",
+ "7 0.0 2.0 \n",
+ "8 12.0 0.0 \n",
+ "9 2.0 0.0 \n",
+ "10 0.0 11.0 \n",
+ "11 0.0 0.0 \n",
+ "12 12.0 0.0 \n",
+ "13 0.0 1.0 \n",
+ "14 0.0 1.0 \n",
+ "15 2.0 0.0 \n",
+ "16 18.0 0.0 \n",
+ "17 0.0 0.0 \n",
+ "18 33.0 0.0 \n",
+ "19 0.0 1.0 \n",
+ "20 16.0 0.0 \n",
+ "21 5.0 0.0 \n",
+ "22 0.0 22.0 \n",
+ "23 0.0 0.0 \n",
+ "24 0.0 0.0 \n",
+ "25 0.0 5.0 \n",
+ "26 0.0 24.0 \n",
+ "27 0.0 10.0 \n",
+ "28 0.0 0.0 \n",
+ "29 4.0 0.0 \n",
+ "... ... ... \n",
+ "44216 0.0 37.0 \n",
+ "44217 4.0 0.0 \n",
+ "44218 8.0 0.0 \n",
+ "44219 0.0 1.0 \n",
+ "44220 0.0 5.0 \n",
+ "44221 0.0 5.0 \n",
+ "44222 5.0 0.0 \n",
+ "44223 2.0 0.0 \n",
+ "44224 0.0 10.0 \n",
+ "44225 0.0 4.0 \n",
+ "44226 15.0 0.0 \n",
+ "44227 0.0 32.0 \n",
+ "44228 0.0 19.0 \n",
+ "44229 10.0 0.0 \n",
+ "44230 0.0 0.0 \n",
+ "44231 0.0 0.0 \n",
+ "44232 32.0 0.0 \n",
+ "44233 0.0 130.0 \n",
+ "44234 0.0 0.0 \n",
+ "44235 0.0 4.0 \n",
+ "44236 9.0 0.0 \n",
+ "44237 0.0 7.0 \n",
+ "44238 0.0 14.0 \n",
+ "44239 0.0 2.0 \n",
+ "44240 1.0 0.0 \n",
+ "44241 0.0 10.0 \n",
+ "44242 0.0 21.0 \n",
+ "44243 0.0 0.0 \n",
+ "44244 0.0 0.0 \n",
+ "44245 20.0 0.0 \n",
+ "\n",
+ " temperature body_degC_223762_COUNT temperature body_degC_676_COUNT \\\n",
+ "0 0.0 0.0 \n",
+ "1 0.0 0.0 \n",
+ "2 0.0 0.0 \n",
+ "3 0.0 0.0 \n",
+ "4 0.0 0.0 \n",
+ "5 0.0 0.0 \n",
+ "6 34.0 0.0 \n",
+ "7 0.0 0.0 \n",
+ "8 0.0 0.0 \n",
+ "9 0.0 0.0 \n",
+ "10 0.0 0.0 \n",
+ "11 14.0 0.0 \n",
+ "12 0.0 0.0 \n",
+ "13 0.0 106.0 \n",
+ "14 0.0 0.0 \n",
+ "15 0.0 0.0 \n",
+ "16 41.0 0.0 \n",
+ "17 0.0 32.0 \n",
+ "18 0.0 0.0 \n",
+ "19 0.0 0.0 \n",
+ "20 0.0 0.0 \n",
+ "21 0.0 0.0 \n",
+ "22 0.0 0.0 \n",
+ "23 11.0 0.0 \n",
+ "24 0.0 1.0 \n",
+ "25 0.0 0.0 \n",
+ "26 0.0 0.0 \n",
+ "27 0.0 0.0 \n",
+ "28 0.0 19.0 \n",
+ "29 0.0 0.0 \n",
+ "... ... ... \n",
+ "44216 0.0 46.0 \n",
+ "44217 0.0 0.0 \n",
+ "44218 0.0 0.0 \n",
+ "44219 0.0 0.0 \n",
+ "44220 0.0 0.0 \n",
+ "44221 0.0 0.0 \n",
+ "44222 0.0 0.0 \n",
+ "44223 0.0 0.0 \n",
+ "44224 0.0 0.0 \n",
+ "44225 0.0 0.0 \n",
+ "44226 0.0 0.0 \n",
+ "44227 0.0 61.0 \n",
+ "44228 0.0 0.0 \n",
+ "44229 0.0 0.0 \n",
+ "44230 0.0 108.0 \n",
+ "44231 0.0 14.0 \n",
+ "44232 0.0 0.0 \n",
+ "44233 0.0 0.0 \n",
+ "44234 15.0 0.0 \n",
+ "44235 0.0 0.0 \n",
+ "44236 0.0 0.0 \n",
+ "44237 0.0 0.0 \n",
+ "44238 0.0 0.0 \n",
+ "44239 0.0 0.0 \n",
+ "44240 1.0 0.0 \n",
+ "44241 0.0 193.0 \n",
+ "44242 0.0 0.0 \n",
+ "44243 0.0 2.0 \n",
+ "44244 0.0 21.0 \n",
+ "44245 0.0 0.0 \n",
+ "\n",
+ " temperature body_degF_223761_LAST temperature body_degF_678_LAST \\\n",
+ "0 98.0 NaN \n",
+ "1 95.9 NaN \n",
+ "2 NaN 97.000000 \n",
+ "3 NaN 95.699997 \n",
+ "4 98.6 NaN \n",
+ "5 100.2 NaN \n",
+ "6 NaN NaN \n",
+ "7 NaN 101.199997 \n",
+ "8 97.4 NaN \n",
+ "9 96.6 NaN \n",
+ "10 NaN 98.500000 \n",
+ "11 NaN NaN \n",
+ "12 98.8 NaN \n",
+ "13 NaN NaN \n",
+ "14 NaN 95.300003 \n",
+ "15 98.6 NaN \n",
+ "16 NaN NaN \n",
+ "17 NaN NaN \n",
+ "18 98.6 NaN \n",
+ "19 NaN 98.800003 \n",
+ "20 97.6 NaN \n",
+ "21 97.8 NaN \n",
+ "22 NaN 97.800003 \n",
+ "23 NaN NaN \n",
+ "24 NaN NaN \n",
+ "25 NaN 97.199997 \n",
+ "26 NaN 97.000000 \n",
+ "27 NaN 94.000000 \n",
+ "28 NaN NaN \n",
+ "29 96.9 NaN \n",
+ "... ... ... \n",
+ "44216 NaN 96.000000 \n",
+ "44217 97.1 NaN \n",
+ "44218 96.3 NaN \n",
+ "44219 NaN 97.800003 \n",
+ "44220 NaN 94.099998 \n",
+ "44221 NaN 97.099998 \n",
+ "44222 99.8 NaN \n",
+ "44223 98.4 NaN \n",
+ "44224 NaN 97.800003 \n",
+ "44225 NaN 97.800003 \n",
+ "44226 98.7 NaN \n",
+ "44227 NaN NaN \n",
+ "44228 NaN 98.000000 \n",
+ "44229 96.9 NaN \n",
+ "44230 NaN NaN \n",
+ "44231 NaN NaN \n",
+ "44232 100.0 NaN \n",
+ "44233 NaN 97.900002 \n",
+ "44234 NaN NaN \n",
+ "44235 NaN 95.599998 \n",
+ "44236 98.4 NaN \n",
+ "44237 NaN 95.900002 \n",
+ "44238 NaN 96.599998 \n",
+ "44239 NaN 95.000000 \n",
+ "44240 NaN NaN \n",
+ "44241 NaN 98.699997 \n",
+ "44242 NaN 99.400002 \n",
+ "44243 NaN NaN \n",
+ "44244 NaN NaN \n",
+ "44245 97.8 NaN \n",
+ "\n",
+ " temperature body_degC_223762_LAST temperature body_degC_676_LAST \n",
+ "0 NaN NaN \n",
+ "1 NaN NaN \n",
+ "2 NaN NaN \n",
+ "3 NaN NaN \n",
+ "4 NaN NaN \n",
+ "5 NaN NaN \n",
+ "6 34.5 NaN \n",
+ "7 NaN NaN \n",
+ "8 NaN NaN \n",
+ "9 NaN NaN \n",
+ "10 NaN NaN \n",
+ "11 36.6 NaN \n",
+ "12 NaN NaN \n",
+ "13 NaN 36.599998 \n",
+ "14 NaN NaN \n",
+ "15 NaN NaN \n",
+ "16 37.5 NaN \n",
+ "17 NaN 36.799999 \n",
+ "18 NaN NaN \n",
+ "19 NaN NaN \n",
+ "20 NaN NaN \n",
+ "21 NaN NaN \n",
+ "22 NaN NaN \n",
+ "23 28.4 NaN \n",
+ "24 NaN 36.799999 \n",
+ "25 NaN NaN \n",
+ "26 NaN NaN \n",
+ "27 NaN NaN \n",
+ "28 NaN 36.200001 \n",
+ "29 NaN NaN \n",
+ "... ... ... \n",
+ "44216 NaN NaN \n",
+ "44217 NaN NaN \n",
+ "44218 NaN NaN \n",
+ "44219 NaN NaN \n",
+ "44220 NaN NaN \n",
+ "44221 NaN NaN \n",
+ "44222 NaN NaN \n",
+ "44223 NaN NaN \n",
+ "44224 NaN NaN \n",
+ "44225 NaN NaN \n",
+ "44226 NaN NaN \n",
+ "44227 NaN 34.500000 \n",
+ "44228 NaN NaN \n",
+ "44229 NaN NaN \n",
+ "44230 NaN 37.299999 \n",
+ "44231 NaN 35.599998 \n",
+ "44232 NaN NaN \n",
+ "44233 NaN NaN \n",
+ "44234 35.0 NaN \n",
+ "44235 NaN NaN \n",
+ "44236 NaN NaN \n",
+ "44237 NaN NaN \n",
+ "44238 NaN NaN \n",
+ "44239 NaN NaN \n",
+ "44240 34.8 NaN \n",
+ "44241 NaN NaN \n",
+ "44242 NaN NaN \n",
+ "44243 NaN 35.099998 \n",
+ "44244 NaN 34.700001 \n",
+ "44245 NaN NaN \n",
+ "\n",
+ "[44246 rows x 16 columns]"
+ ]
+ },
+ "execution_count": 233,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "feature_df"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 120,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "test_mapper_pipeline = Pipeline([\n",
+ " ('ft_mapper',mapped_ft)\n",
+ " ])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 121,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>temperature body_known_qn_degF_223761_MEAN</th>\n",
+ " <th>temperature body_known_qn_degF_678_MEAN</th>\n",
+ " <th>temperature body_known_qn_degF_223762(degC)_MEAN</th>\n",
+ " <th>temperature body_known_qn_degF_676(degC)_MEAN</th>\n",
+ " <th>temperature body_known_qn_degF_223761_STD</th>\n",
+ " <th>temperature body_known_qn_degF_678_STD</th>\n",
+ " <th>temperature body_known_qn_degF_223762(degC)_STD</th>\n",
+ " <th>temperature body_known_qn_degF_676(degC)_STD</th>\n",
+ " <th>temperature body_known_qn_degF_223761_COUNT</th>\n",
+ " <th>temperature body_known_qn_degF_678_COUNT</th>\n",
+ " <th>temperature body_known_qn_degF_223762(degC)_COUNT</th>\n",
+ " <th>temperature body_known_qn_degF_676(degC)_COUNT</th>\n",
+ " <th>temperature body_known_qn_degF_223761_LAST</th>\n",
+ " <th>temperature body_known_qn_degF_678_LAST</th>\n",
+ " <th>temperature body_known_qn_degF_223762(degC)_LAST</th>\n",
+ " <th>temperature body_known_qn_degF_676(degC)_LAST</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>98.537500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.537500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.537500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.537500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>97.166667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.166667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.166667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.166667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.533334</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.533334</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.533334</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.533334</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.591667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.591667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.591667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.591667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>98.100000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.100000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.100000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.100000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>5</th>\n",
+ " <td>98.550000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.550000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.550000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.550000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>6</th>\n",
+ " <td>98.380000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.721177</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.380000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.721177</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.380000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.721177</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.380000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.721177</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>7</th>\n",
+ " <td>NaN</td>\n",
+ " <td>100.649998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.649998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.649998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.649998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>8</th>\n",
+ " <td>97.975000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.975000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.975000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.975000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>9</th>\n",
+ " <td>96.050000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.050000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.050000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.050000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>10</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.536364</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.536364</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.536364</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.536364</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>11</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.481429</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.481429</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.481429</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.481429</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>12</th>\n",
+ " <td>99.466667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.466667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.466667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.466667</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>13</th>\n",
+ " <td>NaN</td>\n",
+ " <td>99.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.178868</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.178868</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.178868</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.099998</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.178868</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>14</th>\n",
+ " <td>NaN</td>\n",
+ " <td>95.300003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.300003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.300003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.300003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>15</th>\n",
+ " <td>98.500000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.500000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.500000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.500000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>16</th>\n",
+ " <td>100.772222</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.895122</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.772222</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.895122</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.772222</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.895122</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.772222</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.895122</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>17</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.948750</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.948750</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.948750</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.948750</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>18</th>\n",
+ " <td>99.345455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.345455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.345455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.345455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>19</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>20</th>\n",
+ " <td>98.312500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.312500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.312500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.312500</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>21</th>\n",
+ " <td>97.760000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.760000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.760000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.760000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>22</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.445455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.445455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.445455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.445455</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>23</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.983637</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.983637</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.983637</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.983637</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>24</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.239999</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.239999</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.239999</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.239999</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.320000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.320000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.320000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.320000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>26</th>\n",
+ " <td>NaN</td>\n",
+ " <td>96.700000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.700000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.700000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.700000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>27</th>\n",
+ " <td>NaN</td>\n",
+ " <td>96.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>28</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.325263</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.325263</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.325263</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.325263</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>29</th>\n",
+ " <td>96.525000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.525000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.525000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.525000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>...</th>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " <td>...</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44216</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.302703</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.639131</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.302703</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.639131</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.302703</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.639131</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.302703</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.639131</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44217</th>\n",
+ " <td>98.475000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.475000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.475000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.475000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44218</th>\n",
+ " <td>96.275000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.275000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.275000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.275000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44219</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.800003</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44220</th>\n",
+ " <td>NaN</td>\n",
+ " <td>95.740001</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.740001</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.740001</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.740001</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44221</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.920000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44222</th>\n",
+ " <td>99.240000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.240000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.240000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.240000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44223</th>\n",
+ " <td>98.450000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.450000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.450000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.450000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44224</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.130000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.130000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.130000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.130000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44225</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.900002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.900002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.900002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.900002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44226</th>\n",
+ " <td>99.753333</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.753333</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.753333</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.753333</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44227</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.071875</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.408525</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.071875</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.408525</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.071875</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.408525</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.071875</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.408525</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44228</th>\n",
+ " <td>NaN</td>\n",
+ " <td>100.526316</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.526316</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.526316</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.526316</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44229</th>\n",
+ " <td>97.580000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.580000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.580000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.580000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44230</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.398333</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.398333</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.398333</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.398333</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44231</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.928572</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.928572</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.928572</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.928572</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44232</th>\n",
+ " <td>98.484375</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.484375</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.484375</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.484375</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44233</th>\n",
+ " <td>NaN</td>\n",
+ " <td>100.278462</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.278462</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.278462</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>100.278462</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44234</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.112000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.112000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.112000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.112000</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44235</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.074999</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.074999</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.074999</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.074999</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44236</th>\n",
+ " <td>97.977778</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.977778</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.977778</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.977778</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44237</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.485713</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.485713</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.485713</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.485713</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44238</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.264285</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.264285</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.264285</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.264285</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44239</th>\n",
+ " <td>NaN</td>\n",
+ " <td>95.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.400002</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44240</th>\n",
+ " <td>95.800000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.640000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.800000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.640000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.800000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.640000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>95.800000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>94.640000</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44241</th>\n",
+ " <td>NaN</td>\n",
+ " <td>97.670000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.357306</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.670000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.357306</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.670000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.357306</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.670000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>99.357306</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44242</th>\n",
+ " <td>NaN</td>\n",
+ " <td>98.980953</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.980953</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.980953</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.980953</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44243</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.350000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.350000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.350000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>96.350000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44244</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.117143</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.117143</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.117143</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>97.117143</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>44245</th>\n",
+ " <td>98.655000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.655000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.655000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>98.655000</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "<p>44246 rows × 16 columns</p>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " temperature body_known_qn_degF_223761_MEAN \\\n",
+ "0 98.537500 \n",
+ "1 97.166667 \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 98.100000 \n",
+ "5 98.550000 \n",
+ "6 98.380000 \n",
+ "7 NaN \n",
+ "8 97.975000 \n",
+ "9 96.050000 \n",
+ "10 NaN \n",
+ "11 NaN \n",
+ "12 99.466667 \n",
+ "13 NaN \n",
+ "14 NaN \n",
+ "15 98.500000 \n",
+ "16 100.772222 \n",
+ "17 NaN \n",
+ "18 99.345455 \n",
+ "19 NaN \n",
+ "20 98.312500 \n",
+ "21 97.760000 \n",
+ "22 NaN \n",
+ "23 NaN \n",
+ "24 NaN \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 NaN \n",
+ "29 96.525000 \n",
+ "... ... \n",
+ "44216 NaN \n",
+ "44217 98.475000 \n",
+ "44218 96.275000 \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 99.240000 \n",
+ "44223 98.450000 \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 99.753333 \n",
+ "44227 NaN \n",
+ "44228 NaN \n",
+ "44229 97.580000 \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 98.484375 \n",
+ "44233 NaN \n",
+ "44234 NaN \n",
+ "44235 NaN \n",
+ "44236 97.977778 \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 95.800000 \n",
+ "44241 NaN \n",
+ "44242 NaN \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 98.655000 \n",
+ "\n",
+ " temperature body_known_qn_degF_678_MEAN \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 97.533334 \n",
+ "3 98.591667 \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 NaN \n",
+ "7 100.649998 \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 98.536364 \n",
+ "11 NaN \n",
+ "12 NaN \n",
+ "13 99.099998 \n",
+ "14 95.300003 \n",
+ "15 NaN \n",
+ "16 NaN \n",
+ "17 NaN \n",
+ "18 NaN \n",
+ "19 98.800003 \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 98.445455 \n",
+ "23 NaN \n",
+ "24 NaN \n",
+ "25 97.320000 \n",
+ "26 96.700000 \n",
+ "27 96.920000 \n",
+ "28 NaN \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 98.302703 \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 97.800003 \n",
+ "44220 95.740001 \n",
+ "44221 97.920000 \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 98.130000 \n",
+ "44225 97.900002 \n",
+ "44226 NaN \n",
+ "44227 98.071875 \n",
+ "44228 100.526316 \n",
+ "44229 NaN \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 NaN \n",
+ "44233 100.278462 \n",
+ "44234 NaN \n",
+ "44235 97.074999 \n",
+ "44236 NaN \n",
+ "44237 97.485713 \n",
+ "44238 97.264285 \n",
+ "44239 95.400002 \n",
+ "44240 NaN \n",
+ "44241 97.670000 \n",
+ "44242 98.980953 \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_223762(degC)_MEAN \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 97.721177 \n",
+ "7 NaN \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 NaN \n",
+ "11 97.481429 \n",
+ "12 NaN \n",
+ "13 NaN \n",
+ "14 NaN \n",
+ "15 NaN \n",
+ "16 99.895122 \n",
+ "17 NaN \n",
+ "18 NaN \n",
+ "19 NaN \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 NaN \n",
+ "23 94.983637 \n",
+ "24 NaN \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 NaN \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 NaN \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 NaN \n",
+ "44227 NaN \n",
+ "44228 NaN \n",
+ "44229 NaN \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 NaN \n",
+ "44233 NaN \n",
+ "44234 97.112000 \n",
+ "44235 NaN \n",
+ "44236 NaN \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 94.640000 \n",
+ "44241 NaN \n",
+ "44242 NaN \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_676(degC)_MEAN \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 NaN \n",
+ "7 NaN \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 NaN \n",
+ "11 NaN \n",
+ "12 NaN \n",
+ "13 98.178868 \n",
+ "14 NaN \n",
+ "15 NaN \n",
+ "16 NaN \n",
+ "17 98.948750 \n",
+ "18 NaN \n",
+ "19 NaN \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 NaN \n",
+ "23 NaN \n",
+ "24 98.239999 \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 98.325263 \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 98.639131 \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 NaN \n",
+ "44227 99.408525 \n",
+ "44228 NaN \n",
+ "44229 NaN \n",
+ "44230 99.398333 \n",
+ "44231 96.928572 \n",
+ "44232 NaN \n",
+ "44233 NaN \n",
+ "44234 NaN \n",
+ "44235 NaN \n",
+ "44236 NaN \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 NaN \n",
+ "44241 99.357306 \n",
+ "44242 NaN \n",
+ "44243 96.350000 \n",
+ "44244 97.117143 \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_223761_STD \\\n",
+ "0 98.537500 \n",
+ "1 97.166667 \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 98.100000 \n",
+ "5 98.550000 \n",
+ "6 98.380000 \n",
+ "7 NaN \n",
+ "8 97.975000 \n",
+ "9 96.050000 \n",
+ "10 NaN \n",
+ "11 NaN \n",
+ "12 99.466667 \n",
+ "13 NaN \n",
+ "14 NaN \n",
+ "15 98.500000 \n",
+ "16 100.772222 \n",
+ "17 NaN \n",
+ "18 99.345455 \n",
+ "19 NaN \n",
+ "20 98.312500 \n",
+ "21 97.760000 \n",
+ "22 NaN \n",
+ "23 NaN \n",
+ "24 NaN \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 NaN \n",
+ "29 96.525000 \n",
+ "... ... \n",
+ "44216 NaN \n",
+ "44217 98.475000 \n",
+ "44218 96.275000 \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 99.240000 \n",
+ "44223 98.450000 \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 99.753333 \n",
+ "44227 NaN \n",
+ "44228 NaN \n",
+ "44229 97.580000 \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 98.484375 \n",
+ "44233 NaN \n",
+ "44234 NaN \n",
+ "44235 NaN \n",
+ "44236 97.977778 \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 95.800000 \n",
+ "44241 NaN \n",
+ "44242 NaN \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 98.655000 \n",
+ "\n",
+ " temperature body_known_qn_degF_678_STD \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 97.533334 \n",
+ "3 98.591667 \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 NaN \n",
+ "7 100.649998 \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 98.536364 \n",
+ "11 NaN \n",
+ "12 NaN \n",
+ "13 99.099998 \n",
+ "14 95.300003 \n",
+ "15 NaN \n",
+ "16 NaN \n",
+ "17 NaN \n",
+ "18 NaN \n",
+ "19 98.800003 \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 98.445455 \n",
+ "23 NaN \n",
+ "24 NaN \n",
+ "25 97.320000 \n",
+ "26 96.700000 \n",
+ "27 96.920000 \n",
+ "28 NaN \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 98.302703 \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 97.800003 \n",
+ "44220 95.740001 \n",
+ "44221 97.920000 \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 98.130000 \n",
+ "44225 97.900002 \n",
+ "44226 NaN \n",
+ "44227 98.071875 \n",
+ "44228 100.526316 \n",
+ "44229 NaN \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 NaN \n",
+ "44233 100.278462 \n",
+ "44234 NaN \n",
+ "44235 97.074999 \n",
+ "44236 NaN \n",
+ "44237 97.485713 \n",
+ "44238 97.264285 \n",
+ "44239 95.400002 \n",
+ "44240 NaN \n",
+ "44241 97.670000 \n",
+ "44242 98.980953 \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_223762(degC)_STD \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 97.721177 \n",
+ "7 NaN \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 NaN \n",
+ "11 97.481429 \n",
+ "12 NaN \n",
+ "13 NaN \n",
+ "14 NaN \n",
+ "15 NaN \n",
+ "16 99.895122 \n",
+ "17 NaN \n",
+ "18 NaN \n",
+ "19 NaN \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 NaN \n",
+ "23 94.983637 \n",
+ "24 NaN \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 NaN \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 NaN \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 NaN \n",
+ "44227 NaN \n",
+ "44228 NaN \n",
+ "44229 NaN \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 NaN \n",
+ "44233 NaN \n",
+ "44234 97.112000 \n",
+ "44235 NaN \n",
+ "44236 NaN \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 94.640000 \n",
+ "44241 NaN \n",
+ "44242 NaN \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_676(degC)_STD \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 NaN \n",
+ "7 NaN \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 NaN \n",
+ "11 NaN \n",
+ "12 NaN \n",
+ "13 98.178868 \n",
+ "14 NaN \n",
+ "15 NaN \n",
+ "16 NaN \n",
+ "17 98.948750 \n",
+ "18 NaN \n",
+ "19 NaN \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 NaN \n",
+ "23 NaN \n",
+ "24 98.239999 \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 98.325263 \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 98.639131 \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 NaN \n",
+ "44227 99.408525 \n",
+ "44228 NaN \n",
+ "44229 NaN \n",
+ "44230 99.398333 \n",
+ "44231 96.928572 \n",
+ "44232 NaN \n",
+ "44233 NaN \n",
+ "44234 NaN \n",
+ "44235 NaN \n",
+ "44236 NaN \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 NaN \n",
+ "44241 99.357306 \n",
+ "44242 NaN \n",
+ "44243 96.350000 \n",
+ "44244 97.117143 \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_223761_COUNT \\\n",
+ "0 98.537500 \n",
+ "1 97.166667 \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 98.100000 \n",
+ "5 98.550000 \n",
+ "6 98.380000 \n",
+ "7 NaN \n",
+ "8 97.975000 \n",
+ "9 96.050000 \n",
+ "10 NaN \n",
+ "11 NaN \n",
+ "12 99.466667 \n",
+ "13 NaN \n",
+ "14 NaN \n",
+ "15 98.500000 \n",
+ "16 100.772222 \n",
+ "17 NaN \n",
+ "18 99.345455 \n",
+ "19 NaN \n",
+ "20 98.312500 \n",
+ "21 97.760000 \n",
+ "22 NaN \n",
+ "23 NaN \n",
+ "24 NaN \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 NaN \n",
+ "29 96.525000 \n",
+ "... ... \n",
+ "44216 NaN \n",
+ "44217 98.475000 \n",
+ "44218 96.275000 \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 99.240000 \n",
+ "44223 98.450000 \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 99.753333 \n",
+ "44227 NaN \n",
+ "44228 NaN \n",
+ "44229 97.580000 \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 98.484375 \n",
+ "44233 NaN \n",
+ "44234 NaN \n",
+ "44235 NaN \n",
+ "44236 97.977778 \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 95.800000 \n",
+ "44241 NaN \n",
+ "44242 NaN \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 98.655000 \n",
+ "\n",
+ " temperature body_known_qn_degF_678_COUNT \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 97.533334 \n",
+ "3 98.591667 \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 NaN \n",
+ "7 100.649998 \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 98.536364 \n",
+ "11 NaN \n",
+ "12 NaN \n",
+ "13 99.099998 \n",
+ "14 95.300003 \n",
+ "15 NaN \n",
+ "16 NaN \n",
+ "17 NaN \n",
+ "18 NaN \n",
+ "19 98.800003 \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 98.445455 \n",
+ "23 NaN \n",
+ "24 NaN \n",
+ "25 97.320000 \n",
+ "26 96.700000 \n",
+ "27 96.920000 \n",
+ "28 NaN \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 98.302703 \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 97.800003 \n",
+ "44220 95.740001 \n",
+ "44221 97.920000 \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 98.130000 \n",
+ "44225 97.900002 \n",
+ "44226 NaN \n",
+ "44227 98.071875 \n",
+ "44228 100.526316 \n",
+ "44229 NaN \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 NaN \n",
+ "44233 100.278462 \n",
+ "44234 NaN \n",
+ "44235 97.074999 \n",
+ "44236 NaN \n",
+ "44237 97.485713 \n",
+ "44238 97.264285 \n",
+ "44239 95.400002 \n",
+ "44240 NaN \n",
+ "44241 97.670000 \n",
+ "44242 98.980953 \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_223762(degC)_COUNT \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 97.721177 \n",
+ "7 NaN \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 NaN \n",
+ "11 97.481429 \n",
+ "12 NaN \n",
+ "13 NaN \n",
+ "14 NaN \n",
+ "15 NaN \n",
+ "16 99.895122 \n",
+ "17 NaN \n",
+ "18 NaN \n",
+ "19 NaN \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 NaN \n",
+ "23 94.983637 \n",
+ "24 NaN \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 NaN \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 NaN \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 NaN \n",
+ "44227 NaN \n",
+ "44228 NaN \n",
+ "44229 NaN \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 NaN \n",
+ "44233 NaN \n",
+ "44234 97.112000 \n",
+ "44235 NaN \n",
+ "44236 NaN \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 94.640000 \n",
+ "44241 NaN \n",
+ "44242 NaN \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_676(degC)_COUNT \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 NaN \n",
+ "7 NaN \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 NaN \n",
+ "11 NaN \n",
+ "12 NaN \n",
+ "13 98.178868 \n",
+ "14 NaN \n",
+ "15 NaN \n",
+ "16 NaN \n",
+ "17 98.948750 \n",
+ "18 NaN \n",
+ "19 NaN \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 NaN \n",
+ "23 NaN \n",
+ "24 98.239999 \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 98.325263 \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 98.639131 \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 NaN \n",
+ "44227 99.408525 \n",
+ "44228 NaN \n",
+ "44229 NaN \n",
+ "44230 99.398333 \n",
+ "44231 96.928572 \n",
+ "44232 NaN \n",
+ "44233 NaN \n",
+ "44234 NaN \n",
+ "44235 NaN \n",
+ "44236 NaN \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 NaN \n",
+ "44241 99.357306 \n",
+ "44242 NaN \n",
+ "44243 96.350000 \n",
+ "44244 97.117143 \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_223761_LAST \\\n",
+ "0 98.537500 \n",
+ "1 97.166667 \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 98.100000 \n",
+ "5 98.550000 \n",
+ "6 98.380000 \n",
+ "7 NaN \n",
+ "8 97.975000 \n",
+ "9 96.050000 \n",
+ "10 NaN \n",
+ "11 NaN \n",
+ "12 99.466667 \n",
+ "13 NaN \n",
+ "14 NaN \n",
+ "15 98.500000 \n",
+ "16 100.772222 \n",
+ "17 NaN \n",
+ "18 99.345455 \n",
+ "19 NaN \n",
+ "20 98.312500 \n",
+ "21 97.760000 \n",
+ "22 NaN \n",
+ "23 NaN \n",
+ "24 NaN \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 NaN \n",
+ "29 96.525000 \n",
+ "... ... \n",
+ "44216 NaN \n",
+ "44217 98.475000 \n",
+ "44218 96.275000 \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 99.240000 \n",
+ "44223 98.450000 \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 99.753333 \n",
+ "44227 NaN \n",
+ "44228 NaN \n",
+ "44229 97.580000 \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 98.484375 \n",
+ "44233 NaN \n",
+ "44234 NaN \n",
+ "44235 NaN \n",
+ "44236 97.977778 \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 95.800000 \n",
+ "44241 NaN \n",
+ "44242 NaN \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 98.655000 \n",
+ "\n",
+ " temperature body_known_qn_degF_678_LAST \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 97.533334 \n",
+ "3 98.591667 \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 NaN \n",
+ "7 100.649998 \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 98.536364 \n",
+ "11 NaN \n",
+ "12 NaN \n",
+ "13 99.099998 \n",
+ "14 95.300003 \n",
+ "15 NaN \n",
+ "16 NaN \n",
+ "17 NaN \n",
+ "18 NaN \n",
+ "19 98.800003 \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 98.445455 \n",
+ "23 NaN \n",
+ "24 NaN \n",
+ "25 97.320000 \n",
+ "26 96.700000 \n",
+ "27 96.920000 \n",
+ "28 NaN \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 98.302703 \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 97.800003 \n",
+ "44220 95.740001 \n",
+ "44221 97.920000 \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 98.130000 \n",
+ "44225 97.900002 \n",
+ "44226 NaN \n",
+ "44227 98.071875 \n",
+ "44228 100.526316 \n",
+ "44229 NaN \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 NaN \n",
+ "44233 100.278462 \n",
+ "44234 NaN \n",
+ "44235 97.074999 \n",
+ "44236 NaN \n",
+ "44237 97.485713 \n",
+ "44238 97.264285 \n",
+ "44239 95.400002 \n",
+ "44240 NaN \n",
+ "44241 97.670000 \n",
+ "44242 98.980953 \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_223762(degC)_LAST \\\n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 97.721177 \n",
+ "7 NaN \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 NaN \n",
+ "11 97.481429 \n",
+ "12 NaN \n",
+ "13 NaN \n",
+ "14 NaN \n",
+ "15 NaN \n",
+ "16 99.895122 \n",
+ "17 NaN \n",
+ "18 NaN \n",
+ "19 NaN \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 NaN \n",
+ "23 94.983637 \n",
+ "24 NaN \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 NaN \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 NaN \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 NaN \n",
+ "44227 NaN \n",
+ "44228 NaN \n",
+ "44229 NaN \n",
+ "44230 NaN \n",
+ "44231 NaN \n",
+ "44232 NaN \n",
+ "44233 NaN \n",
+ "44234 97.112000 \n",
+ "44235 NaN \n",
+ "44236 NaN \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 94.640000 \n",
+ "44241 NaN \n",
+ "44242 NaN \n",
+ "44243 NaN \n",
+ "44244 NaN \n",
+ "44245 NaN \n",
+ "\n",
+ " temperature body_known_qn_degF_676(degC)_LAST \n",
+ "0 NaN \n",
+ "1 NaN \n",
+ "2 NaN \n",
+ "3 NaN \n",
+ "4 NaN \n",
+ "5 NaN \n",
+ "6 NaN \n",
+ "7 NaN \n",
+ "8 NaN \n",
+ "9 NaN \n",
+ "10 NaN \n",
+ "11 NaN \n",
+ "12 NaN \n",
+ "13 98.178868 \n",
+ "14 NaN \n",
+ "15 NaN \n",
+ "16 NaN \n",
+ "17 98.948750 \n",
+ "18 NaN \n",
+ "19 NaN \n",
+ "20 NaN \n",
+ "21 NaN \n",
+ "22 NaN \n",
+ "23 NaN \n",
+ "24 98.239999 \n",
+ "25 NaN \n",
+ "26 NaN \n",
+ "27 NaN \n",
+ "28 98.325263 \n",
+ "29 NaN \n",
+ "... ... \n",
+ "44216 98.639131 \n",
+ "44217 NaN \n",
+ "44218 NaN \n",
+ "44219 NaN \n",
+ "44220 NaN \n",
+ "44221 NaN \n",
+ "44222 NaN \n",
+ "44223 NaN \n",
+ "44224 NaN \n",
+ "44225 NaN \n",
+ "44226 NaN \n",
+ "44227 99.408525 \n",
+ "44228 NaN \n",
+ "44229 NaN \n",
+ "44230 99.398333 \n",
+ "44231 96.928572 \n",
+ "44232 NaN \n",
+ "44233 NaN \n",
+ "44234 NaN \n",
+ "44235 NaN \n",
+ "44236 NaN \n",
+ "44237 NaN \n",
+ "44238 NaN \n",
+ "44239 NaN \n",
+ "44240 NaN \n",
+ "44241 99.357306 \n",
+ "44242 NaN \n",
+ "44243 96.350000 \n",
+ "44244 97.117143 \n",
+ "44245 NaN \n",
+ "\n",
+ "[44246 rows x 16 columns]"
+ ]
+ },
+ "execution_count": 121,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "test_mapper_pipeline.transform(df)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 152,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<units.MedicalUreg at 0x31082eb8>"
+ ]
+ },
+ "execution_count": 152,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "ureg"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 197,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "mass = ureg.parse_units('degF')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 198,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<UnitsContainer({'[temperature]': 1.0})>"
+ ]
+ },
+ "execution_count": 198,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "mass.dimensionality"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 157,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "from pint.unit import UnitsContainer"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 160,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "True"
+ ]
+ },
+ "execution_count": 160,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "units.dimensionality == UnitsContainer({'[length]':3.0})"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 166,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "1e-06 kilogram"
+ ],
+ "text/latex": [
+ "$1e-06\\ \\mathrm{kilogram}$"
+ ],
+ "text/plain": [
+ "<Quantity(1e-06, 'kilogram')>"
+ ]
+ },
+ "execution_count": 166,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "(1*units).to_base_units()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 161,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "uc = UnitsContainer({'[length]':3.0})"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "uc.dim"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "import constants\n",
+ "import mimic\n",
+ "import utils\n",
+ "import pandas as pd\n",
+ "import icu_data_defs\n",
+ "import units\n",
+ "from sklearn.pipeline import Pipeline\n",
+ "import transformers\n",
+ "import logger\n",
+ "import features\n",
+ "import warnings\n",
+ "warnings.filterwarnings('ignore')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload(mimic)\n",
+ "reload(units)\n",
+ "reload(utils)\n",
+ "reload(transformers)\n",
+ "def mimic_ETL(components,data_dict,hdf5_fname,\n",
+ " hadm_ids=constants.ALL,\n",
+ " agg_func=lambda x:x.iloc[0]):\n",
+ " \n",
+ " logger.log('BEGIN ETL for {} admissions'.format(hadm_ids if hadm_ids == constants.ALL else len(hadm_ids)),new_level=True)\n",
+ " category_map = mimic.mimic_category_map(data_dict)\n",
+ " ureg = units.MedicalUreg()\n",
+ " extractor = mimic.mimic_extractor('config/mimic_item_map.csv',data_dict)\n",
+ " \n",
+ "\n",
+ " transform_pipeline = mimic.transform_pipeline()\n",
+ "\n",
+ " standard_clean_pipeline = Pipeline([\n",
+ " ('aggregate_same_datetime',transformers.same_index_aggregator(agg_func)),\n",
+ " ('split_dtype',transformers.split_dtype()),\n",
+ " ('standardize_columns',transformers.column_standardizer(data_dict,ureg)),\n",
+ " ('standardize_categories',transformers.standardize_categories(data_dict,category_map)),\n",
+ " ('split_bad_categories',transformers.split_bad_categories(data_dict)),\n",
+ " ('one_hotter',transformers.nominal_to_onehot()),\n",
+ " ('drop_oob_values',transformers.oob_value_remover(data_dict))\n",
+ " ])\n",
+ " \n",
+ "\n",
+ " logger.log('Extract CONTEXT...')\n",
+ " df_context = mimic.get_context_data(hadm_ids)\n",
+ " utils.save_df(df_context,hdf5_fname,'context')\n",
+ "\n",
+ " \n",
+ " for component in components:\n",
+ " logger.log(component.upper(),new_level=True)\n",
+ " \n",
+ " logger.log(\"Extracting...\",new_level=True)\n",
+ " df_extracted = extractor.extract_component(component,hadm_ids)\n",
+ " utils.save_df(df_extracted,hdf5_fname,'extracted/{}'.format(component))\n",
+ " logger.end_log_level()\n",
+ " \n",
+ " display(df_extracted.head())\n",
+ " \n",
+ " logger.log(\"Transforming... {}\".format(df_extracted.shape))\n",
+ " transform_pipeline.set_params(add_level__level_val=component)\n",
+ " df_transformed = transform_pipeline.transform(df_extracted)\n",
+ " utils.save_df(df_transformed,hdf5_fname,'transformed/{}'.format(component))\n",
+ "\n",
+ " display(df_transformed.head())\n",
+ "\n",
+ " display(df_transformed.describe())\n",
+ "\n",
+ " print utils.data_loss(df_extracted.set_index('id').value.to_frame(),df_transformed)\n",
+ " \n",
+ " logger.log(\"Cleaning... {}\".format(df_transformed.shape)) \n",
+ " df_cleaned = standard_clean_pipeline.transform(df_transformed)\n",
+ " utils.save_df(df_cleaned,hdf5_fname,'cleaned/{}'.format(component))\n",
+ " \n",
+ " display(df_cleaned.head())\n",
+ "\n",
+ " display(df_cleaned.describe())\n",
+ "\n",
+ " print utils.data_loss(df_extracted.set_index('id').value.to_frame(),df_cleaned)\n",
+ " \n",
+ " del df_cleaned,df_transformed,df_extracted\n",
+ " logger.end_log_level()\n",
+ " \n",
+ " \n",
+ " \n",
+ " logger.end_log()\n",
+ " \n",
+ " return\n",
+ " \n",
+ "\n",
+ "def mimic_features(hdf5_fname,specific_path,labels,\n",
+ " custom_cleaners,segmenter,feature_tuples):\n",
+ " \n",
+ " \n",
+ " df_all = None\n",
+ " \n",
+ " for label in labels:\n",
+ " df_base = utils.open_df(hdf5_fname,'cleaned/{}'.format(label))\n",
+ " \n",
+ " df_cleaned = custom_cleaners.transform(df_base)\n",
+ " utils.save_df(df_cleaned,hdf5_fname,'{}/cleaned/{}'.format(specific_path,label))\n",
+ " \n",
+ " if df_all is None:\n",
+ " df_all = df_cleaned\n",
+ " else:\n",
+ " df_all = df_all.join(df_cleaned,how='outer')\n",
+ " del df_cleaned\n",
+ " \n",
+ " utils.save_df(df_all,hdf5_fname,'{}/cleaned/all')\n",
+ " \n",
+ " df_segmented = segmenter.transform(df_all)\n",
+ " utils.save_df(df_segmented,hdf5_fname_target,'{}/segmented'.format(specific_path))\n",
+ " del df_all\n",
+ " \n",
+ " mapped_ft = features.make_mapper(feature_tuples,df_segmented)\n",
+ " df_features = mapped_ft.transform(df_segmented)\n",
+ " utils.save_df(df_features,hdf5_fname_target,'{}/features'.format(specific_path))\n",
+ " del df_segmented\n",
+ " \n",
+ " return df_features"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 37,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "def do_ETL(data_dict,components,tag,n,seed=42):\n",
+ " hdf5_fname = 'data/mimic_{}_{}'.format(tag,n)\n",
+ " hadm_ids = n if n == constants.ALL else mimic.sample_hadm_ids(n,seed) \n",
+ " mimic_ETL(components,data_dict,hdf5_fname,hadm_ids=hadm_ids)\n",
+ " return hdf5_fname"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 43,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "reload(logger)\n",
+ "\n",
+ "data_dict = icu_data_defs.data_dictionary('config/data_definitions.xlsx')\n",
+ "components = data_dict.get_panel_defintions(12).component.unique().tolist() #12 is \"simple data\"\n",
+ "tag = 'simple'"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 40,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-20 10:03:09) BEGIN ETL for 1000 admissions\n",
+ "(2017-06-20 10:03:09)>> Extract CONTEXT...\n",
+ "(2017-06-20 10:03:17)<< DONE (8.0s)\n",
+ "(2017-06-20 10:03:17)>> BLOOD PRESSURE SYSTOLIC\n",
+ "(2017-06-20 10:03:17)>>>> Extracting...\n",
+ "(2017-06-20 10:03:17)>>>>>> Extracting 14 items from chartevents\n",
+ "51 35823\n",
+ "455 26680\n",
+ "220179 21957\n",
+ "220050 15186\n",
+ "3313 2250\n",
+ "225309 1251\n",
+ "3315 50\n",
+ "3317 24\n",
+ "3323 21\n",
+ "442 19\n",
+ "3321 19\n",
+ "224167 12\n",
+ "227243 8\n",
+ "Name: itemid, dtype: int64\n",
+ "Empty DataFrame\n",
+ "Columns: [id, datetime, value, units, itemid]\n",
+ "Index: []\n",
+ "(2017-06-20 10:04:09)<<<<<< DONE (52.0s)\n",
+ "(2017-06-20 10:04:09)>>>>>> Combine DF\n",
+ "(2017-06-20 10:04:09)<<<<<< DONE (0.0s)\n",
+ "(2017-06-20 10:04:09)>>>>>> Clean UOM\n",
+ "(2017-06-20 10:04:10)<<<<<< DONE (1.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th>value</th>\n",
+ " <th>units</th>\n",
+ " <th>itemid</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>0</th>\n",
+ " <td>107880</td>\n",
+ " <td>2106-06-19 22:00:00</td>\n",
+ " <td>99</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>1</th>\n",
+ " <td>107880</td>\n",
+ " <td>2106-06-19 23:00:00</td>\n",
+ " <td>98</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2</th>\n",
+ " <td>107880</td>\n",
+ " <td>2106-06-20 00:00:00</td>\n",
+ " <td>122</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>3</th>\n",
+ " <td>107880</td>\n",
+ " <td>2106-06-20 01:00:00</td>\n",
+ " <td>150</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>4</th>\n",
+ " <td>107880</td>\n",
+ " <td>2106-06-20 02:00:00</td>\n",
+ " <td>133</td>\n",
+ " <td>mmHg</td>\n",
+ " <td>51</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " id datetime value units itemid\n",
+ "0 107880 2106-06-19 22:00:00 99 mmHg 51\n",
+ "1 107880 2106-06-19 23:00:00 98 mmHg 51\n",
+ "2 107880 2106-06-20 00:00:00 122 mmHg 51\n",
+ "3 107880 2106-06-20 01:00:00 150 mmHg 51\n",
+ "4 107880 2106-06-20 02:00:00 133 mmHg 51"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-20 10:04:10)<<<< DONE (53.0s)\n",
+ "(2017-06-20 10:04:10)>>>> Transforming... (103300, 5)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>component</th>\n",
+ " <th colspan=\"13\" halign=\"left\">blood pressure systolic</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th>cc/min</th>\n",
+ " <th colspan=\"5\" halign=\"left\">mmHg</th>\n",
+ " <th colspan=\"4\" halign=\"left\">cc/min</th>\n",
+ " <th colspan=\"3\" halign=\"left\">mmHg</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>3313</th>\n",
+ " <th>455</th>\n",
+ " <th>51</th>\n",
+ " <th>220179</th>\n",
+ " <th>442</th>\n",
+ " <th>220050</th>\n",
+ " <th>3315</th>\n",
+ " <th>3317</th>\n",
+ " <th>3321</th>\n",
+ " <th>3323</th>\n",
+ " <th>224167</th>\n",
+ " <th>227243</th>\n",
+ " <th>225309</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100304</th>\n",
+ " <th>2161-10-01 22:00:00</th>\n",
+ " <td>67</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2161-10-01 23:00:00</th>\n",
+ " <td>68</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">100788</th>\n",
+ " <th>2120-04-10 14:00:00</th>\n",
+ " <td>None</td>\n",
+ " <td>127</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2120-04-10 15:00:00</th>\n",
+ " <td>None</td>\n",
+ " <td>127</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2120-04-10 16:00:00</th>\n",
+ " <td>None</td>\n",
+ " <td>123</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " <td>None</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "component blood pressure systolic \\\n",
+ "units cc/min mmHg \n",
+ "description 3313 455 51 220179 \n",
+ "id datetime \n",
+ "100304 2161-10-01 22:00:00 67 None None None \n",
+ " 2161-10-01 23:00:00 68 None None None \n",
+ "100788 2120-04-10 14:00:00 None 127 None None \n",
+ " 2120-04-10 15:00:00 None 127 None None \n",
+ " 2120-04-10 16:00:00 None 123 None None \n",
+ "\n",
+ "component \\\n",
+ "units cc/min mmHg \n",
+ "description 442 220050 3315 3317 3321 3323 224167 \n",
+ "id datetime \n",
+ "100304 2161-10-01 22:00:00 None None None None None None None \n",
+ " 2161-10-01 23:00:00 None None None None None None None \n",
+ "100788 2120-04-10 14:00:00 None None None None None None None \n",
+ " 2120-04-10 15:00:00 None None None None None None None \n",
+ " 2120-04-10 16:00:00 None None None None None None None \n",
+ "\n",
+ "component \n",
+ "units \n",
+ "description 227243 225309 \n",
+ "id datetime \n",
+ "100304 2161-10-01 22:00:00 None None \n",
+ " 2161-10-01 23:00:00 None None \n",
+ "100788 2120-04-10 14:00:00 None None \n",
+ " 2120-04-10 15:00:00 None None \n",
+ " 2120-04-10 16:00:00 None None "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>component</th>\n",
+ " <th colspan=\"13\" halign=\"left\">blood pressure systolic</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th>cc/min</th>\n",
+ " <th colspan=\"5\" halign=\"left\">mmHg</th>\n",
+ " <th colspan=\"4\" halign=\"left\">cc/min</th>\n",
+ " <th colspan=\"3\" halign=\"left\">mmHg</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>3313</th>\n",
+ " <th>455</th>\n",
+ " <th>51</th>\n",
+ " <th>220179</th>\n",
+ " <th>442</th>\n",
+ " <th>220050</th>\n",
+ " <th>3315</th>\n",
+ " <th>3317</th>\n",
+ " <th>3321</th>\n",
+ " <th>3323</th>\n",
+ " <th>224167</th>\n",
+ " <th>227243</th>\n",
+ " <th>225309</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>2241</td>\n",
+ " <td>26480</td>\n",
+ " <td>35622</td>\n",
+ " <td>21957</td>\n",
+ " <td>17</td>\n",
+ " <td>15186</td>\n",
+ " <td>22</td>\n",
+ " <td>16</td>\n",
+ " <td>13</td>\n",
+ " <td>14</td>\n",
+ " <td>12</td>\n",
+ " <td>8</td>\n",
+ " <td>1251</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>unique</th>\n",
+ " <td>81</td>\n",
+ " <td>181</td>\n",
+ " <td>208</td>\n",
+ " <td>176</td>\n",
+ " <td>14</td>\n",
+ " <td>172</td>\n",
+ " <td>21</td>\n",
+ " <td>13</td>\n",
+ " <td>12</td>\n",
+ " <td>11</td>\n",
+ " <td>9</td>\n",
+ " <td>8</td>\n",
+ " <td>126</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>top</th>\n",
+ " <td>72</td>\n",
+ " <td>106</td>\n",
+ " <td>108</td>\n",
+ " <td>112</td>\n",
+ " <td>122</td>\n",
+ " <td>120</td>\n",
+ " <td>89</td>\n",
+ " <td>74</td>\n",
+ " <td>66</td>\n",
+ " <td>80</td>\n",
+ " <td>102</td>\n",
+ " <td>110</td>\n",
+ " <td>107</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>freq</th>\n",
+ " <td>91</td>\n",
+ " <td>494</td>\n",
+ " <td>641</td>\n",
+ " <td>457</td>\n",
+ " <td>2</td>\n",
+ " <td>296</td>\n",
+ " <td>2</td>\n",
+ " <td>2</td>\n",
+ " <td>2</td>\n",
+ " <td>2</td>\n",
+ " <td>4</td>\n",
+ " <td>1</td>\n",
+ " <td>41</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "component blood pressure systolic \\\n",
+ "units cc/min mmHg cc/min \n",
+ "description 3313 455 51 220179 442 220050 3315 \n",
+ "count 2241 26480 35622 21957 17 15186 22 \n",
+ "unique 81 181 208 176 14 172 21 \n",
+ "top 72 106 108 112 122 120 89 \n",
+ "freq 91 494 641 457 2 296 2 \n",
+ "\n",
+ "component \n",
+ "units mmHg \n",
+ "description 3317 3321 3323 224167 227243 225309 \n",
+ "count 16 13 14 12 8 1251 \n",
+ "unique 13 12 11 9 8 126 \n",
+ "top 74 66 80 102 110 107 \n",
+ "freq 2 2 2 4 1 41 "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "((103300, 1), (97535, 13), 461L, 2, '0.2094% records')\n",
+ "(2017-06-20 10:04:12)<<<< DONE (2.0s)\n",
+ "(2017-06-20 10:04:12)>>>> Cleaning... (97535, 13)\n",
+ "(2017-06-20 10:04:14)<<<< DONE (2.0s)\n",
+ "(2017-06-20 10:04:14)>>>> Nominal to OneHot\n",
+ "(2017-06-20 10:04:14)<<<< DONE (0.0s)\n",
+ "(2017-06-20 10:04:14)>>>> Drop OOB data | (97527, 13)\n",
+ "(2017-06-20 10:04:14)>>>>>> blood pressure systolic, mmHg, 100525\n",
+ "(2017-06-20 10:04:19)<<<<<< DONE (5.0s)\n",
+ "(2017-06-20 10:04:19)>>>>>> blood pressure systolic, cc/min, 2306\n",
+ "(2017-06-20 10:04:19)<<<<<< DONE (0.0s)\n"
+ ]
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>component</th>\n",
+ " <th colspan=\"13\" halign=\"left\">blood pressure systolic</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"8\" halign=\"left\">known</th>\n",
+ " <th colspan=\"5\" halign=\"left\">unknown</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"8\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"5\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"8\" halign=\"left\">mmHg</th>\n",
+ " <th colspan=\"5\" halign=\"left\">cc/min</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th></th>\n",
+ " <th>description</th>\n",
+ " <th>220050</th>\n",
+ " <th>220179</th>\n",
+ " <th>224167</th>\n",
+ " <th>225309</th>\n",
+ " <th>227243</th>\n",
+ " <th>442</th>\n",
+ " <th>455</th>\n",
+ " <th>51</th>\n",
+ " <th>3313</th>\n",
+ " <th>3315</th>\n",
+ " <th>3317</th>\n",
+ " <th>3321</th>\n",
+ " <th>3323</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>id</th>\n",
+ " <th>datetime</th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " <th></th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th rowspan=\"2\" valign=\"top\">100304</th>\n",
+ " <th>2161-10-01 22:00:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>67.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2161-10-01 23:00:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>68.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th rowspan=\"3\" valign=\"top\">100788</th>\n",
+ " <th>2120-04-10 14:00:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>127.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2120-04-10 15:00:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>127.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>2120-04-10 16:00:00</th>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>123.0</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " <td>NaN</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "component blood pressure systolic \\\n",
+ "status known \n",
+ "variable_type qn \n",
+ "units mmHg \n",
+ "description 220050 220179 224167 225309 \n",
+ "id datetime \n",
+ "100304 2161-10-01 22:00:00 NaN NaN NaN NaN \n",
+ " 2161-10-01 23:00:00 NaN NaN NaN NaN \n",
+ "100788 2120-04-10 14:00:00 NaN NaN NaN NaN \n",
+ " 2120-04-10 15:00:00 NaN NaN NaN NaN \n",
+ " 2120-04-10 16:00:00 NaN NaN NaN NaN \n",
+ "\n",
+ "component \n",
+ "status unknown \n",
+ "variable_type qn \n",
+ "units cc/min \n",
+ "description 227243 442 455 51 3313 3315 3317 3321 3323 \n",
+ "id datetime \n",
+ "100304 2161-10-01 22:00:00 NaN NaN NaN NaN 67.0 NaN NaN NaN NaN \n",
+ " 2161-10-01 23:00:00 NaN NaN NaN NaN 68.0 NaN NaN NaN NaN \n",
+ "100788 2120-04-10 14:00:00 NaN NaN 127.0 NaN NaN NaN NaN NaN NaN \n",
+ " 2120-04-10 15:00:00 NaN NaN 127.0 NaN NaN NaN NaN NaN NaN \n",
+ " 2120-04-10 16:00:00 NaN NaN 123.0 NaN NaN NaN NaN NaN NaN "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr>\n",
+ " <th>component</th>\n",
+ " <th colspan=\"13\" halign=\"left\">blood pressure systolic</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>status</th>\n",
+ " <th colspan=\"8\" halign=\"left\">known</th>\n",
+ " <th colspan=\"5\" halign=\"left\">unknown</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>variable_type</th>\n",
+ " <th colspan=\"8\" halign=\"left\">qn</th>\n",
+ " <th colspan=\"5\" halign=\"left\">qn</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>units</th>\n",
+ " <th colspan=\"8\" halign=\"left\">mmHg</th>\n",
+ " <th colspan=\"5\" halign=\"left\">cc/min</th>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>description</th>\n",
+ " <th>220050</th>\n",
+ " <th>220179</th>\n",
+ " <th>224167</th>\n",
+ " <th>225309</th>\n",
+ " <th>227243</th>\n",
+ " <th>442</th>\n",
+ " <th>455</th>\n",
+ " <th>51</th>\n",
+ " <th>3313</th>\n",
+ " <th>3315</th>\n",
+ " <th>3317</th>\n",
+ " <th>3321</th>\n",
+ " <th>3323</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>count</th>\n",
+ " <td>15186.000000</td>\n",
+ " <td>21957.000000</td>\n",
+ " <td>12.000000</td>\n",
+ " <td>1251.000000</td>\n",
+ " <td>8.00000</td>\n",
+ " <td>17.000000</td>\n",
+ " <td>26478.000000</td>\n",
+ " <td>35616.000000</td>\n",
+ " <td>2241.000000</td>\n",
+ " <td>22.000000</td>\n",
+ " <td>16.00000</td>\n",
+ " <td>13.000000</td>\n",
+ " <td>14.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>mean</th>\n",
+ " <td>118.988213</td>\n",
+ " <td>119.200483</td>\n",
+ " <td>104.416667</td>\n",
+ " <td>110.457234</td>\n",
+ " <td>111.87500</td>\n",
+ " <td>122.882353</td>\n",
+ " <td>119.150623</td>\n",
+ " <td>121.264628</td>\n",
+ " <td>70.371709</td>\n",
+ " <td>77.727273</td>\n",
+ " <td>76.68750</td>\n",
+ " <td>77.846154</td>\n",
+ " <td>75.714286</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>std</th>\n",
+ " <td>23.366007</td>\n",
+ " <td>21.757748</td>\n",
+ " <td>15.559027</td>\n",
+ " <td>20.465707</td>\n",
+ " <td>19.05209</td>\n",
+ " <td>31.262762</td>\n",
+ " <td>23.206573</td>\n",
+ " <td>25.927916</td>\n",
+ " <td>12.969975</td>\n",
+ " <td>15.495566</td>\n",
+ " <td>17.72651</td>\n",
+ " <td>14.932326</td>\n",
+ " <td>14.514865</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>min</th>\n",
+ " <td>0.000000</td>\n",
+ " <td>33.000000</td>\n",
+ " <td>86.000000</td>\n",
+ " <td>23.000000</td>\n",
+ " <td>84.00000</td>\n",
+ " <td>70.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>0.000000</td>\n",
+ " <td>38.000000</td>\n",
+ " <td>54.000000</td>\n",
+ " <td>50.00000</td>\n",
+ " <td>58.000000</td>\n",
+ " <td>55.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>25%</th>\n",
+ " <td>103.000000</td>\n",
+ " <td>104.000000</td>\n",
+ " <td>97.500000</td>\n",
+ " <td>99.000000</td>\n",
+ " <td>97.25000</td>\n",
+ " <td>96.000000</td>\n",
+ " <td>102.000000</td>\n",
+ " <td>104.000000</td>\n",
+ " <td>61.000000</td>\n",
+ " <td>66.250000</td>\n",
+ " <td>62.75000</td>\n",
+ " <td>67.000000</td>\n",
+ " <td>66.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>50%</th>\n",
+ " <td>117.000000</td>\n",
+ " <td>117.000000</td>\n",
+ " <td>102.000000</td>\n",
+ " <td>108.000000</td>\n",
+ " <td>116.00000</td>\n",
+ " <td>125.000000</td>\n",
+ " <td>117.000000</td>\n",
+ " <td>119.000000</td>\n",
+ " <td>70.000000</td>\n",
+ " <td>76.000000</td>\n",
+ " <td>76.00000</td>\n",
+ " <td>75.000000</td>\n",
+ " <td>75.500000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>75%</th>\n",
+ " <td>133.000000</td>\n",
+ " <td>133.000000</td>\n",
+ " <td>104.000000</td>\n",
+ " <td>120.000000</td>\n",
+ " <td>128.50000</td>\n",
+ " <td>138.000000</td>\n",
+ " <td>135.000000</td>\n",
+ " <td>137.000000</td>\n",
+ " <td>77.000000</td>\n",
+ " <td>86.750000</td>\n",
+ " <td>86.00000</td>\n",
+ " <td>84.000000</td>\n",
+ " <td>80.000000</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>max</th>\n",
+ " <td>244.000000</td>\n",
+ " <td>247.000000</td>\n",
+ " <td>144.000000</td>\n",
+ " <td>273.000000</td>\n",
+ " <td>132.00000</td>\n",
+ " <td>174.000000</td>\n",
+ " <td>234.000000</td>\n",
+ " <td>284.000000</td>\n",
+ " <td>123.000000</td>\n",
+ " <td>112.000000</td>\n",
+ " <td>120.00000</td>\n",
+ " <td>108.000000</td>\n",
+ " <td>99.000000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ "component blood pressure systolic \\\n",
+ "status known \n",
+ "variable_type qn \n",
+ "units mmHg \n",
+ "description 220050 220179 224167 225309 \n",
+ "count 15186.000000 21957.000000 12.000000 1251.000000 \n",
+ "mean 118.988213 119.200483 104.416667 110.457234 \n",
+ "std 23.366007 21.757748 15.559027 20.465707 \n",
+ "min 0.000000 33.000000 86.000000 23.000000 \n",
+ "25% 103.000000 104.000000 97.500000 99.000000 \n",
+ "50% 117.000000 117.000000 102.000000 108.000000 \n",
+ "75% 133.000000 133.000000 104.000000 120.000000 \n",
+ "max 244.000000 247.000000 144.000000 273.000000 \n",
+ "\n",
+ "component \\\n",
+ "status unknown \n",
+ "variable_type qn \n",
+ "units cc/min \n",
+ "description 227243 442 455 51 3313 \n",
+ "count 8.00000 17.000000 26478.000000 35616.000000 2241.000000 \n",
+ "mean 111.87500 122.882353 119.150623 121.264628 70.371709 \n",
+ "std 19.05209 31.262762 23.206573 25.927916 12.969975 \n",
+ "min 84.00000 70.000000 0.000000 0.000000 38.000000 \n",
+ "25% 97.25000 96.000000 102.000000 104.000000 61.000000 \n",
+ "50% 116.00000 125.000000 117.000000 119.000000 70.000000 \n",
+ "75% 128.50000 138.000000 135.000000 137.000000 77.000000 \n",
+ "max 132.00000 174.000000 234.000000 284.000000 123.000000 \n",
+ "\n",
+ "component \n",
+ "status \n",
+ "variable_type \n",
+ "units \n",
+ "description 3315 3317 3321 3323 \n",
+ "count 22.000000 16.00000 13.000000 14.000000 \n",
+ "mean 77.727273 76.68750 77.846154 75.714286 \n",
+ "std 15.495566 17.72651 14.932326 14.514865 \n",
+ "min 54.000000 50.00000 58.000000 55.000000 \n",
+ "25% 66.250000 62.75000 67.000000 66.000000 \n",
+ "50% 76.000000 76.00000 75.000000 75.500000 \n",
+ "75% 86.750000 86.00000 84.000000 80.000000 \n",
+ "max 112.000000 120.00000 108.000000 99.000000 "
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "((103300, 1), (97527, 13), 469L, 2, '0.2094% records')\n",
+ "(2017-06-20 10:04:19)<<<< DONE (5.0s)\n",
+ "(2017-06-20 10:04:19)<< DONE (62.0s)\n",
+ "(2017-06-20 10:04:19) DONE (70.0s)\n"
+ ]
+ }
+ ],
+ "source": [
+ "n = 100\n",
+ "hdf5_fname = do_ETL(data_dict,[data_dict.components.BLOOD_PRESSURE_SYSTOLIC],tag,n)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 44,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-06-20 10:09:14) BEGIN ETL for all admissions\n",
+ "(2017-06-20 10:09:15)>> Extract CONTEXT...\n",
+ "(2017-06-20 10:09:27)<< DONE (12.0s)\n",
+ "(2017-06-20 10:09:27)>> BLOOD PRESSURE SYSTOLIC\n",
+ "(2017-06-20 10:09:27)>>>> Extracting...\n",
+ "(2017-06-20 10:09:28)>>>>>> Extracting 14 items from chartevents\n",
+ "51 2099353\n",
+ "455 1586769\n",
+ "220179 1290488\n",
+ "220050 1149788\n",
+ "3313 148105\n",
+ "225309 86557\n",
+ "3315 3762\n",
+ "442 2565\n",
+ "3317 2052\n",
+ "3323 2039\n",
+ "3321 2032\n",
+ "224167 740\n",
+ "227243 541\n",
+ "6 33\n",
+ "Name: itemid, dtype: int64\n",
+ " id datetime value units itemid\n",
+ "963709 136796.0 2139-10-06 21:00:00 113/55 6\n",
+ "963711 136796.0 2139-10-06 22:00:00 126/58 6\n",
+ "963713 136796.0 2139-10-06 23:00:00 139/64 6\n",
+ "964245 136796.0 2139-10-07 07:00:00 132/59 6\n",
+ "964247 136796.0 2139-10-07 08:00:00 143/63 6\n",
+ "964301 136796.0 2139-10-07 16:00:00 152/68 6\n",
+ "964304 136796.0 2139-10-07 18:00:00 141/59 6\n",
+ "964710 136796.0 2139-10-07 09:00:00 133/59 6\n",
+ "964743 136796.0 2139-10-07 10:00:00 131/60 6\n",
+ "965088 136796.0 2139-10-07 11:00:00 123/54 6\n",
+ "965090 136796.0 2139-10-07 12:00:00 185/79 6\n",
+ "965092 136796.0 2139-10-07 13:00:00 116/54 6\n",
+ "965094 136796.0 2139-10-07 14:00:00 122/57 6\n",
+ "965096 136796.0 2139-10-07 15:00:00 120/56 6\n",
+ "965438 136796.0 2139-10-06 13:00:00 122/55 6\n",
+ "965440 136796.0 2139-10-06 14:00:00 110/56 6\n",
+ "965854 136796.0 2139-10-06 18:00:00 108/56 6\n",
+ "965856 136796.0 2139-10-06 20:00:00 115/56 6\n",
+ "966407 136796.0 2139-10-07 03:00:00 129/57 6\n",
+ "966409 136796.0 2139-10-07 04:00:00 121/55 6\n",
+ "966411 136796.0 2139-10-07 05:00:00 125/56 6\n",
+ "968122 136796.0 2139-10-06 09:00:00 119/55 6\n",
+ "968125 136796.0 2139-10-06 12:00:00 113/60 6\n",
+ "968615 136796.0 2139-10-07 00:00:00 120/54 6\n",
+ "968617 136796.0 2139-10-07 01:00:00 130/58 6\n",
+ "968619 136796.0 2139-10-07 02:00:00 124/56 6\n"
+ ]
+ },
+ {
+ "ename": "KeyError",
+ "evalue": "0L",
+ "output_type": "error",
+ "traceback": [
+ "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+ "\u001b[1;31mKeyError\u001b[0m Traceback (most recent call last)",
+ "\u001b[1;32m<ipython-input-44-88e79271be02>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m 1\u001b[0m \u001b[0mn\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mconstants\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mALL\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 2\u001b[1;33m \u001b[0mhdf5_fname\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdo_ETL\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdata_dict\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mdata_dict\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcomponents\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mBLOOD_PRESSURE_SYSTOLIC\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'bp'\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mn\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
+ "\u001b[1;32m<ipython-input-37-093e315c4cfe>\u001b[0m in \u001b[0;36mdo_ETL\u001b[1;34m(data_dict, components, tag, n, seed)\u001b[0m\n\u001b[0;32m 2\u001b[0m \u001b[0mhdf5_fname\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m'data/mimic_{}_{}'\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mtag\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mn\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0mhadm_ids\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mn\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mn\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mconstants\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mALL\u001b[0m \u001b[1;32melse\u001b[0m \u001b[0mmimic\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msample_hadm_ids\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mn\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mseed\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 4\u001b[1;33m \u001b[0mmimic_ETL\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcomponents\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mdata_dict\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mhdf5_fname\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mhadm_ids\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mhadm_ids\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 5\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mhdf5_fname\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32m<ipython-input-36-1619d6fa19c9>\u001b[0m in \u001b[0;36mmimic_ETL\u001b[1;34m(components, data_dict, hdf5_fname, hadm_ids, agg_func)\u001b[0m\n\u001b[0;32m 35\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 36\u001b[0m \u001b[0mlogger\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mlog\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Extracting...\"\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mnew_level\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 37\u001b[1;33m \u001b[0mdf_extracted\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mextractor\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mextract_component\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcomponent\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mhadm_ids\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 38\u001b[0m \u001b[0mutils\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msave_df\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf_extracted\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mhdf5_fname\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'extracted/{}'\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mformat\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcomponent\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 39\u001b[0m \u001b[0mlogger\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mend_log_level\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\icu_ml_project\\v5\\mimic.py\u001b[0m in \u001b[0;36mextract_component\u001b[1;34m(self, component, hadm_ids)\u001b[0m\n\u001b[0;32m 95\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 96\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mextract_component\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mcomponent\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mhadm_ids\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mALL\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 97\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mextract_component\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mconn\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mcomponent\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mitem_map\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdata_dict\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mhadm_ids\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 98\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 99\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\icu_ml_project\\v5\\mimic.py\u001b[0m in \u001b[0;36mextract_component\u001b[1;34m(mimic_conn, component, item_map, data_dict, hadm_ids)\u001b[0m\n\u001b[0;32m 132\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mbp_slice\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mshape\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m!=\u001b[0m \u001b[1;36m0\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 133\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mcomponent\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mdata_dict\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcomponents\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mBLOOD_PRESSURE_SYSTOLIC\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 134\u001b[1;33m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mis_item_6\u001b[0m \u001b[1;33m&\u001b[0m \u001b[0mhas_slash\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'value'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mis_item_6\u001b[0m \u001b[1;33m&\u001b[0m \u001b[0mhas_slash\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'value'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'/'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mint\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 135\u001b[0m \u001b[1;32melif\u001b[0m \u001b[0mcomponent\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mdata_dict\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcomponents\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mBLOOD_PRESSURE_DIASTOLIC\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 136\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mhas_slash\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'value'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m==\u001b[0m \u001b[0mdf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mhas_slash\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;34m'value'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstr\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msplit\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'/'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mastype\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mint\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\series.pyc\u001b[0m in \u001b[0;36m__getitem__\u001b[1;34m(self, key)\u001b[0m\n\u001b[0;32m 599\u001b[0m \u001b[0mkey\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_apply_if_callable\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 600\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 601\u001b[1;33m \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_value\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 602\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 603\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mis_scalar\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mresult\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\indexes\\base.pyc\u001b[0m in \u001b[0;36mget_value\u001b[1;34m(self, series, key)\u001b[0m\n\u001b[0;32m 2137\u001b[0m \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2138\u001b[0m return self._engine.get_value(s, k,\n\u001b[1;32m-> 2139\u001b[1;33m tz=getattr(series.dtype, 'tz', None))\n\u001b[0m\u001b[0;32m 2140\u001b[0m \u001b[1;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me1\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 2141\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m>\u001b[0m \u001b[1;36m0\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0minferred_type\u001b[0m \u001b[1;32min\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;34m'integer'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'boolean'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+ "\u001b[1;32mpandas\\index.pyx\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_value (pandas\\index.c:3338)\u001b[1;34m()\u001b[0m\n",
+ "\u001b[1;32mpandas\\index.pyx\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_value (pandas\\index.c:3041)\u001b[1;34m()\u001b[0m\n",
+ "\u001b[1;32mpandas\\index.pyx\u001b[0m in \u001b[0;36mpandas.index.IndexEngine.get_loc (pandas\\index.c:4024)\u001b[1;34m()\u001b[0m\n",
+ "\u001b[1;32mpandas\\src\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas.hashtable.Int64HashTable.get_item (pandas\\hashtable.c:8141)\u001b[1;34m()\u001b[0m\n",
+ "\u001b[1;32mpandas\\src\\hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas.hashtable.Int64HashTable.get_item (pandas\\hashtable.c:8085)\u001b[1;34m()\u001b[0m\n",
+ "\u001b[1;31mKeyError\u001b[0m: 0L"
+ ]
+ }
+ ],
+ "source": [
+ "n = constants.ALL\n",
+ "hdf5_fname = do_ETL(data_dict,[data_dict.components.BLOOD_PRESSURE_SYSTOLIC],'bp',n)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 35,
+ "metadata": {
+ "collapsed": false,
+ "scrolled": true
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "<class 'pandas.io.pytables.HDFStore'>\n",
+ "File path: data/mimic_simple_all\n",
+ "/cleaned/blood pressure diastolic frame \n",
+ "/cleaned/blood pressure mean frame \n",
+ "/cleaned/blood pressure systolic frame \n",
+ "/cleaned/glasgow coma scale eye opening frame \n",
+ "/cleaned/glasgow coma scale motor frame \n",
+ "/cleaned/glasgow coma scale verbal frame \n",
+ "/cleaned/heart rate frame \n",
+ "/cleaned/hemoglobin frame \n",
+ "/cleaned/lactate frame \n",
+ "/cleaned/lactated ringers frame \n",
+ "/cleaned/norepinephrine frame \n",
+ "/cleaned/normal saline frame \n",
+ "/cleaned/output urine frame \n",
+ "/cleaned/oxygen saturation pulse oximetry frame \n",
+ "/cleaned/respiratory rate frame \n",
+ "/cleaned/temperature body frame \n",
+ "/cleaned/vasopressin frame \n",
+ "/cleaned/weight body frame \n",
+ "/context frame (shape->[62722,22]) \n",
+ "/extracted/blood pressure diastolic frame (shape->[6371249,5])\n",
+ "/extracted/blood pressure mean frame (shape->[2536271,5])\n",
+ "/extracted/blood pressure systolic frame (shape->[6374824,5])\n",
+ "/extracted/glasgow coma scale eye opening frame (shape->[956672,5]) \n",
+ "/extracted/glasgow coma scale motor frame (shape->[952565,5]) \n",
+ "/extracted/glasgow coma scale verbal frame (shape->[954700,5]) \n",
+ "/extracted/heart rate frame (shape->[7952939,5])\n",
+ "/extracted/hemoglobin frame (shape->[1167921,5])\n",
+ "/extracted/lactate frame (shape->[393608,5]) \n",
+ "/extracted/lactated ringers frame (shape->[504306,5]) \n",
+ "/extracted/norepinephrine frame (shape->[1136938,5])\n",
+ "/extracted/normal saline frame (shape->[817373,5]) \n",
+ "/extracted/output urine frame (shape->[3644639,5])\n",
+ "/extracted/oxygen saturation pulse oximetry frame (shape->[6099827,5])\n",
+ "/extracted/respiratory rate frame (shape->[7810019,5])\n",
+ "/extracted/temperature body frame (shape->[1751447,5])\n",
+ "/extracted/vasopressin frame (shape->[339184,5]) \n",
+ "/extracted/weight body frame (shape->[95425,5]) \n",
+ "/transformed/blood pressure diastolic frame \n",
+ "/transformed/blood pressure mean frame \n",
+ "/transformed/blood pressure systolic frame \n",
+ "/transformed/glasgow coma scale eye opening frame \n",
+ "/transformed/glasgow coma scale motor frame \n",
+ "/transformed/glasgow coma scale verbal frame \n",
+ "/transformed/heart rate frame \n",
+ "/transformed/hemoglobin frame \n",
+ "/transformed/lactate frame \n",
+ "/transformed/lactated ringers frame \n",
+ "/transformed/norepinephrine frame \n",
+ "/transformed/normal saline frame \n",
+ "/transformed/output urine frame \n",
+ "/transformed/oxygen saturation pulse oximetry frame \n",
+ "/transformed/respiratory rate frame \n",
+ "/transformed/temperature body frame \n",
+ "/transformed/vasopressin frame \n",
+ "/transformed/weight body frame "
+ ]
+ },
+ "execution_count": 35,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "store = pd.HDFStore(hdf5_fname)\n",
+ "store"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 36,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "store.close()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import utils\n",
+ "import mimic\n",
+ "import icu_data_defs\n",
+ "import transformers"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "data_dict = icu_data_defs.data_dictionary('config/data_definitions.xlsx')\n",
+ "components = data_dict.get_panel_defintions(1).component.unique().tolist() #1 is vitals"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "[u'heart rate',\n",
+ " u'blood pressure systolic',\n",
+ " u'blood pressure diastolic',\n",
+ " u'blood pressure mean',\n",
+ " u'respiratory rate',\n",
+ " u'temperature body',\n",
+ " u'oxygen saturation pulse oximetry',\n",
+ " u'weight body']"
+ ]
+ },
+ "execution_count": 6,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "components"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "(2017-07-04 22:28:15)<<<<<<<< --- (25.0s)\n",
+ "(2017-07-04 22:28:15)>>>>>>>> ***ETL***\n",
+ "(2017-07-04 22:28:15)>>>>>>>>>> SETUP\n",
+ "(2017-07-04 22:28:15)<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 22:28:15)>>>>>>>>>> BEGIN ETL for all admissions and 8 components: [u'heart rate', u'blood pressure systolic', u'blood pressure diastolic', u'blood pressure mean', u'respiratory rate', u'temperature body', u'oxygen saturation pulse oximetry', u'weight body']\n",
+ "(2017-07-04 22:28:15)>>>>>>>>>>>> HEART RATE: 1/8\n",
+ "(2017-07-04 22:28:15)>>>>>>>>>>>>>> Extracting...\n",
+ "(2017-07-04 22:28:16)>>>>>>>>>>>>>>>> Extracting 5 items from chartevents\n",
+ "(2017-07-04 22:29:12)<<<<<<<<<<<<<<<< --- (56.0s)\n",
+ "(2017-07-04 22:29:12)>>>>>>>>>>>>>>>> Combine DF\n",
+ "(2017-07-04 22:29:13)<<<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 22:29:13)>>>>>>>>>>>>>>>> Clean UOM\n",
+ "(2017-07-04 22:29:33)<<<<<<<<<<<<<<<< --- (20.0s)\n",
+ "(2017-07-04 22:29:33)<<<<<<<<<<<<<< --- (78.0s)\n",
+ "(2017-07-04 22:29:33)>>>>>>>>>>>>>> Transforming... (7952939, 5)\n",
+ "Data Loss (Extract > Transformed): ((7952939, 1), (7923711, 6), 29066L, 171, '0.3015% records')\n",
+ "(2017-07-04 22:31:25)<<<<<<<<<<<<<< --- (112.0s)\n",
+ "(2017-07-04 22:31:25)>>>>>>>>>>>>>> Cleaning... (7923711, 6)\n",
+ "(2017-07-04 22:32:14)>>>>>>>>>>>>>>>> Nominal to OneHot\n",
+ "(2017-07-04 22:32:14)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 22:32:14)>>>>>>>>>>>>>>>> Drop OOB data | (7922986, 6)\n",
+ "(2017-07-04 22:32:18)>>>>>>>>>>>>>>>>>> heart rate, beats/min, 7923117\n",
+ "(2017-07-04 22:33:29)<<<<<<<<<<<<<<<<<< --- (71.0s)\n",
+ "(2017-07-04 22:33:29)>>>>>>>>>>>>>>>>>> heart rate, no_units, 31\n",
+ "(2017-07-04 22:33:29)<<<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 22:33:29)<<<<<<<<<<<<<<<< --- (75.0s)\n",
+ "Data Loss (Extract > Cleaned): ((7952939, 1), (7922986, 6), 29804L, 171, '0.3015% records')\n",
+ "(2017-07-04 22:33:31)<<<<<<<<<<<<<< --- (126.0s)\n",
+ "(2017-07-04 22:33:31)>>>>>>>>>>>>>> Filter & sort - (7922986, 6)\n",
+ "(2017-07-04 22:33:35)<<<<<<<<<<<<<< --- (4.0s)\n",
+ "(2017-07-04 22:33:35)>>>>>>>>>>>>>> Convert to dask - (7922986, 6)\n",
+ "(2017-07-04 22:33:36)<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 22:33:36)>>>>>>>>>>>>>> Join to big DF\n",
+ "(2017-07-04 22:33:36)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 22:33:36)<<<<<<<<<<<< --- (321.0s)\n",
+ "(2017-07-04 22:33:36)>>>>>>>>>>>> BLOOD PRESSURE SYSTOLIC: 2/8\n",
+ "(2017-07-04 22:33:36)>>>>>>>>>>>>>> Extracting...\n",
+ "(2017-07-04 22:33:36)>>>>>>>>>>>>>>>> Extracting 14 items from chartevents\n",
+ "(2017-07-04 22:35:06)<<<<<<<<<<<<<<<< --- (90.0s)\n",
+ "(2017-07-04 22:35:06)>>>>>>>>>>>>>>>> Combine DF\n",
+ "(2017-07-04 22:35:06)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 22:35:06)>>>>>>>>>>>>>>>> Clean UOM\n",
+ "(2017-07-04 22:35:10)<<<<<<<<<<<<<<<< --- (4.0s)\n",
+ "(2017-07-04 22:35:10)<<<<<<<<<<<<<< --- (94.0s)\n",
+ "(2017-07-04 22:35:10)>>>>>>>>>>>>>> Transforming... (6374824, 5)\n",
+ "Data Loss (Extract > Transformed): ((6374824, 1), (5974719, 15), 43236L, 174, '0.307% records')\n",
+ "(2017-07-04 22:36:52)<<<<<<<<<<<<<< --- (102.0s)\n",
+ "(2017-07-04 22:36:52)>>>>>>>>>>>>>> Cleaning... (5974719, 15)\n",
+ "(2017-07-04 22:42:30)>>>>>>>>>>>>>>>> Nominal to OneHot\n",
+ "(2017-07-04 22:42:31)<<<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 22:42:31)>>>>>>>>>>>>>>>> Drop OOB data | (5974186, 14)\n",
+ "(2017-07-04 22:42:34)>>>>>>>>>>>>>>>>>> blood pressure systolic, mmHg, 6177439\n",
+ "(2017-07-04 22:45:18)<<<<<<<<<<<<<<<<<< --- (164.0s)\n",
+ "(2017-07-04 22:45:18)>>>>>>>>>>>>>>>>>> blood pressure systolic, cc/min, 153573\n",
+ "(2017-07-04 22:45:19)<<<<<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 22:45:19)<<<<<<<<<<<<<<<< --- (168.0s)\n",
+ "Data Loss (Extract > Cleaned): ((6374824, 1), (5974186, 14), 43848L, 174, '0.307% records')\n",
+ "(2017-07-04 22:45:20)<<<<<<<<<<<<<< --- (508.0s)\n",
+ "(2017-07-04 22:45:20)>>>>>>>>>>>>>> Filter & sort - (5974186, 14)\n",
+ "(2017-07-04 22:45:23)<<<<<<<<<<<<<< --- (3.0s)\n",
+ "(2017-07-04 22:45:23)>>>>>>>>>>>>>> Convert to dask - (5974186, 14)\n",
+ "(2017-07-04 22:45:25)<<<<<<<<<<<<<< --- (2.0s)\n",
+ "(2017-07-04 22:45:25)>>>>>>>>>>>>>> Join to big DF\n",
+ "(2017-07-04 22:45:25)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 22:45:25)<<<<<<<<<<<< --- (709.0s)\n",
+ "(2017-07-04 22:45:25)>>>>>>>>>>>> BLOOD PRESSURE DIASTOLIC: 3/8\n",
+ "(2017-07-04 22:45:25)>>>>>>>>>>>>>> Extracting...\n",
+ "(2017-07-04 22:45:25)>>>>>>>>>>>>>>>> Extracting 16 items from chartevents\n",
+ "(2017-07-04 22:48:00)<<<<<<<<<<<<<<<< --- (155.0s)\n",
+ "(2017-07-04 22:48:00)>>>>>>>>>>>>>>>> Combine DF\n",
+ "(2017-07-04 22:48:00)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 22:48:00)>>>>>>>>>>>>>>>> Clean UOM\n",
+ "(2017-07-04 22:48:06)<<<<<<<<<<<<<<<< --- (6.0s)\n",
+ "(2017-07-04 22:48:06)<<<<<<<<<<<<<< --- (161.0s)\n",
+ "(2017-07-04 22:48:06)>>>>>>>>>>>>>> Transforming... (6371282, 5)\n",
+ "Data Loss (Extract > Transformed): ((6371282, 1), (5976845, 17), 24410L, 170, '0.2999% records')\n",
+ "(2017-07-04 22:49:52)<<<<<<<<<<<<<< --- (106.0s)\n",
+ "(2017-07-04 22:49:52)>>>>>>>>>>>>>> Cleaning... (5976845, 17)\n",
+ "(2017-07-04 22:56:05)>>>>>>>>>>>>>>>> Nominal to OneHot\n",
+ "(2017-07-04 22:56:06)<<<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 22:56:06)>>>>>>>>>>>>>>>> Drop OOB data | (5976313, 16)\n",
+ "(2017-07-04 22:56:10)>>>>>>>>>>>>>>>>>> blood pressure diastolic, mmHg, 6194656\n",
+ "(2017-07-04 22:59:39)<<<<<<<<<<<<<<<<<< --- (209.0s)\n",
+ "(2017-07-04 22:59:39)>>>>>>>>>>>>>>>>>> blood pressure diastolic, cc/min, 151640\n",
+ "(2017-07-04 22:59:39)<<<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 22:59:39)<<<<<<<<<<<<<<<< --- (213.0s)\n",
+ "Data Loss (Extract > Cleaned): ((6371282, 1), (5976313, 16), 25238L, 170, '0.2999% records')\n",
+ "(2017-07-04 22:59:41)<<<<<<<<<<<<<< --- (589.0s)\n",
+ "(2017-07-04 22:59:41)>>>>>>>>>>>>>> Filter & sort - (5976313, 16)\n",
+ "(2017-07-04 22:59:45)<<<<<<<<<<<<<< --- (4.0s)\n",
+ "(2017-07-04 22:59:45)>>>>>>>>>>>>>> Convert to dask - (5976313, 16)\n",
+ "(2017-07-04 22:59:46)<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 22:59:46)>>>>>>>>>>>>>> Join to big DF\n",
+ "(2017-07-04 22:59:46)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 22:59:46)<<<<<<<<<<<< --- (861.0s)\n",
+ "(2017-07-04 22:59:46)>>>>>>>>>>>> BLOOD PRESSURE MEAN: 4/8\n",
+ "(2017-07-04 22:59:46)>>>>>>>>>>>>>> Extracting...\n",
+ "(2017-07-04 22:59:46)>>>>>>>>>>>>>>>> Extracting 3 items from chartevents\n",
+ "(2017-07-04 23:00:18)<<<<<<<<<<<<<<<< --- (32.0s)\n",
+ "(2017-07-04 23:00:18)>>>>>>>>>>>>>>>> Combine DF\n",
+ "(2017-07-04 23:00:19)<<<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 23:00:19)>>>>>>>>>>>>>>>> Clean UOM\n",
+ "(2017-07-04 23:00:20)<<<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 23:00:20)<<<<<<<<<<<<<< --- (34.0s)\n",
+ "(2017-07-04 23:00:20)>>>>>>>>>>>>>> Transforming... (2536271, 5)\n",
+ "Data Loss (Extract > Transformed): ((2536271, 1), (2416029, 3), 0L, 0, '0.0% records')\n",
+ "(2017-07-04 23:01:04)<<<<<<<<<<<<<< --- (44.0s)\n",
+ "(2017-07-04 23:01:04)>>>>>>>>>>>>>> Cleaning... (2416029, 3)\n",
+ "(2017-07-04 23:01:19)>>>>>>>>>>>>>>>> Nominal to OneHot\n",
+ "(2017-07-04 23:01:19)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:01:19)>>>>>>>>>>>>>>>> Drop OOB data | (2415995, 3)\n",
+ "(2017-07-04 23:01:20)>>>>>>>>>>>>>>>>>> blood pressure mean, mmHg, 2536236\n",
+ "(2017-07-04 23:01:55)<<<<<<<<<<<<<<<<<< --- (35.0s)\n",
+ "(2017-07-04 23:01:55)<<<<<<<<<<<<<<<< --- (36.0s)\n",
+ "Data Loss (Extract > Cleaned): ((2536271, 1), (2415995, 3), 1873L, 0, '0.0% records')\n",
+ "(2017-07-04 23:01:55)<<<<<<<<<<<<<< --- (51.0s)\n",
+ "(2017-07-04 23:01:55)>>>>>>>>>>>>>> Filter & sort - (2415995, 3)\n",
+ "(2017-07-04 23:01:56)<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 23:01:56)>>>>>>>>>>>>>> Convert to dask - (2415995, 3)\n",
+ "(2017-07-04 23:01:57)<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 23:01:57)>>>>>>>>>>>>>> Join to big DF\n",
+ "(2017-07-04 23:01:57)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:01:57)<<<<<<<<<<<< --- (131.0s)\n",
+ "(2017-07-04 23:01:57)>>>>>>>>>>>> RESPIRATORY RATE: 5/8\n",
+ "(2017-07-04 23:01:57)>>>>>>>>>>>>>> Extracting...\n",
+ "(2017-07-04 23:01:57)>>>>>>>>>>>>>>>> Extracting 4 items from chartevents\n",
+ "(2017-07-04 23:06:09)<<<<<<<<<<<<<<<< --- (252.0s)\n",
+ "(2017-07-04 23:06:09)>>>>>>>>>>>>>>>> Combine DF\n",
+ "(2017-07-04 23:06:09)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:06:09)>>>>>>>>>>>>>>>> Clean UOM\n",
+ "(2017-07-04 23:06:24)<<<<<<<<<<<<<<<< --- (15.0s)\n",
+ "(2017-07-04 23:06:24)<<<<<<<<<<<<<< --- (267.0s)\n",
+ "(2017-07-04 23:06:24)>>>>>>>>>>>>>> Transforming... (7810019, 5)\n",
+ "Data Loss (Extract > Transformed): ((7810019, 1), (7780717, 5), 28707L, 172, '0.3035% records')\n",
+ "(2017-07-04 23:08:13)<<<<<<<<<<<<<< --- (109.0s)\n",
+ "(2017-07-04 23:08:13)>>>>>>>>>>>>>> Cleaning... (7780717, 5)\n",
+ "(2017-07-04 23:11:07)>>>>>>>>>>>>>>>> Nominal to OneHot\n",
+ "(2017-07-04 23:11:07)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:11:07)>>>>>>>>>>>>>>>> Drop OOB data | (7780015, 4)\n",
+ "(2017-07-04 23:11:11)>>>>>>>>>>>>>>>>>> respiratory rate, insp/min, 6108262\n",
+ "(2017-07-04 23:12:08)<<<<<<<<<<<<<<<<<< --- (57.0s)\n",
+ "(2017-07-04 23:12:08)>>>>>>>>>>>>>>>>>> respiratory rate, Breath, 1671901\n",
+ "(2017-07-04 23:12:08)<<<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:12:08)>>>>>>>>>>>>>>>>>> respiratory rate, no_units, 2\n",
+ "(2017-07-04 23:12:08)<<<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:12:08)<<<<<<<<<<<<<<<< --- (61.0s)\n",
+ "Data Loss (Extract > Cleaned): ((7810019, 1), (7780015, 4), 29907L, 172, '0.3035% records')\n",
+ "(2017-07-04 23:12:09)<<<<<<<<<<<<<< --- (236.0s)\n",
+ "(2017-07-04 23:12:10)>>>>>>>>>>>>>> Filter & sort - (7780015, 4)\n",
+ "(2017-07-04 23:12:14)<<<<<<<<<<<<<< --- (4.0s)\n",
+ "(2017-07-04 23:12:14)>>>>>>>>>>>>>> Convert to dask - (7780015, 4)\n",
+ "(2017-07-04 23:12:14)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:12:14)>>>>>>>>>>>>>> Join to big DF\n",
+ "(2017-07-04 23:12:14)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:12:14)<<<<<<<<<<<< --- (617.0s)\n",
+ "(2017-07-04 23:12:14)>>>>>>>>>>>> TEMPERATURE BODY: 6/8\n",
+ "(2017-07-04 23:12:15)>>>>>>>>>>>>>> Extracting...\n",
+ "(2017-07-04 23:12:15)>>>>>>>>>>>>>>>> Extracting 4 items from chartevents\n",
+ "(2017-07-04 23:13:06)<<<<<<<<<<<<<<<< --- (51.0s)\n",
+ "(2017-07-04 23:13:06)>>>>>>>>>>>>>>>> Combine DF\n",
+ "(2017-07-04 23:13:06)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:13:06)>>>>>>>>>>>>>>>> Clean UOM\n",
+ "(2017-07-04 23:13:11)<<<<<<<<<<<<<<<< --- (5.0s)\n",
+ "(2017-07-04 23:13:11)<<<<<<<<<<<<<< --- (56.0s)\n",
+ "(2017-07-04 23:13:11)>>>>>>>>>>>>>> Transforming... (1751447, 5)\n",
+ "Data Loss (Extract > Transformed): ((1751447, 1), (1731875, 4), 16612L, 156, '0.3189% records')\n",
+ "(2017-07-04 23:13:42)<<<<<<<<<<<<<< --- (31.0s)\n",
+ "(2017-07-04 23:13:42)>>>>>>>>>>>>>> Cleaning... (1731875, 4)\n",
+ "(2017-07-04 23:13:54)>>>>>>>>>>>>>>>> Nominal to OneHot\n",
+ "(2017-07-04 23:13:54)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:13:54)>>>>>>>>>>>>>>>> Drop OOB data | (1731794, 4)\n",
+ "(2017-07-04 23:13:55)>>>>>>>>>>>>>>>>>> temperature body, degF, 1734754\n",
+ "(2017-07-04 23:14:24)<<<<<<<<<<<<<<<<<< --- (29.0s)\n",
+ "(2017-07-04 23:14:24)<<<<<<<<<<<<<<<< --- (30.0s)\n",
+ "Data Loss (Extract > Cleaned): ((1751447, 1), (1731794, 4), 17226L, 156, '0.3189% records')\n",
+ "(2017-07-04 23:14:24)<<<<<<<<<<<<<< --- (42.0s)\n",
+ "(2017-07-04 23:14:24)>>>>>>>>>>>>>> Filter & sort - (1731794, 4)\n",
+ "(2017-07-04 23:14:25)<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 23:14:25)>>>>>>>>>>>>>> Convert to dask - (1731794, 4)\n",
+ "(2017-07-04 23:14:25)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:14:25)>>>>>>>>>>>>>> Join to big DF\n",
+ "(2017-07-04 23:14:25)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:14:25)<<<<<<<<<<<< --- (131.0s)\n",
+ "(2017-07-04 23:14:25)>>>>>>>>>>>> OXYGEN SATURATION PULSE OXIMETRY: 7/8\n",
+ "(2017-07-04 23:14:25)>>>>>>>>>>>>>> Extracting...\n",
+ "(2017-07-04 23:14:25)>>>>>>>>>>>>>>>> Extracting 2 items from chartevents\n",
+ "(2017-07-04 23:15:41)<<<<<<<<<<<<<<<< --- (76.0s)\n",
+ "(2017-07-04 23:15:41)>>>>>>>>>>>>>>>> Combine DF\n",
+ "(2017-07-04 23:15:41)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:15:41)>>>>>>>>>>>>>>>> Clean UOM\n",
+ "(2017-07-04 23:15:58)<<<<<<<<<<<<<<<< --- (17.0s)\n",
+ "(2017-07-04 23:15:58)<<<<<<<<<<<<<< --- (93.0s)\n",
+ "(2017-07-04 23:15:58)>>>>>>>>>>>>>> Transforming... (6099827, 5)\n",
+ "Data Loss (Extract > Transformed): ((6099827, 1), (6073540, 2), 26134L, 163, '0.3326% records')\n",
+ "(2017-07-04 23:17:28)<<<<<<<<<<<<<< --- (90.0s)\n",
+ "(2017-07-04 23:17:28)>>>>>>>>>>>>>> Cleaning... (6073540, 2)\n",
+ "(2017-07-04 23:18:01)>>>>>>>>>>>>>>>> Nominal to OneHot\n",
+ "(2017-07-04 23:18:01)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:18:01)>>>>>>>>>>>>>>>> Drop OOB data | (6073019, 2)\n",
+ "(2017-07-04 23:18:03)>>>>>>>>>>>>>>>>>> oxygen saturation pulse oximetry, percent, 6073172\n",
+ "(2017-07-04 23:18:54)<<<<<<<<<<<<<<<<<< --- (51.0s)\n",
+ "(2017-07-04 23:18:54)<<<<<<<<<<<<<<<< --- (53.0s)\n",
+ "Data Loss (Extract > Cleaned): ((6099827, 1), (6073019, 2), 26707L, 163, '0.3326% records')\n",
+ "(2017-07-04 23:18:55)<<<<<<<<<<<<<< --- (87.0s)\n",
+ "(2017-07-04 23:18:56)>>>>>>>>>>>>>> Filter & sort - (6073019, 2)\n",
+ "(2017-07-04 23:18:58)<<<<<<<<<<<<<< --- (2.0s)\n",
+ "(2017-07-04 23:18:58)>>>>>>>>>>>>>> Convert to dask - (6073019, 2)\n",
+ "(2017-07-04 23:18:59)<<<<<<<<<<<<<< --- (1.0s)\n",
+ "(2017-07-04 23:18:59)>>>>>>>>>>>>>> Join to big DF\n",
+ "(2017-07-04 23:18:59)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:18:59)<<<<<<<<<<<< --- (274.0s)\n",
+ "(2017-07-04 23:18:59)>>>>>>>>>>>> WEIGHT BODY: 8/8\n",
+ "(2017-07-04 23:18:59)>>>>>>>>>>>>>> Extracting...\n",
+ "(2017-07-04 23:18:59)>>>>>>>>>>>>>>>> Extracting 3 items from chartevents\n",
+ "(2017-07-04 23:19:34)<<<<<<<<<<<<<<<< --- (35.0s)\n",
+ "(2017-07-04 23:19:34)>>>>>>>>>>>>>>>> Combine DF\n",
+ "(2017-07-04 23:19:34)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:19:34)>>>>>>>>>>>>>>>> Clean UOM\n",
+ "(2017-07-04 23:19:34)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:19:34)<<<<<<<<<<<<<< --- (35.0s)\n",
+ "(2017-07-04 23:19:34)>>>>>>>>>>>>>> Transforming... (95425, 5)\n",
+ "Data Loss (Extract > Transformed): ((95425, 1), (94484, 3), 941L, 158, '0.4958% records')\n",
+ "(2017-07-04 23:19:36)<<<<<<<<<<<<<< --- (2.0s)\n",
+ "(2017-07-04 23:19:36)>>>>>>>>>>>>>> Cleaning... (94484, 3)\n",
+ "(2017-07-04 23:19:37)>>>>>>>>>>>>>>>> Nominal to OneHot\n",
+ "(2017-07-04 23:19:37)<<<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:19:37)>>>>>>>>>>>>>>>> Drop OOB data | (94457, 3)\n",
+ "(2017-07-04 23:19:37)>>>>>>>>>>>>>>>>>> weight body, kg, 94457\n",
+ "(2017-07-04 23:19:42)<<<<<<<<<<<<<<<<<< --- (5.0s)\n",
+ "(2017-07-04 23:19:42)<<<<<<<<<<<<<<<< --- (5.0s)\n",
+ "Data Loss (Extract > Cleaned): ((95425, 1), (94457, 3), 979L, 158, '0.4958% records')\n",
+ "(2017-07-04 23:19:42)<<<<<<<<<<<<<< --- (6.0s)\n",
+ "(2017-07-04 23:19:42)>>>>>>>>>>>>>> Filter & sort - (94457, 3)\n",
+ "(2017-07-04 23:19:42)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:19:42)>>>>>>>>>>>>>> Convert to dask - (94457, 3)\n",
+ "(2017-07-04 23:19:42)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:19:42)>>>>>>>>>>>>>> Join to big DF\n",
+ "(2017-07-04 23:19:42)<<<<<<<<<<<<<< --- (0.0s)\n",
+ "(2017-07-04 23:19:42)<<<<<<<<<<<< --- (43.0s)\n",
+ "(2017-07-04 23:19:42)<<<<<<<<<< --- (3087.0s)\n",
+ "(2017-07-04 23:19:42)<<<<<<<< --- (3087.0s)\n"
+ ]
+ }
+ ],
+ "source": [
+ "df_all = mimic.ETL(mimic.mimic_extractor('config/mimic_item_map.csv',data_dict),\n",
+ " components,\n",
+ " data_dict,\n",
+ " transformers.same_index_aggregator(agg_func=lambda x:x.iloc[0]))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Get all of the data we want and join into a single DF"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import utils\n",
+ "import logger\n",
+ "import transformers\n",
+ "import warnings\n",
+ "warnings.filterwarnings('ignore')\n",
+ "\n",
+ "def get_big_df(hdf5_fname,components):\n",
+ " \n",
+ " df_all = None\n",
+ " logger.log('Make DF for {} components...\\n{}'.format(len(components),'\\n'.join(components)),new_level=True)\n",
+ " for component in components:\n",
+ " logger.log('{}: {}/{}'.format(component.upper(),components.index(component)+1,len(components)),new_level=True)\n",
+ "\n",
+ " logger.log('Opening...')\n",
+ " df = utils.open_df(hdf5_fname,'cleaned/{}'.format(component)).sort_index(axis=1).sort_index()\n",
+ " display(df.describe(include='all'))\n",
+ "\n",
+ " df_cleaned = transformers.remove_small_columns(threshold=5).fit_transform(df)\n",
+ " \n",
+ " display(df_cleaned.describe(include='all'))\n",
+ "\n",
+ " print utils.data_loss(df,df_cleaned)\n",
+ " \n",
+ " logger.log('Join {} to {}'.format(df_cleaned.shape, None if df_all is None else df_all.shape))\n",
+ " if df_all is None: df_all = df_cleaned\n",
+ " else : \n",
+ " df_all = df_all.join(df_cleaned,how='outer')\n",
+ " del df,df_cleaned\n",
+ " \n",
+ " logger.end_log_level()\n",
+ " logger.end_log()\n",
+ "\n",
+ " return df_all"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "import icu_data_defs\n",
+ "data_dict = icu_data_defs.data_dictionary('config/data_definitions.xlsx')"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "components = data_dict.get_panel_defintions(12).component.unique().tolist()\n",
+ "components"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "#everything up to urine output\n",
+ "df1 = get_big_df('data/mimic_data',components[:8])\n",
+ "utils.save_df(df1,'data/mimic_data','cleaned/part1')\n",
+ "\n",
+ "#urine output and forward\n",
+ "df2 = get_big_df('data/mimic_data',components[8:])\n",
+ "utils.save_df(df2,'data/mimic_data','cleaned/part2')\n",
+ "\n",
+ "df_combined = df1.join(df2,how='outer')\n",
+ "\n",
+ "del df1,df2\n",
+ "df_all.shape"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "utils.save_df(df_combined,'data/mimic_data','cleaned/all')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "# Start here"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 70,
+ "metadata": {
+ "collapsed": false
+ },
+ "outputs": [],
+ "source": [
+ "\n",
+ "\n",
+ "def summable_filter(df):\n",
+ " ureg = units.MedicalUreg()\n",
+ " filter_func= lambda x: (ureg.is_volume(str(x[-2])) or ureg.is_mass(str(x[-2]))) and (x[0] != data_dict.labels.WEIGHT_BODY)\n",
+ " return df.loc[:,df.columns.map(filter_func)]\n",
+ "\n",
+ "def lactate_filter_admissions(hdf5_fname)\n",
+ "\n",
+ "def make_lactate_labels(hdf5_fname,custom_cleaners,data_dict):\n",
+ " df = utils.open_df(hdf5_fname,'cleaned/{}'.format(data_dict.labels.LACTATE))\n",
+ " df_cleaned = custom_cleaners.transform(df)\n",
+ " max_col_cleaner = transformers.max_col_only()\n",
+ " df_cleaned = max_col_cleaner.transform(df_cleaned)\n",
+ " df_cleaned.groupby(level=constants.column_names.ID).agg(lambda x: x.iloc[])\n",
+ " \n",
+ " \n",
+ "\n",
+ "basic_feature_tuples = [\n",
+ " ('MEAN',features.segment_mean(),constants.ALL),\n",
+ " ('STD',features.segment_std(),constants.ALL),\n",
+ " ('COUNT',features.segment_count(),constants.ALL),\n",
+ " ('LAST',features.segment_last(),constants.ALL),\n",
+ " ('SUM',features.segment_sum(),{constants.CUSTOM_FILTER:summable_filter})\n",
+ "]\n",
+ "\n",
+ "custom_cleaners = Pipeline([\n",
+ " ('drop_oob_values',transformers.oob_value_remover(data_dict)),\n",
+ " ('drop_small_columns',transformers.remove_small_columns(threshold=50)),\n",
+ " ('combine_like_columns',transformers.combine_like_cols()),\n",
+ "# ('quantitative_only',transformers.filter_var_type(var_types_to_keep)),\n",
+ "# ('known_col_only',transformers.known_col_only()),\n",
+ " ])"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "\n",
+ "\n",
+ "lactate_labels = make_lactate_labels(hdf5_fname,custom_cleaners)\n",
+ "\n",
+ "df_features = mimic_features(hdf5_fname,'basic_all_before',labels,custom_cleaners)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": []
+ }
+ ],
+ "metadata": {
+ "anaconda-cloud": {},
+ "kernelspec": {
+ "display_name": "Python [Root]",
+ "language": "python",
+ "name": "Python [Root]"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 2
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython2",
+ "version": "2.7.12"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}