Downloads: 1
[418e14]:
/
3_smart_data_processing.ipynb
15052 lines (15051 with data), 825.7 kB
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"%matplotlib inline\n",
"from IPython.display import display, HTML\n",
"import warnings\n",
"warnings.filterwarnings('ignore')"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import icu_data_defs\n",
"import load_and_segment "
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"#random state used for random things\n",
"random_state=42\n",
"\n",
"\n",
"#We will need a data dictionary for some of the cleaning steps\n",
"data_dict = icu_data_defs.data_dictionary('config/data_definitions.xlsx')\n",
"\n",
"hdf5_fname = 'data/mimic_data'\n",
"path = 'cleaned'\n",
"loader = load_and_segment.ByComponentLoadAndFilter(hdf5_fname,path,data_needs=None,load_at_init=False)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Train (80%): 47180 > [124598, 131721, 131768, 136497, 102605] ...\n",
"Validate (10%): 5898 > [117593, 153642, 103758, 168128, 153286] ...\n",
"Test (10%): 5898 > [199302, 108697, 151841, 121846, 186819] ...\n"
]
}
],
"source": [
"from sklearn.model_selection import train_test_split\n",
"import mimic\n",
"\n",
"all_ids = mimic.get_all_hadm_ids()\n",
"\n",
"#these test IDs will never be touched again. They are sacred\n",
"train_ids,test_ids = train_test_split(all_ids,test_size=0.1,random_state=random_state)\n",
"train_ids,validate_ids = train_test_split(train_ids,test_size=(1.0/9.0),random_state=random_state)\n",
"\n",
"print 'Train (80%):', len(train_ids),'>',train_ids[:5],'...'\n",
"print 'Validate (10%):', len(validate_ids),'>',validate_ids[:5],'...'\n",
"print 'Test (10%):', len(test_ids),'>',test_ids[:5],'...'"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# LABELS\n",
"\n",
"Our labels will be one random lactate sampled from each admission with 2 or more lactates, 2nd lactate or later\n",
"\n",
"To get to to eligible values, we will...\n",
"1. Use only quantitative data\n",
"2. We will combine all sources of quantitative data into a single columns based on UOM\n",
"3. We will keep only the largest of these columns\n",
"4. We will keep only admissions with 2 or more lactate values\n",
"\n",
"Full label pipeline..."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import features\n",
"import transformers\n",
"from constants import column_names,ALL\n",
"from sklearn.pipeline import Pipeline\n",
"from constants import variable_type"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#will ensure that there is at least 1 lactate before the sampled lactate\n",
"class keep_one_before_sample(features.preserve_datetime_sample):\n",
" \n",
" def transform(self, df, **transform_params):\n",
" df = df.groupby(level=column_names.ID).apply(lambda grp: grp.iloc[1:]).reset_index(0,drop=True)\n",
" return super(keep_one_before_sample,self).transform(df)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"Featurizer(features={(('lactate', 'all'),): {'SAMPLE': Feature(aggregator=keep_one_before_sample(levels=['id'], random_state=None),\n",
" col_filter=filter_to_component(components=['lactate']),\n",
" data_needs=[('lactate', 'all')], fillna_method=do_nothing(),\n",
" name='SAMPLE')}},\n",
" index_levels=['id'],\n",
" loader=ByComponentLoadAndFilter(chunksize=500000, data_needs=None,\n",
" hdf5_fname='data/mimic_data', load_at_init=False,\n",
" path='cleaned'),\n",
" post_cleaners=do_nothing(),\n",
" pre_cleaners=Pipeline(steps=[('quantitative only', filter_var_type(var_types=['qn'])), ('combine_like_columns', combine_like_cols()), ('max_col', max_col_only()), ('two_or_more_lactate', more_than_n_component(component='lactate', n=1)), ('dropna', dropna(axis=0, how='all'))]))"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"next_lactate_sampler = keep_one_before_sample(levels=[column_names.ID],random_state=random_state)\n",
"\n",
"labels = features.Feature(name=next_lactate_sampler.name, \n",
" data_needs=[(data_dict.components.LACTATE,ALL)],\n",
" col_filter=transformers.filter_to_component([data_dict.components.LACTATE]),\n",
" aggregator=next_lactate_sampler)\n",
"label_cleaner = Pipeline([\n",
" ('quantitative only',transformers.filter_var_type([variable_type.QUANTITATIVE])),\n",
" ('combine_like_columns',transformers.combine_like_cols()),\n",
" ('max_col',transformers.max_col_only()),\n",
" ('two_or_more_lactate',transformers.more_than_n_component(1,data_dict.components.LACTATE)),\n",
" ('dropna',transformers.dropna()),\n",
" ]) \n",
"\n",
"next_lactate_labelizer = features.Featurizer(index_levels=[column_names.ID], \n",
" loader=loader,features=[labels],\n",
" pre_cleaners=label_cleaner)\n",
"next_lactate_labelizer"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Features"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import numpy as np\n",
"from sklearn.pipeline import Pipeline\n",
"import load_and_segment"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/plain": [
"SegmentFeaturizer(features={(('blood pressure mean', 'all'),): {'STD': Feature(aggregator=aggregator(agg_func=<function std at 0x000000000432D898>,\n",
" levels=['id', 'seg_id'], name=None),\n",
" col_filter=filter_to_component(components=['blood pressure mean']),\n",
" data_needs=[('blood pressure mean', 'all')], fillna...,\n",
" data_needs=[('blood pressure systolic', 'all')],\n",
" fillna_method=fill_mean(), name='MEAN')}},\n",
" loader=LoadAndSegment(data_loader=ByComponentLoadAndFilter(chunksize=500000, data_needs=None,\n",
" hdf5_fname='data/mimic_data', load_at_init=False,\n",
" path='cleaned'),\n",
" segmenter=None),\n",
" post_cleaners=Pipeline(steps=[('post_cleaner_arg', do_nothing()), ('drop_no_segments', DropNoSegments())]),\n",
" pre_cleaners=Pipeline(steps=[('drop_small_columns', remove_small_columns(threshold=50)), ('drop_low_id_count', record_threshold(threshold=20)), ('quantitative only', filter_var_type(var_types=['qn'])), ('combine_like_columns', combine_like_cols())]),\n",
" segmenter=None)"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"def add_simple_feature(featurizer,component,agg_func,fillna_method):\n",
" featurizer.add_feature(\n",
" name=agg_func.func_name.upper(),\n",
" data_needs=[(component,ALL)],\n",
" col_filter=transformers.filter_to_component([component]),\n",
" agg_func=agg_func,\n",
" fillna_method=fillna_method,\n",
" )\n",
" return featurizer\n",
"\n",
"\"\"\"\n",
"HOW TO CLEAN DATA BEFORE FEATURES\n",
"\"\"\"\n",
"pre_cleaners = Pipeline([\n",
" ('drop_small_columns',transformers.remove_small_columns(threshold=50)),\n",
" ('drop_low_id_count',transformers.record_threshold(threshold=20)),\n",
" ('quantitative only',transformers.filter_var_type([variable_type.QUANTITATIVE])),\n",
" ('combine_like_columns',transformers.combine_like_cols()),\n",
" ])\n",
"\n",
"\"\"\"\n",
"FEATURES\n",
"\"\"\"\n",
"bp_featurizer = load_and_segment.SegmentFeaturizer(loader,segmenter=None,pre_cleaners=pre_cleaners)\n",
"\n",
"fill_mean = transformers.fill_mean\n",
"fill_zero = transformers.fill_zero\n",
"def count(grp): return grp.count()\n",
"\n",
"component = data_dict.components.BLOOD_PRESSURE_SYSTOLIC\n",
"add_simple_feature(bp_featurizer,component,np.mean,fill_mean())\n",
"add_simple_feature(bp_featurizer,component,np.std,fill_zero())\n",
"add_simple_feature(bp_featurizer,component,count,fill_zero())\n",
"add_simple_feature(bp_featurizer,component,features.last,fill_mean())\n",
"\n",
"component = data_dict.components.BLOOD_PRESSURE_DIASTOLIC\n",
"add_simple_feature(bp_featurizer,component,np.mean,fill_mean())\n",
"add_simple_feature(bp_featurizer,component,np.std,fill_zero())\n",
"add_simple_feature(bp_featurizer,component,count,fill_zero())\n",
"add_simple_feature(bp_featurizer,component,features.last,fill_mean())\n",
"\n",
"component = data_dict.components.BLOOD_PRESSURE_MEAN\n",
"add_simple_feature(bp_featurizer,component,np.mean,fill_mean())\n",
"add_simple_feature(bp_featurizer,component,np.std,fill_zero())\n",
"add_simple_feature(bp_featurizer,component,count,fill_zero())\n",
"add_simple_feature(bp_featurizer,component,features.last,fill_mean())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# ALL before lactate"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"import mimic\n",
"import transformers\n",
"import utils\n",
"import constants"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def print_fillna_params(featurizer):\n",
" for dn,f_dict in featurizer.features.iteritems() :\n",
" for name,f in f_dict.iteritems():\n",
" print dn,name\n",
" fillna_method = f.fillna_method\n",
" print fillna_method\n",
" try:\n",
" display(fillna_method.means.to_frame().T)\n",
" except:\n",
" continue\n",
" return"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"labelizer = sample_one_lactate_labelizer\n",
"featurizer = bp_featurizer\n",
"featurizer.loader.segmenter = load_and_segment.n_hrs_before(n_hrs=constants.ALL)"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(2017-07-04 11:56:26)<<<<<< --- (25.0s)\n",
"(2017-07-04 11:56:26)>>>>>> Featurizing...\n",
"(2017-07-04 11:56:26)>>>>>>>> [('lactate', 'all')] - SAMPLE\n",
"(2017-07-04 11:56:26)>>>>>>>>>> DASK OPEN & JOIN n=1 components: ['lactate']\n",
"(2017-07-04 11:56:26)>>>>>>>>>>>> LACTATE: 1/1\n",
"(2017-07-04 11:56:26)>>>>>>>>>>>>>> Convert to dask - (142518, 63)\n",
"(2017-07-04 11:56:26)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>>>>>> Join to big DF\n",
"(2017-07-04 11:56:26)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>>>> Dask DF back to pandas\n",
"(2017-07-04 11:56:26)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>>>> SORT Joined DF\n",
"(2017-07-04 11:56:26)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>> *fit* Filter columns (DataNeedsFilter) (142518, 63)\n",
"(2017-07-04 11:56:26)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>> *transform* Filter columns (DataNeedsFilter) (142518, 63)\n",
"(2017-07-04 11:56:26)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>> *fit* Filter columns (filter_var_type) (142518, 63)\n",
"(2017-07-04 11:56:26)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>> *transform* Filter columns (filter_var_type) (142518, 63)\n",
"(2017-07-04 11:56:26)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>> FIT Combine like columns (142518, 7)\n",
"(2017-07-04 11:56:26)>>>>>>>>>>>> ('lactate', 'known', 'qn', 'mmol/L')\n",
"(2017-07-04 11:56:26)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>>>> ('lactate', 'unknown', 'qn', 'no_units')\n",
"(2017-07-04 11:56:26)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:26)>>>>>>>>>> TRANSFORM Combine like columns (142518, 7)\n",
"(2017-07-04 11:56:26)>>>>>>>>>>>> ('lactate', 'unknown', 'qn', 'no_units')\n",
"(2017-07-04 11:56:30)<<<<<<<<<<<< --- (4.0s)\n",
"(2017-07-04 11:56:30)>>>>>>>>>>>> ('lactate', 'known', 'qn', 'mmol/L')\n",
"(2017-07-04 11:56:33)<<<<<<<<<<<< --- (3.0s)\n",
"(2017-07-04 11:56:33)<<<<<<<<<< --- (7.0s)\n",
"(2017-07-04 11:56:33)>>>>>>>>>> *fit* Filter columns (max_col_only) (142518, 2)\n",
"(2017-07-04 11:56:33)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:33)>>>>>>>>>> *transform* Filter columns (max_col_only) (142518, 2)\n",
"(2017-07-04 11:56:33)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:33)>>>>>>>>>> fit_transform features on DF (134782, 1)\n",
"(2017-07-04 11:56:33)>>>>>>>>>>>> SAMPLE\n",
"(2017-07-04 11:56:33)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:33)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (134782, 1)\n",
"(2017-07-04 11:56:33)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:33)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (134782, 1)\n",
"component lactate\n",
"status known\n",
"variable_type qn\n",
"units mmol/L\n",
"description all\n",
"id datetime \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",
"feature SAMPLE\n",
"component lactate\n",
"status known\n",
"variable_type qn\n",
"units mmol/L\n",
"description all\n",
"id datetime \n",
"100009 2162-05-17 17:14:00 1.5\n",
"100010 2109-12-10 12:11:00 0.9\n",
"100011 2177-08-29 06:55:00 2.3\n",
"100018 2176-08-30 10:19:00 1.0\n",
"100020 2142-12-03 00:17:00 1.0\n",
"(2017-07-04 11:56:56)<<<<<<<<<<<< --- (23.0s)\n",
"(2017-07-04 11:56:56)<<<<<<<<<< --- (23.0s)\n",
"(2017-07-04 11:56:56)<<<<<<<< --- (30.0s)\n",
"(2017-07-04 11:56:56)<<<<<< --- (30.0s)\n",
"(2017-07-04 11:56:56)>>>>>> Featurizing...\n",
"(2017-07-04 11:56:56)>>>>>>>> [('blood pressure mean', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-04 11:56:56)>>>>>>>>>> DASK OPEN & JOIN n=1 components: ['blood pressure mean']\n",
"(2017-07-04 11:56:56)>>>>>>>>>>>> BLOOD PRESSURE MEAN: 1/1\n",
"(2017-07-04 11:56:57)>>>>>>>>>>>>>> Convert to dask - (1513298, 3)\n",
"(2017-07-04 11:56:57)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:57)>>>>>>>>>>>>>> Join to big DF\n",
"(2017-07-04 11:56:57)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:57)<<<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 11:56:57)>>>>>>>>>>>> Dask DF back to pandas\n",
"(2017-07-04 11:56:58)<<<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 11:56:58)>>>>>>>>>>>> SORT Joined DF\n",
"(2017-07-04 11:56:58)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:58)<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 11:56:58)>>>>>>>>>> *fit* Filter columns (DataNeedsFilter) (1513298, 3)\n",
"(2017-07-04 11:56:58)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:58)>>>>>>>>>> *transform* Filter columns (DataNeedsFilter) (1513298, 3)\n",
"(2017-07-04 11:56:58)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:58)>>>>>>>>>> Segment df (1513298, 3)\n",
"(2017-07-04 11:56:58)>>>>>>>>>>>> Get Segments\n",
"(2017-07-04 11:56:58)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 11:56:58)>>>>>>>>>>>> Apply n=19793 Segments to df.shape = (1513298, 3)\n",
"(2017-07-04 12:21:25)<<<<<<<<<<<< --- (1467.0s)\n",
"(2017-07-04 12:21:25)<<<<<<<<<< --- (1467.0s)\n",
"(2017-07-04 12:21:25)>>>>>>>>>> *fit* Filter columns (remove_small_columns) (1526462, 3)\n",
"(2017-07-04 12:21:25)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:21:25)>>>>>>>>>> *transform* Filter columns (remove_small_columns) (1526462, 3)\n",
"(2017-07-04 12:21:25)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:21:25)>>>>>>>>>> *fit* Filter columns (record_threshold) (1526462, 3)\n",
"(2017-07-04 12:21:25)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:21:25)>>>>>>>>>> *transform* Filter columns (record_threshold) (1526462, 3)\n",
"(2017-07-04 12:21:25)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:21:25)>>>>>>>>>> *fit* Filter columns (filter_var_type) (1526462, 3)\n",
"(2017-07-04 12:21:25)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:21:25)>>>>>>>>>> *transform* Filter columns (filter_var_type) (1526462, 3)\n",
"(2017-07-04 12:21:25)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:21:25)>>>>>>>>>> FIT Combine like columns (1526462, 3)\n",
"(2017-07-04 12:21:25)>>>>>>>>>>>> ('blood pressure mean', 'known', 'qn', 'mmHg')\n",
"(2017-07-04 12:21:25)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:21:25)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:21:25)>>>>>>>>>> TRANSFORM Combine like columns (1526462, 3)\n",
"(2017-07-04 12:21:25)>>>>>>>>>>>> ('blood pressure mean', 'known', 'qn', 'mmHg')\n",
"(2017-07-04 12:22:00)<<<<<<<<<<<< --- (35.0s)\n",
"(2017-07-04 12:22:00)<<<<<<<<<< --- (35.0s)\n",
"(2017-07-04 12:22:00)>>>>>>>>>> fit_transform features on DF (1526462, 1)\n",
"(2017-07-04 12:22:00)>>>>>>>>>>>> STD\n",
"(2017-07-04 12:22:00)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:00)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-07-04 12:22:00)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:00)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (1526462, 1)\n",
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 79.0\n",
" 2162-05-17 18:25:00 76.0\n",
" 2162-05-17 18:30:00 77.0\n",
" 2162-05-17 18:45:00 69.0\n",
" 2162-05-17 19:00:00 67.0\n",
"feature STD\n",
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 7.505409\n",
" 0 0.000000\n",
"100010 -1 23.165879\n",
" 0 0.000000\n",
"100011 -1 11.599159\n",
"(2017-07-04 12:22:00)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:00)>>>>>>>>>>>> COUNT\n",
"(2017-07-04 12:22:00)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:00)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-07-04 12:22:00)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:00)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (1526462, 1)\n",
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 79.0\n",
" 2162-05-17 18:25:00 76.0\n",
" 2162-05-17 18:30:00 77.0\n",
" 2162-05-17 18:45:00 69.0\n",
" 2162-05-17 19:00:00 67.0\n",
"feature COUNT\n",
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 56.0\n",
" 0 0.0\n",
"100010 -1 42.0\n",
" 0 0.0\n",
"100011 -1 289.0\n",
"(2017-07-04 12:22:04)<<<<<<<<<<<< --- (4.0s)\n",
"(2017-07-04 12:22:04)>>>>>>>>>>>> LAST\n",
"(2017-07-04 12:22:04)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:04)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-07-04 12:22:04)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:04)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (1526462, 1)\n",
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 79.0\n",
" 2162-05-17 18:25:00 76.0\n",
" 2162-05-17 18:30:00 77.0\n",
" 2162-05-17 18:45:00 69.0\n",
" 2162-05-17 19:00:00 67.0\n",
"feature LAST\n",
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 70.000000\n",
" 0 75.758916\n",
"100010 -1 79.000000\n",
" 0 75.758916\n",
"100011 -1 88.000000\n",
"(2017-07-04 12:22:25)<<<<<<<<<<<< --- (21.0s)\n",
"(2017-07-04 12:22:25)>>>>>>>>>>>> MEAN\n",
"(2017-07-04 12:22:25)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:25)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-07-04 12:22:25)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:25)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (1526462, 1)\n",
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 79.0\n",
" 2162-05-17 18:25:00 76.0\n",
" 2162-05-17 18:30:00 77.0\n",
" 2162-05-17 18:45:00 69.0\n",
" 2162-05-17 19:00:00 67.0\n",
"feature MEAN\n",
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 66.178571\n",
" 0 77.487629\n",
"100010 -1 73.976190\n",
" 0 77.487629\n",
"100011 -1 88.910035\n",
"(2017-07-04 12:22:25)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:25)<<<<<<<<<< --- (25.0s)\n",
"(2017-07-04 12:22:25)<<<<<<<< --- (1529.0s)\n",
"(2017-07-04 12:22:25)>>>>>>>> [('blood pressure diastolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-04 12:22:25)>>>>>>>>>> DASK OPEN & JOIN n=1 components: ['blood pressure diastolic']\n",
"(2017-07-04 12:22:25)>>>>>>>>>>>> BLOOD PRESSURE DIASTOLIC: 1/1\n",
"(2017-07-04 12:22:30)>>>>>>>>>>>>>> Convert to dask - (3457122, 42)\n",
"(2017-07-04 12:22:32)<<<<<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 12:22:32)>>>>>>>>>>>>>> Join to big DF\n",
"(2017-07-04 12:22:32)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:32)<<<<<<<<<<<< --- (7.0s)\n",
"(2017-07-04 12:22:32)>>>>>>>>>>>> Dask DF back to pandas\n",
"(2017-07-04 12:22:34)<<<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 12:22:34)>>>>>>>>>>>> SORT Joined DF\n",
"(2017-07-04 12:22:36)<<<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 12:22:36)<<<<<<<<<< --- (11.0s)\n",
"(2017-07-04 12:22:37)>>>>>>>>>> *fit* Filter columns (DataNeedsFilter) (3457122, 42)\n",
"(2017-07-04 12:22:37)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:37)>>>>>>>>>> *transform* Filter columns (DataNeedsFilter) (3457122, 42)\n",
"(2017-07-04 12:22:38)<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 12:22:38)>>>>>>>>>> Segment df (3457122, 42)\n",
"(2017-07-04 12:22:38)>>>>>>>>>>>> Get Segments\n",
"(2017-07-04 12:22:38)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 12:22:38)>>>>>>>>>>>> Apply n=19793 Segments to df.shape = (3457122, 42)\n",
"(2017-07-04 14:19:40)<<<<<<<<<<<< --- (7022.0s)\n",
"(2017-07-04 14:19:40)<<<<<<<<<< --- (7022.0s)\n",
"(2017-07-04 14:19:40)>>>>>>>>>> *fit* Filter columns (remove_small_columns) (3463407, 42)\n",
"(2017-07-04 14:19:40)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:19:40)>>>>>>>>>> *transform* Filter columns (remove_small_columns) (3463407, 42)\n",
"(2017-07-04 14:19:41)<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 14:19:41)>>>>>>>>>> *fit* Filter columns (record_threshold) (3463407, 36)\n",
"(2017-07-04 14:19:43)<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 14:19:43)>>>>>>>>>> *transform* Filter columns (record_threshold) (3463407, 36)\n",
"(2017-07-04 14:19:44)<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 14:19:44)>>>>>>>>>> *fit* Filter columns (filter_var_type) (3463407, 35)\n",
"(2017-07-04 14:19:44)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:19:44)>>>>>>>>>> *transform* Filter columns (filter_var_type) (3463407, 35)\n",
"(2017-07-04 14:19:44)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:19:44)>>>>>>>>>> FIT Combine like columns (3463407, 9)\n",
"(2017-07-04 14:19:44)>>>>>>>>>>>> ('blood pressure diastolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-04 14:19:44)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:19:44)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:19:44)>>>>>>>>>> TRANSFORM Combine like columns (3463407, 9)\n",
"(2017-07-04 14:19:44)>>>>>>>>>>>> ('blood pressure diastolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-04 14:20:53)<<<<<<<<<<<< --- (69.0s)\n",
"(2017-07-04 14:20:53)<<<<<<<<<< --- (69.0s)\n",
"(2017-07-04 14:20:53)>>>>>>>>>> fit_transform features on DF (3463407, 1)\n",
"(2017-07-04 14:20:53)>>>>>>>>>>>> STD\n",
"(2017-07-04 14:20:53)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:20:53)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-04 14:20:53)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:20:53)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (3463407, 1)\n",
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 58.0\n",
" 2162-05-17 18:25:00 56.0\n",
" 2162-05-17 18:30:00 58.0\n",
" 2162-05-17 18:45:00 53.0\n",
" 2162-05-17 19:00:00 51.0\n",
"feature STD\n",
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 6.118248\n",
" 0 0.000000\n",
"100010 -1 22.639797\n",
" 0 0.000000\n",
"100011 -1 11.973983\n",
"(2017-07-04 14:20:54)<<<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 14:20:54)>>>>>>>>>>>> COUNT\n",
"(2017-07-04 14:20:54)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:20:54)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-04 14:20:54)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:20:54)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (3463407, 1)\n",
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 58.0\n",
" 2162-05-17 18:25:00 56.0\n",
" 2162-05-17 18:30:00 58.0\n",
" 2162-05-17 18:45:00 53.0\n",
" 2162-05-17 19:00:00 51.0\n",
"feature COUNT\n",
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 57.0\n",
" 0 0.0\n",
"100010 -1 42.0\n",
" 0 0.0\n",
"100011 -1 288.0\n",
"(2017-07-04 14:21:00)<<<<<<<<<<<< --- (6.0s)\n",
"(2017-07-04 14:21:00)>>>>>>>>>>>> LAST\n",
"(2017-07-04 14:21:00)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:21:00)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-04 14:21:00)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:21:00)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (3463407, 1)\n",
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 58.0\n",
" 2162-05-17 18:25:00 56.0\n",
" 2162-05-17 18:30:00 58.0\n",
" 2162-05-17 18:45:00 53.0\n",
" 2162-05-17 19:00:00 51.0\n",
"feature LAST\n",
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 58.000000\n",
" 0 58.870209\n",
"100010 -1 55.000000\n",
" 0 58.870209\n",
"100011 -1 67.000000\n",
"(2017-07-04 14:21:34)<<<<<<<<<<<< --- (34.0s)\n",
"(2017-07-04 14:21:34)>>>>>>>>>>>> MEAN\n",
"(2017-07-04 14:21:34)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:21:34)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-04 14:21:34)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:21:34)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (3463407, 1)\n",
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 58.0\n",
" 2162-05-17 18:25:00 56.0\n",
" 2162-05-17 18:30:00 58.0\n",
" 2162-05-17 18:45:00 53.0\n",
" 2162-05-17 19:00:00 51.0\n",
"feature MEAN\n",
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 51.175439\n",
" 0 60.420185\n",
"100010 -1 58.690476\n",
" 0 60.420185\n",
"100011 -1 69.756944\n",
"(2017-07-04 14:21:34)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:21:34)<<<<<<<<<< --- (41.0s)\n",
"(2017-07-04 14:21:34)<<<<<<<< --- (7149.0s)\n",
"(2017-07-04 14:21:34)>>>>>>>> [('blood pressure systolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-04 14:21:34)>>>>>>>>>> DASK OPEN & JOIN n=1 components: ['blood pressure systolic']\n",
"(2017-07-04 14:21:34)>>>>>>>>>>>> BLOOD PRESSURE SYSTOLIC: 1/1\n",
"(2017-07-04 14:21:39)>>>>>>>>>>>>>> Convert to dask - (3455115, 40)\n",
"(2017-07-04 14:21:41)<<<<<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 14:21:41)>>>>>>>>>>>>>> Join to big DF\n",
"(2017-07-04 14:21:41)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:21:41)<<<<<<<<<<<< --- (7.0s)\n",
"(2017-07-04 14:21:41)>>>>>>>>>>>> Dask DF back to pandas\n",
"(2017-07-04 14:21:43)<<<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 14:21:43)>>>>>>>>>>>> SORT Joined DF\n",
"(2017-07-04 14:21:45)<<<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 14:21:45)<<<<<<<<<< --- (11.0s)\n",
"(2017-07-04 14:21:46)>>>>>>>>>> *fit* Filter columns (DataNeedsFilter) (3455115, 40)\n",
"(2017-07-04 14:21:46)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:21:46)>>>>>>>>>> *transform* Filter columns (DataNeedsFilter) (3455115, 40)\n",
"(2017-07-04 14:21:46)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:21:46)>>>>>>>>>> Segment df (3455115, 40)\n",
"(2017-07-04 14:21:46)>>>>>>>>>>>> Get Segments\n",
"(2017-07-04 14:21:46)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 14:21:46)>>>>>>>>>>>> Apply n=19793 Segments to df.shape = (3455115, 40)\n",
"(2017-07-04 16:18:20)<<<<<<<<<<<< --- (6994.0s)\n",
"(2017-07-04 16:18:20)<<<<<<<<<< --- (6994.0s)\n",
"(2017-07-04 16:18:20)>>>>>>>>>> *fit* Filter columns (remove_small_columns) (3461400, 40)\n",
"(2017-07-04 16:18:20)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:18:20)>>>>>>>>>> *transform* Filter columns (remove_small_columns) (3461400, 40)\n",
"(2017-07-04 16:18:21)<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:18:21)>>>>>>>>>> *fit* Filter columns (record_threshold) (3461400, 35)\n",
"(2017-07-04 16:18:23)<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 16:18:23)>>>>>>>>>> *transform* Filter columns (record_threshold) (3461400, 35)\n",
"(2017-07-04 16:18:24)<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:18:24)>>>>>>>>>> *fit* Filter columns (filter_var_type) (3461400, 34)\n",
"(2017-07-04 16:18:24)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:18:24)>>>>>>>>>> *transform* Filter columns (filter_var_type) (3461400, 34)\n",
"(2017-07-04 16:18:24)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:18:24)>>>>>>>>>> FIT Combine like columns (3461400, 8)\n",
"(2017-07-04 16:18:24)>>>>>>>>>>>> ('blood pressure systolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-04 16:18:24)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:18:24)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:18:24)>>>>>>>>>> TRANSFORM Combine like columns (3461400, 8)\n",
"(2017-07-04 16:18:24)>>>>>>>>>>>> ('blood pressure systolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-04 16:19:34)<<<<<<<<<<<< --- (70.0s)\n",
"(2017-07-04 16:19:34)<<<<<<<<<< --- (70.0s)\n",
"(2017-07-04 16:19:34)>>>>>>>>>> fit_transform features on DF (3461400, 1)\n",
"(2017-07-04 16:19:34)>>>>>>>>>>>> STD\n",
"(2017-07-04 16:19:34)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:19:34)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-04 16:19:34)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:19:34)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (3461400, 1)\n",
"component blood pressure systolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 128.0\n",
" 2162-05-17 18:25:00 123.0\n",
" 2162-05-17 18:30:00 125.0\n",
" 2162-05-17 18:45:00 111.0\n",
" 2162-05-17 19:00:00 109.0\n",
"feature STD\n",
"component blood pressure systolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 12.652033\n",
" 0 0.000000\n",
"100010 -1 25.086667\n",
" 0 0.000000\n",
"100011 -1 15.720698\n",
"(2017-07-04 16:19:34)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:19:34)>>>>>>>>>>>> COUNT\n",
"(2017-07-04 16:19:34)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:19:34)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-04 16:19:34)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:19:34)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (3461400, 1)\n",
"component blood pressure systolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 128.0\n",
" 2162-05-17 18:25:00 123.0\n",
" 2162-05-17 18:30:00 125.0\n",
" 2162-05-17 18:45:00 111.0\n",
" 2162-05-17 19:00:00 109.0\n",
"feature COUNT\n",
"component blood pressure systolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 57.0\n",
" 0 0.0\n",
"100010 -1 42.0\n",
" 0 0.0\n",
"100011 -1 288.0\n",
"(2017-07-04 16:19:40)<<<<<<<<<<<< --- (6.0s)\n",
"(2017-07-04 16:19:40)>>>>>>>>>>>> LAST\n",
"(2017-07-04 16:19:40)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:19:40)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-04 16:19:40)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:19:40)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (3461400, 1)\n",
"component blood pressure systolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 128.0\n",
" 2162-05-17 18:25:00 123.0\n",
" 2162-05-17 18:30:00 125.0\n",
" 2162-05-17 18:45:00 111.0\n",
" 2162-05-17 19:00:00 109.0\n",
"feature LAST\n",
"component blood pressure systolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 105.000000\n",
" 0 115.628637\n",
"100010 -1 124.000000\n",
" 0 115.628637\n",
"100011 -1 149.000000\n",
"(2017-07-04 16:20:14)<<<<<<<<<<<< --- (34.0s)\n",
"(2017-07-04 16:20:14)>>>>>>>>>>>> MEAN\n",
"(2017-07-04 16:20:14)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:14)>>>>>>>>>>>> *fit* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-04 16:20:14)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:14)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (3461400, 1)\n",
"component blood pressure systolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id datetime \n",
"100009 -1 2162-05-17 18:23:00 128.0\n",
" 2162-05-17 18:25:00 123.0\n",
" 2162-05-17 18:30:00 125.0\n",
" 2162-05-17 18:45:00 111.0\n",
" 2162-05-17 19:00:00 109.0\n",
"feature MEAN\n",
"component blood pressure systolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"id seg_id \n",
"100009 -1 110.543860\n",
" 0 118.662692\n",
"100010 -1 101.976190\n",
" 0 118.662692\n",
"100011 -1 144.402778\n",
"(2017-07-04 16:20:14)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:14)<<<<<<<<<< --- (40.0s)\n",
"(2017-07-04 16:20:14)<<<<<<<< --- (7120.0s)\n",
"(2017-07-04 16:20:14)<<<<<< --- (15798.0s)\n"
]
}
],
"source": [
"#TRAIN\n",
"y_train1 = labelizer.fit_transform(X=train_ids)\n",
"X_train1 = featurizer.fit_transform(X=y_train1)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"collapsed": false
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(19793, 12) (19793, 1)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</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>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>qn</th>\n",
" <th>qn</th>\n",
" <th>qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" </tr>\n",
" <tr>\n",
" <th>id</th>\n",
" <th>seg_id</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>100009</th>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100010</th>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100011</th>\n",
" <th>0</th>\n",
" <td>10.737784</td>\n",
" <td>5.0</td>\n",
" <td>64.000000</td>\n",
" <td>70.600000</td>\n",
" <td>11.606033</td>\n",
" <td>5.0</td>\n",
" <td>46.000000</td>\n",
" <td>57.800000</td>\n",
" <td>11.300442</td>\n",
" <td>5.0</td>\n",
" <td>102.000000</td>\n",
" <td>108.800000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100018</th>\n",
" <th>0</th>\n",
" <td>9.917247</td>\n",
" <td>23.0</td>\n",
" <td>89.000000</td>\n",
" <td>79.521739</td>\n",
" <td>6.660010</td>\n",
" <td>23.0</td>\n",
" <td>64.000000</td>\n",
" <td>57.086957</td>\n",
" <td>15.660176</td>\n",
" <td>23.0</td>\n",
" <td>133.000000</td>\n",
" <td>124.826087</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100020</th>\n",
" <th>0</th>\n",
" <td>21.120986</td>\n",
" <td>29.0</td>\n",
" <td>90.000000</td>\n",
" <td>87.103448</td>\n",
" <td>18.688001</td>\n",
" <td>29.0</td>\n",
" <td>71.000000</td>\n",
" <td>72.206897</td>\n",
" <td>31.660686</td>\n",
" <td>29.0</td>\n",
" <td>144.000000</td>\n",
" <td>135.551724</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature STD COUNT LAST \\\n",
"component blood pressure mean blood pressure mean blood pressure mean \n",
"status known known known \n",
"variable_type qn qn qn \n",
"units mmHg mmHg mmHg \n",
"description all all all \n",
"id seg_id \n",
"100009 0 0.000000 0.0 75.758916 \n",
"100010 0 0.000000 0.0 75.758916 \n",
"100011 0 10.737784 5.0 64.000000 \n",
"100018 0 9.917247 23.0 89.000000 \n",
"100020 0 21.120986 29.0 90.000000 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure mean blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100009 0 77.487629 0.000000 \n",
"100010 0 77.487629 0.000000 \n",
"100011 0 70.600000 11.606033 \n",
"100018 0 79.521739 6.660010 \n",
"100020 0 87.103448 18.688001 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure diastolic blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100009 0 0.0 58.870209 \n",
"100010 0 0.0 58.870209 \n",
"100011 0 5.0 46.000000 \n",
"100018 0 23.0 64.000000 \n",
"100020 0 29.0 71.000000 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure diastolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100009 0 60.420185 0.000000 \n",
"100010 0 60.420185 0.000000 \n",
"100011 0 57.800000 11.300442 \n",
"100018 0 57.086957 15.660176 \n",
"100020 0 72.206897 31.660686 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure systolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100009 0 0.0 115.628637 \n",
"100010 0 0.0 115.628637 \n",
"100011 0 5.0 102.000000 \n",
"100018 0 23.0 133.000000 \n",
"100020 0 29.0 144.000000 \n",
"\n",
"feature MEAN \n",
"component blood pressure systolic \n",
"status known \n",
"variable_type qn \n",
"units mmHg \n",
"description all \n",
"id seg_id \n",
"100009 0 118.662692 \n",
"100010 0 118.662692 \n",
"100011 0 108.800000 \n",
"100018 0 124.826087 \n",
"100020 0 135.551724 "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>SAMPLE</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</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></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>100009</th>\n",
" <th>2162-05-17 17:14:00</th>\n",
" <td>1.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100010</th>\n",
" <th>2109-12-10 12:11:00</th>\n",
" <td>0.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100011</th>\n",
" <th>2177-08-29 06:55:00</th>\n",
" <td>2.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100018</th>\n",
" <th>2176-08-30 10:19:00</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100020</th>\n",
" <th>2142-12-03 00:17:00</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature SAMPLE\n",
"component lactate\n",
"status known\n",
"variable_type qn\n",
"units mmol/L\n",
"description all\n",
"id datetime \n",
"100009 2162-05-17 17:14:00 1.5\n",
"100010 2109-12-10 12:11:00 0.9\n",
"100011 2177-08-29 06:55:00 2.3\n",
"100018 2176-08-30 10:19:00 1.0\n",
"100020 2142-12-03 00:17:00 1.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure mean', 'all'),) STD\n",
"fill_zero()\n",
"(('blood pressure mean', 'all'),) COUNT\n",
"fill_zero()\n",
"(('blood pressure mean', 'all'),) LAST\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>75.758916</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"0 75.758916"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure mean', 'all'),) MEAN\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>77.487629</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"0 77.487629"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure diastolic', 'all'),) STD\n",
"fill_zero()\n",
"(('blood pressure diastolic', 'all'),) COUNT\n",
"fill_zero()\n",
"(('blood pressure diastolic', 'all'),) LAST\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>58.870209</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"0 58.870209"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure diastolic', 'all'),) MEAN\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>60.420185</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"0 60.420185"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure systolic', 'all'),) STD\n",
"fill_zero()\n",
"(('blood pressure systolic', 'all'),) COUNT\n",
"fill_zero()\n",
"(('blood pressure systolic', 'all'),) LAST\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>115.628637</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 all\n",
"0 115.628637"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure systolic', 'all'),) MEAN\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>118.662692</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 all\n",
"0 118.662692"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print X_train1.shape,y_train1.shape\n",
"display(X_train1.head())\n",
"display(y_train1.head())\n",
"\n",
"print_fillna_params(featurizer)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(2017-07-04 16:20:15)>>>>>> Featurizing...\n",
"(2017-07-04 16:20:15)>>>>>>>> [('lactate', 'all')] - SAMPLE\n",
"(2017-07-04 16:20:15)>>>>>>>>>> DASK OPEN & JOIN n=1 components: ['lactate']\n",
"(2017-07-04 16:20:15)>>>>>>>>>>>> LACTATE: 1/1\n",
"(2017-07-04 16:20:15)>>>>>>>>>>>>>> Convert to dask - (17859, 63)\n",
"(2017-07-04 16:20:15)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:15)>>>>>>>>>>>>>> Join to big DF\n",
"(2017-07-04 16:20:15)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:15)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:15)>>>>>>>>>>>> Dask DF back to pandas\n",
"(2017-07-04 16:20:15)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:15)>>>>>>>>>>>> SORT Joined DF\n",
"(2017-07-04 16:20:17)<<<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 16:20:17)<<<<<<<<<< --- (2.0s)\n",
"(2017-07-04 16:20:17)>>>>>>>>>> *fit* Filter columns (DataNeedsFilter) (17859, 63)\n",
"(2017-07-04 16:20:17)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:17)>>>>>>>>>> *transform* Filter columns (DataNeedsFilter) (17859, 63)\n",
"(2017-07-04 16:20:17)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:17)>>>>>>>>>> *transform* Filter columns (filter_var_type) (17859, 63)\n",
"(2017-07-04 16:20:17)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:17)>>>>>>>>>> TRANSFORM Combine like columns (17859, 7)\n",
"(2017-07-04 16:20:17)>>>>>>>>>>>> ('lactate', 'unknown', 'qn', 'no_units')\n",
"(2017-07-04 16:20:17)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:17)>>>>>>>>>>>> ('lactate', 'known', 'qn', 'mmol/L')\n",
"(2017-07-04 16:20:18)<<<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:20:18)<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:20:18)>>>>>>>>>> *transform* Filter columns (max_col_only) (17859, 2)\n",
"(2017-07-04 16:20:18)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:18)>>>>>>>>>> transform features on DF (16926, 1)\n",
"(2017-07-04 16:20:18)>>>>>>>>>>>> SAMPLE\n",
"(2017-07-04 16:20:18)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:18)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (16926, 1)\n",
"(2017-07-04 16:20:21)<<<<<<<<<<<< --- (3.0s)\n",
"(2017-07-04 16:20:21)<<<<<<<<<< --- (3.0s)\n",
"(2017-07-04 16:20:21)<<<<<<<< --- (6.0s)\n",
"(2017-07-04 16:20:21)<<<<<< --- (6.0s)\n",
"(2017-07-04 16:20:21)>>>>>> Featurizing...\n",
"(2017-07-04 16:20:21)>>>>>>>> [('blood pressure mean', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-04 16:20:21)>>>>>>>>>> DASK OPEN & JOIN n=1 components: ['blood pressure mean']\n",
"(2017-07-04 16:20:21)>>>>>>>>>>>> BLOOD PRESSURE MEAN: 1/1\n",
"(2017-07-04 16:20:22)>>>>>>>>>>>>>> Convert to dask - (227456, 3)\n",
"(2017-07-04 16:20:22)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:22)>>>>>>>>>>>>>> Join to big DF\n",
"(2017-07-04 16:20:22)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:22)<<<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:20:22)>>>>>>>>>>>> Dask DF back to pandas\n",
"(2017-07-04 16:20:22)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:22)>>>>>>>>>>>> SORT Joined DF\n",
"(2017-07-04 16:20:22)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:22)<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:20:22)>>>>>>>>>> *fit* Filter columns (DataNeedsFilter) (227456, 3)\n",
"(2017-07-04 16:20:22)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:22)>>>>>>>>>> *transform* Filter columns (DataNeedsFilter) (227456, 3)\n",
"(2017-07-04 16:20:22)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:22)>>>>>>>>>> Segment df (227456, 3)\n",
"(2017-07-04 16:20:22)>>>>>>>>>>>> Get Segments\n",
"(2017-07-04 16:20:22)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:20:22)>>>>>>>>>>>> Apply n=2482 Segments to df.shape = (227456, 3)\n",
"(2017-07-04 16:21:00)<<<<<<<<<<<< --- (38.0s)\n",
"(2017-07-04 16:21:00)<<<<<<<<<< --- (38.0s)\n",
"(2017-07-04 16:21:00)>>>>>>>>>> *transform* Filter columns (remove_small_columns) (229085, 3)\n",
"(2017-07-04 16:21:00)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:00)>>>>>>>>>> *transform* Filter columns (record_threshold) (229085, 3)\n",
"(2017-07-04 16:21:00)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:00)>>>>>>>>>> *transform* Filter columns (filter_var_type) (229085, 3)\n",
"(2017-07-04 16:21:00)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:00)>>>>>>>>>> TRANSFORM Combine like columns (229085, 3)\n",
"(2017-07-04 16:21:00)>>>>>>>>>>>> ('blood pressure mean', 'known', 'qn', 'mmHg')\n",
"(2017-07-04 16:21:06)<<<<<<<<<<<< --- (6.0s)\n",
"(2017-07-04 16:21:06)<<<<<<<<<< --- (6.0s)\n",
"(2017-07-04 16:21:06)>>>>>>>>>> transform features on DF (229085, 1)\n",
"(2017-07-04 16:21:06)>>>>>>>>>>>> STD\n",
"(2017-07-04 16:21:06)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:06)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (229085, 1)\n",
"(2017-07-04 16:21:06)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:06)>>>>>>>>>>>> COUNT\n",
"(2017-07-04 16:21:06)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:06)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (229085, 1)\n",
"(2017-07-04 16:21:07)<<<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:21:07)>>>>>>>>>>>> LAST\n",
"(2017-07-04 16:21:07)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:07)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (229085, 1)\n",
"(2017-07-04 16:21:10)<<<<<<<<<<<< --- (3.0s)\n",
"(2017-07-04 16:21:10)>>>>>>>>>>>> MEAN\n",
"(2017-07-04 16:21:10)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:10)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (229085, 1)\n",
"(2017-07-04 16:21:10)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:10)<<<<<<<<<< --- (4.0s)\n",
"(2017-07-04 16:21:10)<<<<<<<< --- (49.0s)\n",
"(2017-07-04 16:21:10)>>>>>>>> [('blood pressure diastolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-04 16:21:10)>>>>>>>>>> DASK OPEN & JOIN n=1 components: ['blood pressure diastolic']\n",
"(2017-07-04 16:21:10)>>>>>>>>>>>> BLOOD PRESSURE DIASTOLIC: 1/1\n",
"(2017-07-04 16:21:14)>>>>>>>>>>>>>> Convert to dask - (457700, 42)\n",
"(2017-07-04 16:21:15)<<<<<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:21:15)>>>>>>>>>>>>>> Join to big DF\n",
"(2017-07-04 16:21:15)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:15)<<<<<<<<<<<< --- (5.0s)\n",
"(2017-07-04 16:21:15)>>>>>>>>>>>> Dask DF back to pandas\n",
"(2017-07-04 16:21:15)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:15)>>>>>>>>>>>> SORT Joined DF\n",
"(2017-07-04 16:21:15)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:15)<<<<<<<<<< --- (5.0s)\n",
"(2017-07-04 16:21:15)>>>>>>>>>> *fit* Filter columns (DataNeedsFilter) (457700, 42)\n",
"(2017-07-04 16:21:16)<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:21:16)>>>>>>>>>> *transform* Filter columns (DataNeedsFilter) (457700, 42)\n",
"(2017-07-04 16:21:16)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:16)>>>>>>>>>> Segment df (457700, 42)\n",
"(2017-07-04 16:21:16)>>>>>>>>>>>> Get Segments\n",
"(2017-07-04 16:21:16)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:21:16)>>>>>>>>>>>> Apply n=2482 Segments to df.shape = (457700, 42)\n",
"(2017-07-04 16:23:15)<<<<<<<<<<<< --- (119.0s)\n",
"(2017-07-04 16:23:15)<<<<<<<<<< --- (119.0s)\n",
"(2017-07-04 16:23:15)>>>>>>>>>> *transform* Filter columns (remove_small_columns) (458492, 42)\n",
"(2017-07-04 16:23:15)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:15)>>>>>>>>>> *transform* Filter columns (record_threshold) (458492, 36)\n",
"(2017-07-04 16:23:15)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:15)>>>>>>>>>> *transform* Filter columns (filter_var_type) (458492, 35)\n",
"(2017-07-04 16:23:15)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:15)>>>>>>>>>> TRANSFORM Combine like columns (458492, 9)\n",
"(2017-07-04 16:23:15)>>>>>>>>>>>> ('blood pressure diastolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-04 16:23:28)<<<<<<<<<<<< --- (13.0s)\n",
"(2017-07-04 16:23:28)<<<<<<<<<< --- (13.0s)\n",
"(2017-07-04 16:23:28)>>>>>>>>>> transform features on DF (458492, 1)\n",
"(2017-07-04 16:23:28)>>>>>>>>>>>> STD\n",
"(2017-07-04 16:23:28)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:28)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (458492, 1)\n",
"(2017-07-04 16:23:28)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:28)>>>>>>>>>>>> COUNT\n",
"(2017-07-04 16:23:28)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:28)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (458492, 1)\n",
"(2017-07-04 16:23:28)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:28)>>>>>>>>>>>> LAST\n",
"(2017-07-04 16:23:28)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:28)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (458492, 1)\n",
"(2017-07-04 16:23:33)<<<<<<<<<<<< --- (5.0s)\n",
"(2017-07-04 16:23:33)>>>>>>>>>>>> MEAN\n",
"(2017-07-04 16:23:33)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:33)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (458492, 1)\n",
"(2017-07-04 16:23:33)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:33)<<<<<<<<<< --- (5.0s)\n",
"(2017-07-04 16:23:33)<<<<<<<< --- (143.0s)\n",
"(2017-07-04 16:23:33)>>>>>>>> [('blood pressure systolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-04 16:23:33)>>>>>>>>>> DASK OPEN & JOIN n=1 components: ['blood pressure systolic']\n",
"(2017-07-04 16:23:33)>>>>>>>>>>>> BLOOD PRESSURE SYSTOLIC: 1/1\n",
"(2017-07-04 16:23:37)>>>>>>>>>>>>>> Convert to dask - (457598, 40)\n",
"(2017-07-04 16:23:38)<<<<<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:23:38)>>>>>>>>>>>>>> Join to big DF\n",
"(2017-07-04 16:23:38)<<<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:38)<<<<<<<<<<<< --- (5.0s)\n",
"(2017-07-04 16:23:38)>>>>>>>>>>>> Dask DF back to pandas\n",
"(2017-07-04 16:23:38)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:38)>>>>>>>>>>>> SORT Joined DF\n",
"(2017-07-04 16:23:38)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:38)<<<<<<<<<< --- (5.0s)\n",
"(2017-07-04 16:23:39)>>>>>>>>>> *fit* Filter columns (DataNeedsFilter) (457598, 40)\n",
"(2017-07-04 16:23:39)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:39)>>>>>>>>>> *transform* Filter columns (DataNeedsFilter) (457598, 40)\n",
"(2017-07-04 16:23:39)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:39)>>>>>>>>>> Segment df (457598, 40)\n",
"(2017-07-04 16:23:39)>>>>>>>>>>>> Get Segments\n",
"(2017-07-04 16:23:39)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:23:39)>>>>>>>>>>>> Apply n=2482 Segments to df.shape = (457598, 40)\n",
"(2017-07-04 16:25:37)<<<<<<<<<<<< --- (118.0s)\n",
"(2017-07-04 16:25:37)<<<<<<<<<< --- (118.0s)\n",
"(2017-07-04 16:25:37)>>>>>>>>>> *transform* Filter columns (remove_small_columns) (458390, 40)\n",
"(2017-07-04 16:25:37)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:25:37)>>>>>>>>>> *transform* Filter columns (record_threshold) (458390, 35)\n",
"(2017-07-04 16:25:38)<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:25:38)>>>>>>>>>> *transform* Filter columns (filter_var_type) (458390, 34)\n",
"(2017-07-04 16:25:38)<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:25:38)>>>>>>>>>> TRANSFORM Combine like columns (458390, 8)\n",
"(2017-07-04 16:25:38)>>>>>>>>>>>> ('blood pressure systolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-04 16:25:50)<<<<<<<<<<<< --- (12.0s)\n",
"(2017-07-04 16:25:50)<<<<<<<<<< --- (12.0s)\n",
"(2017-07-04 16:25:50)>>>>>>>>>> transform features on DF (458390, 1)\n",
"(2017-07-04 16:25:50)>>>>>>>>>>>> STD\n",
"(2017-07-04 16:25:50)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:25:50)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (458390, 1)\n",
"(2017-07-04 16:25:50)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:25:50)>>>>>>>>>>>> COUNT\n",
"(2017-07-04 16:25:50)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:25:50)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (458390, 1)\n",
"(2017-07-04 16:25:51)<<<<<<<<<<<< --- (1.0s)\n",
"(2017-07-04 16:25:51)>>>>>>>>>>>> LAST\n",
"(2017-07-04 16:25:51)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:25:51)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (458390, 1)\n",
"(2017-07-04 16:25:55)<<<<<<<<<<<< --- (4.0s)\n",
"(2017-07-04 16:25:55)>>>>>>>>>>>> MEAN\n",
"(2017-07-04 16:25:55)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:25:55)>>>>>>>>>>>> *transform* Filter columns (filter_to_component) (458390, 1)\n",
"(2017-07-04 16:25:55)<<<<<<<<<<<< --- (0.0s)\n",
"(2017-07-04 16:25:55)<<<<<<<<<< --- (5.0s)\n",
"(2017-07-04 16:25:55)<<<<<<<< --- (142.0s)\n",
"(2017-07-04 16:25:55)<<<<<< --- (334.0s)\n"
]
}
],
"source": [
"#VALIDATE\n",
"y_validate1 = labelizer.transform(X=validate_ids)\n",
"X_validate1 = featurizer.transform(X=y_validate1)"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(2482, 12) (2482, 1)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</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>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>qn</th>\n",
" <th>qn</th>\n",
" <th>qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" </tr>\n",
" <tr>\n",
" <th>id</th>\n",
" <th>seg_id</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>100028</th>\n",
" <th>0</th>\n",
" <td>11.091809</td>\n",
" <td>32.0</td>\n",
" <td>65.000000</td>\n",
" <td>58.062500</td>\n",
" <td>12.709812</td>\n",
" <td>32.0</td>\n",
" <td>49.000000</td>\n",
" <td>46.406250</td>\n",
" <td>12.541544</td>\n",
" <td>32.0</td>\n",
" <td>113.000000</td>\n",
" <td>97.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100085</th>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100091</th>\n",
" <th>0</th>\n",
" <td>15.624633</td>\n",
" <td>16.0</td>\n",
" <td>51.000000</td>\n",
" <td>66.437500</td>\n",
" <td>19.103119</td>\n",
" <td>16.0</td>\n",
" <td>32.000000</td>\n",
" <td>48.562500</td>\n",
" <td>16.445744</td>\n",
" <td>16.0</td>\n",
" <td>103.000000</td>\n",
" <td>123.937500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100179</th>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>11.024216</td>\n",
" <td>16.0</td>\n",
" <td>74.000000</td>\n",
" <td>69.750000</td>\n",
" <td>10.770136</td>\n",
" <td>16.0</td>\n",
" <td>130.000000</td>\n",
" <td>127.437500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100210</th>\n",
" <th>0</th>\n",
" <td>11.813525</td>\n",
" <td>241.0</td>\n",
" <td>106.000000</td>\n",
" <td>83.497925</td>\n",
" <td>10.422712</td>\n",
" <td>241.0</td>\n",
" <td>98.000000</td>\n",
" <td>68.224066</td>\n",
" <td>15.507445</td>\n",
" <td>241.0</td>\n",
" <td>131.000000</td>\n",
" <td>104.950207</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature STD COUNT LAST \\\n",
"component blood pressure mean blood pressure mean blood pressure mean \n",
"status known known known \n",
"variable_type qn qn qn \n",
"units mmHg mmHg mmHg \n",
"description all all all \n",
"id seg_id \n",
"100028 0 11.091809 32.0 65.000000 \n",
"100085 0 0.000000 0.0 75.758916 \n",
"100091 0 15.624633 16.0 51.000000 \n",
"100179 0 0.000000 0.0 75.758916 \n",
"100210 0 11.813525 241.0 106.000000 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure mean blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100028 0 58.062500 12.709812 \n",
"100085 0 77.487629 0.000000 \n",
"100091 0 66.437500 19.103119 \n",
"100179 0 77.487629 11.024216 \n",
"100210 0 83.497925 10.422712 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure diastolic blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100028 0 32.0 49.000000 \n",
"100085 0 0.0 58.870209 \n",
"100091 0 16.0 32.000000 \n",
"100179 0 16.0 74.000000 \n",
"100210 0 241.0 98.000000 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure diastolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100028 0 46.406250 12.541544 \n",
"100085 0 60.420185 0.000000 \n",
"100091 0 48.562500 16.445744 \n",
"100179 0 69.750000 10.770136 \n",
"100210 0 68.224066 15.507445 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure systolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100028 0 32.0 113.000000 \n",
"100085 0 0.0 115.628637 \n",
"100091 0 16.0 103.000000 \n",
"100179 0 16.0 130.000000 \n",
"100210 0 241.0 131.000000 \n",
"\n",
"feature MEAN \n",
"component blood pressure systolic \n",
"status known \n",
"variable_type qn \n",
"units mmHg \n",
"description all \n",
"id seg_id \n",
"100028 0 97.250000 \n",
"100085 0 118.662692 \n",
"100091 0 123.937500 \n",
"100179 0 127.437500 \n",
"100210 0 104.950207 "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>SAMPLE</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</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></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>100028</th>\n",
" <th>2142-12-25 02:44:00</th>\n",
" <td>1.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100085</th>\n",
" <th>2126-08-30 10:36:00</th>\n",
" <td>1.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100091</th>\n",
" <th>2162-06-04 00:33:00</th>\n",
" <td>1.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100179</th>\n",
" <th>2135-12-27 13:14:00</th>\n",
" <td>1.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100210</th>\n",
" <th>2159-06-01 13:43:00</th>\n",
" <td>1.7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature SAMPLE\n",
"component lactate\n",
"status known\n",
"variable_type qn\n",
"units mmol/L\n",
"description all\n",
"id datetime \n",
"100028 2142-12-25 02:44:00 1.1\n",
"100085 2126-08-30 10:36:00 1.3\n",
"100091 2162-06-04 00:33:00 1.4\n",
"100179 2135-12-27 13:14:00 1.1\n",
"100210 2159-06-01 13:43:00 1.7"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure mean', 'all'),) STD\n",
"fill_zero()\n",
"(('blood pressure mean', 'all'),) COUNT\n",
"fill_zero()\n",
"(('blood pressure mean', 'all'),) LAST\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>75.758916</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"0 75.758916"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure mean', 'all'),) MEAN\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>77.487629</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"component blood pressure mean\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"0 77.487629"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure diastolic', 'all'),) STD\n",
"fill_zero()\n",
"(('blood pressure diastolic', 'all'),) COUNT\n",
"fill_zero()\n",
"(('blood pressure diastolic', 'all'),) LAST\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>58.870209</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"0 58.870209"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure diastolic', 'all'),) MEAN\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>60.420185</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"component blood pressure diastolic\n",
"status known\n",
"variable_type qn\n",
"units mmHg\n",
"description all\n",
"0 60.420185"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure systolic', 'all'),) STD\n",
"fill_zero()\n",
"(('blood pressure systolic', 'all'),) COUNT\n",
"fill_zero()\n",
"(('blood pressure systolic', 'all'),) LAST\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>115.628637</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 all\n",
"0 115.628637"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"(('blood pressure systolic', 'all'),) MEAN\n",
"fill_mean()\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>component</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",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>118.662692</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 all\n",
"0 118.662692"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print X_validate1.shape,y_validate1.shape\n",
"display(X_validate1.head())\n",
"display(y_validate1.head())\n",
"print_fillna_params(featurizer)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Visualize!"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"\n",
"def heatmap(df_ts):\n",
" sns.set(context=\"paper\", font=\"monospace\")\n",
" corrmat = df_ts.corr()\n",
" # Set up the matplotlib figure\n",
" f, ax = plt.subplots(figsize=(50, 50))\n",
" # Draw the heatmap using seaborn\n",
" sns.heatmap(corrmat, vmax=1, square=True)\n",
" return"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th>feature</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>next_lactate</th>\n",
" </tr>\n",
" <tr>\n",
" <th>component</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th></th>\n",
" </tr>\n",
" <tr>\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>known</th>\n",
" <th>known</th>\n",
" <th></th>\n",
" </tr>\n",
" <tr>\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>qn</th>\n",
" <th>qn</th>\n",
" <th>qn</th>\n",
" <th></th>\n",
" </tr>\n",
" <tr>\n",
" <th>units</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th></th>\n",
" </tr>\n",
" <tr>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>1.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>0.90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>10.737784</td>\n",
" <td>5.0</td>\n",
" <td>64.000000</td>\n",
" <td>70.600000</td>\n",
" <td>11.606033</td>\n",
" <td>5.0</td>\n",
" <td>46.000000</td>\n",
" <td>57.800000</td>\n",
" <td>11.300442</td>\n",
" <td>5.0</td>\n",
" <td>102.000000</td>\n",
" <td>108.800000</td>\n",
" <td>2.30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>9.917247</td>\n",
" <td>23.0</td>\n",
" <td>89.000000</td>\n",
" <td>79.521739</td>\n",
" <td>6.660010</td>\n",
" <td>23.0</td>\n",
" <td>64.000000</td>\n",
" <td>57.086957</td>\n",
" <td>15.660176</td>\n",
" <td>23.0</td>\n",
" <td>133.000000</td>\n",
" <td>124.826087</td>\n",
" <td>1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>21.120986</td>\n",
" <td>29.0</td>\n",
" <td>90.000000</td>\n",
" <td>87.103448</td>\n",
" <td>18.688001</td>\n",
" <td>29.0</td>\n",
" <td>71.000000</td>\n",
" <td>72.206897</td>\n",
" <td>31.660686</td>\n",
" <td>29.0</td>\n",
" <td>144.000000</td>\n",
" <td>135.551724</td>\n",
" <td>1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>8.350766</td>\n",
" <td>17.0</td>\n",
" <td>69.000000</td>\n",
" <td>76.117647</td>\n",
" <td>6.626040</td>\n",
" <td>17.0</td>\n",
" <td>52.000000</td>\n",
" <td>57.823529</td>\n",
" <td>13.182542</td>\n",
" <td>17.0</td>\n",
" <td>107.000000</td>\n",
" <td>121.176471</td>\n",
" <td>3.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>6</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>7.536650</td>\n",
" <td>107.0</td>\n",
" <td>55.000000</td>\n",
" <td>50.971963</td>\n",
" <td>22.696327</td>\n",
" <td>107.0</td>\n",
" <td>139.000000</td>\n",
" <td>117.906542</td>\n",
" <td>1.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>7</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>2.90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>8</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>1.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>9</th>\n",
" <td>9.019227</td>\n",
" <td>45.0</td>\n",
" <td>73.000000</td>\n",
" <td>84.511111</td>\n",
" <td>7.410780</td>\n",
" <td>44.0</td>\n",
" <td>70.000000</td>\n",
" <td>69.681818</td>\n",
" <td>18.580776</td>\n",
" <td>44.0</td>\n",
" <td>94.000000</td>\n",
" <td>135.681818</td>\n",
" <td>2.90</td>\n",
" </tr>\n",
" <tr>\n",
" <th>10</th>\n",
" <td>12.892625</td>\n",
" <td>14.0</td>\n",
" <td>65.000000</td>\n",
" <td>78.285714</td>\n",
" <td>12.445927</td>\n",
" <td>14.0</td>\n",
" <td>52.000000</td>\n",
" <td>66.857143</td>\n",
" <td>18.550792</td>\n",
" <td>14.0</td>\n",
" <td>92.000000</td>\n",
" <td>104.142857</td>\n",
" <td>1.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>11</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>2.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>12</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>3.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>13</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>1.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14</th>\n",
" <td>13.675442</td>\n",
" <td>43.0</td>\n",
" <td>78.000000</td>\n",
" <td>66.511628</td>\n",
" <td>14.263227</td>\n",
" <td>43.0</td>\n",
" <td>59.000000</td>\n",
" <td>55.581395</td>\n",
" <td>17.200402</td>\n",
" <td>43.0</td>\n",
" <td>131.000000</td>\n",
" <td>101.162791</td>\n",
" <td>2.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>11.537702</td>\n",
" <td>23.0</td>\n",
" <td>101.000000</td>\n",
" <td>86.130435</td>\n",
" <td>16.103789</td>\n",
" <td>23.0</td>\n",
" <td>143.000000</td>\n",
" <td>117.173913</td>\n",
" <td>1.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16</th>\n",
" <td>5.191269</td>\n",
" <td>24.0</td>\n",
" <td>69.000000</td>\n",
" <td>61.416667</td>\n",
" <td>9.654915</td>\n",
" <td>24.0</td>\n",
" <td>52.000000</td>\n",
" <td>47.500000</td>\n",
" <td>8.839962</td>\n",
" <td>24.0</td>\n",
" <td>126.000000</td>\n",
" <td>110.833333</td>\n",
" <td>1.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>17</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>3.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>18</th>\n",
" <td>6.106463</td>\n",
" <td>10.0</td>\n",
" <td>101.000000</td>\n",
" <td>101.200000</td>\n",
" <td>5.699903</td>\n",
" <td>10.0</td>\n",
" <td>79.000000</td>\n",
" <td>82.600000</td>\n",
" <td>10.033832</td>\n",
" <td>10.0</td>\n",
" <td>147.000000</td>\n",
" <td>140.300000</td>\n",
" <td>1.30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>7.046624</td>\n",
" <td>99.0</td>\n",
" <td>50.000000</td>\n",
" <td>46.575758</td>\n",
" <td>15.361795</td>\n",
" <td>99.0</td>\n",
" <td>97.000000</td>\n",
" <td>105.070707</td>\n",
" <td>1.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>20</th>\n",
" <td>11.369047</td>\n",
" <td>761.0</td>\n",
" <td>48.000000</td>\n",
" <td>69.519054</td>\n",
" <td>7.847005</td>\n",
" <td>762.0</td>\n",
" <td>41.000000</td>\n",
" <td>48.431759</td>\n",
" <td>14.089663</td>\n",
" <td>762.0</td>\n",
" <td>69.000000</td>\n",
" <td>105.127297</td>\n",
" <td>2.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>21</th>\n",
" <td>19.132819</td>\n",
" <td>124.0</td>\n",
" <td>82.000000</td>\n",
" <td>83.016129</td>\n",
" <td>14.808587</td>\n",
" <td>124.0</td>\n",
" <td>66.000000</td>\n",
" <td>67.080645</td>\n",
" <td>14.416337</td>\n",
" <td>124.0</td>\n",
" <td>114.000000</td>\n",
" <td>117.620968</td>\n",
" <td>1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>22</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>6.623246</td>\n",
" <td>75.0</td>\n",
" <td>62.000000</td>\n",
" <td>59.586667</td>\n",
" <td>17.123315</td>\n",
" <td>75.0</td>\n",
" <td>118.000000</td>\n",
" <td>121.853333</td>\n",
" <td>1.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>23</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>9.373399</td>\n",
" <td>80.0</td>\n",
" <td>61.000000</td>\n",
" <td>55.387500</td>\n",
" <td>18.069447</td>\n",
" <td>80.0</td>\n",
" <td>129.000000</td>\n",
" <td>108.337500</td>\n",
" <td>4.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>24</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>1.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25</th>\n",
" <td>33.274342</td>\n",
" <td>12.0</td>\n",
" <td>66.000000</td>\n",
" <td>68.500000</td>\n",
" <td>11.939240</td>\n",
" <td>12.0</td>\n",
" <td>70.000000</td>\n",
" <td>70.000000</td>\n",
" <td>13.970478</td>\n",
" <td>12.0</td>\n",
" <td>100.000000</td>\n",
" <td>119.416667</td>\n",
" <td>2.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>26</th>\n",
" <td>4.429339</td>\n",
" <td>7.0</td>\n",
" <td>59.000000</td>\n",
" <td>62.428571</td>\n",
" <td>4.259443</td>\n",
" <td>7.0</td>\n",
" <td>51.000000</td>\n",
" <td>53.142857</td>\n",
" <td>4.220133</td>\n",
" <td>7.0</td>\n",
" <td>89.000000</td>\n",
" <td>91.142857</td>\n",
" <td>1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>27</th>\n",
" <td>10.413666</td>\n",
" <td>10.0</td>\n",
" <td>58.000000</td>\n",
" <td>66.000000</td>\n",
" <td>13.065646</td>\n",
" <td>10.0</td>\n",
" <td>46.000000</td>\n",
" <td>53.600000</td>\n",
" <td>7.184087</td>\n",
" <td>10.0</td>\n",
" <td>93.000000</td>\n",
" <td>104.500000</td>\n",
" <td>0.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>28</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>7.745967</td>\n",
" <td>5.0</td>\n",
" <td>47.000000</td>\n",
" <td>52.000000</td>\n",
" <td>12.477981</td>\n",
" <td>5.0</td>\n",
" <td>102.000000</td>\n",
" <td>103.200000</td>\n",
" <td>1.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>29</th>\n",
" <td>4.582576</td>\n",
" <td>7.0</td>\n",
" <td>73.000000</td>\n",
" <td>77.000000</td>\n",
" <td>4.956958</td>\n",
" <td>7.0</td>\n",
" <td>66.000000</td>\n",
" <td>68.714286</td>\n",
" <td>5.282496</td>\n",
" <td>7.0</td>\n",
" <td>102.000000</td>\n",
" <td>106.285714</td>\n",
" <td>1.10</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",
" </tr>\n",
" <tr>\n",
" <th>19763</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>5.635377</td>\n",
" <td>30.0</td>\n",
" <td>59.000000</td>\n",
" <td>58.966667</td>\n",
" <td>14.718235</td>\n",
" <td>30.0</td>\n",
" <td>116.000000</td>\n",
" <td>119.833333</td>\n",
" <td>1.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19764</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>5.131601</td>\n",
" <td>3.0</td>\n",
" <td>49.000000</td>\n",
" <td>54.666667</td>\n",
" <td>10.785793</td>\n",
" <td>3.0</td>\n",
" <td>91.000000</td>\n",
" <td>103.333333</td>\n",
" <td>2.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19765</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>2.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19766</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>5.468493</td>\n",
" <td>17.0</td>\n",
" <td>69.000000</td>\n",
" <td>67.823529</td>\n",
" <td>16.480827</td>\n",
" <td>17.0</td>\n",
" <td>109.000000</td>\n",
" <td>104.647059</td>\n",
" <td>4.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19767</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>9.024209</td>\n",
" <td>329.0</td>\n",
" <td>74.000000</td>\n",
" <td>64.316109</td>\n",
" <td>18.766478</td>\n",
" <td>329.0</td>\n",
" <td>188.000000</td>\n",
" <td>170.623100</td>\n",
" <td>0.83</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19768</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>13.20</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19769</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>3.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19770</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>17.711477</td>\n",
" <td>8.0</td>\n",
" <td>97.000000</td>\n",
" <td>64.375000</td>\n",
" <td>7.818248</td>\n",
" <td>8.0</td>\n",
" <td>143.000000</td>\n",
" <td>154.375000</td>\n",
" <td>2.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19771</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>5.827805</td>\n",
" <td>56.0</td>\n",
" <td>47.000000</td>\n",
" <td>52.482143</td>\n",
" <td>12.402228</td>\n",
" <td>56.0</td>\n",
" <td>98.000000</td>\n",
" <td>98.446429</td>\n",
" <td>3.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19772</th>\n",
" <td>9.266427</td>\n",
" <td>6.0</td>\n",
" <td>71.000000</td>\n",
" <td>85.333333</td>\n",
" <td>7.547627</td>\n",
" <td>6.0</td>\n",
" <td>59.000000</td>\n",
" <td>71.166667</td>\n",
" <td>22.759613</td>\n",
" <td>6.0</td>\n",
" <td>89.000000</td>\n",
" <td>119.000000</td>\n",
" <td>2.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19773</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>8.330053</td>\n",
" <td>194.0</td>\n",
" <td>50.000000</td>\n",
" <td>49.391753</td>\n",
" <td>11.793507</td>\n",
" <td>194.0</td>\n",
" <td>99.000000</td>\n",
" <td>98.206186</td>\n",
" <td>6.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19774</th>\n",
" <td>8.102847</td>\n",
" <td>23.0</td>\n",
" <td>68.000000</td>\n",
" <td>71.739130</td>\n",
" <td>6.321742</td>\n",
" <td>23.0</td>\n",
" <td>50.000000</td>\n",
" <td>56.652174</td>\n",
" <td>16.021724</td>\n",
" <td>23.0</td>\n",
" <td>124.000000</td>\n",
" <td>118.173913</td>\n",
" <td>1.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19775</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>2.40</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19776</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>9.366175</td>\n",
" <td>37.0</td>\n",
" <td>52.000000</td>\n",
" <td>66.324324</td>\n",
" <td>17.978466</td>\n",
" <td>37.0</td>\n",
" <td>111.000000</td>\n",
" <td>115.324324</td>\n",
" <td>1.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19777</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>10.273801</td>\n",
" <td>217.0</td>\n",
" <td>52.000000</td>\n",
" <td>63.764977</td>\n",
" <td>17.493589</td>\n",
" <td>217.0</td>\n",
" <td>122.000000</td>\n",
" <td>136.046083</td>\n",
" <td>1.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19778</th>\n",
" <td>7.255414</td>\n",
" <td>13.0</td>\n",
" <td>81.000000</td>\n",
" <td>74.846154</td>\n",
" <td>9.426504</td>\n",
" <td>13.0</td>\n",
" <td>75.000000</td>\n",
" <td>64.230769</td>\n",
" <td>9.106915</td>\n",
" <td>13.0</td>\n",
" <td>104.000000</td>\n",
" <td>108.461538</td>\n",
" <td>1.30</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19779</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19780</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>11.910648</td>\n",
" <td>51.0</td>\n",
" <td>68.000000</td>\n",
" <td>68.764706</td>\n",
" <td>21.111097</td>\n",
" <td>51.0</td>\n",
" <td>158.000000</td>\n",
" <td>145.039216</td>\n",
" <td>1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19781</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>11.301707</td>\n",
" <td>21.0</td>\n",
" <td>47.000000</td>\n",
" <td>64.857143</td>\n",
" <td>14.705846</td>\n",
" <td>21.0</td>\n",
" <td>57.000000</td>\n",
" <td>81.523810</td>\n",
" <td>3.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19782</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>4.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19783</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>12.449827</td>\n",
" <td>24.0</td>\n",
" <td>69.000000</td>\n",
" <td>64.958333</td>\n",
" <td>22.167184</td>\n",
" <td>24.0</td>\n",
" <td>120.000000</td>\n",
" <td>108.916667</td>\n",
" <td>1.60</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19784</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>1.79</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19785</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>2.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19786</th>\n",
" <td>9.412602</td>\n",
" <td>56.0</td>\n",
" <td>78.000000</td>\n",
" <td>73.053571</td>\n",
" <td>5.656826</td>\n",
" <td>56.0</td>\n",
" <td>53.000000</td>\n",
" <td>51.767857</td>\n",
" <td>18.020974</td>\n",
" <td>56.0</td>\n",
" <td>133.000000</td>\n",
" <td>117.589286</td>\n",
" <td>1.80</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19787</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>12.506550</td>\n",
" <td>409.0</td>\n",
" <td>67.000000</td>\n",
" <td>56.911980</td>\n",
" <td>27.365297</td>\n",
" <td>409.0</td>\n",
" <td>174.000000</td>\n",
" <td>171.437653</td>\n",
" <td>1.10</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19788</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>2.910507</td>\n",
" <td>20.0</td>\n",
" <td>58.000000</td>\n",
" <td>57.450000</td>\n",
" <td>14.543854</td>\n",
" <td>20.0</td>\n",
" <td>96.000000</td>\n",
" <td>107.950000</td>\n",
" <td>1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19789</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>5.689903</td>\n",
" <td>17.0</td>\n",
" <td>44.000000</td>\n",
" <td>49.000000</td>\n",
" <td>13.266222</td>\n",
" <td>17.0</td>\n",
" <td>104.000000</td>\n",
" <td>97.647059</td>\n",
" <td>1.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19790</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>6.584614</td>\n",
" <td>8.0</td>\n",
" <td>42.000000</td>\n",
" <td>38.750000</td>\n",
" <td>10.392305</td>\n",
" <td>8.0</td>\n",
" <td>104.000000</td>\n",
" <td>94.500000</td>\n",
" <td>0.70</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19791</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>2.00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>19792</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" <td>1.80</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>19793 rows × 13 columns</p>\n",
"</div>"
],
"text/plain": [
"feature STD COUNT LAST \\\n",
"component blood pressure mean blood pressure mean blood pressure mean \n",
"status known known known \n",
"variable_type qn qn qn \n",
"units mmHg mmHg mmHg \n",
"description all all all \n",
"0 0.000000 0.0 75.758916 \n",
"1 0.000000 0.0 75.758916 \n",
"2 10.737784 5.0 64.000000 \n",
"3 9.917247 23.0 89.000000 \n",
"4 21.120986 29.0 90.000000 \n",
"5 8.350766 17.0 69.000000 \n",
"6 0.000000 0.0 75.758916 \n",
"7 0.000000 0.0 75.758916 \n",
"8 0.000000 0.0 75.758916 \n",
"9 9.019227 45.0 73.000000 \n",
"10 12.892625 14.0 65.000000 \n",
"11 0.000000 0.0 75.758916 \n",
"12 0.000000 0.0 75.758916 \n",
"13 0.000000 0.0 75.758916 \n",
"14 13.675442 43.0 78.000000 \n",
"15 0.000000 0.0 75.758916 \n",
"16 5.191269 24.0 69.000000 \n",
"17 0.000000 0.0 75.758916 \n",
"18 6.106463 10.0 101.000000 \n",
"19 0.000000 0.0 75.758916 \n",
"20 11.369047 761.0 48.000000 \n",
"21 19.132819 124.0 82.000000 \n",
"22 0.000000 0.0 75.758916 \n",
"23 0.000000 0.0 75.758916 \n",
"24 0.000000 0.0 75.758916 \n",
"25 33.274342 12.0 66.000000 \n",
"26 4.429339 7.0 59.000000 \n",
"27 10.413666 10.0 58.000000 \n",
"28 0.000000 0.0 75.758916 \n",
"29 4.582576 7.0 73.000000 \n",
"... ... ... ... \n",
"19763 0.000000 0.0 75.758916 \n",
"19764 0.000000 0.0 75.758916 \n",
"19765 0.000000 0.0 75.758916 \n",
"19766 0.000000 0.0 75.758916 \n",
"19767 0.000000 0.0 75.758916 \n",
"19768 0.000000 0.0 75.758916 \n",
"19769 0.000000 0.0 75.758916 \n",
"19770 0.000000 0.0 75.758916 \n",
"19771 0.000000 0.0 75.758916 \n",
"19772 9.266427 6.0 71.000000 \n",
"19773 0.000000 0.0 75.758916 \n",
"19774 8.102847 23.0 68.000000 \n",
"19775 0.000000 0.0 75.758916 \n",
"19776 0.000000 0.0 75.758916 \n",
"19777 0.000000 0.0 75.758916 \n",
"19778 7.255414 13.0 81.000000 \n",
"19779 0.000000 0.0 75.758916 \n",
"19780 0.000000 0.0 75.758916 \n",
"19781 0.000000 0.0 75.758916 \n",
"19782 0.000000 0.0 75.758916 \n",
"19783 0.000000 0.0 75.758916 \n",
"19784 0.000000 0.0 75.758916 \n",
"19785 0.000000 0.0 75.758916 \n",
"19786 9.412602 56.0 78.000000 \n",
"19787 0.000000 0.0 75.758916 \n",
"19788 0.000000 0.0 75.758916 \n",
"19789 0.000000 0.0 75.758916 \n",
"19790 0.000000 0.0 75.758916 \n",
"19791 0.000000 0.0 75.758916 \n",
"19792 0.000000 0.0 75.758916 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure mean blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"0 77.487629 0.000000 \n",
"1 77.487629 0.000000 \n",
"2 70.600000 11.606033 \n",
"3 79.521739 6.660010 \n",
"4 87.103448 18.688001 \n",
"5 76.117647 6.626040 \n",
"6 77.487629 7.536650 \n",
"7 77.487629 0.000000 \n",
"8 77.487629 0.000000 \n",
"9 84.511111 7.410780 \n",
"10 78.285714 12.445927 \n",
"11 77.487629 0.000000 \n",
"12 77.487629 0.000000 \n",
"13 77.487629 0.000000 \n",
"14 66.511628 14.263227 \n",
"15 77.487629 11.537702 \n",
"16 61.416667 9.654915 \n",
"17 77.487629 0.000000 \n",
"18 101.200000 5.699903 \n",
"19 77.487629 7.046624 \n",
"20 69.519054 7.847005 \n",
"21 83.016129 14.808587 \n",
"22 77.487629 6.623246 \n",
"23 77.487629 9.373399 \n",
"24 77.487629 0.000000 \n",
"25 68.500000 11.939240 \n",
"26 62.428571 4.259443 \n",
"27 66.000000 13.065646 \n",
"28 77.487629 7.745967 \n",
"29 77.000000 4.956958 \n",
"... ... ... \n",
"19763 77.487629 5.635377 \n",
"19764 77.487629 5.131601 \n",
"19765 77.487629 0.000000 \n",
"19766 77.487629 5.468493 \n",
"19767 77.487629 9.024209 \n",
"19768 77.487629 0.000000 \n",
"19769 77.487629 0.000000 \n",
"19770 77.487629 17.711477 \n",
"19771 77.487629 5.827805 \n",
"19772 85.333333 7.547627 \n",
"19773 77.487629 8.330053 \n",
"19774 71.739130 6.321742 \n",
"19775 77.487629 0.000000 \n",
"19776 77.487629 9.366175 \n",
"19777 77.487629 10.273801 \n",
"19778 74.846154 9.426504 \n",
"19779 77.487629 0.000000 \n",
"19780 77.487629 11.910648 \n",
"19781 77.487629 11.301707 \n",
"19782 77.487629 0.000000 \n",
"19783 77.487629 12.449827 \n",
"19784 77.487629 0.000000 \n",
"19785 77.487629 0.000000 \n",
"19786 73.053571 5.656826 \n",
"19787 77.487629 12.506550 \n",
"19788 77.487629 2.910507 \n",
"19789 77.487629 5.689903 \n",
"19790 77.487629 6.584614 \n",
"19791 77.487629 0.000000 \n",
"19792 77.487629 0.000000 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure diastolic blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"0 0.0 58.870209 \n",
"1 0.0 58.870209 \n",
"2 5.0 46.000000 \n",
"3 23.0 64.000000 \n",
"4 29.0 71.000000 \n",
"5 17.0 52.000000 \n",
"6 107.0 55.000000 \n",
"7 0.0 58.870209 \n",
"8 0.0 58.870209 \n",
"9 44.0 70.000000 \n",
"10 14.0 52.000000 \n",
"11 0.0 58.870209 \n",
"12 0.0 58.870209 \n",
"13 0.0 58.870209 \n",
"14 43.0 59.000000 \n",
"15 23.0 101.000000 \n",
"16 24.0 52.000000 \n",
"17 0.0 58.870209 \n",
"18 10.0 79.000000 \n",
"19 99.0 50.000000 \n",
"20 762.0 41.000000 \n",
"21 124.0 66.000000 \n",
"22 75.0 62.000000 \n",
"23 80.0 61.000000 \n",
"24 0.0 58.870209 \n",
"25 12.0 70.000000 \n",
"26 7.0 51.000000 \n",
"27 10.0 46.000000 \n",
"28 5.0 47.000000 \n",
"29 7.0 66.000000 \n",
"... ... ... \n",
"19763 30.0 59.000000 \n",
"19764 3.0 49.000000 \n",
"19765 0.0 58.870209 \n",
"19766 17.0 69.000000 \n",
"19767 329.0 74.000000 \n",
"19768 0.0 58.870209 \n",
"19769 0.0 58.870209 \n",
"19770 8.0 97.000000 \n",
"19771 56.0 47.000000 \n",
"19772 6.0 59.000000 \n",
"19773 194.0 50.000000 \n",
"19774 23.0 50.000000 \n",
"19775 0.0 58.870209 \n",
"19776 37.0 52.000000 \n",
"19777 217.0 52.000000 \n",
"19778 13.0 75.000000 \n",
"19779 0.0 58.870209 \n",
"19780 51.0 68.000000 \n",
"19781 21.0 47.000000 \n",
"19782 0.0 58.870209 \n",
"19783 24.0 69.000000 \n",
"19784 0.0 58.870209 \n",
"19785 0.0 58.870209 \n",
"19786 56.0 53.000000 \n",
"19787 409.0 67.000000 \n",
"19788 20.0 58.000000 \n",
"19789 17.0 44.000000 \n",
"19790 8.0 42.000000 \n",
"19791 0.0 58.870209 \n",
"19792 0.0 58.870209 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure diastolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"0 60.420185 0.000000 \n",
"1 60.420185 0.000000 \n",
"2 57.800000 11.300442 \n",
"3 57.086957 15.660176 \n",
"4 72.206897 31.660686 \n",
"5 57.823529 13.182542 \n",
"6 50.971963 22.696327 \n",
"7 60.420185 0.000000 \n",
"8 60.420185 0.000000 \n",
"9 69.681818 18.580776 \n",
"10 66.857143 18.550792 \n",
"11 60.420185 0.000000 \n",
"12 60.420185 0.000000 \n",
"13 60.420185 0.000000 \n",
"14 55.581395 17.200402 \n",
"15 86.130435 16.103789 \n",
"16 47.500000 8.839962 \n",
"17 60.420185 0.000000 \n",
"18 82.600000 10.033832 \n",
"19 46.575758 15.361795 \n",
"20 48.431759 14.089663 \n",
"21 67.080645 14.416337 \n",
"22 59.586667 17.123315 \n",
"23 55.387500 18.069447 \n",
"24 60.420185 0.000000 \n",
"25 70.000000 13.970478 \n",
"26 53.142857 4.220133 \n",
"27 53.600000 7.184087 \n",
"28 52.000000 12.477981 \n",
"29 68.714286 5.282496 \n",
"... ... ... \n",
"19763 58.966667 14.718235 \n",
"19764 54.666667 10.785793 \n",
"19765 60.420185 0.000000 \n",
"19766 67.823529 16.480827 \n",
"19767 64.316109 18.766478 \n",
"19768 60.420185 0.000000 \n",
"19769 60.420185 0.000000 \n",
"19770 64.375000 7.818248 \n",
"19771 52.482143 12.402228 \n",
"19772 71.166667 22.759613 \n",
"19773 49.391753 11.793507 \n",
"19774 56.652174 16.021724 \n",
"19775 60.420185 0.000000 \n",
"19776 66.324324 17.978466 \n",
"19777 63.764977 17.493589 \n",
"19778 64.230769 9.106915 \n",
"19779 60.420185 0.000000 \n",
"19780 68.764706 21.111097 \n",
"19781 64.857143 14.705846 \n",
"19782 60.420185 0.000000 \n",
"19783 64.958333 22.167184 \n",
"19784 60.420185 0.000000 \n",
"19785 60.420185 0.000000 \n",
"19786 51.767857 18.020974 \n",
"19787 56.911980 27.365297 \n",
"19788 57.450000 14.543854 \n",
"19789 49.000000 13.266222 \n",
"19790 38.750000 10.392305 \n",
"19791 60.420185 0.000000 \n",
"19792 60.420185 0.000000 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure systolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"0 0.0 115.628637 \n",
"1 0.0 115.628637 \n",
"2 5.0 102.000000 \n",
"3 23.0 133.000000 \n",
"4 29.0 144.000000 \n",
"5 17.0 107.000000 \n",
"6 107.0 139.000000 \n",
"7 0.0 115.628637 \n",
"8 0.0 115.628637 \n",
"9 44.0 94.000000 \n",
"10 14.0 92.000000 \n",
"11 0.0 115.628637 \n",
"12 0.0 115.628637 \n",
"13 0.0 115.628637 \n",
"14 43.0 131.000000 \n",
"15 23.0 143.000000 \n",
"16 24.0 126.000000 \n",
"17 0.0 115.628637 \n",
"18 10.0 147.000000 \n",
"19 99.0 97.000000 \n",
"20 762.0 69.000000 \n",
"21 124.0 114.000000 \n",
"22 75.0 118.000000 \n",
"23 80.0 129.000000 \n",
"24 0.0 115.628637 \n",
"25 12.0 100.000000 \n",
"26 7.0 89.000000 \n",
"27 10.0 93.000000 \n",
"28 5.0 102.000000 \n",
"29 7.0 102.000000 \n",
"... ... ... \n",
"19763 30.0 116.000000 \n",
"19764 3.0 91.000000 \n",
"19765 0.0 115.628637 \n",
"19766 17.0 109.000000 \n",
"19767 329.0 188.000000 \n",
"19768 0.0 115.628637 \n",
"19769 0.0 115.628637 \n",
"19770 8.0 143.000000 \n",
"19771 56.0 98.000000 \n",
"19772 6.0 89.000000 \n",
"19773 194.0 99.000000 \n",
"19774 23.0 124.000000 \n",
"19775 0.0 115.628637 \n",
"19776 37.0 111.000000 \n",
"19777 217.0 122.000000 \n",
"19778 13.0 104.000000 \n",
"19779 0.0 115.628637 \n",
"19780 51.0 158.000000 \n",
"19781 21.0 57.000000 \n",
"19782 0.0 115.628637 \n",
"19783 24.0 120.000000 \n",
"19784 0.0 115.628637 \n",
"19785 0.0 115.628637 \n",
"19786 56.0 133.000000 \n",
"19787 409.0 174.000000 \n",
"19788 20.0 96.000000 \n",
"19789 17.0 104.000000 \n",
"19790 8.0 104.000000 \n",
"19791 0.0 115.628637 \n",
"19792 0.0 115.628637 \n",
"\n",
"feature MEAN next_lactate \n",
"component blood pressure systolic \n",
"status known \n",
"variable_type qn \n",
"units mmHg \n",
"description all \n",
"0 118.662692 1.50 \n",
"1 118.662692 0.90 \n",
"2 108.800000 2.30 \n",
"3 124.826087 1.00 \n",
"4 135.551724 1.00 \n",
"5 121.176471 3.20 \n",
"6 117.906542 1.20 \n",
"7 118.662692 2.90 \n",
"8 118.662692 1.60 \n",
"9 135.681818 2.90 \n",
"10 104.142857 1.70 \n",
"11 118.662692 2.40 \n",
"12 118.662692 3.00 \n",
"13 118.662692 1.20 \n",
"14 101.162791 2.50 \n",
"15 117.173913 1.80 \n",
"16 110.833333 1.40 \n",
"17 118.662692 3.00 \n",
"18 140.300000 1.30 \n",
"19 105.070707 1.10 \n",
"20 105.127297 2.50 \n",
"21 117.620968 1.00 \n",
"22 121.853333 1.20 \n",
"23 108.337500 4.50 \n",
"24 118.662692 1.70 \n",
"25 119.416667 2.70 \n",
"26 91.142857 1.00 \n",
"27 104.500000 0.80 \n",
"28 103.200000 1.50 \n",
"29 106.285714 1.10 \n",
"... ... ... \n",
"19763 119.833333 1.20 \n",
"19764 103.333333 2.20 \n",
"19765 118.662692 2.00 \n",
"19766 104.647059 4.00 \n",
"19767 170.623100 0.83 \n",
"19768 118.662692 13.20 \n",
"19769 118.662692 3.50 \n",
"19770 154.375000 2.00 \n",
"19771 98.446429 3.10 \n",
"19772 119.000000 2.00 \n",
"19773 98.206186 6.10 \n",
"19774 118.173913 1.60 \n",
"19775 118.662692 2.40 \n",
"19776 115.324324 1.10 \n",
"19777 136.046083 1.70 \n",
"19778 108.461538 1.30 \n",
"19779 118.662692 1.00 \n",
"19780 145.039216 1.00 \n",
"19781 81.523810 3.50 \n",
"19782 118.662692 4.70 \n",
"19783 108.916667 1.60 \n",
"19784 118.662692 1.79 \n",
"19785 118.662692 2.10 \n",
"19786 117.589286 1.80 \n",
"19787 171.437653 1.10 \n",
"19788 107.950000 1.00 \n",
"19789 97.647059 1.00 \n",
"19790 94.500000 0.70 \n",
"19791 118.662692 2.00 \n",
"19792 118.662692 1.80 \n",
"\n",
"[19793 rows x 13 columns]"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"combined = X_train1.reset_index(drop=True)\n",
"combined['next_lactate'] = y_train1.reset_index(drop=True)\n",
"combined"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAACvQAAAr0CAYAAADq8Aw0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nfSBYUAAAAABJRU5ErkJggg==\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x15923470>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"heatmap(combined)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(2017-06-30 23:20:48) Featurizing...\n",
"(2017-06-30 23:20:48)>> [('lactate', 'all')] - SAMPLE\n",
"(2017-06-30 23:20:48)>>>> DASK OPEN & JOIN n=1 components: ['lactate']\n",
"(2017-06-30 23:20:48)>>>>>> LACTATE: 1/1\n",
"(2017-06-30 23:20:48)>>>>>>>> Convert to dask - (142518, 63)\n",
"(2017-06-30 23:20:48)<<<<<<<< --- (0.0s)\n",
"(2017-06-30 23:20:48)>>>>>>>> Join to big DF\n",
"(2017-06-30 23:20:48)<<<<<<<< --- (0.0s)\n",
"(2017-06-30 23:20:48)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:20:48)>>>>>> Dask DF back to pandas\n",
"(2017-06-30 23:20:49)<<<<<< --- (1.0s)\n",
"(2017-06-30 23:20:49)>>>>>> SORT Joined DF\n",
"(2017-06-30 23:20:49)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:20:49)<<<< --- (1.0s)\n",
"(2017-06-30 23:20:49)>>>> *fit* Filter columns (DataNeedsFilter) (142518, 63)\n",
"(2017-06-30 23:20:49)<<<< --- (0.0s)\n",
"(2017-06-30 23:20:49)>>>> *transform* Filter columns (DataNeedsFilter) (142518, 63)\n",
"(2017-06-30 23:20:49)<<<< --- (0.0s)\n",
"(2017-06-30 23:20:49)>>>> *fit* Filter columns (filter_var_type) (142518, 63)\n",
"(2017-06-30 23:20:49)<<<< --- (0.0s)\n",
"(2017-06-30 23:20:49)>>>> *transform* Filter columns (filter_var_type) (142518, 63)\n",
"(2017-06-30 23:20:49)<<<< --- (0.0s)\n",
"(2017-06-30 23:20:49)>>>> FIT Combine like columns (142518, 7)\n",
"(2017-06-30 23:20:49)>>>>>> ('lactate', 'known', 'qn', 'mmol/L')\n",
"(2017-06-30 23:20:49)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:20:49)>>>>>> ('lactate', 'unknown', 'qn', 'no_units')\n",
"(2017-06-30 23:20:49)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:20:49)<<<< --- (0.0s)\n",
"(2017-06-30 23:20:49)>>>> TRANSFORM Combine like columns (142518, 7)\n",
"(2017-06-30 23:20:49)>>>>>> ('lactate', 'unknown', 'qn', 'no_units')\n",
"(2017-06-30 23:20:52)<<<<<< --- (3.0s)\n",
"(2017-06-30 23:20:52)>>>>>> ('lactate', 'known', 'qn', 'mmol/L')\n",
"(2017-06-30 23:20:55)<<<<<< --- (3.0s)\n",
"(2017-06-30 23:20:55)<<<< --- (6.0s)\n",
"(2017-06-30 23:20:55)>>>> *fit* Filter columns (max_col_only) (142518, 2)\n",
"(2017-06-30 23:20:55)<<<< --- (0.0s)\n",
"(2017-06-30 23:20:55)>>>> *transform* Filter columns (max_col_only) (142518, 2)\n",
"(2017-06-30 23:20:55)<<<< --- (0.0s)\n",
"(2017-06-30 23:20:55)>>>> fit_transform features on DF (134782, 1)\n",
"(2017-06-30 23:20:55)>>>>>> SAMPLE\n",
"(2017-06-30 23:20:55)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:20:55)>>>>>> *fit* Filter columns (filter_to_component) (134782, 1)\n",
"(2017-06-30 23:20:55)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:20:55)>>>>>> *transform* Filter columns (filter_to_component) (134782, 1)\n",
"(2017-06-30 23:21:17)<<<<<< --- (22.0s)\n",
"(2017-06-30 23:21:17)<<<< --- (22.0s)\n",
"(2017-06-30 23:21:17)<< --- (29.0s)\n",
"(2017-06-30 23:21:17) --- (29.0s)\n",
"(2017-06-30 23:21:17) Featurizing...\n",
"(2017-06-30 23:21:17)>> [('blood pressure mean', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-06-30 23:21:17)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure mean']\n",
"(2017-06-30 23:21:17)>>>>>> BLOOD PRESSURE MEAN: 1/1\n",
"(2017-06-30 23:21:18)>>>>>>>> Convert to dask - (1513298, 3)\n",
"(2017-06-30 23:21:18)<<<<<<<< --- (0.0s)\n",
"(2017-06-30 23:21:18)>>>>>>>> Join to big DF\n",
"(2017-06-30 23:21:18)<<<<<<<< --- (0.0s)\n",
"(2017-06-30 23:21:18)<<<<<< --- (1.0s)\n",
"(2017-06-30 23:21:18)>>>>>> Dask DF back to pandas\n",
"(2017-06-30 23:21:19)<<<<<< --- (1.0s)\n",
"(2017-06-30 23:21:19)>>>>>> SORT Joined DF\n",
"(2017-06-30 23:21:19)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:21:19)<<<< --- (2.0s)\n",
"(2017-06-30 23:21:19)>>>> *fit* Filter columns (DataNeedsFilter) (1513298, 3)\n",
"(2017-06-30 23:21:19)<<<< --- (0.0s)\n",
"(2017-06-30 23:21:19)>>>> *transform* Filter columns (DataNeedsFilter) (1513298, 3)\n",
"(2017-06-30 23:21:19)<<<< --- (0.0s)\n",
"(2017-06-30 23:21:19)>>>> Segment df (1513298, 3)\n",
"(2017-06-30 23:21:19)>>>>>> Get Segments\n",
"(2017-06-30 23:21:19)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:21:19)>>>>>> Apply n=19793 Segments to df.shape = (1513298, 3)\n",
"(2017-06-30 23:43:39)<<<<<< --- (1340.0s)\n",
"(2017-06-30 23:43:39)<<<< --- (1340.0s)\n",
"(2017-06-30 23:43:39)>>>> *fit* Filter columns (remove_small_columns) (1526462, 3)\n",
"(2017-06-30 23:43:39)<<<< --- (0.0s)\n",
"(2017-06-30 23:43:39)>>>> *transform* Filter columns (remove_small_columns) (1526462, 3)\n",
"(2017-06-30 23:43:39)<<<< --- (0.0s)\n",
"(2017-06-30 23:43:39)>>>> *fit* Filter columns (record_threshold) (1526462, 3)\n",
"(2017-06-30 23:43:39)<<<< --- (0.0s)\n",
"(2017-06-30 23:43:39)>>>> *transform* Filter columns (record_threshold) (1526462, 3)\n",
"(2017-06-30 23:43:39)<<<< --- (0.0s)\n",
"(2017-06-30 23:43:39)>>>> *fit* Filter columns (filter_var_type) (1526462, 3)\n",
"(2017-06-30 23:43:39)<<<< --- (0.0s)\n",
"(2017-06-30 23:43:39)>>>> *transform* Filter columns (filter_var_type) (1526462, 3)\n",
"(2017-06-30 23:43:39)<<<< --- (0.0s)\n",
"(2017-06-30 23:43:39)>>>> FIT Combine like columns (1526462, 3)\n",
"(2017-06-30 23:43:39)>>>>>> ('blood pressure mean', 'known', 'qn', 'mmHg')\n",
"(2017-06-30 23:43:39)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:43:39)<<<< --- (0.0s)\n",
"(2017-06-30 23:43:39)>>>> TRANSFORM Combine like columns (1526462, 3)\n",
"(2017-06-30 23:43:39)>>>>>> ('blood pressure mean', 'known', 'qn', 'mmHg')\n",
"(2017-06-30 23:44:12)<<<<<< --- (33.0s)\n",
"(2017-06-30 23:44:12)<<<< --- (33.0s)\n",
"(2017-06-30 23:44:12)>>>> fit_transform features on DF (1526462, 1)\n",
"(2017-06-30 23:44:12)>>>>>> STD\n",
"(2017-06-30 23:44:12)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:12)>>>>>> *fit* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-06-30 23:44:12)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:12)>>>>>> *transform* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-06-30 23:44:12)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:12)>>>>>> COUNT\n",
"(2017-06-30 23:44:12)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:12)>>>>>> *fit* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-06-30 23:44:12)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:12)>>>>>> *transform* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-06-30 23:44:16)<<<<<< --- (4.0s)\n",
"(2017-06-30 23:44:16)>>>>>> LAST\n",
"(2017-06-30 23:44:16)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:16)>>>>>> *fit* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-06-30 23:44:16)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:16)>>>>>> *transform* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-06-30 23:44:37)<<<<<< --- (21.0s)\n",
"(2017-06-30 23:44:37)>>>>>> MEAN\n",
"(2017-06-30 23:44:37)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:37)>>>>>> *fit* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-06-30 23:44:37)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:37)>>>>>> *transform* Filter columns (filter_to_component) (1526462, 1)\n",
"(2017-06-30 23:44:37)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:37)<<<< --- (25.0s)\n",
"(2017-06-30 23:44:37)<< --- (1400.0s)\n",
"(2017-06-30 23:44:37)>> [('blood pressure diastolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-06-30 23:44:37)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure diastolic']\n",
"(2017-06-30 23:44:37)>>>>>> BLOOD PRESSURE DIASTOLIC: 1/1\n",
"(2017-06-30 23:44:42)>>>>>>>> Convert to dask - (3457122, 42)\n",
"(2017-06-30 23:44:44)<<<<<<<< --- (2.0s)\n",
"(2017-06-30 23:44:44)>>>>>>>> Join to big DF\n",
"(2017-06-30 23:44:44)<<<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:44)<<<<<< --- (7.0s)\n",
"(2017-06-30 23:44:44)>>>>>> Dask DF back to pandas\n",
"(2017-06-30 23:44:46)<<<<<< --- (2.0s)\n",
"(2017-06-30 23:44:46)>>>>>> SORT Joined DF\n",
"(2017-06-30 23:44:48)<<<<<< --- (2.0s)\n",
"(2017-06-30 23:44:48)<<<< --- (11.0s)\n",
"(2017-06-30 23:44:49)>>>> *fit* Filter columns (DataNeedsFilter) (3457122, 42)\n",
"(2017-06-30 23:44:49)<<<< --- (0.0s)\n",
"(2017-06-30 23:44:49)>>>> *transform* Filter columns (DataNeedsFilter) (3457122, 42)\n",
"(2017-06-30 23:44:50)<<<< --- (1.0s)\n",
"(2017-06-30 23:44:50)>>>> Segment df (3457122, 42)\n",
"(2017-06-30 23:44:50)>>>>>> Get Segments\n",
"(2017-06-30 23:44:50)<<<<<< --- (0.0s)\n",
"(2017-06-30 23:44:50)>>>>>> Apply n=19793 Segments to df.shape = (3457122, 42)\n",
"(2017-07-01 01:42:39)<<<<<< --- (7069.0s)\n",
"(2017-07-01 01:42:39)<<<< --- (7069.0s)\n",
"(2017-07-01 01:42:39)>>>> *fit* Filter columns (remove_small_columns) (3463407, 42)\n",
"(2017-07-01 01:42:40)<<<< --- (1.0s)\n",
"(2017-07-01 01:42:40)>>>> *transform* Filter columns (remove_small_columns) (3463407, 42)\n",
"(2017-07-01 01:42:40)<<<< --- (0.0s)\n",
"(2017-07-01 01:42:40)>>>> *fit* Filter columns (record_threshold) (3463407, 36)\n",
"(2017-07-01 01:42:43)<<<< --- (3.0s)\n",
"(2017-07-01 01:42:43)>>>> *transform* Filter columns (record_threshold) (3463407, 36)\n",
"(2017-07-01 01:42:43)<<<< --- (0.0s)\n",
"(2017-07-01 01:42:43)>>>> *fit* Filter columns (filter_var_type) (3463407, 35)\n",
"(2017-07-01 01:42:43)<<<< --- (0.0s)\n",
"(2017-07-01 01:42:43)>>>> *transform* Filter columns (filter_var_type) (3463407, 35)\n",
"(2017-07-01 01:42:43)<<<< --- (0.0s)\n",
"(2017-07-01 01:42:43)>>>> FIT Combine like columns (3463407, 9)\n",
"(2017-07-01 01:42:43)>>>>>> ('blood pressure diastolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-01 01:42:43)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:42:43)<<<< --- (0.0s)\n",
"(2017-07-01 01:42:43)>>>> TRANSFORM Combine like columns (3463407, 9)\n",
"(2017-07-01 01:42:43)>>>>>> ('blood pressure diastolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-01 01:43:51)<<<<<< --- (68.0s)\n",
"(2017-07-01 01:43:51)<<<< --- (68.0s)\n",
"(2017-07-01 01:43:51)>>>> fit_transform features on DF (3463407, 1)\n",
"(2017-07-01 01:43:51)>>>>>> STD\n",
"(2017-07-01 01:43:51)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:43:51)>>>>>> *fit* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-01 01:43:51)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:43:51)>>>>>> *transform* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-01 01:43:51)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:43:51)>>>>>> COUNT\n",
"(2017-07-01 01:43:51)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:43:51)>>>>>> *fit* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-01 01:43:51)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:43:51)>>>>>> *transform* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-01 01:43:57)<<<<<< --- (6.0s)\n",
"(2017-07-01 01:43:57)>>>>>> LAST\n",
"(2017-07-01 01:43:57)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:43:57)>>>>>> *fit* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-01 01:43:57)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:43:57)>>>>>> *transform* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-01 01:44:31)<<<<<< --- (34.0s)\n",
"(2017-07-01 01:44:31)>>>>>> MEAN\n",
"(2017-07-01 01:44:31)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:44:31)>>>>>> *fit* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-01 01:44:31)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:44:31)>>>>>> *transform* Filter columns (filter_to_component) (3463407, 1)\n",
"(2017-07-01 01:44:32)<<<<<< --- (1.0s)\n",
"(2017-07-01 01:44:32)<<<< --- (41.0s)\n",
"(2017-07-01 01:44:32)<< --- (7195.0s)\n",
"(2017-07-01 01:44:32)>> [('blood pressure systolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-01 01:44:32)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure systolic']\n",
"(2017-07-01 01:44:32)>>>>>> BLOOD PRESSURE SYSTOLIC: 1/1\n",
"(2017-07-01 01:44:37)>>>>>>>> Convert to dask - (3455115, 40)\n",
"(2017-07-01 01:44:38)<<<<<<<< --- (1.0s)\n",
"(2017-07-01 01:44:38)>>>>>>>> Join to big DF\n",
"(2017-07-01 01:44:38)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 01:44:38)<<<<<< --- (6.0s)\n",
"(2017-07-01 01:44:38)>>>>>> Dask DF back to pandas\n",
"(2017-07-01 01:44:40)<<<<<< --- (2.0s)\n",
"(2017-07-01 01:44:40)>>>>>> SORT Joined DF\n",
"(2017-07-01 01:44:42)<<<<<< --- (2.0s)\n",
"(2017-07-01 01:44:42)<<<< --- (10.0s)\n",
"(2017-07-01 01:44:43)>>>> *fit* Filter columns (DataNeedsFilter) (3455115, 40)\n",
"(2017-07-01 01:44:43)<<<< --- (0.0s)\n",
"(2017-07-01 01:44:43)>>>> *transform* Filter columns (DataNeedsFilter) (3455115, 40)\n",
"(2017-07-01 01:44:44)<<<< --- (1.0s)\n",
"(2017-07-01 01:44:44)>>>> Segment df (3455115, 40)\n",
"(2017-07-01 01:44:44)>>>>>> Get Segments\n",
"(2017-07-01 01:44:44)<<<<<< --- (0.0s)\n",
"(2017-07-01 01:44:44)>>>>>> Apply n=19793 Segments to df.shape = (3455115, 40)\n",
"(2017-07-01 03:42:08)<<<<<< --- (7044.0s)\n",
"(2017-07-01 03:42:08)<<<< --- (7044.0s)\n",
"(2017-07-01 03:42:08)>>>> *fit* Filter columns (remove_small_columns) (3461400, 40)\n",
"(2017-07-01 03:42:08)<<<< --- (0.0s)\n",
"(2017-07-01 03:42:08)>>>> *transform* Filter columns (remove_small_columns) (3461400, 40)\n",
"(2017-07-01 03:42:08)<<<< --- (0.0s)\n",
"(2017-07-01 03:42:08)>>>> *fit* Filter columns (record_threshold) (3461400, 35)\n",
"(2017-07-01 03:42:11)<<<< --- (3.0s)\n",
"(2017-07-01 03:42:11)>>>> *transform* Filter columns (record_threshold) (3461400, 35)\n",
"(2017-07-01 03:42:11)<<<< --- (0.0s)\n",
"(2017-07-01 03:42:11)>>>> *fit* Filter columns (filter_var_type) (3461400, 34)\n",
"(2017-07-01 03:42:11)<<<< --- (0.0s)\n",
"(2017-07-01 03:42:11)>>>> *transform* Filter columns (filter_var_type) (3461400, 34)\n",
"(2017-07-01 03:42:11)<<<< --- (0.0s)\n",
"(2017-07-01 03:42:11)>>>> FIT Combine like columns (3461400, 8)\n",
"(2017-07-01 03:42:11)>>>>>> ('blood pressure systolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-01 03:42:12)<<<<<< --- (1.0s)\n",
"(2017-07-01 03:42:12)<<<< --- (1.0s)\n",
"(2017-07-01 03:42:12)>>>> TRANSFORM Combine like columns (3461400, 8)\n",
"(2017-07-01 03:42:12)>>>>>> ('blood pressure systolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-01 03:43:20)<<<<<< --- (68.0s)\n",
"(2017-07-01 03:43:20)<<<< --- (68.0s)\n",
"(2017-07-01 03:43:20)>>>> fit_transform features on DF (3461400, 1)\n",
"(2017-07-01 03:43:20)>>>>>> STD\n",
"(2017-07-01 03:43:20)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:43:20)>>>>>> *fit* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-01 03:43:20)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:43:20)>>>>>> *transform* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-01 03:43:20)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:43:20)>>>>>> COUNT\n",
"(2017-07-01 03:43:20)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:43:20)>>>>>> *fit* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-01 03:43:20)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:43:20)>>>>>> *transform* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-01 03:43:27)<<<<<< --- (7.0s)\n",
"(2017-07-01 03:43:27)>>>>>> LAST\n",
"(2017-07-01 03:43:27)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:43:27)>>>>>> *fit* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-01 03:43:27)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:43:27)>>>>>> *transform* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-01 03:44:01)<<<<<< --- (34.0s)\n",
"(2017-07-01 03:44:01)>>>>>> MEAN\n",
"(2017-07-01 03:44:01)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:01)>>>>>> *fit* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-01 03:44:01)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:01)>>>>>> *transform* Filter columns (filter_to_component) (3461400, 1)\n",
"(2017-07-01 03:44:01)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:01)<<<< --- (41.0s)\n",
"(2017-07-01 03:44:01)<< --- (7169.0s)\n",
"(2017-07-01 03:44:01) --- (15764.0s)\n",
"(2017-07-01 03:44:01) Featurizing...\n",
"(2017-07-01 03:44:01)>> [('lactate', 'all')] - SAMPLE\n",
"(2017-07-01 03:44:01)>>>> DASK OPEN & JOIN n=1 components: ['lactate']\n",
"(2017-07-01 03:44:01)>>>>>> LACTATE: 1/1\n",
"(2017-07-01 03:44:01)>>>>>>>> Convert to dask - (17859, 63)\n",
"(2017-07-01 03:44:01)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:01)>>>>>>>> Join to big DF\n",
"(2017-07-01 03:44:01)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:01)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:01)>>>>>> Dask DF back to pandas\n",
"(2017-07-01 03:44:01)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:01)>>>>>> SORT Joined DF\n",
"(2017-07-01 03:44:04)<<<<<< --- (3.0s)\n",
"(2017-07-01 03:44:04)<<<< --- (3.0s)\n",
"(2017-07-01 03:44:04)>>>> *fit* Filter columns (DataNeedsFilter) (17859, 63)\n",
"(2017-07-01 03:44:04)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:04)>>>> *transform* Filter columns (DataNeedsFilter) (17859, 63)\n",
"(2017-07-01 03:44:04)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:04)>>>> *transform* Filter columns (filter_var_type) (17859, 63)\n",
"(2017-07-01 03:44:04)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:04)>>>> TRANSFORM Combine like columns (17859, 7)\n",
"(2017-07-01 03:44:04)>>>>>> ('lactate', 'unknown', 'qn', 'no_units')\n",
"(2017-07-01 03:44:04)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:04)>>>>>> ('lactate', 'known', 'qn', 'mmol/L')\n",
"(2017-07-01 03:44:04)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:04)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:04)>>>> *transform* Filter columns (max_col_only) (17859, 2)\n",
"(2017-07-01 03:44:04)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:04)>>>> transform features on DF (16926, 1)\n",
"(2017-07-01 03:44:04)>>>>>> SAMPLE\n",
"(2017-07-01 03:44:04)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:04)>>>>>> *transform* Filter columns (filter_to_component) (16926, 1)\n",
"(2017-07-01 03:44:07)<<<<<< --- (3.0s)\n",
"(2017-07-01 03:44:07)<<<< --- (3.0s)\n",
"(2017-07-01 03:44:07)<< --- (6.0s)\n",
"(2017-07-01 03:44:07) --- (6.0s)\n",
"(2017-07-01 03:44:07) Featurizing...\n",
"(2017-07-01 03:44:07)>> [('blood pressure mean', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-01 03:44:07)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure mean']\n",
"(2017-07-01 03:44:07)>>>>>> BLOOD PRESSURE MEAN: 1/1\n",
"(2017-07-01 03:44:08)>>>>>>>> Convert to dask - (227456, 3)\n",
"(2017-07-01 03:44:08)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:08)>>>>>>>> Join to big DF\n",
"(2017-07-01 03:44:08)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:08)<<<<<< --- (1.0s)\n",
"(2017-07-01 03:44:08)>>>>>> Dask DF back to pandas\n",
"(2017-07-01 03:44:08)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:08)>>>>>> SORT Joined DF\n",
"(2017-07-01 03:44:09)<<<<<< --- (1.0s)\n",
"(2017-07-01 03:44:09)<<<< --- (2.0s)\n",
"(2017-07-01 03:44:09)>>>> *fit* Filter columns (DataNeedsFilter) (227456, 3)\n",
"(2017-07-01 03:44:09)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:09)>>>> *transform* Filter columns (DataNeedsFilter) (227456, 3)\n",
"(2017-07-01 03:44:09)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:09)>>>> Segment df (227456, 3)\n",
"(2017-07-01 03:44:09)>>>>>> Get Segments\n",
"(2017-07-01 03:44:09)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:09)>>>>>> Apply n=2482 Segments to df.shape = (227456, 3)\n",
"(2017-07-01 03:44:46)<<<<<< --- (37.0s)\n",
"(2017-07-01 03:44:46)<<<< --- (37.0s)\n",
"(2017-07-01 03:44:46)>>>> *transform* Filter columns (remove_small_columns) (229085, 3)\n",
"(2017-07-01 03:44:46)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:46)>>>> *transform* Filter columns (record_threshold) (229085, 3)\n",
"(2017-07-01 03:44:46)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:46)>>>> *transform* Filter columns (filter_var_type) (229085, 3)\n",
"(2017-07-01 03:44:46)<<<< --- (0.0s)\n",
"(2017-07-01 03:44:46)>>>> TRANSFORM Combine like columns (229085, 3)\n",
"(2017-07-01 03:44:46)>>>>>> ('blood pressure mean', 'known', 'qn', 'mmHg')\n",
"(2017-07-01 03:44:52)<<<<<< --- (6.0s)\n",
"(2017-07-01 03:44:52)<<<< --- (6.0s)\n",
"(2017-07-01 03:44:52)>>>> transform features on DF (229085, 1)\n",
"(2017-07-01 03:44:52)>>>>>> STD\n",
"(2017-07-01 03:44:52)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:52)>>>>>> *transform* Filter columns (filter_to_component) (229085, 1)\n",
"(2017-07-01 03:44:52)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:52)>>>>>> COUNT\n",
"(2017-07-01 03:44:52)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:52)>>>>>> *transform* Filter columns (filter_to_component) (229085, 1)\n",
"(2017-07-01 03:44:53)<<<<<< --- (1.0s)\n",
"(2017-07-01 03:44:53)>>>>>> LAST\n",
"(2017-07-01 03:44:53)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:53)>>>>>> *transform* Filter columns (filter_to_component) (229085, 1)\n",
"(2017-07-01 03:44:56)<<<<<< --- (3.0s)\n",
"(2017-07-01 03:44:56)>>>>>> MEAN\n",
"(2017-07-01 03:44:56)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:56)>>>>>> *transform* Filter columns (filter_to_component) (229085, 1)\n",
"(2017-07-01 03:44:56)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:44:56)<<<< --- (4.0s)\n",
"(2017-07-01 03:44:56)<< --- (49.0s)\n",
"(2017-07-01 03:44:56)>> [('blood pressure diastolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-01 03:44:56)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure diastolic']\n",
"(2017-07-01 03:44:56)>>>>>> BLOOD PRESSURE DIASTOLIC: 1/1\n",
"(2017-07-01 03:45:00)>>>>>>>> Convert to dask - (457700, 42)\n",
"(2017-07-01 03:45:01)<<<<<<<< --- (1.0s)\n",
"(2017-07-01 03:45:01)>>>>>>>> Join to big DF\n",
"(2017-07-01 03:45:01)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 03:45:01)<<<<<< --- (5.0s)\n",
"(2017-07-01 03:45:01)>>>>>> Dask DF back to pandas\n",
"(2017-07-01 03:45:01)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:45:01)>>>>>> SORT Joined DF\n",
"(2017-07-01 03:45:01)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:45:01)<<<< --- (5.0s)\n",
"(2017-07-01 03:45:01)>>>> *fit* Filter columns (DataNeedsFilter) (457700, 42)\n",
"(2017-07-01 03:45:01)<<<< --- (0.0s)\n",
"(2017-07-01 03:45:01)>>>> *transform* Filter columns (DataNeedsFilter) (457700, 42)\n",
"(2017-07-01 03:45:01)<<<< --- (0.0s)\n",
"(2017-07-01 03:45:01)>>>> Segment df (457700, 42)\n",
"(2017-07-01 03:45:01)>>>>>> Get Segments\n",
"(2017-07-01 03:45:01)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:45:01)>>>>>> Apply n=2482 Segments to df.shape = (457700, 42)\n",
"(2017-07-01 03:47:03)<<<<<< --- (122.0s)\n",
"(2017-07-01 03:47:03)<<<< --- (122.0s)\n",
"(2017-07-01 03:47:03)>>>> *transform* Filter columns (remove_small_columns) (458492, 42)\n",
"(2017-07-01 03:47:03)<<<< --- (0.0s)\n",
"(2017-07-01 03:47:03)>>>> *transform* Filter columns (record_threshold) (458492, 36)\n",
"(2017-07-01 03:47:03)<<<< --- (0.0s)\n",
"(2017-07-01 03:47:03)>>>> *transform* Filter columns (filter_var_type) (458492, 35)\n",
"(2017-07-01 03:47:03)<<<< --- (0.0s)\n",
"(2017-07-01 03:47:03)>>>> TRANSFORM Combine like columns (458492, 9)\n",
"(2017-07-01 03:47:03)>>>>>> ('blood pressure diastolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-01 03:47:14)<<<<<< --- (11.0s)\n",
"(2017-07-01 03:47:14)<<<< --- (11.0s)\n",
"(2017-07-01 03:47:14)>>>> transform features on DF (458492, 1)\n",
"(2017-07-01 03:47:14)>>>>>> STD\n",
"(2017-07-01 03:47:14)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:47:14)>>>>>> *transform* Filter columns (filter_to_component) (458492, 1)\n",
"(2017-07-01 03:47:14)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:47:14)>>>>>> COUNT\n",
"(2017-07-01 03:47:14)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:47:14)>>>>>> *transform* Filter columns (filter_to_component) (458492, 1)\n",
"(2017-07-01 03:47:15)<<<<<< --- (1.0s)\n",
"(2017-07-01 03:47:15)>>>>>> LAST\n",
"(2017-07-01 03:47:15)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:47:15)>>>>>> *transform* Filter columns (filter_to_component) (458492, 1)\n",
"(2017-07-01 03:47:19)<<<<<< --- (4.0s)\n",
"(2017-07-01 03:47:19)>>>>>> MEAN\n",
"(2017-07-01 03:47:19)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:47:19)>>>>>> *transform* Filter columns (filter_to_component) (458492, 1)\n",
"(2017-07-01 03:47:20)<<<<<< --- (1.0s)\n",
"(2017-07-01 03:47:20)<<<< --- (6.0s)\n",
"(2017-07-01 03:47:20)<< --- (144.0s)\n",
"(2017-07-01 03:47:20)>> [('blood pressure systolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-01 03:47:20)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure systolic']\n",
"(2017-07-01 03:47:20)>>>>>> BLOOD PRESSURE SYSTOLIC: 1/1\n",
"(2017-07-01 03:47:24)>>>>>>>> Convert to dask - (457598, 40)\n",
"(2017-07-01 03:47:25)<<<<<<<< --- (1.0s)\n",
"(2017-07-01 03:47:25)>>>>>>>> Join to big DF\n",
"(2017-07-01 03:47:25)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 03:47:25)<<<<<< --- (5.0s)\n",
"(2017-07-01 03:47:25)>>>>>> Dask DF back to pandas\n",
"(2017-07-01 03:47:25)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:47:25)>>>>>> SORT Joined DF\n",
"(2017-07-01 03:47:25)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:47:25)<<<< --- (5.0s)\n",
"(2017-07-01 03:47:25)>>>> *fit* Filter columns (DataNeedsFilter) (457598, 40)\n",
"(2017-07-01 03:47:25)<<<< --- (0.0s)\n",
"(2017-07-01 03:47:25)>>>> *transform* Filter columns (DataNeedsFilter) (457598, 40)\n",
"(2017-07-01 03:47:25)<<<< --- (0.0s)\n",
"(2017-07-01 03:47:25)>>>> Segment df (457598, 40)\n",
"(2017-07-01 03:47:25)>>>>>> Get Segments\n",
"(2017-07-01 03:47:25)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:47:25)>>>>>> Apply n=2482 Segments to df.shape = (457598, 40)\n",
"(2017-07-01 03:49:27)<<<<<< --- (122.0s)\n",
"(2017-07-01 03:49:27)<<<< --- (122.0s)\n",
"(2017-07-01 03:49:27)>>>> *transform* Filter columns (remove_small_columns) (458390, 40)\n",
"(2017-07-01 03:49:27)<<<< --- (0.0s)\n",
"(2017-07-01 03:49:27)>>>> *transform* Filter columns (record_threshold) (458390, 35)\n",
"(2017-07-01 03:49:27)<<<< --- (0.0s)\n",
"(2017-07-01 03:49:27)>>>> *transform* Filter columns (filter_var_type) (458390, 34)\n",
"(2017-07-01 03:49:27)<<<< --- (0.0s)\n",
"(2017-07-01 03:49:27)>>>> TRANSFORM Combine like columns (458390, 8)\n",
"(2017-07-01 03:49:27)>>>>>> ('blood pressure systolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-01 03:49:38)<<<<<< --- (11.0s)\n",
"(2017-07-01 03:49:38)<<<< --- (11.0s)\n",
"(2017-07-01 03:49:38)>>>> transform features on DF (458390, 1)\n",
"(2017-07-01 03:49:38)>>>>>> STD\n",
"(2017-07-01 03:49:38)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:49:38)>>>>>> *transform* Filter columns (filter_to_component) (458390, 1)\n",
"(2017-07-01 03:49:38)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:49:38)>>>>>> COUNT\n",
"(2017-07-01 03:49:38)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:49:38)>>>>>> *transform* Filter columns (filter_to_component) (458390, 1)\n",
"(2017-07-01 03:49:39)<<<<<< --- (1.0s)\n",
"(2017-07-01 03:49:39)>>>>>> LAST\n",
"(2017-07-01 03:49:39)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:49:39)>>>>>> *transform* Filter columns (filter_to_component) (458390, 1)\n",
"(2017-07-01 03:49:43)<<<<<< --- (4.0s)\n",
"(2017-07-01 03:49:43)>>>>>> MEAN\n",
"(2017-07-01 03:49:43)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:49:43)>>>>>> *transform* Filter columns (filter_to_component) (458390, 1)\n",
"(2017-07-01 03:49:43)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:49:43)<<<< --- (5.0s)\n",
"(2017-07-01 03:49:44)<< --- (144.0s)\n",
"(2017-07-01 03:49:44) --- (337.0s)\n",
"(19793, 12) (19793, 1)\n",
"(2482, 12) (2482, 1)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</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>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>qn</th>\n",
" <th>qn</th>\n",
" <th>qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" </tr>\n",
" <tr>\n",
" <th>id</th>\n",
" <th>seg_id</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>100009</th>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100010</th>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100011</th>\n",
" <th>0</th>\n",
" <td>10.737784</td>\n",
" <td>5.0</td>\n",
" <td>64.000000</td>\n",
" <td>70.600000</td>\n",
" <td>11.606033</td>\n",
" <td>5.0</td>\n",
" <td>46.000000</td>\n",
" <td>57.800000</td>\n",
" <td>11.300442</td>\n",
" <td>5.0</td>\n",
" <td>102.000000</td>\n",
" <td>108.800000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100018</th>\n",
" <th>0</th>\n",
" <td>9.917247</td>\n",
" <td>23.0</td>\n",
" <td>89.000000</td>\n",
" <td>79.521739</td>\n",
" <td>6.660010</td>\n",
" <td>23.0</td>\n",
" <td>64.000000</td>\n",
" <td>57.086957</td>\n",
" <td>15.660176</td>\n",
" <td>23.0</td>\n",
" <td>133.000000</td>\n",
" <td>124.826087</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100020</th>\n",
" <th>0</th>\n",
" <td>21.120986</td>\n",
" <td>29.0</td>\n",
" <td>90.000000</td>\n",
" <td>87.103448</td>\n",
" <td>18.688001</td>\n",
" <td>29.0</td>\n",
" <td>71.000000</td>\n",
" <td>72.206897</td>\n",
" <td>31.660686</td>\n",
" <td>29.0</td>\n",
" <td>144.000000</td>\n",
" <td>135.551724</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature STD COUNT LAST \\\n",
"component blood pressure mean blood pressure mean blood pressure mean \n",
"status known known known \n",
"variable_type qn qn qn \n",
"units mmHg mmHg mmHg \n",
"description all all all \n",
"id seg_id \n",
"100009 0 0.000000 0.0 75.758916 \n",
"100010 0 0.000000 0.0 75.758916 \n",
"100011 0 10.737784 5.0 64.000000 \n",
"100018 0 9.917247 23.0 89.000000 \n",
"100020 0 21.120986 29.0 90.000000 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure mean blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100009 0 77.487629 0.000000 \n",
"100010 0 77.487629 0.000000 \n",
"100011 0 70.600000 11.606033 \n",
"100018 0 79.521739 6.660010 \n",
"100020 0 87.103448 18.688001 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure diastolic blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100009 0 0.0 58.870209 \n",
"100010 0 0.0 58.870209 \n",
"100011 0 5.0 46.000000 \n",
"100018 0 23.0 64.000000 \n",
"100020 0 29.0 71.000000 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure diastolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100009 0 60.420185 0.000000 \n",
"100010 0 60.420185 0.000000 \n",
"100011 0 57.800000 11.300442 \n",
"100018 0 57.086957 15.660176 \n",
"100020 0 72.206897 31.660686 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure systolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100009 0 0.0 115.628637 \n",
"100010 0 0.0 115.628637 \n",
"100011 0 5.0 102.000000 \n",
"100018 0 23.0 133.000000 \n",
"100020 0 29.0 144.000000 \n",
"\n",
"feature MEAN \n",
"component blood pressure systolic \n",
"status known \n",
"variable_type qn \n",
"units mmHg \n",
"description all \n",
"id seg_id \n",
"100009 0 118.662692 \n",
"100010 0 118.662692 \n",
"100011 0 108.800000 \n",
"100018 0 124.826087 \n",
"100020 0 135.551724 "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>SAMPLE</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</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></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>100009</th>\n",
" <th>2162-05-17 17:14:00</th>\n",
" <td>1.5</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100010</th>\n",
" <th>2109-12-10 12:11:00</th>\n",
" <td>0.9</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100011</th>\n",
" <th>2177-08-29 06:55:00</th>\n",
" <td>2.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100018</th>\n",
" <th>2176-08-30 10:19:00</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100020</th>\n",
" <th>2142-12-03 00:17:00</th>\n",
" <td>1.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature SAMPLE\n",
"component lactate\n",
"status known\n",
"variable_type qn\n",
"units mmol/L\n",
"description all\n",
"id datetime \n",
"100009 2162-05-17 17:14:00 1.5\n",
"100010 2109-12-10 12:11:00 0.9\n",
"100011 2177-08-29 06:55:00 2.3\n",
"100018 2176-08-30 10:19:00 1.0\n",
"100020 2142-12-03 00:17:00 1.0"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure diastolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</th>\n",
" <th>blood pressure systolic</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>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>qn</th>\n",
" <th>qn</th>\n",
" <th>qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" </tr>\n",
" <tr>\n",
" <th>id</th>\n",
" <th>seg_id</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>100028</th>\n",
" <th>0</th>\n",
" <td>11.091809</td>\n",
" <td>32.0</td>\n",
" <td>65.000000</td>\n",
" <td>58.062500</td>\n",
" <td>12.709812</td>\n",
" <td>32.0</td>\n",
" <td>49.000000</td>\n",
" <td>46.406250</td>\n",
" <td>12.541544</td>\n",
" <td>32.0</td>\n",
" <td>113.000000</td>\n",
" <td>97.250000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100085</th>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>58.870209</td>\n",
" <td>60.420185</td>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>115.628637</td>\n",
" <td>118.662692</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100091</th>\n",
" <th>0</th>\n",
" <td>15.624633</td>\n",
" <td>16.0</td>\n",
" <td>51.000000</td>\n",
" <td>66.437500</td>\n",
" <td>19.103119</td>\n",
" <td>16.0</td>\n",
" <td>32.000000</td>\n",
" <td>48.562500</td>\n",
" <td>16.445744</td>\n",
" <td>16.0</td>\n",
" <td>103.000000</td>\n",
" <td>123.937500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100179</th>\n",
" <th>0</th>\n",
" <td>0.000000</td>\n",
" <td>0.0</td>\n",
" <td>75.758916</td>\n",
" <td>77.487629</td>\n",
" <td>11.024216</td>\n",
" <td>16.0</td>\n",
" <td>74.000000</td>\n",
" <td>69.750000</td>\n",
" <td>10.770136</td>\n",
" <td>16.0</td>\n",
" <td>130.000000</td>\n",
" <td>127.437500</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100210</th>\n",
" <th>0</th>\n",
" <td>11.813525</td>\n",
" <td>241.0</td>\n",
" <td>106.000000</td>\n",
" <td>83.497925</td>\n",
" <td>10.422712</td>\n",
" <td>241.0</td>\n",
" <td>98.000000</td>\n",
" <td>68.224066</td>\n",
" <td>15.507445</td>\n",
" <td>241.0</td>\n",
" <td>131.000000</td>\n",
" <td>104.950207</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature STD COUNT LAST \\\n",
"component blood pressure mean blood pressure mean blood pressure mean \n",
"status known known known \n",
"variable_type qn qn qn \n",
"units mmHg mmHg mmHg \n",
"description all all all \n",
"id seg_id \n",
"100028 0 11.091809 32.0 65.000000 \n",
"100085 0 0.000000 0.0 75.758916 \n",
"100091 0 15.624633 16.0 51.000000 \n",
"100179 0 0.000000 0.0 75.758916 \n",
"100210 0 11.813525 241.0 106.000000 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure mean blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100028 0 58.062500 12.709812 \n",
"100085 0 77.487629 0.000000 \n",
"100091 0 66.437500 19.103119 \n",
"100179 0 77.487629 11.024216 \n",
"100210 0 83.497925 10.422712 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure diastolic blood pressure diastolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100028 0 32.0 49.000000 \n",
"100085 0 0.0 58.870209 \n",
"100091 0 16.0 32.000000 \n",
"100179 0 16.0 74.000000 \n",
"100210 0 241.0 98.000000 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure diastolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100028 0 46.406250 12.541544 \n",
"100085 0 60.420185 0.000000 \n",
"100091 0 48.562500 16.445744 \n",
"100179 0 69.750000 10.770136 \n",
"100210 0 68.224066 15.507445 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure systolic blood pressure systolic \n",
"status known known \n",
"variable_type qn qn \n",
"units mmHg mmHg \n",
"description all all \n",
"id seg_id \n",
"100028 0 32.0 113.000000 \n",
"100085 0 0.0 115.628637 \n",
"100091 0 16.0 103.000000 \n",
"100179 0 16.0 130.000000 \n",
"100210 0 241.0 131.000000 \n",
"\n",
"feature MEAN \n",
"component blood pressure systolic \n",
"status known \n",
"variable_type qn \n",
"units mmHg \n",
"description all \n",
"id seg_id \n",
"100028 0 97.250000 \n",
"100085 0 118.662692 \n",
"100091 0 123.937500 \n",
"100179 0 127.437500 \n",
"100210 0 104.950207 "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>SAMPLE</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</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></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>100028</th>\n",
" <th>2142-12-25 02:44:00</th>\n",
" <td>1.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100085</th>\n",
" <th>2126-08-30 10:36:00</th>\n",
" <td>1.3</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100091</th>\n",
" <th>2162-06-04 00:33:00</th>\n",
" <td>1.4</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100179</th>\n",
" <th>2135-12-27 13:14:00</th>\n",
" <td>1.1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100210</th>\n",
" <th>2159-06-01 13:43:00</th>\n",
" <td>1.7</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature SAMPLE\n",
"component lactate\n",
"status known\n",
"variable_type qn\n",
"units mmol/L\n",
"description all\n",
"id datetime \n",
"100028 2142-12-25 02:44:00 1.1\n",
"100085 2126-08-30 10:36:00 1.3\n",
"100091 2162-06-04 00:33:00 1.4\n",
"100179 2135-12-27 13:14:00 1.1\n",
"100210 2159-06-01 13:43:00 1.7"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"labelizer = sample_one_lactate_labelizer\n",
"featurizer = bp_featurizer\n",
"featurizer.loader.segmenter = load_and_segment.n_hrs_before(n_hrs=12)\n",
"\n",
"y_train2 = labelizer.fit_transform(X=train_ids)\n",
"X_train2 = featurizer.fit_transform(X=y_train1)\n",
"\n",
"y_validate2 = labelizer.transform(X=validate_ids)\n",
"X_validate2 = featurizer.transform(X=y_validate1)\n",
"\n",
"\n",
"print X_train2.shape,y_train2.shape\n",
"print X_validate2.shape,y_validate2.shape\n",
"\n",
"display(X_train2.head())\n",
"display(y_train2.head())\n",
"\n",
"display(X_validate2.head())\n",
"display(y_validate2.head())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Models!"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from sklearn.metrics import mean_squared_error\n",
"import pandas as pd\n",
"\n",
"def try_model(train_ft,train_lbl,test_ft,test_lbl,prep_pipeline,model):\n",
" # apply final cleaning to our data\n",
" X_train = prep_pipeline.fit_transform(train_ft.copy())\n",
" y_train = train_lbl.reset_index(drop=True).iloc[:,0]\n",
" X_test = prep_pipeline.fit_transform(test_ft.copy())\n",
" y_test = test_lbl.reset_index(drop=True).iloc[:,0]\n",
" \n",
" model = model.fit(X_train,y_train)\n",
" y_pred = model.predict(X_test)\n",
" \n",
" rmse = pd.np.sqrt(mean_squared_error(y_test,y_pred))\n",
"\n",
" results = pd.DataFrame(zip(y_test,y_pred), columns=['actual','predicted'])\n",
" \n",
" display(results.head())\n",
" display(results.describe())\n",
" print(\"Training set score: %f\" % model.score(X_train, y_train))\n",
" print(\"Test set score: %f\" % model.score(X_test, y_test))\n",
" \n",
" print \"RMSE:\",rmse\n",
" \n",
" return model,results,rmse"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [],
"source": [
"from sklearn.linear_model import LinearRegression\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"prep_pipeline = Pipeline([\n",
" ('flatten_index',transformers.flatten_index(axis=0)),\n",
" ('flatten_columns',transformers.flatten_index(axis=1)),\n",
" ('scaler',StandardScaler())\n",
" ])\n",
"\n",
"lin_reg = LinearRegression()\n",
"\n",
"\n",
"model,results,rmse = try_model(X_train,y_train,X_test,y_test,prep_pipeline,lin_reg)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"pd.Series(model.coef_, index=X_train.columns).sort_values().to_frame()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"from sklearn.linear_model import ElasticNet\n",
"model,results,rmse = try_model(X_train,y_train,X_test,y_test,prep_pipeline,ElasticNet())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"pd.Series(model.coef_, index=X_train.columns).sort_values().to_frame()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Optimizing segmetation"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import utils\n",
"import icu_data_defs\n",
"import load_and_segment\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"#load data\n",
"df_lactate = utils.open_df('data/mimic_data','cleaned/lactate')\n",
"df_heart_rate = utils.open_df('data/mimic_data','cleaned/heart rate')"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</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 colspan=\"14\" halign=\"left\">nom</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th colspan=\"4\" halign=\"left\">mmol/L</th>\n",
" <th colspan=\"14\" halign=\"left\">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>1531</th>\n",
" <th>225668</th>\n",
" <th>50813</th>\n",
" <th>818</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>...</th>\n",
" <th>818(mmol/L)_7.9O1B</th>\n",
" <th>818(mmol/L)_>30</th>\n",
" <th>818(mmol/L)_>30.0</th>\n",
" <th>818(mmol/L)_CLOTTED</th>\n",
" <th>818(mmol/L)_ERROR</th>\n",
" <th>818(mmol/L)_VOIDED</th>\n",
" <th>818(mmol/L)_no data</th>\n",
" <th>225668</th>\n",
" <th>50813</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",
" <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>NaN</td>\n",
" <td>NaN</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>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>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>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>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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.5</td>\n",
" <td>4.5</td>\n",
" <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>...</td>\n",
" <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>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>3.1</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>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>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>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>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>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>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>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>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>1.5</td>\n",
" <td>1.5</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>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>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>0.6</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>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>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>0.9</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>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>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>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>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>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>0.8</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>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>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>3.8</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>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>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>2.3</td>\n",
" <td>2.3</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>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>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>2.3</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>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>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>2.5</td>\n",
" <td>2.5</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>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>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>2.1</td>\n",
" <td>2.1</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>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>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>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>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>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>1.8</td>\n",
" <td>1.8</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>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>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>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>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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.1</td>\n",
" <td>1.1</td>\n",
" <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>...</td>\n",
" <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>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>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>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>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>0.9</td>\n",
" <td>0.9</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>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>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>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>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>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>0.9</td>\n",
" <td>0.9</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>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>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>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>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>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>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>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>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>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>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>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>1.4</td>\n",
" <td>1.4</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>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>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>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>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>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>3.2</td>\n",
" <td>3.2</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>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>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=\"8\" valign=\"top\">100223</th>\n",
" <th>2162-04-03 23:07:00</th>\n",
" <td>NaN</td>\n",
" <td>3.3</td>\n",
" <td>3.3</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2162-04-04 04:17:00</th>\n",
" <td>NaN</td>\n",
" <td>2.1</td>\n",
" <td>2.1</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2162-04-05 02:27:00</th>\n",
" <td>NaN</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2162-04-06 02:28:00</th>\n",
" <td>NaN</td>\n",
" <td>3.8</td>\n",
" <td>3.8</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2162-04-06 10:01:00</th>\n",
" <td>NaN</td>\n",
" <td>5.4</td>\n",
" <td>5.4</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2162-04-06 14:18:00</th>\n",
" <td>NaN</td>\n",
" <td>4.4</td>\n",
" <td>4.4</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2162-04-07 02:51:00</th>\n",
" <td>NaN</td>\n",
" <td>2.5</td>\n",
" <td>2.5</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2162-04-14 10:33:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.7</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"2\" valign=\"top\">100227</th>\n",
" <th>2160-12-07 16:15:00</th>\n",
" <td>NaN</td>\n",
" <td>1.4</td>\n",
" <td>1.4</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2160-12-08 03:07:00</th>\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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"4\" valign=\"top\">100229</th>\n",
" <th>2114-12-24 12:27:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>5.9</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2114-12-24 14:36:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.5</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2114-12-24 16:29:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.8</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2114-12-24 16:45:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.6</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"9\" valign=\"top\">100234</th>\n",
" <th>2118-10-23 17:51:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.7</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2118-11-04 00:30:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.5</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2118-11-04 06:14:00</th>\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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2118-11-04 10:57:00</th>\n",
" <td>NaN</td>\n",
" <td>1.2</td>\n",
" <td>1.2</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2118-11-04 13:15:00</th>\n",
" <td>NaN</td>\n",
" <td>1.8</td>\n",
" <td>1.8</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2118-11-04 14:35:00</th>\n",
" <td>NaN</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2118-11-04 21:23:00</th>\n",
" <td>NaN</td>\n",
" <td>1.8</td>\n",
" <td>1.8</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2118-11-05 00:53:00</th>\n",
" <td>NaN</td>\n",
" <td>2.2</td>\n",
" <td>2.2</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2118-11-05 03:01:00</th>\n",
" <td>NaN</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>100237</th>\n",
" <th>2165-01-11 16:25:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"6\" valign=\"top\">100242</th>\n",
" <th>2161-08-30 03:55:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.5</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2161-08-30 13:48:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.2</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2161-09-14 12:36:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.7</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>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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2161-09-29 10:58:00</th>\n",
" <td>0.9</td>\n",
" <td>NaN</td>\n",
" <td>0.9</td>\n",
" <td>0.9</td>\n",
" <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>...</td>\n",
" <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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2161-09-29 16:18:00</th>\n",
" <td>2.6</td>\n",
" <td>NaN</td>\n",
" <td>2.6</td>\n",
" <td>2.6</td>\n",
" <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>...</td>\n",
" <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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2161-09-29 16:55:00</th>\n",
" <td>2.1</td>\n",
" <td>NaN</td>\n",
" <td>2.1</td>\n",
" <td>2.1</td>\n",
" <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>...</td>\n",
" <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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>500 rows × 63 columns</p>\n",
"</div>"
],
"text/plain": [
"component lactate \\\n",
"status known unknown \n",
"variable_type qn nom \n",
"units mmol/L no_units \n",
"description 1531 225668 50813 818 1531(mmol/L)_. \n",
"id datetime \n",
"100001 2117-09-11 09:32:00 NaN NaN 1.9 NaN 0 \n",
"100003 2150-04-17 19:12:00 NaN 1.1 1.1 NaN 0 \n",
"100006 2108-04-08 10:58:00 NaN NaN 4.5 4.5 0 \n",
"100007 2145-03-31 00:44:00 NaN NaN 3.1 NaN 0 \n",
" 2145-04-02 14:10:00 NaN NaN 1.9 NaN 0 \n",
"100009 2162-05-17 13:19:00 NaN 1.1 1.1 NaN 0 \n",
" 2162-05-17 17:14:00 NaN 1.5 1.5 NaN 0 \n",
"100010 2109-12-10 10:25:00 NaN NaN 0.6 NaN 0 \n",
" 2109-12-10 12:11:00 NaN NaN 0.9 NaN 0 \n",
" 2109-12-10 13:05:00 NaN NaN 1.0 NaN 0 \n",
" 2109-12-10 13:58:00 NaN NaN 0.8 NaN 0 \n",
"100011 2177-08-29 04:44:00 NaN NaN 3.8 NaN 0 \n",
" 2177-08-29 06:55:00 NaN 2.3 2.3 NaN 0 \n",
"100012 2177-03-14 07:38:00 NaN NaN 2.3 NaN 0 \n",
" 2177-03-14 11:42:00 NaN 2.5 2.5 NaN 0 \n",
" 2177-03-15 08:05:00 NaN 2.1 2.1 NaN 0 \n",
" 2177-03-15 14:01:00 NaN 2.6 2.6 NaN 0 \n",
" 2177-03-15 21:42:00 NaN 1.8 1.8 NaN 0 \n",
"100016 2188-05-24 12:00:00 NaN NaN 2.0 NaN 0 \n",
"100017 2103-03-11 05:10:00 NaN NaN 1.1 1.1 0 \n",
"100018 2176-08-29 15:29:00 NaN NaN 1.3 NaN 0 \n",
" 2176-08-30 09:23:00 NaN 0.9 0.9 NaN 0 \n",
" 2176-08-30 10:19:00 NaN 1.0 1.0 NaN 0 \n",
" 2176-08-30 11:29:00 NaN 0.9 0.9 NaN 0 \n",
" 2176-08-30 12:40:00 NaN 1.1 1.1 NaN 0 \n",
"100020 2142-11-30 21:54:00 NaN NaN 1.1 NaN 0 \n",
" 2142-12-03 00:17:00 NaN NaN 1.0 NaN 0 \n",
"100024 2170-09-19 10:25:00 NaN 1.4 1.4 NaN 0 \n",
" 2170-09-19 16:33:00 NaN 2.6 2.6 NaN 0 \n",
" 2170-09-20 02:04:00 NaN 3.2 3.2 NaN 0 \n",
"... ... ... ... ... ... \n",
"100223 2162-04-03 23:07:00 NaN 3.3 3.3 NaN 0 \n",
" 2162-04-04 04:17:00 NaN 2.1 2.1 NaN 0 \n",
" 2162-04-05 02:27:00 NaN 1.9 1.9 NaN 0 \n",
" 2162-04-06 02:28:00 NaN 3.8 3.8 NaN 0 \n",
" 2162-04-06 10:01:00 NaN 5.4 5.4 NaN 0 \n",
" 2162-04-06 14:18:00 NaN 4.4 4.4 NaN 0 \n",
" 2162-04-07 02:51:00 NaN 2.5 2.5 NaN 0 \n",
" 2162-04-14 10:33:00 NaN NaN 1.7 NaN 0 \n",
"100227 2160-12-07 16:15:00 NaN 1.4 1.4 NaN 0 \n",
" 2160-12-08 03:07:00 NaN 1.0 1.0 NaN 0 \n",
"100229 2114-12-24 12:27:00 NaN NaN 5.9 NaN 0 \n",
" 2114-12-24 14:36:00 NaN NaN 4.5 NaN 0 \n",
" 2114-12-24 16:29:00 NaN NaN 4.8 NaN 0 \n",
" 2114-12-24 16:45:00 NaN NaN 4.6 NaN 0 \n",
"100234 2118-10-23 17:51:00 NaN NaN 1.7 NaN 0 \n",
" 2118-11-04 00:30:00 NaN NaN 1.5 NaN 0 \n",
" 2118-11-04 06:14:00 NaN 1.0 1.0 NaN 0 \n",
" 2118-11-04 10:57:00 NaN 1.2 1.2 NaN 0 \n",
" 2118-11-04 13:15:00 NaN 1.8 1.8 NaN 0 \n",
" 2118-11-04 14:35:00 NaN 1.3 1.3 NaN 0 \n",
" 2118-11-04 21:23:00 NaN 1.8 1.8 NaN 0 \n",
" 2118-11-05 00:53:00 NaN 2.2 2.2 NaN 0 \n",
" 2118-11-05 03:01:00 NaN 2.0 2.0 NaN 0 \n",
"100237 2165-01-11 16:25:00 NaN NaN 1.3 NaN 0 \n",
"100242 2161-08-30 03:55:00 NaN NaN 1.5 NaN 0 \n",
" 2161-08-30 13:48:00 NaN NaN 1.2 NaN 0 \n",
" 2161-09-14 12:36:00 NaN NaN 0.7 NaN 0 \n",
" 2161-09-29 10:58:00 0.9 NaN 0.9 0.9 0 \n",
" 2161-09-29 16:18:00 2.6 NaN 2.6 2.6 0 \n",
" 2161-09-29 16:55:00 2.1 NaN 2.1 2.1 0 \n",
"\n",
"component \\\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",
"100223 2162-04-03 23:07:00 0 0 \n",
" 2162-04-04 04:17:00 0 0 \n",
" 2162-04-05 02:27:00 0 0 \n",
" 2162-04-06 02:28:00 0 0 \n",
" 2162-04-06 10:01:00 0 0 \n",
" 2162-04-06 14:18:00 0 0 \n",
" 2162-04-07 02:51:00 0 0 \n",
" 2162-04-14 10:33:00 0 0 \n",
"100227 2160-12-07 16:15:00 0 0 \n",
" 2160-12-08 03:07:00 0 0 \n",
"100229 2114-12-24 12:27:00 0 0 \n",
" 2114-12-24 14:36:00 0 0 \n",
" 2114-12-24 16:29:00 0 0 \n",
" 2114-12-24 16:45:00 0 0 \n",
"100234 2118-10-23 17:51:00 0 0 \n",
" 2118-11-04 00:30:00 0 0 \n",
" 2118-11-04 06:14:00 0 0 \n",
" 2118-11-04 10:57:00 0 0 \n",
" 2118-11-04 13:15:00 0 0 \n",
" 2118-11-04 14:35:00 0 0 \n",
" 2118-11-04 21:23:00 0 0 \n",
" 2118-11-05 00:53:00 0 0 \n",
" 2118-11-05 03:01:00 0 0 \n",
"100237 2165-01-11 16:25:00 0 0 \n",
"100242 2161-08-30 03:55:00 0 0 \n",
" 2161-08-30 13:48:00 0 0 \n",
" 2161-09-14 12:36:00 0 0 \n",
" 2161-09-29 10:58:00 0 0 \n",
" 2161-09-29 16:18:00 0 0 \n",
" 2161-09-29 16:55:00 0 0 \n",
"\n",
"component \\\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",
"100223 2162-04-03 23:07:00 0 0 \n",
" 2162-04-04 04:17:00 0 0 \n",
" 2162-04-05 02:27:00 0 0 \n",
" 2162-04-06 02:28:00 0 0 \n",
" 2162-04-06 10:01:00 0 0 \n",
" 2162-04-06 14:18:00 0 0 \n",
" 2162-04-07 02:51:00 0 0 \n",
" 2162-04-14 10:33:00 0 0 \n",
"100227 2160-12-07 16:15:00 0 0 \n",
" 2160-12-08 03:07:00 0 0 \n",
"100229 2114-12-24 12:27:00 0 0 \n",
" 2114-12-24 14:36:00 0 0 \n",
" 2114-12-24 16:29:00 0 0 \n",
" 2114-12-24 16:45:00 0 0 \n",
"100234 2118-10-23 17:51:00 0 0 \n",
" 2118-11-04 00:30:00 0 0 \n",
" 2118-11-04 06:14:00 0 0 \n",
" 2118-11-04 10:57:00 0 0 \n",
" 2118-11-04 13:15:00 0 0 \n",
" 2118-11-04 14:35:00 0 0 \n",
" 2118-11-04 21:23:00 0 0 \n",
" 2118-11-05 00:53:00 0 0 \n",
" 2118-11-05 03:01:00 0 0 \n",
"100237 2165-01-11 16:25:00 0 0 \n",
"100242 2161-08-30 03:55:00 0 0 \n",
" 2161-08-30 13:48:00 0 0 \n",
" 2161-09-14 12:36:00 0 0 \n",
" 2161-09-29 10:58:00 0 0 \n",
" 2161-09-29 16:18:00 0 0 \n",
" 2161-09-29 16:55:00 0 0 \n",
"\n",
"component ... \\\n",
"status ... \n",
"variable_type ... \n",
"units ... \n",
"description 1531(mmol/L)_ERROR ... 818(mmol/L)_7.9O1B \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",
"100223 2162-04-03 23:07:00 0 ... 0 \n",
" 2162-04-04 04:17:00 0 ... 0 \n",
" 2162-04-05 02:27:00 0 ... 0 \n",
" 2162-04-06 02:28:00 0 ... 0 \n",
" 2162-04-06 10:01:00 0 ... 0 \n",
" 2162-04-06 14:18:00 0 ... 0 \n",
" 2162-04-07 02:51:00 0 ... 0 \n",
" 2162-04-14 10:33:00 0 ... 0 \n",
"100227 2160-12-07 16:15:00 0 ... 0 \n",
" 2160-12-08 03:07:00 0 ... 0 \n",
"100229 2114-12-24 12:27:00 0 ... 0 \n",
" 2114-12-24 14:36:00 0 ... 0 \n",
" 2114-12-24 16:29:00 0 ... 0 \n",
" 2114-12-24 16:45:00 0 ... 0 \n",
"100234 2118-10-23 17:51:00 0 ... 0 \n",
" 2118-11-04 00:30:00 0 ... 0 \n",
" 2118-11-04 06:14:00 0 ... 0 \n",
" 2118-11-04 10:57:00 0 ... 0 \n",
" 2118-11-04 13:15:00 0 ... 0 \n",
" 2118-11-04 14:35:00 0 ... 0 \n",
" 2118-11-04 21:23:00 0 ... 0 \n",
" 2118-11-05 00:53:00 0 ... 0 \n",
" 2118-11-05 03:01:00 0 ... 0 \n",
"100237 2165-01-11 16:25:00 0 ... 0 \n",
"100242 2161-08-30 03:55:00 0 ... 0 \n",
" 2161-08-30 13:48:00 0 ... 0 \n",
" 2161-09-14 12:36:00 0 ... 0 \n",
" 2161-09-29 10:58:00 0 ... 0 \n",
" 2161-09-29 16:18:00 0 ... 0 \n",
" 2161-09-29 16:55:00 0 ... 0 \n",
"\n",
"component \\\n",
"status \n",
"variable_type \n",
"units \n",
"description 818(mmol/L)_>30 818(mmol/L)_>30.0 \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",
"100223 2162-04-03 23:07:00 0 0 \n",
" 2162-04-04 04:17:00 0 0 \n",
" 2162-04-05 02:27:00 0 0 \n",
" 2162-04-06 02:28:00 0 0 \n",
" 2162-04-06 10:01:00 0 0 \n",
" 2162-04-06 14:18:00 0 0 \n",
" 2162-04-07 02:51:00 0 0 \n",
" 2162-04-14 10:33:00 0 0 \n",
"100227 2160-12-07 16:15:00 0 0 \n",
" 2160-12-08 03:07:00 0 0 \n",
"100229 2114-12-24 12:27:00 0 0 \n",
" 2114-12-24 14:36:00 0 0 \n",
" 2114-12-24 16:29:00 0 0 \n",
" 2114-12-24 16:45:00 0 0 \n",
"100234 2118-10-23 17:51:00 0 0 \n",
" 2118-11-04 00:30:00 0 0 \n",
" 2118-11-04 06:14:00 0 0 \n",
" 2118-11-04 10:57:00 0 0 \n",
" 2118-11-04 13:15:00 0 0 \n",
" 2118-11-04 14:35:00 0 0 \n",
" 2118-11-04 21:23:00 0 0 \n",
" 2118-11-05 00:53:00 0 0 \n",
" 2118-11-05 03:01:00 0 0 \n",
"100237 2165-01-11 16:25:00 0 0 \n",
"100242 2161-08-30 03:55:00 0 0 \n",
" 2161-08-30 13:48:00 0 0 \n",
" 2161-09-14 12:36:00 0 0 \n",
" 2161-09-29 10:58:00 0 0 \n",
" 2161-09-29 16:18:00 0 0 \n",
" 2161-09-29 16:55:00 0 0 \n",
"\n",
"component \\\n",
"status \n",
"variable_type \n",
"units \n",
"description 818(mmol/L)_CLOTTED 818(mmol/L)_ERROR \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",
"100223 2162-04-03 23:07:00 0 0 \n",
" 2162-04-04 04:17:00 0 0 \n",
" 2162-04-05 02:27:00 0 0 \n",
" 2162-04-06 02:28:00 0 0 \n",
" 2162-04-06 10:01:00 0 0 \n",
" 2162-04-06 14:18:00 0 0 \n",
" 2162-04-07 02:51:00 0 0 \n",
" 2162-04-14 10:33:00 0 0 \n",
"100227 2160-12-07 16:15:00 0 0 \n",
" 2160-12-08 03:07:00 0 0 \n",
"100229 2114-12-24 12:27:00 0 0 \n",
" 2114-12-24 14:36:00 0 0 \n",
" 2114-12-24 16:29:00 0 0 \n",
" 2114-12-24 16:45:00 0 0 \n",
"100234 2118-10-23 17:51:00 0 0 \n",
" 2118-11-04 00:30:00 0 0 \n",
" 2118-11-04 06:14:00 0 0 \n",
" 2118-11-04 10:57:00 0 0 \n",
" 2118-11-04 13:15:00 0 0 \n",
" 2118-11-04 14:35:00 0 0 \n",
" 2118-11-04 21:23:00 0 0 \n",
" 2118-11-05 00:53:00 0 0 \n",
" 2118-11-05 03:01:00 0 0 \n",
"100237 2165-01-11 16:25:00 0 0 \n",
"100242 2161-08-30 03:55:00 0 0 \n",
" 2161-08-30 13:48:00 0 0 \n",
" 2161-09-14 12:36:00 0 0 \n",
" 2161-09-29 10:58:00 0 0 \n",
" 2161-09-29 16:18:00 0 0 \n",
" 2161-09-29 16:55:00 0 0 \n",
"\n",
"component \\\n",
"status \n",
"variable_type qn \n",
"units no_units \n",
"description 818(mmol/L)_VOIDED 818(mmol/L)_no data 225668 \n",
"id datetime \n",
"100001 2117-09-11 09:32:00 0 0 NaN \n",
"100003 2150-04-17 19:12:00 0 0 NaN \n",
"100006 2108-04-08 10:58:00 0 0 NaN \n",
"100007 2145-03-31 00:44:00 0 0 NaN \n",
" 2145-04-02 14:10:00 0 0 NaN \n",
"100009 2162-05-17 13:19:00 0 0 NaN \n",
" 2162-05-17 17:14:00 0 0 NaN \n",
"100010 2109-12-10 10:25:00 0 0 NaN \n",
" 2109-12-10 12:11:00 0 0 NaN \n",
" 2109-12-10 13:05:00 0 0 NaN \n",
" 2109-12-10 13:58:00 0 0 NaN \n",
"100011 2177-08-29 04:44:00 0 0 NaN \n",
" 2177-08-29 06:55:00 0 0 NaN \n",
"100012 2177-03-14 07:38:00 0 0 NaN \n",
" 2177-03-14 11:42:00 0 0 NaN \n",
" 2177-03-15 08:05:00 0 0 NaN \n",
" 2177-03-15 14:01:00 0 0 NaN \n",
" 2177-03-15 21:42:00 0 0 NaN \n",
"100016 2188-05-24 12:00:00 0 0 NaN \n",
"100017 2103-03-11 05:10:00 0 0 NaN \n",
"100018 2176-08-29 15:29:00 0 0 NaN \n",
" 2176-08-30 09:23:00 0 0 NaN \n",
" 2176-08-30 10:19:00 0 0 NaN \n",
" 2176-08-30 11:29:00 0 0 NaN \n",
" 2176-08-30 12:40:00 0 0 NaN \n",
"100020 2142-11-30 21:54:00 0 0 NaN \n",
" 2142-12-03 00:17:00 0 0 NaN \n",
"100024 2170-09-19 10:25:00 0 0 NaN \n",
" 2170-09-19 16:33:00 0 0 NaN \n",
" 2170-09-20 02:04:00 0 0 NaN \n",
"... ... ... ... \n",
"100223 2162-04-03 23:07:00 0 0 NaN \n",
" 2162-04-04 04:17:00 0 0 NaN \n",
" 2162-04-05 02:27:00 0 0 NaN \n",
" 2162-04-06 02:28:00 0 0 NaN \n",
" 2162-04-06 10:01:00 0 0 NaN \n",
" 2162-04-06 14:18:00 0 0 NaN \n",
" 2162-04-07 02:51:00 0 0 NaN \n",
" 2162-04-14 10:33:00 0 0 NaN \n",
"100227 2160-12-07 16:15:00 0 0 NaN \n",
" 2160-12-08 03:07:00 0 0 NaN \n",
"100229 2114-12-24 12:27:00 0 0 NaN \n",
" 2114-12-24 14:36:00 0 0 NaN \n",
" 2114-12-24 16:29:00 0 0 NaN \n",
" 2114-12-24 16:45:00 0 0 NaN \n",
"100234 2118-10-23 17:51:00 0 0 NaN \n",
" 2118-11-04 00:30:00 0 0 NaN \n",
" 2118-11-04 06:14:00 0 0 NaN \n",
" 2118-11-04 10:57:00 0 0 NaN \n",
" 2118-11-04 13:15:00 0 0 NaN \n",
" 2118-11-04 14:35:00 0 0 NaN \n",
" 2118-11-04 21:23:00 0 0 NaN \n",
" 2118-11-05 00:53:00 0 0 NaN \n",
" 2118-11-05 03:01:00 0 0 NaN \n",
"100237 2165-01-11 16:25:00 0 0 NaN \n",
"100242 2161-08-30 03:55:00 0 0 NaN \n",
" 2161-08-30 13:48:00 0 0 NaN \n",
" 2161-09-14 12:36:00 0 0 NaN \n",
" 2161-09-29 10:58:00 0 0 NaN \n",
" 2161-09-29 16:18:00 0 0 NaN \n",
" 2161-09-29 16:55:00 0 0 NaN \n",
"\n",
"component \n",
"status \n",
"variable_type \n",
"units \n",
"description 50813 818 \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 \n",
"100009 2162-05-17 13:19:00 NaN NaN \n",
" 2162-05-17 17:14:00 NaN NaN \n",
"100010 2109-12-10 10:25:00 NaN NaN \n",
" 2109-12-10 12:11:00 NaN NaN \n",
" 2109-12-10 13:05:00 NaN NaN \n",
" 2109-12-10 13:58:00 NaN NaN \n",
"100011 2177-08-29 04:44:00 NaN NaN \n",
" 2177-08-29 06:55:00 NaN NaN \n",
"100012 2177-03-14 07:38:00 NaN NaN \n",
" 2177-03-14 11:42:00 NaN NaN \n",
" 2177-03-15 08:05:00 NaN NaN \n",
" 2177-03-15 14:01:00 NaN NaN \n",
" 2177-03-15 21:42:00 NaN NaN \n",
"100016 2188-05-24 12:00:00 NaN NaN \n",
"100017 2103-03-11 05:10:00 NaN NaN \n",
"100018 2176-08-29 15:29:00 NaN NaN \n",
" 2176-08-30 09:23:00 NaN NaN \n",
" 2176-08-30 10:19:00 NaN NaN \n",
" 2176-08-30 11:29:00 NaN NaN \n",
" 2176-08-30 12:40:00 NaN NaN \n",
"100020 2142-11-30 21:54:00 NaN NaN \n",
" 2142-12-03 00:17:00 NaN NaN \n",
"100024 2170-09-19 10:25:00 NaN NaN \n",
" 2170-09-19 16:33:00 NaN NaN \n",
" 2170-09-20 02:04:00 NaN NaN \n",
"... ... .. \n",
"100223 2162-04-03 23:07:00 NaN NaN \n",
" 2162-04-04 04:17:00 NaN NaN \n",
" 2162-04-05 02:27:00 NaN NaN \n",
" 2162-04-06 02:28:00 NaN NaN \n",
" 2162-04-06 10:01:00 NaN NaN \n",
" 2162-04-06 14:18:00 NaN NaN \n",
" 2162-04-07 02:51:00 NaN NaN \n",
" 2162-04-14 10:33:00 NaN NaN \n",
"100227 2160-12-07 16:15:00 NaN NaN \n",
" 2160-12-08 03:07:00 NaN NaN \n",
"100229 2114-12-24 12:27:00 NaN NaN \n",
" 2114-12-24 14:36:00 NaN NaN \n",
" 2114-12-24 16:29:00 NaN NaN \n",
" 2114-12-24 16:45:00 NaN NaN \n",
"100234 2118-10-23 17:51:00 NaN NaN \n",
" 2118-11-04 00:30:00 NaN NaN \n",
" 2118-11-04 06:14:00 NaN NaN \n",
" 2118-11-04 10:57:00 NaN NaN \n",
" 2118-11-04 13:15:00 NaN NaN \n",
" 2118-11-04 14:35:00 NaN NaN \n",
" 2118-11-04 21:23:00 NaN NaN \n",
" 2118-11-05 00:53:00 NaN NaN \n",
" 2118-11-05 03:01:00 NaN NaN \n",
"100237 2165-01-11 16:25:00 NaN NaN \n",
"100242 2161-08-30 03:55:00 NaN NaN \n",
" 2161-08-30 13:48:00 NaN NaN \n",
" 2161-09-14 12:36:00 NaN NaN \n",
" 2161-09-29 10:58:00 NaN NaN \n",
" 2161-09-29 16:18:00 NaN NaN \n",
" 2161-09-29 16:55:00 NaN NaN \n",
"\n",
"[500 rows x 63 columns]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</th>\n",
" <th colspan=\"6\" halign=\"left\">heart rate</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>status</th>\n",
" <th colspan=\"3\" halign=\"left\">known</th>\n",
" <th colspan=\"3\" halign=\"left\">unknown</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>variable_type</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th colspan=\"3\" halign=\"left\">beats/min</th>\n",
" <th colspan=\"3\" halign=\"left\">no_units</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>description</th>\n",
" <th>211(BPM)</th>\n",
" <th>211(bpm)</th>\n",
" <th>220045(bpm)</th>\n",
" <th>1332</th>\n",
" <th>1341</th>\n",
" <th>1725</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 rowspan=\"30\" valign=\"top\">100001</th>\n",
" <th>2117-09-11 12:57:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>122.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>118.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>118.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>118.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>110.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>104.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>101.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>112.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>108.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-11 20:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>116.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>117.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>124.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-11 23:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>115.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 00:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>115.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>118.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 02:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>114.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 03:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>106.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>90.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 05:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>99.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 06:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>103.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 07:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>113.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>107.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 09:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>115.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 10:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>114.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 11:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>117.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>115.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 13:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>112.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 14:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>117.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 15:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>117.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 16:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>124.0</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=\"30\" valign=\"top\">100011</th>\n",
" <th>2177-08-29 22:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>103.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-29 23:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>99.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 00:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>103.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 01:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>107.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 02:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>128.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 03:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>111.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 04:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>102.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 05:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>93.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 06:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>91.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 07:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>87.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 08:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>92.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 09:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>99.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 10:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>107.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 11:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>94.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 12:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>93.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 12:28:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>89.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 13:00:00</th>\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",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 14:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>95.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 14:39:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>93.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 15:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>93.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 16:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>92.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 17:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>86.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 18:18:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>88.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 19:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>90.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 20:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>94.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 21:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>99.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 22:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>104.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-30 23:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>103.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-31 00:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>102.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2177-08-31 01:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>108.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>500 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
"component heart rate \n",
"status known unknown \n",
"variable_type qn qn \n",
"units beats/min no_units \n",
"description 211(BPM) 211(bpm) 220045(bpm) 1332 1341 1725\n",
"id datetime \n",
"100001 2117-09-11 12:57:00 NaN NaN 122.0 NaN NaN NaN\n",
" 2117-09-11 13:00:00 NaN NaN 118.0 NaN NaN NaN\n",
" 2117-09-11 13:50:00 NaN NaN 118.0 NaN NaN NaN\n",
" 2117-09-11 14:00:00 NaN NaN 118.0 NaN NaN NaN\n",
" 2117-09-11 15:00:00 NaN NaN 110.0 NaN NaN NaN\n",
" 2117-09-11 16:00:00 NaN NaN 104.0 NaN NaN NaN\n",
" 2117-09-11 17:00:00 NaN NaN 101.0 NaN NaN NaN\n",
" 2117-09-11 18:00:00 NaN NaN 112.0 NaN NaN NaN\n",
" 2117-09-11 19:00:00 NaN NaN 108.0 NaN NaN NaN\n",
" 2117-09-11 20:00:00 NaN NaN 116.0 NaN NaN NaN\n",
" 2117-09-11 21:00:00 NaN NaN 117.0 NaN NaN NaN\n",
" 2117-09-11 22:00:00 NaN NaN 124.0 NaN NaN NaN\n",
" 2117-09-11 23:00:00 NaN NaN 115.0 NaN NaN NaN\n",
" 2117-09-12 00:00:00 NaN NaN 115.0 NaN NaN NaN\n",
" 2117-09-12 01:00:00 NaN NaN 118.0 NaN NaN NaN\n",
" 2117-09-12 02:00:00 NaN NaN 114.0 NaN NaN NaN\n",
" 2117-09-12 03:00:00 NaN NaN 106.0 NaN NaN NaN\n",
" 2117-09-12 04:00:00 NaN NaN 90.0 NaN NaN NaN\n",
" 2117-09-12 05:00:00 NaN NaN 99.0 NaN NaN NaN\n",
" 2117-09-12 06:00:00 NaN NaN 103.0 NaN NaN NaN\n",
" 2117-09-12 07:00:00 NaN NaN 113.0 NaN NaN NaN\n",
" 2117-09-12 08:00:00 NaN NaN 107.0 NaN NaN NaN\n",
" 2117-09-12 09:00:00 NaN NaN 115.0 NaN NaN NaN\n",
" 2117-09-12 10:00:00 NaN NaN 114.0 NaN NaN NaN\n",
" 2117-09-12 11:00:00 NaN NaN 117.0 NaN NaN NaN\n",
" 2117-09-12 12:00:00 NaN NaN 115.0 NaN NaN NaN\n",
" 2117-09-12 13:00:00 NaN NaN 112.0 NaN NaN NaN\n",
" 2117-09-12 14:00:00 NaN NaN 117.0 NaN NaN NaN\n",
" 2117-09-12 15:00:00 NaN NaN 117.0 NaN NaN NaN\n",
" 2117-09-12 16:00:00 NaN NaN 124.0 NaN NaN NaN\n",
"... ... ... ... ... ... ...\n",
"100011 2177-08-29 22:00:00 NaN NaN 103.0 NaN NaN NaN\n",
" 2177-08-29 23:00:00 NaN NaN 99.0 NaN NaN NaN\n",
" 2177-08-30 00:00:00 NaN NaN 103.0 NaN NaN NaN\n",
" 2177-08-30 01:00:00 NaN NaN 107.0 NaN NaN NaN\n",
" 2177-08-30 02:00:00 NaN NaN 128.0 NaN NaN NaN\n",
" 2177-08-30 03:00:00 NaN NaN 111.0 NaN NaN NaN\n",
" 2177-08-30 04:00:00 NaN NaN 102.0 NaN NaN NaN\n",
" 2177-08-30 05:00:00 NaN NaN 93.0 NaN NaN NaN\n",
" 2177-08-30 06:00:00 NaN NaN 91.0 NaN NaN NaN\n",
" 2177-08-30 07:00:00 NaN NaN 87.0 NaN NaN NaN\n",
" 2177-08-30 08:00:00 NaN NaN 92.0 NaN NaN NaN\n",
" 2177-08-30 09:00:00 NaN NaN 99.0 NaN NaN NaN\n",
" 2177-08-30 10:00:00 NaN NaN 107.0 NaN NaN NaN\n",
" 2177-08-30 11:00:00 NaN NaN 94.0 NaN NaN NaN\n",
" 2177-08-30 12:00:00 NaN NaN 93.0 NaN NaN NaN\n",
" 2177-08-30 12:28:00 NaN NaN 89.0 NaN NaN NaN\n",
" 2177-08-30 13:00:00 NaN NaN 100.0 NaN NaN NaN\n",
" 2177-08-30 14:00:00 NaN NaN 95.0 NaN NaN NaN\n",
" 2177-08-30 14:39:00 NaN NaN 93.0 NaN NaN NaN\n",
" 2177-08-30 15:00:00 NaN NaN 93.0 NaN NaN NaN\n",
" 2177-08-30 16:00:00 NaN NaN 92.0 NaN NaN NaN\n",
" 2177-08-30 17:00:00 NaN NaN 86.0 NaN NaN NaN\n",
" 2177-08-30 18:18:00 NaN NaN 88.0 NaN NaN NaN\n",
" 2177-08-30 19:00:00 NaN NaN 90.0 NaN NaN NaN\n",
" 2177-08-30 20:00:00 NaN NaN 94.0 NaN NaN NaN\n",
" 2177-08-30 21:00:00 NaN NaN 99.0 NaN NaN NaN\n",
" 2177-08-30 22:00:00 NaN NaN 104.0 NaN NaN NaN\n",
" 2177-08-30 23:00:00 NaN NaN 103.0 NaN NaN NaN\n",
" 2177-08-31 00:00:00 NaN NaN 102.0 NaN NaN NaN\n",
" 2177-08-31 01:00:00 NaN NaN 108.0 NaN NaN NaN\n",
"\n",
"[500 rows x 6 columns]"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"small_lactate = df_lactate.head(500)\n",
"display(small_lactate)\n",
"small_heart_rate = df_heart_rate.head(500)\n",
"display(small_heart_rate)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"resampled_lactate = df_lactate.groupby(level='id').resample(rule='2H',level='datetime').mean()"
]
},
{
"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>component</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 colspan=\"14\" halign=\"left\">nom</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th colspan=\"4\" halign=\"left\">mmol/L</th>\n",
" <th colspan=\"14\" halign=\"left\">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>1531</th>\n",
" <th>225668</th>\n",
" <th>50813</th>\n",
" <th>818</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>...</th>\n",
" <th>818(mmol/L)_7.9O1B</th>\n",
" <th>818(mmol/L)_>30</th>\n",
" <th>818(mmol/L)_>30.0</th>\n",
" <th>818(mmol/L)_CLOTTED</th>\n",
" <th>818(mmol/L)_ERROR</th>\n",
" <th>818(mmol/L)_VOIDED</th>\n",
" <th>818(mmol/L)_no data</th>\n",
" <th>225668</th>\n",
" <th>50813</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",
" <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 08:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.900000</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</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 18:00:00</th>\n",
" <td>NaN</td>\n",
" <td>1.100000</td>\n",
" <td>1.100000</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</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 10:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>4.500000</td>\n",
" <td>4.500000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"27\" valign=\"top\">100007</th>\n",
" <th>2145-03-31 00:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>3.100000</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2145-03-31 02:00:00</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>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>2145-03-31 04:00:00</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>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>2145-03-31 06:00:00</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>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>2145-03-31 08:00:00</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>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>2145-03-31 10:00:00</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>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>2145-03-31 12:00:00</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>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>2145-03-31 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>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>2145-03-31 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>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>2145-03-31 18:00:00</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>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>2145-03-31 20:00:00</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>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>2145-03-31 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>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>2145-04-01 00:00:00</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>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>2145-04-01 02:00:00</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>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>2145-04-01 04:00:00</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>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>2145-04-01 06:00:00</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>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>2145-04-01 08:00:00</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>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>2145-04-01 10:00:00</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>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>2145-04-01 12:00:00</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>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>2145-04-01 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>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>2145-04-01 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>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>2145-04-01 18:00:00</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>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>2145-04-01 20:00:00</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>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>2145-04-01 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>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>2145-04-02 00:00:00</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>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>2145-04-02 02:00:00</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>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>2145-04-02 04:00:00</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>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>...</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=\"2\" valign=\"top\">199994</th>\n",
" <th>2188-07-08 04:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.600000</td>\n",
" <td>0.600000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2188-07-08 06:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.700000</td>\n",
" <td>0.700000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"6\" valign=\"top\">199998</th>\n",
" <th>2119-02-20 10:00:00</th>\n",
" <td>1.100000</td>\n",
" <td>1.100000</td>\n",
" <td>1.100000</td>\n",
" <td>1.100000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2119-02-20 12:00:00</th>\n",
" <td>2.166667</td>\n",
" <td>2.166667</td>\n",
" <td>2.166667</td>\n",
" <td>2.166667</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2119-02-20 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>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>2119-02-20 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>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>2119-02-20 18:00:00</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>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>2119-02-20 20:00:00</th>\n",
" <td>1.300000</td>\n",
" <td>1.300000</td>\n",
" <td>1.300000</td>\n",
" <td>1.300000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th rowspan=\"22\" valign=\"top\">199999</th>\n",
" <th>2136-04-04 20:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.900000</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2136-04-04 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>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>2136-04-05 00:00:00</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>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>2136-04-05 02:00:00</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>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>2136-04-05 04:00:00</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>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>2136-04-05 06:00:00</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>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>2136-04-05 08:00:00</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>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>2136-04-05 10:00:00</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>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>2136-04-05 12:00:00</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>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>2136-04-05 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>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>2136-04-05 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>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>2136-04-05 18:00:00</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>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>2136-04-05 20:00:00</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>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>2136-04-05 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>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>2136-04-06 00:00:00</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>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>2136-04-06 02:00:00</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>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>2136-04-06 04:00:00</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>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>2136-04-06 06:00:00</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>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>2136-04-06 08:00:00</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>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>2136-04-06 10:00:00</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>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>2136-04-06 12:00:00</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>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>2136-04-06 14:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.800000</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>1427082 rows × 63 columns</p>\n",
"</div>"
],
"text/plain": [
"component lactate \\\n",
"status known \n",
"variable_type qn \n",
"units mmol/L \n",
"description 1531 225668 50813 818 \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 NaN NaN 1.900000 NaN \n",
"100003 2150-04-17 18:00:00 NaN 1.100000 1.100000 NaN \n",
"100006 2108-04-08 10:00:00 NaN NaN 4.500000 4.500000 \n",
"100007 2145-03-31 00:00:00 NaN NaN 3.100000 NaN \n",
" 2145-03-31 02:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 04:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 06:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 08:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 10:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 12:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 14:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 16:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 18:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 20:00:00 NaN NaN NaN NaN \n",
" 2145-03-31 22:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 00:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 02:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 04:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 06:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 08:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 10:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 12:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 14:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 16:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 18:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 20:00:00 NaN NaN NaN NaN \n",
" 2145-04-01 22:00:00 NaN NaN NaN NaN \n",
" 2145-04-02 00:00:00 NaN NaN NaN NaN \n",
" 2145-04-02 02:00:00 NaN NaN NaN NaN \n",
" 2145-04-02 04:00:00 NaN NaN NaN NaN \n",
"... ... ... ... ... \n",
"199994 2188-07-08 04:00:00 NaN NaN 0.600000 0.600000 \n",
" 2188-07-08 06:00:00 NaN NaN 0.700000 0.700000 \n",
"199998 2119-02-20 10:00:00 1.100000 1.100000 1.100000 1.100000 \n",
" 2119-02-20 12:00:00 2.166667 2.166667 2.166667 2.166667 \n",
" 2119-02-20 14:00:00 NaN NaN NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN NaN NaN \n",
" 2119-02-20 20:00:00 1.300000 1.300000 1.300000 1.300000 \n",
"199999 2136-04-04 20:00:00 NaN NaN 1.900000 NaN \n",
" 2136-04-04 22:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 14:00:00 NaN NaN 1.800000 NaN \n",
"\n",
"component \\\n",
"status unknown \n",
"variable_type nom \n",
"units no_units \n",
"description 1531(mmol/L)_. 1531(mmol/L)_5,0 1531(mmol/L)_>30 \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 0.0 0.0 0.0 \n",
"100003 2150-04-17 18:00:00 0.0 0.0 0.0 \n",
"100006 2108-04-08 10:00:00 0.0 0.0 0.0 \n",
"100007 2145-03-31 00:00:00 0.0 0.0 0.0 \n",
" 2145-03-31 02:00:00 NaN NaN NaN \n",
" 2145-03-31 04:00:00 NaN NaN NaN \n",
" 2145-03-31 06:00:00 NaN NaN NaN \n",
" 2145-03-31 08:00:00 NaN NaN NaN \n",
" 2145-03-31 10:00:00 NaN NaN NaN \n",
" 2145-03-31 12:00:00 NaN NaN NaN \n",
" 2145-03-31 14:00:00 NaN NaN NaN \n",
" 2145-03-31 16:00:00 NaN NaN NaN \n",
" 2145-03-31 18:00:00 NaN NaN NaN \n",
" 2145-03-31 20:00:00 NaN NaN NaN \n",
" 2145-03-31 22:00:00 NaN NaN NaN \n",
" 2145-04-01 00:00:00 NaN NaN NaN \n",
" 2145-04-01 02:00:00 NaN NaN NaN \n",
" 2145-04-01 04:00:00 NaN NaN NaN \n",
" 2145-04-01 06:00:00 NaN NaN NaN \n",
" 2145-04-01 08:00:00 NaN NaN NaN \n",
" 2145-04-01 10:00:00 NaN NaN NaN \n",
" 2145-04-01 12:00:00 NaN NaN NaN \n",
" 2145-04-01 14:00:00 NaN NaN NaN \n",
" 2145-04-01 16:00:00 NaN NaN NaN \n",
" 2145-04-01 18:00:00 NaN NaN NaN \n",
" 2145-04-01 20:00:00 NaN NaN NaN \n",
" 2145-04-01 22:00:00 NaN NaN NaN \n",
" 2145-04-02 00:00:00 NaN NaN NaN \n",
" 2145-04-02 02:00:00 NaN NaN NaN \n",
" 2145-04-02 04:00:00 NaN NaN NaN \n",
"... ... ... ... \n",
"199994 2188-07-08 04:00:00 0.0 0.0 0.0 \n",
" 2188-07-08 06:00:00 0.0 0.0 0.0 \n",
"199998 2119-02-20 10:00:00 0.0 0.0 0.0 \n",
" 2119-02-20 12:00:00 0.0 0.0 0.0 \n",
" 2119-02-20 14:00:00 NaN NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN NaN \n",
" 2119-02-20 20:00:00 0.0 0.0 0.0 \n",
"199999 2136-04-04 20:00:00 0.0 0.0 0.0 \n",
" 2136-04-04 22:00:00 NaN NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN NaN \n",
" 2136-04-06 14:00:00 0.0 0.0 0.0 \n",
"\n",
"component \\\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 08:00:00 0.0 0.0 \n",
"100003 2150-04-17 18:00:00 0.0 0.0 \n",
"100006 2108-04-08 10:00:00 0.0 0.0 \n",
"100007 2145-03-31 00:00:00 0.0 0.0 \n",
" 2145-03-31 02:00:00 NaN NaN \n",
" 2145-03-31 04:00:00 NaN NaN \n",
" 2145-03-31 06:00:00 NaN NaN \n",
" 2145-03-31 08:00:00 NaN NaN \n",
" 2145-03-31 10:00:00 NaN NaN \n",
" 2145-03-31 12:00:00 NaN NaN \n",
" 2145-03-31 14:00:00 NaN NaN \n",
" 2145-03-31 16:00:00 NaN NaN \n",
" 2145-03-31 18:00:00 NaN NaN \n",
" 2145-03-31 20:00:00 NaN NaN \n",
" 2145-03-31 22:00:00 NaN NaN \n",
" 2145-04-01 00:00:00 NaN NaN \n",
" 2145-04-01 02:00:00 NaN NaN \n",
" 2145-04-01 04:00:00 NaN NaN \n",
" 2145-04-01 06:00:00 NaN NaN \n",
" 2145-04-01 08:00:00 NaN NaN \n",
" 2145-04-01 10:00:00 NaN NaN \n",
" 2145-04-01 12:00:00 NaN NaN \n",
" 2145-04-01 14:00:00 NaN NaN \n",
" 2145-04-01 16:00:00 NaN NaN \n",
" 2145-04-01 18:00:00 NaN NaN \n",
" 2145-04-01 20:00:00 NaN NaN \n",
" 2145-04-01 22:00:00 NaN NaN \n",
" 2145-04-02 00:00:00 NaN NaN \n",
" 2145-04-02 02:00:00 NaN NaN \n",
" 2145-04-02 04:00:00 NaN NaN \n",
"... ... ... \n",
"199994 2188-07-08 04:00:00 0.0 0.0 \n",
" 2188-07-08 06:00:00 0.0 0.0 \n",
"199998 2119-02-20 10:00:00 0.0 0.0 \n",
" 2119-02-20 12:00:00 0.0 0.0 \n",
" 2119-02-20 14:00:00 NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN \n",
" 2119-02-20 20:00:00 0.0 0.0 \n",
"199999 2136-04-04 20:00:00 0.0 0.0 \n",
" 2136-04-04 22:00:00 NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN \n",
" 2136-04-06 14:00:00 0.0 0.0 \n",
"\n",
"component ... \\\n",
"status ... \n",
"variable_type ... \n",
"units ... \n",
"description 1531(mmol/L)_ERROR ... 818(mmol/L)_7.9O1B \n",
"id datetime ... \n",
"100001 2117-09-11 08:00:00 0.0 ... 0.0 \n",
"100003 2150-04-17 18:00:00 0.0 ... 0.0 \n",
"100006 2108-04-08 10:00:00 0.0 ... 0.0 \n",
"100007 2145-03-31 00:00:00 0.0 ... 0.0 \n",
" 2145-03-31 02:00:00 NaN ... NaN \n",
" 2145-03-31 04:00:00 NaN ... NaN \n",
" 2145-03-31 06:00:00 NaN ... NaN \n",
" 2145-03-31 08:00:00 NaN ... NaN \n",
" 2145-03-31 10:00:00 NaN ... NaN \n",
" 2145-03-31 12:00:00 NaN ... NaN \n",
" 2145-03-31 14:00:00 NaN ... NaN \n",
" 2145-03-31 16:00:00 NaN ... NaN \n",
" 2145-03-31 18:00:00 NaN ... NaN \n",
" 2145-03-31 20:00:00 NaN ... NaN \n",
" 2145-03-31 22:00:00 NaN ... NaN \n",
" 2145-04-01 00:00:00 NaN ... NaN \n",
" 2145-04-01 02:00:00 NaN ... NaN \n",
" 2145-04-01 04:00:00 NaN ... NaN \n",
" 2145-04-01 06:00:00 NaN ... NaN \n",
" 2145-04-01 08:00:00 NaN ... NaN \n",
" 2145-04-01 10:00:00 NaN ... NaN \n",
" 2145-04-01 12:00:00 NaN ... NaN \n",
" 2145-04-01 14:00:00 NaN ... NaN \n",
" 2145-04-01 16:00:00 NaN ... NaN \n",
" 2145-04-01 18:00:00 NaN ... NaN \n",
" 2145-04-01 20:00:00 NaN ... NaN \n",
" 2145-04-01 22:00:00 NaN ... NaN \n",
" 2145-04-02 00:00:00 NaN ... NaN \n",
" 2145-04-02 02:00:00 NaN ... NaN \n",
" 2145-04-02 04:00:00 NaN ... NaN \n",
"... ... ... ... \n",
"199994 2188-07-08 04:00:00 0.0 ... 0.0 \n",
" 2188-07-08 06:00:00 0.0 ... 0.0 \n",
"199998 2119-02-20 10:00:00 0.0 ... 0.0 \n",
" 2119-02-20 12:00:00 0.0 ... 0.0 \n",
" 2119-02-20 14:00:00 NaN ... NaN \n",
" 2119-02-20 16:00:00 NaN ... NaN \n",
" 2119-02-20 18:00:00 NaN ... NaN \n",
" 2119-02-20 20:00:00 0.0 ... 0.0 \n",
"199999 2136-04-04 20:00:00 0.0 ... 0.0 \n",
" 2136-04-04 22:00:00 NaN ... NaN \n",
" 2136-04-05 00:00:00 NaN ... NaN \n",
" 2136-04-05 02:00:00 NaN ... NaN \n",
" 2136-04-05 04:00:00 NaN ... NaN \n",
" 2136-04-05 06:00:00 NaN ... NaN \n",
" 2136-04-05 08:00:00 NaN ... NaN \n",
" 2136-04-05 10:00:00 NaN ... NaN \n",
" 2136-04-05 12:00:00 NaN ... NaN \n",
" 2136-04-05 14:00:00 NaN ... NaN \n",
" 2136-04-05 16:00:00 NaN ... NaN \n",
" 2136-04-05 18:00:00 NaN ... NaN \n",
" 2136-04-05 20:00:00 NaN ... NaN \n",
" 2136-04-05 22:00:00 NaN ... NaN \n",
" 2136-04-06 00:00:00 NaN ... NaN \n",
" 2136-04-06 02:00:00 NaN ... NaN \n",
" 2136-04-06 04:00:00 NaN ... NaN \n",
" 2136-04-06 06:00:00 NaN ... NaN \n",
" 2136-04-06 08:00:00 NaN ... NaN \n",
" 2136-04-06 10:00:00 NaN ... NaN \n",
" 2136-04-06 12:00:00 NaN ... NaN \n",
" 2136-04-06 14:00:00 0.0 ... 0.0 \n",
"\n",
"component \\\n",
"status \n",
"variable_type \n",
"units \n",
"description 818(mmol/L)_>30 818(mmol/L)_>30.0 \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 0.0 0.0 \n",
"100003 2150-04-17 18:00:00 0.0 0.0 \n",
"100006 2108-04-08 10:00:00 0.0 0.0 \n",
"100007 2145-03-31 00:00:00 0.0 0.0 \n",
" 2145-03-31 02:00:00 NaN NaN \n",
" 2145-03-31 04:00:00 NaN NaN \n",
" 2145-03-31 06:00:00 NaN NaN \n",
" 2145-03-31 08:00:00 NaN NaN \n",
" 2145-03-31 10:00:00 NaN NaN \n",
" 2145-03-31 12:00:00 NaN NaN \n",
" 2145-03-31 14:00:00 NaN NaN \n",
" 2145-03-31 16:00:00 NaN NaN \n",
" 2145-03-31 18:00:00 NaN NaN \n",
" 2145-03-31 20:00:00 NaN NaN \n",
" 2145-03-31 22:00:00 NaN NaN \n",
" 2145-04-01 00:00:00 NaN NaN \n",
" 2145-04-01 02:00:00 NaN NaN \n",
" 2145-04-01 04:00:00 NaN NaN \n",
" 2145-04-01 06:00:00 NaN NaN \n",
" 2145-04-01 08:00:00 NaN NaN \n",
" 2145-04-01 10:00:00 NaN NaN \n",
" 2145-04-01 12:00:00 NaN NaN \n",
" 2145-04-01 14:00:00 NaN NaN \n",
" 2145-04-01 16:00:00 NaN NaN \n",
" 2145-04-01 18:00:00 NaN NaN \n",
" 2145-04-01 20:00:00 NaN NaN \n",
" 2145-04-01 22:00:00 NaN NaN \n",
" 2145-04-02 00:00:00 NaN NaN \n",
" 2145-04-02 02:00:00 NaN NaN \n",
" 2145-04-02 04:00:00 NaN NaN \n",
"... ... ... \n",
"199994 2188-07-08 04:00:00 0.0 0.0 \n",
" 2188-07-08 06:00:00 0.0 0.0 \n",
"199998 2119-02-20 10:00:00 0.0 0.0 \n",
" 2119-02-20 12:00:00 0.0 0.0 \n",
" 2119-02-20 14:00:00 NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN \n",
" 2119-02-20 20:00:00 0.0 0.0 \n",
"199999 2136-04-04 20:00:00 0.0 0.0 \n",
" 2136-04-04 22:00:00 NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN \n",
" 2136-04-06 14:00:00 0.0 0.0 \n",
"\n",
"component \\\n",
"status \n",
"variable_type \n",
"units \n",
"description 818(mmol/L)_CLOTTED 818(mmol/L)_ERROR \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 0.0 0.0 \n",
"100003 2150-04-17 18:00:00 0.0 0.0 \n",
"100006 2108-04-08 10:00:00 0.0 0.0 \n",
"100007 2145-03-31 00:00:00 0.0 0.0 \n",
" 2145-03-31 02:00:00 NaN NaN \n",
" 2145-03-31 04:00:00 NaN NaN \n",
" 2145-03-31 06:00:00 NaN NaN \n",
" 2145-03-31 08:00:00 NaN NaN \n",
" 2145-03-31 10:00:00 NaN NaN \n",
" 2145-03-31 12:00:00 NaN NaN \n",
" 2145-03-31 14:00:00 NaN NaN \n",
" 2145-03-31 16:00:00 NaN NaN \n",
" 2145-03-31 18:00:00 NaN NaN \n",
" 2145-03-31 20:00:00 NaN NaN \n",
" 2145-03-31 22:00:00 NaN NaN \n",
" 2145-04-01 00:00:00 NaN NaN \n",
" 2145-04-01 02:00:00 NaN NaN \n",
" 2145-04-01 04:00:00 NaN NaN \n",
" 2145-04-01 06:00:00 NaN NaN \n",
" 2145-04-01 08:00:00 NaN NaN \n",
" 2145-04-01 10:00:00 NaN NaN \n",
" 2145-04-01 12:00:00 NaN NaN \n",
" 2145-04-01 14:00:00 NaN NaN \n",
" 2145-04-01 16:00:00 NaN NaN \n",
" 2145-04-01 18:00:00 NaN NaN \n",
" 2145-04-01 20:00:00 NaN NaN \n",
" 2145-04-01 22:00:00 NaN NaN \n",
" 2145-04-02 00:00:00 NaN NaN \n",
" 2145-04-02 02:00:00 NaN NaN \n",
" 2145-04-02 04:00:00 NaN NaN \n",
"... ... ... \n",
"199994 2188-07-08 04:00:00 0.0 0.0 \n",
" 2188-07-08 06:00:00 0.0 0.0 \n",
"199998 2119-02-20 10:00:00 0.0 0.0 \n",
" 2119-02-20 12:00:00 0.0 0.0 \n",
" 2119-02-20 14:00:00 NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN \n",
" 2119-02-20 20:00:00 0.0 0.0 \n",
"199999 2136-04-04 20:00:00 0.0 0.0 \n",
" 2136-04-04 22:00:00 NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN \n",
" 2136-04-06 14:00:00 0.0 0.0 \n",
"\n",
"component \\\n",
"status \n",
"variable_type qn \n",
"units no_units \n",
"description 818(mmol/L)_VOIDED 818(mmol/L)_no data 225668 \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 0.0 0.0 NaN \n",
"100003 2150-04-17 18:00:00 0.0 0.0 NaN \n",
"100006 2108-04-08 10:00:00 0.0 0.0 NaN \n",
"100007 2145-03-31 00:00:00 0.0 0.0 NaN \n",
" 2145-03-31 02:00:00 NaN NaN NaN \n",
" 2145-03-31 04:00:00 NaN NaN NaN \n",
" 2145-03-31 06:00:00 NaN NaN NaN \n",
" 2145-03-31 08:00:00 NaN NaN NaN \n",
" 2145-03-31 10:00:00 NaN NaN NaN \n",
" 2145-03-31 12:00:00 NaN NaN NaN \n",
" 2145-03-31 14:00:00 NaN NaN NaN \n",
" 2145-03-31 16:00:00 NaN NaN NaN \n",
" 2145-03-31 18:00:00 NaN NaN NaN \n",
" 2145-03-31 20:00:00 NaN NaN NaN \n",
" 2145-03-31 22:00:00 NaN NaN NaN \n",
" 2145-04-01 00:00:00 NaN NaN NaN \n",
" 2145-04-01 02:00:00 NaN NaN NaN \n",
" 2145-04-01 04:00:00 NaN NaN NaN \n",
" 2145-04-01 06:00:00 NaN NaN NaN \n",
" 2145-04-01 08:00:00 NaN NaN NaN \n",
" 2145-04-01 10:00:00 NaN NaN NaN \n",
" 2145-04-01 12:00:00 NaN NaN NaN \n",
" 2145-04-01 14:00:00 NaN NaN NaN \n",
" 2145-04-01 16:00:00 NaN NaN NaN \n",
" 2145-04-01 18:00:00 NaN NaN NaN \n",
" 2145-04-01 20:00:00 NaN NaN NaN \n",
" 2145-04-01 22:00:00 NaN NaN NaN \n",
" 2145-04-02 00:00:00 NaN NaN NaN \n",
" 2145-04-02 02:00:00 NaN NaN NaN \n",
" 2145-04-02 04:00:00 NaN NaN NaN \n",
"... ... ... ... \n",
"199994 2188-07-08 04:00:00 0.0 0.0 NaN \n",
" 2188-07-08 06:00:00 0.0 0.0 NaN \n",
"199998 2119-02-20 10:00:00 0.0 0.0 NaN \n",
" 2119-02-20 12:00:00 0.0 0.0 NaN \n",
" 2119-02-20 14:00:00 NaN NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN NaN \n",
" 2119-02-20 20:00:00 0.0 0.0 NaN \n",
"199999 2136-04-04 20:00:00 0.0 0.0 NaN \n",
" 2136-04-04 22:00:00 NaN NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN NaN \n",
" 2136-04-06 14:00:00 0.0 0.0 NaN \n",
"\n",
"component \n",
"status \n",
"variable_type \n",
"units \n",
"description 50813 818 \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 NaN NaN \n",
"100003 2150-04-17 18:00:00 NaN NaN \n",
"100006 2108-04-08 10:00:00 NaN NaN \n",
"100007 2145-03-31 00:00:00 NaN NaN \n",
" 2145-03-31 02:00:00 NaN NaN \n",
" 2145-03-31 04:00:00 NaN NaN \n",
" 2145-03-31 06:00:00 NaN NaN \n",
" 2145-03-31 08:00:00 NaN NaN \n",
" 2145-03-31 10:00:00 NaN NaN \n",
" 2145-03-31 12:00:00 NaN NaN \n",
" 2145-03-31 14:00:00 NaN NaN \n",
" 2145-03-31 16:00:00 NaN NaN \n",
" 2145-03-31 18:00:00 NaN NaN \n",
" 2145-03-31 20:00:00 NaN NaN \n",
" 2145-03-31 22:00:00 NaN NaN \n",
" 2145-04-01 00:00:00 NaN NaN \n",
" 2145-04-01 02:00:00 NaN NaN \n",
" 2145-04-01 04:00:00 NaN NaN \n",
" 2145-04-01 06:00:00 NaN NaN \n",
" 2145-04-01 08:00:00 NaN NaN \n",
" 2145-04-01 10:00:00 NaN NaN \n",
" 2145-04-01 12:00:00 NaN NaN \n",
" 2145-04-01 14:00:00 NaN NaN \n",
" 2145-04-01 16:00:00 NaN NaN \n",
" 2145-04-01 18:00:00 NaN NaN \n",
" 2145-04-01 20:00:00 NaN NaN \n",
" 2145-04-01 22:00:00 NaN NaN \n",
" 2145-04-02 00:00:00 NaN NaN \n",
" 2145-04-02 02:00:00 NaN NaN \n",
" 2145-04-02 04:00:00 NaN NaN \n",
"... ... .. \n",
"199994 2188-07-08 04:00:00 NaN NaN \n",
" 2188-07-08 06:00:00 NaN NaN \n",
"199998 2119-02-20 10:00:00 NaN NaN \n",
" 2119-02-20 12:00:00 NaN NaN \n",
" 2119-02-20 14:00:00 NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN \n",
" 2119-02-20 20:00:00 NaN NaN \n",
"199999 2136-04-04 20:00:00 NaN NaN \n",
" 2136-04-04 22:00:00 NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN \n",
" 2136-04-06 14:00:00 NaN NaN \n",
"\n",
"[1427082 rows x 63 columns]"
]
},
"execution_count": 17,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"resampled_lactate"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"resampled_heart_rate = df_heart_rate.head(200).groupby(level='id').resample(rule='2H',level='datetime').mean()"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"collapsed": false
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</th>\n",
" <th colspan=\"15\" halign=\"left\">lactate</th>\n",
" <th colspan=\"6\" halign=\"left\">heart rate</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>status</th>\n",
" <th colspan=\"4\" halign=\"left\">known</th>\n",
" <th colspan=\"11\" halign=\"left\">unknown</th>\n",
" <th colspan=\"3\" halign=\"left\">known</th>\n",
" <th colspan=\"3\" 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 colspan=\"8\" halign=\"left\">nom</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th colspan=\"4\" halign=\"left\">mmol/L</th>\n",
" <th colspan=\"8\" halign=\"left\">no_units</th>\n",
" <th colspan=\"3\" halign=\"left\">no_units</th>\n",
" <th colspan=\"3\" halign=\"left\">beats/min</th>\n",
" <th colspan=\"3\" halign=\"left\">no_units</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>description</th>\n",
" <th>1531</th>\n",
" <th>225668</th>\n",
" <th>50813</th>\n",
" <th>818</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>...</th>\n",
" <th>818(mmol/L)_no data</th>\n",
" <th>225668</th>\n",
" <th>50813</th>\n",
" <th>818</th>\n",
" <th>211(BPM)</th>\n",
" <th>211(bpm)</th>\n",
" <th>220045(bpm)</th>\n",
" <th>1332</th>\n",
" <th>1341</th>\n",
" <th>1725</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 08:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.900000</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</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>2117-09-11 12:00:00</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>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>119.333333</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>114.000000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>102.500000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>110.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-11 20:00:00</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>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>116.500000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>119.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 00:00:00</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>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>116.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 02:00:00</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>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>110.000000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>94.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 06:00:00</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>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>108.000000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>111.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 10:00:00</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>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>115.500000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>113.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 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>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>117.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 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>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>124.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 18:00:00</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>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>124.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 20:00:00</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>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>127.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-12 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>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>128.500000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>128.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-13 02:00:00</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>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>127.500000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>124.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-13 06:00:00</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>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>120.500000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>118.250000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-13 10:00:00</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>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>114.500000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>102.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-13 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>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>109.000000</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>93.500000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-13 18:00:00</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>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>93.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2117-09-13 20:00:00</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>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>100.000000</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=\"2\" valign=\"top\">199994</th>\n",
" <th>2188-07-08 04:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.600000</td>\n",
" <td>0.600000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</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>2188-07-08 06:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>0.700000</td>\n",
" <td>0.700000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</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 rowspan=\"6\" valign=\"top\">199998</th>\n",
" <th>2119-02-20 10:00:00</th>\n",
" <td>1.100000</td>\n",
" <td>1.100000</td>\n",
" <td>1.100000</td>\n",
" <td>1.100000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</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>2119-02-20 12:00:00</th>\n",
" <td>2.166667</td>\n",
" <td>2.166667</td>\n",
" <td>2.166667</td>\n",
" <td>2.166667</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</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>2119-02-20 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>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>2119-02-20 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>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>2119-02-20 18:00:00</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>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>2119-02-20 20:00:00</th>\n",
" <td>1.300000</td>\n",
" <td>1.300000</td>\n",
" <td>1.300000</td>\n",
" <td>1.300000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</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 rowspan=\"22\" valign=\"top\">199999</th>\n",
" <th>2136-04-04 20:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.900000</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</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>2136-04-04 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>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>2136-04-05 00:00:00</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>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>2136-04-05 02:00:00</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>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>2136-04-05 04:00:00</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>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>2136-04-05 06:00:00</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>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>2136-04-05 08:00:00</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>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>2136-04-05 10:00:00</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>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>2136-04-05 12:00:00</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>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>2136-04-05 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>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>2136-04-05 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>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>2136-04-05 18:00:00</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>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>2136-04-05 20:00:00</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>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>2136-04-05 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>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>2136-04-06 00:00:00</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>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>2136-04-06 02:00:00</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>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>2136-04-06 04:00:00</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>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>2136-04-06 06:00:00</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>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>2136-04-06 08:00:00</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>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>2136-04-06 10:00:00</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>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>2136-04-06 12:00:00</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>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>2136-04-06 14:00:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.800000</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</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",
" </tbody>\n",
"</table>\n",
"<p>1427183 rows × 69 columns</p>\n",
"</div>"
],
"text/plain": [
"component lactate \\\n",
"status known \n",
"variable_type qn \n",
"units mmol/L \n",
"description 1531 225668 50813 818 \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 NaN NaN 1.900000 NaN \n",
" 2117-09-11 12:00:00 NaN NaN NaN NaN \n",
" 2117-09-11 14:00:00 NaN NaN NaN NaN \n",
" 2117-09-11 16:00:00 NaN NaN NaN NaN \n",
" 2117-09-11 18:00:00 NaN NaN NaN NaN \n",
" 2117-09-11 20:00:00 NaN NaN NaN NaN \n",
" 2117-09-11 22:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 00:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 02:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 04:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 06:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 08:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 10:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 12:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 14:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 16:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 18:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 20:00:00 NaN NaN NaN NaN \n",
" 2117-09-12 22:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 00:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 02:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 04:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 06:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 08:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 10:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 12:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 14:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 16:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 18:00:00 NaN NaN NaN NaN \n",
" 2117-09-13 20:00:00 NaN NaN NaN NaN \n",
"... ... ... ... ... \n",
"199994 2188-07-08 04:00:00 NaN NaN 0.600000 0.600000 \n",
" 2188-07-08 06:00:00 NaN NaN 0.700000 0.700000 \n",
"199998 2119-02-20 10:00:00 1.100000 1.100000 1.100000 1.100000 \n",
" 2119-02-20 12:00:00 2.166667 2.166667 2.166667 2.166667 \n",
" 2119-02-20 14:00:00 NaN NaN NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN NaN NaN \n",
" 2119-02-20 20:00:00 1.300000 1.300000 1.300000 1.300000 \n",
"199999 2136-04-04 20:00:00 NaN NaN 1.900000 NaN \n",
" 2136-04-04 22:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN NaN NaN \n",
" 2136-04-06 14:00:00 NaN NaN 1.800000 NaN \n",
"\n",
"component \\\n",
"status unknown \n",
"variable_type nom \n",
"units no_units \n",
"description 1531(mmol/L)_. 1531(mmol/L)_5,0 1531(mmol/L)_>30 \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 0.0 0.0 0.0 \n",
" 2117-09-11 12:00:00 NaN NaN NaN \n",
" 2117-09-11 14:00:00 NaN NaN NaN \n",
" 2117-09-11 16:00:00 NaN NaN NaN \n",
" 2117-09-11 18:00:00 NaN NaN NaN \n",
" 2117-09-11 20:00:00 NaN NaN NaN \n",
" 2117-09-11 22:00:00 NaN NaN NaN \n",
" 2117-09-12 00:00:00 NaN NaN NaN \n",
" 2117-09-12 02:00:00 NaN NaN NaN \n",
" 2117-09-12 04:00:00 NaN NaN NaN \n",
" 2117-09-12 06:00:00 NaN NaN NaN \n",
" 2117-09-12 08:00:00 NaN NaN NaN \n",
" 2117-09-12 10:00:00 NaN NaN NaN \n",
" 2117-09-12 12:00:00 NaN NaN NaN \n",
" 2117-09-12 14:00:00 NaN NaN NaN \n",
" 2117-09-12 16:00:00 NaN NaN NaN \n",
" 2117-09-12 18:00:00 NaN NaN NaN \n",
" 2117-09-12 20:00:00 NaN NaN NaN \n",
" 2117-09-12 22:00:00 NaN NaN NaN \n",
" 2117-09-13 00:00:00 NaN NaN NaN \n",
" 2117-09-13 02:00:00 NaN NaN NaN \n",
" 2117-09-13 04:00:00 NaN NaN NaN \n",
" 2117-09-13 06:00:00 NaN NaN NaN \n",
" 2117-09-13 08:00:00 NaN NaN NaN \n",
" 2117-09-13 10:00:00 NaN NaN NaN \n",
" 2117-09-13 12:00:00 NaN NaN NaN \n",
" 2117-09-13 14:00:00 NaN NaN NaN \n",
" 2117-09-13 16:00:00 NaN NaN NaN \n",
" 2117-09-13 18:00:00 NaN NaN NaN \n",
" 2117-09-13 20:00:00 NaN NaN NaN \n",
"... ... ... ... \n",
"199994 2188-07-08 04:00:00 0.0 0.0 0.0 \n",
" 2188-07-08 06:00:00 0.0 0.0 0.0 \n",
"199998 2119-02-20 10:00:00 0.0 0.0 0.0 \n",
" 2119-02-20 12:00:00 0.0 0.0 0.0 \n",
" 2119-02-20 14:00:00 NaN NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN NaN \n",
" 2119-02-20 20:00:00 0.0 0.0 0.0 \n",
"199999 2136-04-04 20:00:00 0.0 0.0 0.0 \n",
" 2136-04-04 22:00:00 NaN NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN NaN \n",
" 2136-04-06 14:00:00 0.0 0.0 0.0 \n",
"\n",
"component \\\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 08:00:00 0.0 0.0 \n",
" 2117-09-11 12:00:00 NaN NaN \n",
" 2117-09-11 14:00:00 NaN NaN \n",
" 2117-09-11 16:00:00 NaN NaN \n",
" 2117-09-11 18:00:00 NaN NaN \n",
" 2117-09-11 20:00:00 NaN NaN \n",
" 2117-09-11 22:00:00 NaN NaN \n",
" 2117-09-12 00:00:00 NaN NaN \n",
" 2117-09-12 02:00:00 NaN NaN \n",
" 2117-09-12 04:00:00 NaN NaN \n",
" 2117-09-12 06:00:00 NaN NaN \n",
" 2117-09-12 08:00:00 NaN NaN \n",
" 2117-09-12 10:00:00 NaN NaN \n",
" 2117-09-12 12:00:00 NaN NaN \n",
" 2117-09-12 14:00:00 NaN NaN \n",
" 2117-09-12 16:00:00 NaN NaN \n",
" 2117-09-12 18:00:00 NaN NaN \n",
" 2117-09-12 20:00:00 NaN NaN \n",
" 2117-09-12 22:00:00 NaN NaN \n",
" 2117-09-13 00:00:00 NaN NaN \n",
" 2117-09-13 02:00:00 NaN NaN \n",
" 2117-09-13 04:00:00 NaN NaN \n",
" 2117-09-13 06:00:00 NaN NaN \n",
" 2117-09-13 08:00:00 NaN NaN \n",
" 2117-09-13 10:00:00 NaN NaN \n",
" 2117-09-13 12:00:00 NaN NaN \n",
" 2117-09-13 14:00:00 NaN NaN \n",
" 2117-09-13 16:00:00 NaN NaN \n",
" 2117-09-13 18:00:00 NaN NaN \n",
" 2117-09-13 20:00:00 NaN NaN \n",
"... ... ... \n",
"199994 2188-07-08 04:00:00 0.0 0.0 \n",
" 2188-07-08 06:00:00 0.0 0.0 \n",
"199998 2119-02-20 10:00:00 0.0 0.0 \n",
" 2119-02-20 12:00:00 0.0 0.0 \n",
" 2119-02-20 14:00:00 NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN \n",
" 2119-02-20 20:00:00 0.0 0.0 \n",
"199999 2136-04-04 20:00:00 0.0 0.0 \n",
" 2136-04-04 22:00:00 NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN \n",
" 2136-04-06 14:00:00 0.0 0.0 \n",
"\n",
"component ... \\\n",
"status ... \n",
"variable_type ... \n",
"units ... \n",
"description 1531(mmol/L)_ERROR ... 818(mmol/L)_no data \n",
"id datetime ... \n",
"100001 2117-09-11 08:00:00 0.0 ... 0.0 \n",
" 2117-09-11 12:00:00 NaN ... NaN \n",
" 2117-09-11 14:00:00 NaN ... NaN \n",
" 2117-09-11 16:00:00 NaN ... NaN \n",
" 2117-09-11 18:00:00 NaN ... NaN \n",
" 2117-09-11 20:00:00 NaN ... NaN \n",
" 2117-09-11 22:00:00 NaN ... NaN \n",
" 2117-09-12 00:00:00 NaN ... NaN \n",
" 2117-09-12 02:00:00 NaN ... NaN \n",
" 2117-09-12 04:00:00 NaN ... NaN \n",
" 2117-09-12 06:00:00 NaN ... NaN \n",
" 2117-09-12 08:00:00 NaN ... NaN \n",
" 2117-09-12 10:00:00 NaN ... NaN \n",
" 2117-09-12 12:00:00 NaN ... NaN \n",
" 2117-09-12 14:00:00 NaN ... NaN \n",
" 2117-09-12 16:00:00 NaN ... NaN \n",
" 2117-09-12 18:00:00 NaN ... NaN \n",
" 2117-09-12 20:00:00 NaN ... NaN \n",
" 2117-09-12 22:00:00 NaN ... NaN \n",
" 2117-09-13 00:00:00 NaN ... NaN \n",
" 2117-09-13 02:00:00 NaN ... NaN \n",
" 2117-09-13 04:00:00 NaN ... NaN \n",
" 2117-09-13 06:00:00 NaN ... NaN \n",
" 2117-09-13 08:00:00 NaN ... NaN \n",
" 2117-09-13 10:00:00 NaN ... NaN \n",
" 2117-09-13 12:00:00 NaN ... NaN \n",
" 2117-09-13 14:00:00 NaN ... NaN \n",
" 2117-09-13 16:00:00 NaN ... NaN \n",
" 2117-09-13 18:00:00 NaN ... NaN \n",
" 2117-09-13 20:00:00 NaN ... NaN \n",
"... ... ... ... \n",
"199994 2188-07-08 04:00:00 0.0 ... 0.0 \n",
" 2188-07-08 06:00:00 0.0 ... 0.0 \n",
"199998 2119-02-20 10:00:00 0.0 ... 0.0 \n",
" 2119-02-20 12:00:00 0.0 ... 0.0 \n",
" 2119-02-20 14:00:00 NaN ... NaN \n",
" 2119-02-20 16:00:00 NaN ... NaN \n",
" 2119-02-20 18:00:00 NaN ... NaN \n",
" 2119-02-20 20:00:00 0.0 ... 0.0 \n",
"199999 2136-04-04 20:00:00 0.0 ... 0.0 \n",
" 2136-04-04 22:00:00 NaN ... NaN \n",
" 2136-04-05 00:00:00 NaN ... NaN \n",
" 2136-04-05 02:00:00 NaN ... NaN \n",
" 2136-04-05 04:00:00 NaN ... NaN \n",
" 2136-04-05 06:00:00 NaN ... NaN \n",
" 2136-04-05 08:00:00 NaN ... NaN \n",
" 2136-04-05 10:00:00 NaN ... NaN \n",
" 2136-04-05 12:00:00 NaN ... NaN \n",
" 2136-04-05 14:00:00 NaN ... NaN \n",
" 2136-04-05 16:00:00 NaN ... NaN \n",
" 2136-04-05 18:00:00 NaN ... NaN \n",
" 2136-04-05 20:00:00 NaN ... NaN \n",
" 2136-04-05 22:00:00 NaN ... NaN \n",
" 2136-04-06 00:00:00 NaN ... NaN \n",
" 2136-04-06 02:00:00 NaN ... NaN \n",
" 2136-04-06 04:00:00 NaN ... NaN \n",
" 2136-04-06 06:00:00 NaN ... NaN \n",
" 2136-04-06 08:00:00 NaN ... NaN \n",
" 2136-04-06 10:00:00 NaN ... NaN \n",
" 2136-04-06 12:00:00 NaN ... NaN \n",
" 2136-04-06 14:00:00 0.0 ... 0.0 \n",
"\n",
"component heart rate \\\n",
"status known \n",
"variable_type qn qn \n",
"units no_units beats/min \n",
"description 225668 50813 818 211(BPM) 211(bpm) 220045(bpm) \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2117-09-11 12:00:00 NaN NaN NaN NaN NaN 119.333333 \n",
" 2117-09-11 14:00:00 NaN NaN NaN NaN NaN 114.000000 \n",
" 2117-09-11 16:00:00 NaN NaN NaN NaN NaN 102.500000 \n",
" 2117-09-11 18:00:00 NaN NaN NaN NaN NaN 110.000000 \n",
" 2117-09-11 20:00:00 NaN NaN NaN NaN NaN 116.500000 \n",
" 2117-09-11 22:00:00 NaN NaN NaN NaN NaN 119.500000 \n",
" 2117-09-12 00:00:00 NaN NaN NaN NaN NaN 116.500000 \n",
" 2117-09-12 02:00:00 NaN NaN NaN NaN NaN 110.000000 \n",
" 2117-09-12 04:00:00 NaN NaN NaN NaN NaN 94.500000 \n",
" 2117-09-12 06:00:00 NaN NaN NaN NaN NaN 108.000000 \n",
" 2117-09-12 08:00:00 NaN NaN NaN NaN NaN 111.000000 \n",
" 2117-09-12 10:00:00 NaN NaN NaN NaN NaN 115.500000 \n",
" 2117-09-12 12:00:00 NaN NaN NaN NaN NaN 113.500000 \n",
" 2117-09-12 14:00:00 NaN NaN NaN NaN NaN 117.000000 \n",
" 2117-09-12 16:00:00 NaN NaN NaN NaN NaN 124.000000 \n",
" 2117-09-12 18:00:00 NaN NaN NaN NaN NaN 124.000000 \n",
" 2117-09-12 20:00:00 NaN NaN NaN NaN NaN 127.500000 \n",
" 2117-09-12 22:00:00 NaN NaN NaN NaN NaN 128.500000 \n",
" 2117-09-13 00:00:00 NaN NaN NaN NaN NaN 128.500000 \n",
" 2117-09-13 02:00:00 NaN NaN NaN NaN NaN 127.500000 \n",
" 2117-09-13 04:00:00 NaN NaN NaN NaN NaN 124.500000 \n",
" 2117-09-13 06:00:00 NaN NaN NaN NaN NaN 120.500000 \n",
" 2117-09-13 08:00:00 NaN NaN NaN NaN NaN 118.250000 \n",
" 2117-09-13 10:00:00 NaN NaN NaN NaN NaN 114.500000 \n",
" 2117-09-13 12:00:00 NaN NaN NaN NaN NaN 102.500000 \n",
" 2117-09-13 14:00:00 NaN NaN NaN NaN NaN 109.000000 \n",
" 2117-09-13 16:00:00 NaN NaN NaN NaN NaN 93.500000 \n",
" 2117-09-13 18:00:00 NaN NaN NaN NaN NaN 93.000000 \n",
" 2117-09-13 20:00:00 NaN NaN NaN NaN NaN 100.000000 \n",
"... ... ... .. ... ... ... \n",
"199994 2188-07-08 04:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2188-07-08 06:00:00 NaN NaN NaN NaN NaN NaN \n",
"199998 2119-02-20 10:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2119-02-20 12:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2119-02-20 14:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2119-02-20 20:00:00 NaN NaN NaN NaN NaN NaN \n",
"199999 2136-04-04 20:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-04 22:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN NaN NaN NaN NaN \n",
" 2136-04-06 14:00:00 NaN NaN NaN NaN NaN NaN \n",
"\n",
"component \n",
"status unknown \n",
"variable_type qn \n",
"units no_units \n",
"description 1332 1341 1725 \n",
"id datetime \n",
"100001 2117-09-11 08:00:00 NaN NaN NaN \n",
" 2117-09-11 12:00:00 NaN NaN NaN \n",
" 2117-09-11 14:00:00 NaN NaN NaN \n",
" 2117-09-11 16:00:00 NaN NaN NaN \n",
" 2117-09-11 18:00:00 NaN NaN NaN \n",
" 2117-09-11 20:00:00 NaN NaN NaN \n",
" 2117-09-11 22:00:00 NaN NaN NaN \n",
" 2117-09-12 00:00:00 NaN NaN NaN \n",
" 2117-09-12 02:00:00 NaN NaN NaN \n",
" 2117-09-12 04:00:00 NaN NaN NaN \n",
" 2117-09-12 06:00:00 NaN NaN NaN \n",
" 2117-09-12 08:00:00 NaN NaN NaN \n",
" 2117-09-12 10:00:00 NaN NaN NaN \n",
" 2117-09-12 12:00:00 NaN NaN NaN \n",
" 2117-09-12 14:00:00 NaN NaN NaN \n",
" 2117-09-12 16:00:00 NaN NaN NaN \n",
" 2117-09-12 18:00:00 NaN NaN NaN \n",
" 2117-09-12 20:00:00 NaN NaN NaN \n",
" 2117-09-12 22:00:00 NaN NaN NaN \n",
" 2117-09-13 00:00:00 NaN NaN NaN \n",
" 2117-09-13 02:00:00 NaN NaN NaN \n",
" 2117-09-13 04:00:00 NaN NaN NaN \n",
" 2117-09-13 06:00:00 NaN NaN NaN \n",
" 2117-09-13 08:00:00 NaN NaN NaN \n",
" 2117-09-13 10:00:00 NaN NaN NaN \n",
" 2117-09-13 12:00:00 NaN NaN NaN \n",
" 2117-09-13 14:00:00 NaN NaN NaN \n",
" 2117-09-13 16:00:00 NaN NaN NaN \n",
" 2117-09-13 18:00:00 NaN NaN NaN \n",
" 2117-09-13 20:00:00 NaN NaN NaN \n",
"... ... ... ... \n",
"199994 2188-07-08 04:00:00 NaN NaN NaN \n",
" 2188-07-08 06:00:00 NaN NaN NaN \n",
"199998 2119-02-20 10:00:00 NaN NaN NaN \n",
" 2119-02-20 12:00:00 NaN NaN NaN \n",
" 2119-02-20 14:00:00 NaN NaN NaN \n",
" 2119-02-20 16:00:00 NaN NaN NaN \n",
" 2119-02-20 18:00:00 NaN NaN NaN \n",
" 2119-02-20 20:00:00 NaN NaN NaN \n",
"199999 2136-04-04 20:00:00 NaN NaN NaN \n",
" 2136-04-04 22:00:00 NaN NaN NaN \n",
" 2136-04-05 00:00:00 NaN NaN NaN \n",
" 2136-04-05 02:00:00 NaN NaN NaN \n",
" 2136-04-05 04:00:00 NaN NaN NaN \n",
" 2136-04-05 06:00:00 NaN NaN NaN \n",
" 2136-04-05 08:00:00 NaN NaN NaN \n",
" 2136-04-05 10:00:00 NaN NaN NaN \n",
" 2136-04-05 12:00:00 NaN NaN NaN \n",
" 2136-04-05 14:00:00 NaN NaN NaN \n",
" 2136-04-05 16:00:00 NaN NaN NaN \n",
" 2136-04-05 18:00:00 NaN NaN NaN \n",
" 2136-04-05 20:00:00 NaN NaN NaN \n",
" 2136-04-05 22:00:00 NaN NaN NaN \n",
" 2136-04-06 00:00:00 NaN NaN NaN \n",
" 2136-04-06 02:00:00 NaN NaN NaN \n",
" 2136-04-06 04:00:00 NaN NaN NaN \n",
" 2136-04-06 06:00:00 NaN NaN NaN \n",
" 2136-04-06 08:00:00 NaN NaN NaN \n",
" 2136-04-06 10:00:00 NaN NaN NaN \n",
" 2136-04-06 12:00:00 NaN NaN NaN \n",
" 2136-04-06 14:00:00 NaN NaN NaN \n",
"\n",
"[1427183 rows x 69 columns]"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"resampled_lactate.join(resampled_heart_rate,how='outer')"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"collapsed": true
},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</th>\n",
" <th colspan=\"15\" halign=\"left\">lactate</th>\n",
" <th colspan=\"6\" halign=\"left\">heart rate</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>status</th>\n",
" <th colspan=\"4\" halign=\"left\">known</th>\n",
" <th colspan=\"11\" halign=\"left\">unknown</th>\n",
" <th colspan=\"3\" halign=\"left\">known</th>\n",
" <th colspan=\"3\" 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 colspan=\"8\" halign=\"left\">nom</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" <th colspan=\"3\" halign=\"left\">qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th colspan=\"4\" halign=\"left\">mmol/L</th>\n",
" <th colspan=\"8\" halign=\"left\">no_units</th>\n",
" <th colspan=\"3\" halign=\"left\">no_units</th>\n",
" <th colspan=\"3\" halign=\"left\">beats/min</th>\n",
" <th colspan=\"3\" halign=\"left\">no_units</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>description</th>\n",
" <th>1531</th>\n",
" <th>225668</th>\n",
" <th>50813</th>\n",
" <th>818</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>...</th>\n",
" <th>818(mmol/L)_no data</th>\n",
" <th>225668</th>\n",
" <th>50813</th>\n",
" <th>818</th>\n",
" <th>211(BPM)</th>\n",
" <th>211(bpm)</th>\n",
" <th>220045(bpm)</th>\n",
" <th>1332</th>\n",
" <th>1341</th>\n",
" <th>1725</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=\"5\" valign=\"top\">100001</th>\n",
" <th>2117-09-11 09:32:00</th>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1.9</td>\n",
" <td>NaN</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>...</td>\n",
" <td>0.0</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>2117-09-11 12:57:00</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>122.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>118.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>118.0</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>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>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>118.0</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 69 columns</p>\n",
"</div>"
],
"text/plain": [
"component lactate \\\n",
"status known unknown \n",
"variable_type qn nom \n",
"units mmol/L no_units \n",
"description 1531 225668 50813 818 1531(mmol/L)_. \n",
"id datetime \n",
"100001 2117-09-11 09:32:00 NaN NaN 1.9 NaN 0.0 \n",
" 2117-09-11 12:57:00 NaN NaN NaN NaN NaN \n",
" 2117-09-11 13:00:00 NaN NaN NaN NaN NaN \n",
" 2117-09-11 13:50:00 NaN NaN NaN NaN NaN \n",
" 2117-09-11 14:00:00 NaN NaN NaN NaN NaN \n",
"\n",
"component \\\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 0.0 \n",
" 2117-09-11 12:57:00 NaN NaN \n",
" 2117-09-11 13:00:00 NaN NaN \n",
" 2117-09-11 13:50:00 NaN NaN \n",
" 2117-09-11 14:00:00 NaN NaN \n",
"\n",
"component \\\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 0.0 \n",
" 2117-09-11 12:57:00 NaN NaN \n",
" 2117-09-11 13:00:00 NaN NaN \n",
" 2117-09-11 13:50:00 NaN NaN \n",
" 2117-09-11 14:00:00 NaN NaN \n",
"\n",
"component ... \\\n",
"status ... \n",
"variable_type ... \n",
"units ... \n",
"description 1531(mmol/L)_ERROR ... 818(mmol/L)_no data \n",
"id datetime ... \n",
"100001 2117-09-11 09:32:00 0.0 ... 0.0 \n",
" 2117-09-11 12:57:00 NaN ... NaN \n",
" 2117-09-11 13:00:00 NaN ... NaN \n",
" 2117-09-11 13:50:00 NaN ... NaN \n",
" 2117-09-11 14:00:00 NaN ... NaN \n",
"\n",
"component heart rate \\\n",
"status known \n",
"variable_type qn qn \n",
"units no_units beats/min \n",
"description 225668 50813 818 211(BPM) 211(bpm) 220045(bpm) \n",
"id datetime \n",
"100001 2117-09-11 09:32:00 NaN NaN NaN NaN NaN NaN \n",
" 2117-09-11 12:57:00 NaN NaN NaN NaN NaN 122.0 \n",
" 2117-09-11 13:00:00 NaN NaN NaN NaN NaN 118.0 \n",
" 2117-09-11 13:50:00 NaN NaN NaN NaN NaN 118.0 \n",
" 2117-09-11 14:00:00 NaN NaN NaN NaN NaN 118.0 \n",
"\n",
"component \n",
"status unknown \n",
"variable_type qn \n",
"units no_units \n",
"description 1332 1341 1725 \n",
"id datetime \n",
"100001 2117-09-11 09:32:00 NaN NaN NaN \n",
" 2117-09-11 12:57:00 NaN NaN NaN \n",
" 2117-09-11 13:00:00 NaN NaN NaN \n",
" 2117-09-11 13:50:00 NaN NaN NaN \n",
" 2117-09-11 14:00:00 NaN NaN NaN \n",
"\n",
"[5 rows x 69 columns]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_both = df_lactate.join(df_heart_rate, how='outer')\n",
"df_both.head()"
]
},
{
"cell_type": "code",
"execution_count": 28,
"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>seg_id</th>\n",
" <th>start_dt</th>\n",
" <th>end_dt</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100001</td>\n",
" <td>0</td>\n",
" <td>2117-09-11 09:32:00</td>\n",
" <td>2117-09-11 21:32:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>100001</td>\n",
" <td>1</td>\n",
" <td>2117-09-11 21:32:00</td>\n",
" <td>2117-09-12 09:32:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>100001</td>\n",
" <td>2</td>\n",
" <td>2117-09-12 09:32:00</td>\n",
" <td>2117-09-12 21:32:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>100001</td>\n",
" <td>3</td>\n",
" <td>2117-09-12 21:32:00</td>\n",
" <td>2117-09-13 09:32:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100001</td>\n",
" <td>4</td>\n",
" <td>2117-09-13 09:32:00</td>\n",
" <td>2117-09-13 21:32:00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id seg_id start_dt end_dt\n",
"0 100001 0 2117-09-11 09:32:00 2117-09-11 21:32:00\n",
"1 100001 1 2117-09-11 21:32:00 2117-09-12 09:32:00\n",
"2 100001 2 2117-09-12 09:32:00 2117-09-12 21:32:00\n",
"3 100001 3 2117-09-12 21:32:00 2117-09-13 09:32:00\n",
"4 100001 4 2117-09-13 09:32:00 2117-09-13 21:32:00"
]
},
"execution_count": 28,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"periodic_seg = load_and_segment.periodic(n_hrs=12)\n",
"df_segments = periodic_seg._segmenter__segment(df_both).reset_index(drop=False)\n",
"df_segments.head()"
]
},
{
"cell_type": "code",
"execution_count": 29,
"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",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100001</td>\n",
" <td>2117-09-11 09:32:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>100001</td>\n",
" <td>2117-09-11 12:57:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>100001</td>\n",
" <td>2117-09-11 13:00:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>100001</td>\n",
" <td>2117-09-11 13:50:00</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100001</td>\n",
" <td>2117-09-11 14:00:00</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" id datetime\n",
"0 100001 2117-09-11 09:32:00\n",
"1 100001 2117-09-11 12:57:00\n",
"2 100001 2117-09-11 13:00:00\n",
"3 100001 2117-09-11 13:50:00\n",
"4 100001 2117-09-11 14:00:00"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_dt = df_both.drop(df_both.columns, axis=1).reset_index(drop=False)\n",
"df_dt.columns = df_dt.columns.get_level_values('component').tolist()\n",
"df_dt.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"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-30-11cc016470f0>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf_combined\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdf_segments\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmerge\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf_dt\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mon\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'id'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 2\u001b[0m \u001b[0mafter_start\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0misnull\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf_combined\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'start_dt'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m|\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mdf_combined\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'datetime'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m>=\u001b[0m \u001b[0mdf_combined\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'start_dt'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 3\u001b[0m \u001b[0mbefore_end\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0misnull\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf_combined\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'end_dt'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m|\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mdf_combined\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'datetime'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m<\u001b[0m \u001b[0mdf_combined\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'end_dt'\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4\u001b[0m \u001b[0min_seg\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mafter_start\u001b[0m \u001b[1;33m&\u001b[0m \u001b[0mbefore_end\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5\u001b[0m \u001b[0mdf_combined\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;34m'in_seg'\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0min_seg\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\frame.pyc\u001b[0m in \u001b[0;36mmerge\u001b[1;34m(self, right, how, on, left_on, right_on, left_index, right_index, sort, suffixes, copy, indicator)\u001b[0m\n\u001b[0;32m 4586\u001b[0m \u001b[0mright_on\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mright_on\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mleft_index\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mleft_index\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4587\u001b[0m \u001b[0mright_index\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mright_index\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msort\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msort\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msuffixes\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msuffixes\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 4588\u001b[1;33m copy=copy, indicator=indicator)\n\u001b[0m\u001b[0;32m 4589\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4590\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mround\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdecimals\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\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;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\tools\\merge.pyc\u001b[0m in \u001b[0;36mmerge\u001b[1;34m(left, right, how, on, left_on, right_on, left_index, right_index, sort, suffixes, copy, indicator)\u001b[0m\n\u001b[0;32m 57\u001b[0m \u001b[0mright_index\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mright_index\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msort\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msort\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msuffixes\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msuffixes\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 58\u001b[0m copy=copy, indicator=indicator)\n\u001b[1;32m---> 59\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 60\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0m__debug__\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 61\u001b[0m \u001b[0mmerge\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__doc__\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_merge_doc\u001b[0m \u001b[1;33m%\u001b[0m \u001b[1;34m'\\nleft : DataFrame'\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\tools\\merge.pyc\u001b[0m in \u001b[0;36mget_result\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 506\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mldata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mlindexers\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mrdata\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mrindexers\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 507\u001b[0m \u001b[0maxes\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mllabels\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mappend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrlabels\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mjoin_index\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 508\u001b[1;33m concat_axis=0, copy=self.copy)\n\u001b[0m\u001b[0;32m 509\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 510\u001b[0m \u001b[0mtyp\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mleft\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_constructor\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;36mconcatenate_block_managers\u001b[1;34m(mgrs_indexers, axes, concat_axis, copy)\u001b[0m\n\u001b[0;32m 4795\u001b[0m blocks = [make_block(\n\u001b[0;32m 4796\u001b[0m \u001b[0mconcatenate_join_units\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mjoin_units\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mconcat_axis\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mcopy\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 4797\u001b[1;33m placement=placement) for placement, join_units in concat_plan]\n\u001b[0m\u001b[0;32m 4798\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4799\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mBlockManager\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mblocks\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0maxes\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;36mconcatenate_join_units\u001b[1;34m(join_units, concat_axis, copy)\u001b[0m\n\u001b[0;32m 4888\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mAssertionError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Concatenating join units along axis0\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4889\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 4890\u001b[1;33m \u001b[0mempty_dtype\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mupcasted_na\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mget_empty_dtype_and_na\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mjoin_units\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 4891\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4892\u001b[0m to_concat = [ju.get_reindexed_values(empty_dtype=empty_dtype,\n",
"\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\internals.pyc\u001b[0m in \u001b[0;36mget_empty_dtype_and_na\u001b[1;34m(join_units)\u001b[0m\n\u001b[0;32m 4823\u001b[0m \u001b[0mhas_none_blocks\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4824\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 4825\u001b[1;33m \u001b[0mdtypes\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m]\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0munit\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 4826\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4827\u001b[0m \u001b[0mupcast_classes\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mdefaultdict\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlist\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mpandas\\src\\properties.pyx\u001b[0m in \u001b[0;36mpandas.lib.cache_readonly.__get__ (pandas\\lib.c:43685)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\internals.pyc\u001b[0m in \u001b[0;36mdtype\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 5103\u001b[0m \u001b[1;32mraise\u001b[0m \u001b[0mAssertionError\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"Block is None, no dtype\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5104\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5105\u001b[1;33m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mneeds_filling\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 5106\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mblock\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mdtype\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5107\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mpandas\\src\\properties.pyx\u001b[0m in \u001b[0;36mpandas.lib.cache_readonly.__get__ (pandas\\lib.c:43685)\u001b[1;34m()\u001b[0m\n",
"\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\internals.pyc\u001b[0m in \u001b[0;36mneeds_filling\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 5093\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mindexer\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mindexers\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mvalues\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 5094\u001b[0m \u001b[1;31m# FIXME: cache results of indexer == -1 checks.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5095\u001b[1;33m \u001b[1;32mif\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mindexer\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[0many\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[0m\u001b[0;32m 5096\u001b[0m \u001b[1;32mreturn\u001b[0m \u001b[0mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 5097\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"df_combined = df_segments.merge(df_dt,on='id')\n",
"after_start = pd.isnull(df_combined['start_dt']) | (df_combined['datetime'] >= df_combined['start_dt'])\n",
"before_end = pd.isnull(df_combined['end_dt']) | (df_combined['datetime'] < df_combined['end_dt'])\n",
"in_seg = after_start & before_end\n",
"df_combined['in_seg'] = in_seg "
]
},
{
"cell_type": "code",
"execution_count": 66,
"metadata": {
"collapsed": false
},
"outputs": [],
"source": [
"def clean_seg(seg):\n",
" has_values = seg['in_seg'].any()\n",
" \n",
" if has_values: return seg[seg['in_seg']]\n",
" \n",
" start_dt = seg['start_dt'].iloc[0]\n",
" end_dt = seg['end_dt'].iloc[0]\n",
"\n",
" in_seg_dt = start_dt\n",
" if pd.isnull(in_seg_dt):\n",
" in_seg_dt = end_dt - pd.Timedelta(value=1,unit='s')\n",
" \n",
" seg = seg.iloc[[0]]\n",
" seg.datetime = in_seg_dt\n",
" \n",
" return seg"
]
},
{
"cell_type": "code",
"execution_count": 67,
"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></th>\n",
" <th>id</th>\n",
" <th>seg_id</th>\n",
" <th>start_dt</th>\n",
" <th>end_dt</th>\n",
" <th>datetime</th>\n",
" <th>in_seg</th>\n",
" </tr>\n",
" <tr>\n",
" <th>id</th>\n",
" <th>seg_id</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>0</th>\n",
" <td>100001</td>\n",
" <td>0</td>\n",
" <td>2117-09-11 09:32:00</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 09:32:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100001</td>\n",
" <td>0</td>\n",
" <td>2117-09-11 09:32:00</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 12:57:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100001</td>\n",
" <td>0</td>\n",
" <td>2117-09-11 09:32:00</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 13:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100001</td>\n",
" <td>0</td>\n",
" <td>2117-09-11 09:32:00</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 13:50:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>100001</td>\n",
" <td>0</td>\n",
" <td>2117-09-11 09:32:00</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 14:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>100001</td>\n",
" <td>1</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-11 15:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>100001</td>\n",
" <td>1</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-11 16:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>100001</td>\n",
" <td>1</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-11 17:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>100001</td>\n",
" <td>1</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-11 18:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>100001</td>\n",
" <td>1</td>\n",
" <td>2117-09-11 14:32:00</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-11 19:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>100001</td>\n",
" <td>2</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-11 20:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>100001</td>\n",
" <td>2</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-11 21:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>100001</td>\n",
" <td>2</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-11 22:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>100001</td>\n",
" <td>2</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-11 23:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>100001</td>\n",
" <td>2</td>\n",
" <td>2117-09-11 19:32:00</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-12 00:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>100001</td>\n",
" <td>3</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 01:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>100001</td>\n",
" <td>3</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 02:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>100001</td>\n",
" <td>3</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 03:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>100001</td>\n",
" <td>3</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 04:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>100001</td>\n",
" <td>3</td>\n",
" <td>2117-09-12 00:32:00</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 05:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100001</td>\n",
" <td>4</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 06:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100001</td>\n",
" <td>4</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 07:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100001</td>\n",
" <td>4</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 08:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100001</td>\n",
" <td>4</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 09:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>100001</td>\n",
" <td>4</td>\n",
" <td>2117-09-12 05:32:00</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 10:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>100001</td>\n",
" <td>5</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 15:32:00</td>\n",
" <td>2117-09-12 11:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>100001</td>\n",
" <td>5</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 15:32:00</td>\n",
" <td>2117-09-12 12:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>100001</td>\n",
" <td>5</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 15:32:00</td>\n",
" <td>2117-09-12 13:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>100001</td>\n",
" <td>5</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 15:32:00</td>\n",
" <td>2117-09-12 14:00:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>5</th>\n",
" <td>100001</td>\n",
" <td>5</td>\n",
" <td>2117-09-12 10:32:00</td>\n",
" <td>2117-09-12 15:32:00</td>\n",
" <td>2117-09-12 15:00:00</td>\n",
" <td>True</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=\"30\" valign=\"top\">100242</th>\n",
" <th>118</th>\n",
" <td>100242</td>\n",
" <td>118</td>\n",
" <td>2161-09-23 17:55:00</td>\n",
" <td>2161-09-23 22:55:00</td>\n",
" <td>2161-09-23 17:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>119</th>\n",
" <td>100242</td>\n",
" <td>119</td>\n",
" <td>2161-09-23 22:55:00</td>\n",
" <td>2161-09-24 03:55:00</td>\n",
" <td>2161-09-23 22:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>120</th>\n",
" <td>100242</td>\n",
" <td>120</td>\n",
" <td>2161-09-24 03:55:00</td>\n",
" <td>2161-09-24 08:55:00</td>\n",
" <td>2161-09-24 03:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>121</th>\n",
" <td>100242</td>\n",
" <td>121</td>\n",
" <td>2161-09-24 08:55:00</td>\n",
" <td>2161-09-24 13:55:00</td>\n",
" <td>2161-09-24 08:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>122</th>\n",
" <td>100242</td>\n",
" <td>122</td>\n",
" <td>2161-09-24 13:55:00</td>\n",
" <td>2161-09-24 18:55:00</td>\n",
" <td>2161-09-24 13:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>123</th>\n",
" <td>100242</td>\n",
" <td>123</td>\n",
" <td>2161-09-24 18:55:00</td>\n",
" <td>2161-09-24 23:55:00</td>\n",
" <td>2161-09-24 18:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>124</th>\n",
" <td>100242</td>\n",
" <td>124</td>\n",
" <td>2161-09-24 23:55:00</td>\n",
" <td>2161-09-25 04:55:00</td>\n",
" <td>2161-09-24 23:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>125</th>\n",
" <td>100242</td>\n",
" <td>125</td>\n",
" <td>2161-09-25 04:55:00</td>\n",
" <td>2161-09-25 09:55:00</td>\n",
" <td>2161-09-25 04:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>126</th>\n",
" <td>100242</td>\n",
" <td>126</td>\n",
" <td>2161-09-25 09:55:00</td>\n",
" <td>2161-09-25 14:55:00</td>\n",
" <td>2161-09-25 09:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>127</th>\n",
" <td>100242</td>\n",
" <td>127</td>\n",
" <td>2161-09-25 14:55:00</td>\n",
" <td>2161-09-25 19:55:00</td>\n",
" <td>2161-09-25 14:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>128</th>\n",
" <td>100242</td>\n",
" <td>128</td>\n",
" <td>2161-09-25 19:55:00</td>\n",
" <td>2161-09-26 00:55:00</td>\n",
" <td>2161-09-25 19:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>129</th>\n",
" <td>100242</td>\n",
" <td>129</td>\n",
" <td>2161-09-26 00:55:00</td>\n",
" <td>2161-09-26 05:55:00</td>\n",
" <td>2161-09-26 00:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>130</th>\n",
" <td>100242</td>\n",
" <td>130</td>\n",
" <td>2161-09-26 05:55:00</td>\n",
" <td>2161-09-26 10:55:00</td>\n",
" <td>2161-09-26 05:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>131</th>\n",
" <td>100242</td>\n",
" <td>131</td>\n",
" <td>2161-09-26 10:55:00</td>\n",
" <td>2161-09-26 15:55:00</td>\n",
" <td>2161-09-26 10:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>132</th>\n",
" <td>100242</td>\n",
" <td>132</td>\n",
" <td>2161-09-26 15:55:00</td>\n",
" <td>2161-09-26 20:55:00</td>\n",
" <td>2161-09-26 15:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>133</th>\n",
" <td>100242</td>\n",
" <td>133</td>\n",
" <td>2161-09-26 20:55:00</td>\n",
" <td>2161-09-27 01:55:00</td>\n",
" <td>2161-09-26 20:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>134</th>\n",
" <td>100242</td>\n",
" <td>134</td>\n",
" <td>2161-09-27 01:55:00</td>\n",
" <td>2161-09-27 06:55:00</td>\n",
" <td>2161-09-27 01:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>135</th>\n",
" <td>100242</td>\n",
" <td>135</td>\n",
" <td>2161-09-27 06:55:00</td>\n",
" <td>2161-09-27 11:55:00</td>\n",
" <td>2161-09-27 06:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>136</th>\n",
" <td>100242</td>\n",
" <td>136</td>\n",
" <td>2161-09-27 11:55:00</td>\n",
" <td>2161-09-27 16:55:00</td>\n",
" <td>2161-09-27 11:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>137</th>\n",
" <td>100242</td>\n",
" <td>137</td>\n",
" <td>2161-09-27 16:55:00</td>\n",
" <td>2161-09-27 21:55:00</td>\n",
" <td>2161-09-27 16:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>138</th>\n",
" <td>100242</td>\n",
" <td>138</td>\n",
" <td>2161-09-27 21:55:00</td>\n",
" <td>2161-09-28 02:55:00</td>\n",
" <td>2161-09-27 21:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>139</th>\n",
" <td>100242</td>\n",
" <td>139</td>\n",
" <td>2161-09-28 02:55:00</td>\n",
" <td>2161-09-28 07:55:00</td>\n",
" <td>2161-09-28 02:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>140</th>\n",
" <td>100242</td>\n",
" <td>140</td>\n",
" <td>2161-09-28 07:55:00</td>\n",
" <td>2161-09-28 12:55:00</td>\n",
" <td>2161-09-28 07:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>141</th>\n",
" <td>100242</td>\n",
" <td>141</td>\n",
" <td>2161-09-28 12:55:00</td>\n",
" <td>2161-09-28 17:55:00</td>\n",
" <td>2161-09-28 12:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>142</th>\n",
" <td>100242</td>\n",
" <td>142</td>\n",
" <td>2161-09-28 17:55:00</td>\n",
" <td>2161-09-28 22:55:00</td>\n",
" <td>2161-09-28 17:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>143</th>\n",
" <td>100242</td>\n",
" <td>143</td>\n",
" <td>2161-09-28 22:55:00</td>\n",
" <td>2161-09-29 03:55:00</td>\n",
" <td>2161-09-28 22:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>144</th>\n",
" <td>100242</td>\n",
" <td>144</td>\n",
" <td>2161-09-29 03:55:00</td>\n",
" <td>2161-09-29 08:55:00</td>\n",
" <td>2161-09-29 03:55:00</td>\n",
" <td>False</td>\n",
" </tr>\n",
" <tr>\n",
" <th>145</th>\n",
" <td>100242</td>\n",
" <td>145</td>\n",
" <td>2161-09-29 08:55:00</td>\n",
" <td>2161-09-29 13:55:00</td>\n",
" <td>2161-09-29 10:58:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>100242</td>\n",
" <td>146</td>\n",
" <td>2161-09-29 13:55:00</td>\n",
" <td>2161-09-29 18:55:00</td>\n",
" <td>2161-09-29 16:18:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" <tr>\n",
" <th>146</th>\n",
" <td>100242</td>\n",
" <td>146</td>\n",
" <td>2161-09-29 13:55:00</td>\n",
" <td>2161-09-29 18:55:00</td>\n",
" <td>2161-09-29 16:55:00</td>\n",
" <td>True</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2293 rows × 6 columns</p>\n",
"</div>"
],
"text/plain": [
" id seg_id start_dt end_dt \\\n",
"id seg_id \n",
"100001 0 100001 0 2117-09-11 09:32:00 2117-09-11 14:32:00 \n",
" 0 100001 0 2117-09-11 09:32:00 2117-09-11 14:32:00 \n",
" 0 100001 0 2117-09-11 09:32:00 2117-09-11 14:32:00 \n",
" 0 100001 0 2117-09-11 09:32:00 2117-09-11 14:32:00 \n",
" 0 100001 0 2117-09-11 09:32:00 2117-09-11 14:32:00 \n",
" 1 100001 1 2117-09-11 14:32:00 2117-09-11 19:32:00 \n",
" 1 100001 1 2117-09-11 14:32:00 2117-09-11 19:32:00 \n",
" 1 100001 1 2117-09-11 14:32:00 2117-09-11 19:32:00 \n",
" 1 100001 1 2117-09-11 14:32:00 2117-09-11 19:32:00 \n",
" 1 100001 1 2117-09-11 14:32:00 2117-09-11 19:32:00 \n",
" 2 100001 2 2117-09-11 19:32:00 2117-09-12 00:32:00 \n",
" 2 100001 2 2117-09-11 19:32:00 2117-09-12 00:32:00 \n",
" 2 100001 2 2117-09-11 19:32:00 2117-09-12 00:32:00 \n",
" 2 100001 2 2117-09-11 19:32:00 2117-09-12 00:32:00 \n",
" 2 100001 2 2117-09-11 19:32:00 2117-09-12 00:32:00 \n",
" 3 100001 3 2117-09-12 00:32:00 2117-09-12 05:32:00 \n",
" 3 100001 3 2117-09-12 00:32:00 2117-09-12 05:32:00 \n",
" 3 100001 3 2117-09-12 00:32:00 2117-09-12 05:32:00 \n",
" 3 100001 3 2117-09-12 00:32:00 2117-09-12 05:32:00 \n",
" 3 100001 3 2117-09-12 00:32:00 2117-09-12 05:32:00 \n",
" 4 100001 4 2117-09-12 05:32:00 2117-09-12 10:32:00 \n",
" 4 100001 4 2117-09-12 05:32:00 2117-09-12 10:32:00 \n",
" 4 100001 4 2117-09-12 05:32:00 2117-09-12 10:32:00 \n",
" 4 100001 4 2117-09-12 05:32:00 2117-09-12 10:32:00 \n",
" 4 100001 4 2117-09-12 05:32:00 2117-09-12 10:32:00 \n",
" 5 100001 5 2117-09-12 10:32:00 2117-09-12 15:32:00 \n",
" 5 100001 5 2117-09-12 10:32:00 2117-09-12 15:32:00 \n",
" 5 100001 5 2117-09-12 10:32:00 2117-09-12 15:32:00 \n",
" 5 100001 5 2117-09-12 10:32:00 2117-09-12 15:32:00 \n",
" 5 100001 5 2117-09-12 10:32:00 2117-09-12 15:32:00 \n",
"... ... ... ... ... \n",
"100242 118 100242 118 2161-09-23 17:55:00 2161-09-23 22:55:00 \n",
" 119 100242 119 2161-09-23 22:55:00 2161-09-24 03:55:00 \n",
" 120 100242 120 2161-09-24 03:55:00 2161-09-24 08:55:00 \n",
" 121 100242 121 2161-09-24 08:55:00 2161-09-24 13:55:00 \n",
" 122 100242 122 2161-09-24 13:55:00 2161-09-24 18:55:00 \n",
" 123 100242 123 2161-09-24 18:55:00 2161-09-24 23:55:00 \n",
" 124 100242 124 2161-09-24 23:55:00 2161-09-25 04:55:00 \n",
" 125 100242 125 2161-09-25 04:55:00 2161-09-25 09:55:00 \n",
" 126 100242 126 2161-09-25 09:55:00 2161-09-25 14:55:00 \n",
" 127 100242 127 2161-09-25 14:55:00 2161-09-25 19:55:00 \n",
" 128 100242 128 2161-09-25 19:55:00 2161-09-26 00:55:00 \n",
" 129 100242 129 2161-09-26 00:55:00 2161-09-26 05:55:00 \n",
" 130 100242 130 2161-09-26 05:55:00 2161-09-26 10:55:00 \n",
" 131 100242 131 2161-09-26 10:55:00 2161-09-26 15:55:00 \n",
" 132 100242 132 2161-09-26 15:55:00 2161-09-26 20:55:00 \n",
" 133 100242 133 2161-09-26 20:55:00 2161-09-27 01:55:00 \n",
" 134 100242 134 2161-09-27 01:55:00 2161-09-27 06:55:00 \n",
" 135 100242 135 2161-09-27 06:55:00 2161-09-27 11:55:00 \n",
" 136 100242 136 2161-09-27 11:55:00 2161-09-27 16:55:00 \n",
" 137 100242 137 2161-09-27 16:55:00 2161-09-27 21:55:00 \n",
" 138 100242 138 2161-09-27 21:55:00 2161-09-28 02:55:00 \n",
" 139 100242 139 2161-09-28 02:55:00 2161-09-28 07:55:00 \n",
" 140 100242 140 2161-09-28 07:55:00 2161-09-28 12:55:00 \n",
" 141 100242 141 2161-09-28 12:55:00 2161-09-28 17:55:00 \n",
" 142 100242 142 2161-09-28 17:55:00 2161-09-28 22:55:00 \n",
" 143 100242 143 2161-09-28 22:55:00 2161-09-29 03:55:00 \n",
" 144 100242 144 2161-09-29 03:55:00 2161-09-29 08:55:00 \n",
" 145 100242 145 2161-09-29 08:55:00 2161-09-29 13:55:00 \n",
" 146 100242 146 2161-09-29 13:55:00 2161-09-29 18:55:00 \n",
" 146 100242 146 2161-09-29 13:55:00 2161-09-29 18:55:00 \n",
"\n",
" datetime in_seg \n",
"id seg_id \n",
"100001 0 2117-09-11 09:32:00 True \n",
" 0 2117-09-11 12:57:00 True \n",
" 0 2117-09-11 13:00:00 True \n",
" 0 2117-09-11 13:50:00 True \n",
" 0 2117-09-11 14:00:00 True \n",
" 1 2117-09-11 15:00:00 True \n",
" 1 2117-09-11 16:00:00 True \n",
" 1 2117-09-11 17:00:00 True \n",
" 1 2117-09-11 18:00:00 True \n",
" 1 2117-09-11 19:00:00 True \n",
" 2 2117-09-11 20:00:00 True \n",
" 2 2117-09-11 21:00:00 True \n",
" 2 2117-09-11 22:00:00 True \n",
" 2 2117-09-11 23:00:00 True \n",
" 2 2117-09-12 00:00:00 True \n",
" 3 2117-09-12 01:00:00 True \n",
" 3 2117-09-12 02:00:00 True \n",
" 3 2117-09-12 03:00:00 True \n",
" 3 2117-09-12 04:00:00 True \n",
" 3 2117-09-12 05:00:00 True \n",
" 4 2117-09-12 06:00:00 True \n",
" 4 2117-09-12 07:00:00 True \n",
" 4 2117-09-12 08:00:00 True \n",
" 4 2117-09-12 09:00:00 True \n",
" 4 2117-09-12 10:00:00 True \n",
" 5 2117-09-12 11:00:00 True \n",
" 5 2117-09-12 12:00:00 True \n",
" 5 2117-09-12 13:00:00 True \n",
" 5 2117-09-12 14:00:00 True \n",
" 5 2117-09-12 15:00:00 True \n",
"... ... ... \n",
"100242 118 2161-09-23 17:55:00 False \n",
" 119 2161-09-23 22:55:00 False \n",
" 120 2161-09-24 03:55:00 False \n",
" 121 2161-09-24 08:55:00 False \n",
" 122 2161-09-24 13:55:00 False \n",
" 123 2161-09-24 18:55:00 False \n",
" 124 2161-09-24 23:55:00 False \n",
" 125 2161-09-25 04:55:00 False \n",
" 126 2161-09-25 09:55:00 False \n",
" 127 2161-09-25 14:55:00 False \n",
" 128 2161-09-25 19:55:00 False \n",
" 129 2161-09-26 00:55:00 False \n",
" 130 2161-09-26 05:55:00 False \n",
" 131 2161-09-26 10:55:00 False \n",
" 132 2161-09-26 15:55:00 False \n",
" 133 2161-09-26 20:55:00 False \n",
" 134 2161-09-27 01:55:00 False \n",
" 135 2161-09-27 06:55:00 False \n",
" 136 2161-09-27 11:55:00 False \n",
" 137 2161-09-27 16:55:00 False \n",
" 138 2161-09-27 21:55:00 False \n",
" 139 2161-09-28 02:55:00 False \n",
" 140 2161-09-28 07:55:00 False \n",
" 141 2161-09-28 12:55:00 False \n",
" 142 2161-09-28 17:55:00 False \n",
" 143 2161-09-28 22:55:00 False \n",
" 144 2161-09-29 03:55:00 False \n",
" 145 2161-09-29 10:58:00 True \n",
" 146 2161-09-29 16:18:00 True \n",
" 146 2161-09-29 16:55:00 True \n",
"\n",
"[2293 rows x 6 columns]"
]
},
"execution_count": 67,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df_combined.groupby(['id','seg_id']).apply(clean_seg).reset_index(level=2,drop=True)"
]
},
{
"cell_type": "code",
"execution_count": 59,
"metadata": {
"collapsed": false
},
"outputs": [
{
"ename": "ValueError",
"evalue": "columns overlap but no suffix specified: Index([u'id'], dtype='object')",
"output_type": "error",
"traceback": [
"\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[1;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[1;32m<ipython-input-59-ec1c604b303c>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[1;32m----> 1\u001b[1;33m \u001b[0mdf_dt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mjoin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mdf_segments\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mhow\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;34m'outer'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
"\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\frame.pyc\u001b[0m in \u001b[0;36mjoin\u001b[1;34m(self, other, on, how, lsuffix, rsuffix, sort)\u001b[0m\n\u001b[0;32m 4534\u001b[0m \u001b[1;31m# For SparseDataFrame's benefit\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4535\u001b[0m return self._join_compat(other, on=on, how=how, lsuffix=lsuffix,\n\u001b[1;32m-> 4536\u001b[1;33m rsuffix=rsuffix, sort=sort)\n\u001b[0m\u001b[0;32m 4537\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4538\u001b[0m def _join_compat(self, other, on=None, how='left', lsuffix='', rsuffix='',\n",
"\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\core\\frame.pyc\u001b[0m in \u001b[0;36m_join_compat\u001b[1;34m(self, other, on, how, lsuffix, rsuffix, sort)\u001b[0m\n\u001b[0;32m 4548\u001b[0m return merge(self, other, left_on=on, how=how,\n\u001b[0;32m 4549\u001b[0m \u001b[0mleft_index\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mon\u001b[0m \u001b[1;32mis\u001b[0m \u001b[0mNone\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mright_index\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-> 4550\u001b[1;33m suffixes=(lsuffix, rsuffix), sort=sort)\n\u001b[0m\u001b[0;32m 4551\u001b[0m \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4552\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mon\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;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\tools\\merge.pyc\u001b[0m in \u001b[0;36mmerge\u001b[1;34m(left, right, how, on, left_on, right_on, left_index, right_index, sort, suffixes, copy, indicator)\u001b[0m\n\u001b[0;32m 57\u001b[0m \u001b[0mright_index\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mright_index\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msort\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msort\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0msuffixes\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0msuffixes\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 58\u001b[0m copy=copy, indicator=indicator)\n\u001b[1;32m---> 59\u001b[1;33m \u001b[1;32mreturn\u001b[0m \u001b[0mop\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget_result\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m 60\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0m__debug__\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 61\u001b[0m \u001b[0mmerge\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__doc__\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_merge_doc\u001b[0m \u001b[1;33m%\u001b[0m \u001b[1;34m'\\nleft : DataFrame'\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;32mC:\\Users\\genkinjz\\AppData\\Local\\Continuum\\Anaconda2\\lib\\site-packages\\pandas\\tools\\merge.pyc\u001b[0m in \u001b[0;36mget_result\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m 498\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 499\u001b[0m llabels, rlabels = items_overlap_with_suffix(ldata.items, lsuf,\n\u001b[1;32m--> 500\u001b[1;33m rdata.items, rsuf)\n\u001b[0m\u001b[0;32m 501\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 502\u001b[0m \u001b[0mlindexers\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m{\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mleft_indexer\u001b[0m\u001b[1;33m}\u001b[0m \u001b[1;32mif\u001b[0m \u001b[0mleft_indexer\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mNone\u001b[0m \u001b[1;32melse\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;36mitems_overlap_with_suffix\u001b[1;34m(left, lsuffix, right, rsuffix)\u001b[0m\n\u001b[0;32m 4674\u001b[0m \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mlsuffix\u001b[0m \u001b[1;32mand\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mrsuffix\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4675\u001b[0m raise ValueError('columns overlap but no suffix specified: %s' %\n\u001b[1;32m-> 4676\u001b[1;33m to_rename)\n\u001b[0m\u001b[0;32m 4677\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m 4678\u001b[0m \u001b[1;32mdef\u001b[0m \u001b[0mlrenamer\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mx\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
"\u001b[1;31mValueError\u001b[0m: columns overlap but no suffix specified: Index([u'id'], dtype='object')"
]
}
],
"source": [
"df_dt.join(df_segments,how='outer')"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"#Vitals\n",
"# component = data_dict.components.HEART_RATE\n",
"# add_simple_feature(featurizer,component,np.mean,fill_mean())\n",
"# add_simple_feature(featurizer,component,np.std,fill_zero())\n",
"# add_simple_feature(featurizer,component,count,fill_zero())\n",
"# add_simple_feature(featurizer,component,features.last,fill_mean())\n",
"\n",
"# component = data_dict.components.OXYGEN_SATURATION_PULSE_OXIMETRY\n",
"# add_simple_feature(featurizer,component,np.mean,fill_mean())\n",
"# add_simple_feature(featurizer,component,np.std,fill_zero())\n",
"# add_simple_feature(featurizer,component,count,fill_zero())\n",
"# add_simple_feature(featurizer,component,features.last,fill_mean())\n",
"\n",
"# component = data_dict.components.TEMPERATURE_BODY\n",
"# add_simple_feature(featurizer,component,np.mean,fill_mean())\n",
"# add_simple_feature(featurizer,component,np.std,fill_zero())\n",
"# add_simple_feature(featurizer,component,count,fill_zero())\n",
"# add_simple_feature(featurizer,component,features.last,fill_mean())\n",
"\n",
"# component = data_dict.components.HEMOGLOBIN\n",
"# add_simple_feature(featurizer,component,np.mean,fill_mean())\n",
"# add_simple_feature(featurizer,component,np.std,fill_zero())\n",
"# add_simple_feature(featurizer,component,count,fill_zero())\n",
"# add_simple_feature(featurizer,component,features.last,fill_mean())\n",
"\n",
"# #UOP\n",
"# component = data_dict.components.OUTPUT_URINE\n",
"# add_simple_feature(featurizer,component,np.sum,fill_zero())\n",
"# add_simple_feature(featurizer,component,np.std,fill_zero())\n",
"# add_simple_feature(featurizer,component,count,fill_zero())\n",
"# add_simple_feature(featurizer,component,features.last,fill_zero())"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {
"collapsed": false,
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(2017-07-01 03:49:44) Featurizing...\n",
"(2017-07-01 03:49:44)>> [('blood pressure mean', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-01 03:49:44)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure mean']\n",
"(2017-07-01 03:49:44)>>>>>> BLOOD PRESSURE MEAN: 1/1\n",
"(2017-07-01 03:49:45)>>>>>>>> Convert to dask - (1917776, 3)\n",
"(2017-07-01 03:49:45)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 03:49:45)>>>>>>>> Join to big DF\n",
"(2017-07-01 03:49:45)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 03:49:45)<<<<<< --- (1.0s)\n",
"(2017-07-01 03:49:45)>>>>>> Dask DF back to pandas\n",
"(2017-07-01 03:49:46)<<<<<< --- (1.0s)\n",
"(2017-07-01 03:49:46)>>>>>> SORT Joined DF\n",
"(2017-07-01 03:49:46)<<<<<< --- (0.0s)\n",
"(2017-07-01 03:49:46)<<<< --- (2.0s)\n",
"(2017-07-01 03:49:47)>>>> *fit* Filter columns (DataNeedsFilter) (1917776, 3)\n",
"(2017-07-01 03:49:47)<<<< --- (0.0s)\n",
"(2017-07-01 03:49:47)>>>> *transform* Filter columns (DataNeedsFilter) (1917776, 3)\n",
"(2017-07-01 03:49:47)<<<< --- (0.0s)\n",
"(2017-07-01 03:49:47)>>>> Segment df (1917776, 3)\n",
"(2017-07-01 03:49:47)>>>>>> Get Segments\n",
"(2017-07-01 03:50:20)<<<<<< --- (33.0s)\n",
"(2017-07-01 03:50:20)>>>>>> Apply n=299044 Segments to df.shape = (1917776, 3)\n",
"(2017-07-01 08:36:41)<<<<<< --- (17181.0s)\n",
"(2017-07-01 08:36:41)<<<< --- (17214.0s)\n",
"(2017-07-01 08:36:41)>>>> *fit* Filter columns (remove_small_columns) (1947107, 3)\n",
"(2017-07-01 08:36:41)<<<< --- (0.0s)\n",
"(2017-07-01 08:36:41)>>>> *transform* Filter columns (remove_small_columns) (1947107, 3)\n",
"(2017-07-01 08:36:41)<<<< --- (0.0s)\n",
"(2017-07-01 08:36:41)>>>> *fit* Filter columns (record_threshold) (1947107, 3)\n",
"(2017-07-01 08:36:41)<<<< --- (0.0s)\n",
"(2017-07-01 08:36:41)>>>> *transform* Filter columns (record_threshold) (1947107, 3)\n",
"(2017-07-01 08:36:41)<<<< --- (0.0s)\n",
"(2017-07-01 08:36:41)>>>> *fit* Filter columns (filter_var_type) (1947107, 3)\n",
"(2017-07-01 08:36:41)<<<< --- (0.0s)\n",
"(2017-07-01 08:36:41)>>>> *transform* Filter columns (filter_var_type) (1947107, 3)\n",
"(2017-07-01 08:36:41)<<<< --- (0.0s)\n",
"(2017-07-01 08:36:41)>>>> FIT Combine like columns (1947107, 3)\n",
"(2017-07-01 08:36:41)>>>>>> ('blood pressure mean', 'known', 'qn', 'mmHg')\n",
"(2017-07-01 08:36:41)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:36:41)<<<< --- (0.0s)\n",
"(2017-07-01 08:36:41)>>>> TRANSFORM Combine like columns (1947107, 3)\n",
"(2017-07-01 08:36:41)>>>>>> ('blood pressure mean', 'known', 'qn', 'mmHg')\n",
"(2017-07-01 08:37:23)<<<<<< --- (42.0s)\n",
"(2017-07-01 08:37:23)<<<< --- (42.0s)\n",
"(2017-07-01 08:37:23)>>>> fit_transform features on DF (1947107, 1)\n",
"(2017-07-01 08:37:23)>>>>>> STD\n",
"(2017-07-01 08:37:23)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:37:23)>>>>>> *fit* Filter columns (filter_to_component) (1947107, 1)\n",
"(2017-07-01 08:37:23)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:37:23)>>>>>> *transform* Filter columns (filter_to_component) (1947107, 1)\n",
"(2017-07-01 08:37:23)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:37:23)>>>>>> COUNT\n",
"(2017-07-01 08:37:23)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:37:23)>>>>>> *fit* Filter columns (filter_to_component) (1947107, 1)\n",
"(2017-07-01 08:37:23)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:37:23)>>>>>> *transform* Filter columns (filter_to_component) (1947107, 1)\n",
"(2017-07-01 08:38:09)<<<<<< --- (46.0s)\n",
"(2017-07-01 08:38:09)>>>>>> LAST\n",
"(2017-07-01 08:38:09)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:38:09)>>>>>> *fit* Filter columns (filter_to_component) (1947107, 1)\n",
"(2017-07-01 08:38:09)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:38:09)>>>>>> *transform* Filter columns (filter_to_component) (1947107, 1)\n",
"(2017-07-01 08:41:02)<<<<<< --- (173.0s)\n",
"(2017-07-01 08:41:02)>>>>>> MEAN\n",
"(2017-07-01 08:41:02)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:41:02)>>>>>> *fit* Filter columns (filter_to_component) (1947107, 1)\n",
"(2017-07-01 08:41:02)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:41:02)>>>>>> *transform* Filter columns (filter_to_component) (1947107, 1)\n",
"(2017-07-01 08:41:02)<<<<<< --- (0.0s)\n",
"(2017-07-01 08:41:02)<<<< --- (219.0s)\n",
"(2017-07-01 08:41:02)<< --- (17478.0s)\n",
"(2017-07-01 08:41:02)>> [('blood pressure diastolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-01 08:41:02)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure diastolic']\n",
"(2017-07-01 08:41:02)>>>>>> BLOOD PRESSURE DIASTOLIC: 1/1\n",
"(2017-07-01 08:41:08)>>>>>>>> Convert to dask - (4766507, 42)\n",
"(2017-07-01 08:41:10)<<<<<<<< --- (2.0s)\n",
"(2017-07-01 08:41:10)>>>>>>>> Join to big DF\n",
"(2017-07-01 08:41:10)<<<<<<<< --- (0.0s)\n",
"(2017-07-01 08:41:10)<<<<<< --- (8.0s)\n",
"(2017-07-01 08:41:10)>>>>>> Dask DF back to pandas\n",
"(2017-07-01 08:41:13)<<<<<< --- (3.0s)\n",
"(2017-07-01 08:41:13)>>>>>> SORT Joined DF\n",
"(2017-07-01 08:41:16)<<<<<< --- (3.0s)\n",
"(2017-07-01 08:41:16)<<<< --- (14.0s)\n",
"(2017-07-01 08:41:17)>>>> *fit* Filter columns (DataNeedsFilter) (4766507, 42)\n",
"(2017-07-01 08:41:18)<<<< --- (1.0s)\n",
"(2017-07-01 08:41:18)>>>> *transform* Filter columns (DataNeedsFilter) (4766507, 42)\n",
"(2017-07-01 08:41:18)<<<< --- (0.0s)\n",
"(2017-07-01 08:41:18)>>>> Segment df (4766507, 42)\n",
"(2017-07-01 08:41:18)>>>>>> Get Segments\n",
"(2017-07-01 08:42:53)<<<<<< --- (95.0s)\n",
"(2017-07-01 08:42:53)>>>>>> Apply n=992332 Segments to df.shape = (4766507, 42)\n",
"(2017-07-02 12:51:33)<<<<<< --- (101320.0s)\n",
"(2017-07-02 12:51:33)<<<< --- (101415.0s)\n",
"(2017-07-02 12:51:33)>>>> *fit* Filter columns (remove_small_columns) (4984612, 42)\n",
"(2017-07-02 12:51:34)<<<< --- (1.0s)\n",
"(2017-07-02 12:51:34)>>>> *transform* Filter columns (remove_small_columns) (4984612, 42)\n",
"(2017-07-02 12:51:34)<<<< --- (0.0s)\n",
"(2017-07-02 12:51:34)>>>> *fit* Filter columns (record_threshold) (4984612, 40)\n",
"(2017-07-02 12:51:39)<<<< --- (5.0s)\n",
"(2017-07-02 12:51:39)>>>> *transform* Filter columns (record_threshold) (4984612, 40)\n",
"(2017-07-02 12:51:39)<<<< --- (0.0s)\n",
"(2017-07-02 12:51:39)>>>> *fit* Filter columns (filter_var_type) (4984612, 40)\n",
"(2017-07-02 12:51:39)<<<< --- (0.0s)\n",
"(2017-07-02 12:51:39)>>>> *transform* Filter columns (filter_var_type) (4984612, 40)\n",
"(2017-07-02 12:51:39)<<<< --- (0.0s)\n",
"(2017-07-02 12:51:39)>>>> FIT Combine like columns (4984612, 14)\n",
"(2017-07-02 12:51:40)>>>>>> ('blood pressure diastolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-02 12:51:40)<<<<<< --- (0.0s)\n",
"(2017-07-02 12:51:40)>>>>>> ('blood pressure diastolic', 'unknown', 'qn', 'cc/min')\n",
"(2017-07-02 12:51:40)<<<<<< --- (0.0s)\n",
"(2017-07-02 12:51:40)<<<< --- (1.0s)\n",
"(2017-07-02 12:51:40)>>>> TRANSFORM Combine like columns (4984612, 14)\n",
"(2017-07-02 12:51:40)>>>>>> ('blood pressure diastolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-02 12:53:07)<<<<<< --- (87.0s)\n",
"(2017-07-02 12:53:07)>>>>>> ('blood pressure diastolic', 'unknown', 'qn', 'cc/min')\n",
"(2017-07-02 12:54:01)<<<<<< --- (54.0s)\n",
"(2017-07-02 12:54:01)<<<< --- (141.0s)\n",
"(2017-07-02 12:54:01)>>>> fit_transform features on DF (4984612, 2)\n",
"(2017-07-02 12:54:01)>>>>>> STD\n",
"(2017-07-02 12:54:01)<<<<<< --- (0.0s)\n",
"(2017-07-02 12:54:01)>>>>>> *fit* Filter columns (filter_to_component) (4984612, 2)\n",
"(2017-07-02 12:54:01)<<<<<< --- (0.0s)\n",
"(2017-07-02 12:54:01)>>>>>> *transform* Filter columns (filter_to_component) (4984612, 2)\n",
"(2017-07-02 12:54:02)<<<<<< --- (1.0s)\n",
"(2017-07-02 12:54:02)>>>>>> COUNT\n",
"(2017-07-02 12:54:02)<<<<<< --- (0.0s)\n",
"(2017-07-02 12:54:02)>>>>>> *fit* Filter columns (filter_to_component) (4984612, 2)\n",
"(2017-07-02 12:54:02)<<<<<< --- (0.0s)\n",
"(2017-07-02 12:54:02)>>>>>> *transform* Filter columns (filter_to_component) (4984612, 2)\n",
"(2017-07-02 12:58:54)<<<<<< --- (292.0s)\n",
"(2017-07-02 12:58:54)>>>>>> LAST\n",
"(2017-07-02 12:58:54)<<<<<< --- (0.0s)\n",
"(2017-07-02 12:58:54)>>>>>> *fit* Filter columns (filter_to_component) (4984612, 2)\n",
"(2017-07-02 12:58:54)<<<<<< --- (0.0s)\n",
"(2017-07-02 12:58:54)>>>>>> *transform* Filter columns (filter_to_component) (4984612, 2)\n",
"(2017-07-02 13:16:20)<<<<<< --- (1046.0s)\n",
"(2017-07-02 13:16:20)>>>>>> MEAN\n",
"(2017-07-02 13:16:20)<<<<<< --- (0.0s)\n",
"(2017-07-02 13:16:20)>>>>>> *fit* Filter columns (filter_to_component) (4984612, 2)\n",
"(2017-07-02 13:16:20)<<<<<< --- (0.0s)\n",
"(2017-07-02 13:16:20)>>>>>> *transform* Filter columns (filter_to_component) (4984612, 2)\n",
"(2017-07-02 13:16:25)<<<<<< --- (5.0s)\n",
"(2017-07-02 13:16:25)<<<< --- (1344.0s)\n",
"(2017-07-02 13:16:26)<< --- (102924.0s)\n",
"(2017-07-02 13:16:26)>> [('blood pressure systolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-02 13:16:26)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure systolic']\n",
"(2017-07-02 13:16:26)>>>>>> BLOOD PRESSURE SYSTOLIC: 1/1\n",
"(2017-07-02 13:16:41)>>>>>>>> Convert to dask - (4764591, 40)\n",
"(2017-07-02 13:16:44)<<<<<<<< --- (3.0s)\n",
"(2017-07-02 13:16:44)>>>>>>>> Join to big DF\n",
"(2017-07-02 13:16:44)<<<<<<<< --- (0.0s)\n",
"(2017-07-02 13:16:44)<<<<<< --- (18.0s)\n",
"(2017-07-02 13:16:44)>>>>>> Dask DF back to pandas\n",
"(2017-07-02 13:16:46)<<<<<< --- (2.0s)\n",
"(2017-07-02 13:16:46)>>>>>> SORT Joined DF\n",
"(2017-07-02 13:16:49)<<<<<< --- (3.0s)\n",
"(2017-07-02 13:16:49)<<<< --- (23.0s)\n",
"(2017-07-02 13:16:50)>>>> *fit* Filter columns (DataNeedsFilter) (4764591, 40)\n",
"(2017-07-02 13:16:51)<<<< --- (1.0s)\n",
"(2017-07-02 13:16:51)>>>> *transform* Filter columns (DataNeedsFilter) (4764591, 40)\n",
"(2017-07-02 13:16:51)<<<< --- (0.0s)\n",
"(2017-07-02 13:16:51)>>>> Segment df (4764591, 40)\n",
"(2017-07-02 13:16:51)>>>>>> Get Segments\n",
"(2017-07-02 13:18:24)<<<<<< --- (93.0s)\n",
"(2017-07-02 13:18:24)>>>>>> Apply n=992353 Segments to df.shape = (4764591, 40)\n",
"(2017-07-03 17:16:10)<<<<<< --- (100666.0s)\n",
"(2017-07-03 17:16:10)<<<< --- (100759.0s)\n",
"(2017-07-03 17:16:10)>>>> *fit* Filter columns (remove_small_columns) (4983025, 40)\n",
"(2017-07-03 17:16:10)<<<< --- (0.0s)\n",
"(2017-07-03 17:16:10)>>>> *transform* Filter columns (remove_small_columns) (4983025, 40)\n",
"(2017-07-03 17:16:11)<<<< --- (1.0s)\n",
"(2017-07-03 17:16:11)>>>> *fit* Filter columns (record_threshold) (4983025, 39)\n",
"(2017-07-03 17:16:15)<<<< --- (4.0s)\n",
"(2017-07-03 17:16:15)>>>> *transform* Filter columns (record_threshold) (4983025, 39)\n",
"(2017-07-03 17:16:16)<<<< --- (1.0s)\n",
"(2017-07-03 17:16:16)>>>> *fit* Filter columns (filter_var_type) (4983025, 39)\n",
"(2017-07-03 17:16:16)<<<< --- (0.0s)\n",
"(2017-07-03 17:16:16)>>>> *transform* Filter columns (filter_var_type) (4983025, 39)\n",
"(2017-07-03 17:16:16)<<<< --- (0.0s)\n",
"(2017-07-03 17:16:16)>>>> FIT Combine like columns (4983025, 13)\n",
"(2017-07-03 17:16:16)>>>>>> ('blood pressure systolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-03 17:16:16)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:16:16)>>>>>> ('blood pressure systolic', 'unknown', 'qn', 'cc/min')\n",
"(2017-07-03 17:16:17)<<<<<< --- (1.0s)\n",
"(2017-07-03 17:16:17)<<<< --- (1.0s)\n",
"(2017-07-03 17:16:17)>>>> TRANSFORM Combine like columns (4983025, 13)\n",
"(2017-07-03 17:16:17)>>>>>> ('blood pressure systolic', 'unknown', 'qn', 'cc/min')\n",
"(2017-07-03 17:17:20)<<<<<< --- (63.0s)\n",
"(2017-07-03 17:17:20)>>>>>> ('blood pressure systolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-03 17:18:36)<<<<<< --- (76.0s)\n",
"(2017-07-03 17:18:36)<<<< --- (139.0s)\n",
"(2017-07-03 17:18:36)>>>> fit_transform features on DF (4983025, 2)\n",
"(2017-07-03 17:18:36)>>>>>> STD\n",
"(2017-07-03 17:18:36)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:18:36)>>>>>> *fit* Filter columns (filter_to_component) (4983025, 2)\n",
"(2017-07-03 17:18:36)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:18:36)>>>>>> *transform* Filter columns (filter_to_component) (4983025, 2)\n",
"(2017-07-03 17:18:37)<<<<<< --- (1.0s)\n",
"(2017-07-03 17:18:37)>>>>>> COUNT\n",
"(2017-07-03 17:18:37)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:18:37)>>>>>> *fit* Filter columns (filter_to_component) (4983025, 2)\n",
"(2017-07-03 17:18:37)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:18:37)>>>>>> *transform* Filter columns (filter_to_component) (4983025, 2)\n",
"(2017-07-03 17:23:27)<<<<<< --- (290.0s)\n",
"(2017-07-03 17:23:27)>>>>>> LAST\n",
"(2017-07-03 17:23:27)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:23:27)>>>>>> *fit* Filter columns (filter_to_component) (4983025, 2)\n",
"(2017-07-03 17:23:27)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:23:27)>>>>>> *transform* Filter columns (filter_to_component) (4983025, 2)\n",
"(2017-07-03 17:40:53)<<<<<< --- (1046.0s)\n",
"(2017-07-03 17:40:53)>>>>>> MEAN\n",
"(2017-07-03 17:40:53)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:40:53)>>>>>> *fit* Filter columns (filter_to_component) (4983025, 2)\n",
"(2017-07-03 17:40:53)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:40:53)>>>>>> *transform* Filter columns (filter_to_component) (4983025, 2)\n",
"(2017-07-03 17:40:54)<<<<<< --- (1.0s)\n",
"(2017-07-03 17:40:54)<<<< --- (1338.0s)\n",
"(2017-07-03 17:40:56)<< --- (102270.0s)\n",
"(2017-07-03 17:40:56) --- (222672.0s)\n",
"(2017-07-03 17:40:56) Featurizing...\n",
"(2017-07-03 17:40:56)>> [('blood pressure mean', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-03 17:40:56)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure mean']\n",
"(2017-07-03 17:40:56)>>>>>> BLOOD PRESSURE MEAN: 1/1\n",
"(2017-07-03 17:40:58)>>>>>>>> Convert to dask - (277779, 3)\n",
"(2017-07-03 17:40:58)<<<<<<<< --- (0.0s)\n",
"(2017-07-03 17:40:58)>>>>>>>> Join to big DF\n",
"(2017-07-03 17:40:58)<<<<<<<< --- (0.0s)\n",
"(2017-07-03 17:40:58)<<<<<< --- (2.0s)\n",
"(2017-07-03 17:40:58)>>>>>> Dask DF back to pandas\n",
"(2017-07-03 17:40:58)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:40:58)>>>>>> SORT Joined DF\n",
"(2017-07-03 17:40:59)<<<<<< --- (1.0s)\n",
"(2017-07-03 17:40:59)<<<< --- (3.0s)\n",
"(2017-07-03 17:40:59)>>>> *fit* Filter columns (DataNeedsFilter) (277779, 3)\n",
"(2017-07-03 17:40:59)<<<< --- (0.0s)\n",
"(2017-07-03 17:40:59)>>>> *transform* Filter columns (DataNeedsFilter) (277779, 3)\n",
"(2017-07-03 17:40:59)<<<< --- (0.0s)\n",
"(2017-07-03 17:40:59)>>>> Segment df (277779, 3)\n",
"(2017-07-03 17:40:59)>>>>>> Get Segments\n",
"(2017-07-03 17:41:03)<<<<<< --- (4.0s)\n",
"(2017-07-03 17:41:03)>>>>>> Apply n=39175 Segments to df.shape = (277779, 3)\n",
"(2017-07-03 17:47:49)<<<<<< --- (406.0s)\n",
"(2017-07-03 17:47:49)<<<< --- (410.0s)\n",
"(2017-07-03 17:47:49)>>>> *transform* Filter columns (remove_small_columns) (281282, 3)\n",
"(2017-07-03 17:47:49)<<<< --- (0.0s)\n",
"(2017-07-03 17:47:49)>>>> *transform* Filter columns (record_threshold) (281282, 3)\n",
"(2017-07-03 17:47:49)<<<< --- (0.0s)\n",
"(2017-07-03 17:47:49)>>>> *transform* Filter columns (filter_var_type) (281282, 3)\n",
"(2017-07-03 17:47:49)<<<< --- (0.0s)\n",
"(2017-07-03 17:47:49)>>>> TRANSFORM Combine like columns (281282, 3)\n",
"(2017-07-03 17:47:49)>>>>>> ('blood pressure mean', 'known', 'qn', 'mmHg')\n",
"(2017-07-03 17:47:56)<<<<<< --- (7.0s)\n",
"(2017-07-03 17:47:56)<<<< --- (7.0s)\n",
"(2017-07-03 17:47:56)>>>> transform features on DF (281282, 1)\n",
"(2017-07-03 17:47:56)>>>>>> STD\n",
"(2017-07-03 17:47:56)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:47:56)>>>>>> *transform* Filter columns (filter_to_component) (281282, 1)\n",
"(2017-07-03 17:47:56)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:47:56)>>>>>> COUNT\n",
"(2017-07-03 17:47:56)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:47:56)>>>>>> *transform* Filter columns (filter_to_component) (281282, 1)\n",
"(2017-07-03 17:48:02)<<<<<< --- (6.0s)\n",
"(2017-07-03 17:48:02)>>>>>> LAST\n",
"(2017-07-03 17:48:02)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:48:02)>>>>>> *transform* Filter columns (filter_to_component) (281282, 1)\n",
"(2017-07-03 17:48:25)<<<<<< --- (23.0s)\n",
"(2017-07-03 17:48:25)>>>>>> MEAN\n",
"(2017-07-03 17:48:25)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:48:25)>>>>>> *transform* Filter columns (filter_to_component) (281282, 1)\n",
"(2017-07-03 17:48:25)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:48:25)<<<< --- (29.0s)\n",
"(2017-07-03 17:48:25)<< --- (449.0s)\n",
"(2017-07-03 17:48:25)>> [('blood pressure diastolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-03 17:48:25)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure diastolic']\n",
"(2017-07-03 17:48:25)>>>>>> BLOOD PRESSURE DIASTOLIC: 1/1\n",
"(2017-07-03 17:48:40)>>>>>>>> Convert to dask - (629046, 42)\n",
"(2017-07-03 17:48:40)<<<<<<<< --- (0.0s)\n",
"(2017-07-03 17:48:40)>>>>>>>> Join to big DF\n",
"(2017-07-03 17:48:40)<<<<<<<< --- (0.0s)\n",
"(2017-07-03 17:48:40)<<<<<< --- (15.0s)\n",
"(2017-07-03 17:48:40)>>>>>> Dask DF back to pandas\n",
"(2017-07-03 17:48:40)<<<<<< --- (0.0s)\n",
"(2017-07-03 17:48:40)>>>>>> SORT Joined DF\n",
"(2017-07-03 17:48:41)<<<<<< --- (1.0s)\n",
"(2017-07-03 17:48:41)<<<< --- (16.0s)\n",
"(2017-07-03 17:48:41)>>>> *fit* Filter columns (DataNeedsFilter) (629046, 42)\n",
"(2017-07-03 17:48:41)<<<< --- (0.0s)\n",
"(2017-07-03 17:48:41)>>>> *transform* Filter columns (DataNeedsFilter) (629046, 42)\n",
"(2017-07-03 17:48:41)<<<< --- (0.0s)\n",
"(2017-07-03 17:48:41)>>>> Segment df (629046, 42)\n",
"(2017-07-03 17:48:41)>>>>>> Get Segments\n",
"(2017-07-03 17:48:53)<<<<<< --- (12.0s)\n",
"(2017-07-03 17:48:53)>>>>>> Apply n=130645 Segments to df.shape = (629046, 42)\n",
"(2017-07-03 18:24:38)<<<<<< --- (2145.0s)\n",
"(2017-07-03 18:24:38)<<<< --- (2157.0s)\n",
"(2017-07-03 18:24:38)>>>> *transform* Filter columns (remove_small_columns) (659876, 42)\n",
"(2017-07-03 18:24:38)<<<< --- (0.0s)\n",
"(2017-07-03 18:24:38)>>>> *transform* Filter columns (record_threshold) (659876, 40)\n",
"(2017-07-03 18:24:38)<<<< --- (0.0s)\n",
"(2017-07-03 18:24:38)>>>> *transform* Filter columns (filter_var_type) (659876, 40)\n",
"(2017-07-03 18:24:38)<<<< --- (0.0s)\n",
"(2017-07-03 18:24:38)>>>> TRANSFORM Combine like columns (659876, 14)\n",
"(2017-07-03 18:24:38)>>>>>> ('blood pressure diastolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-03 18:24:53)<<<<<< --- (15.0s)\n",
"(2017-07-03 18:24:53)>>>>>> ('blood pressure diastolic', 'unknown', 'qn', 'cc/min')\n",
"(2017-07-03 18:25:00)<<<<<< --- (7.0s)\n",
"(2017-07-03 18:25:00)<<<< --- (22.0s)\n",
"(2017-07-03 18:25:00)>>>> transform features on DF (659876, 2)\n",
"(2017-07-03 18:25:00)>>>>>> STD\n",
"(2017-07-03 18:25:00)<<<<<< --- (0.0s)\n",
"(2017-07-03 18:25:00)>>>>>> *transform* Filter columns (filter_to_component) (659876, 2)\n",
"(2017-07-03 18:25:01)<<<<<< --- (1.0s)\n",
"(2017-07-03 18:25:01)>>>>>> COUNT\n",
"(2017-07-03 18:25:01)<<<<<< --- (0.0s)\n",
"(2017-07-03 18:25:01)>>>>>> *transform* Filter columns (filter_to_component) (659876, 2)\n",
"(2017-07-03 18:25:39)<<<<<< --- (38.0s)\n",
"(2017-07-03 18:25:39)>>>>>> LAST\n",
"(2017-07-03 18:25:39)<<<<<< --- (0.0s)\n",
"(2017-07-03 18:25:39)>>>>>> *transform* Filter columns (filter_to_component) (659876, 2)\n",
"(2017-07-03 18:27:56)<<<<<< --- (137.0s)\n",
"(2017-07-03 18:27:56)>>>>>> MEAN\n",
"(2017-07-03 18:27:56)<<<<<< --- (0.0s)\n",
"(2017-07-03 18:27:56)>>>>>> *transform* Filter columns (filter_to_component) (659876, 2)\n",
"(2017-07-03 18:27:56)<<<<<< --- (0.0s)\n",
"(2017-07-03 18:27:56)<<<< --- (176.0s)\n",
"(2017-07-03 18:27:56)<< --- (2371.0s)\n",
"(2017-07-03 18:27:56)>> [('blood pressure systolic', 'all')] - STD, COUNT, LAST, MEAN\n",
"(2017-07-03 18:27:56)>>>> DASK OPEN & JOIN n=1 components: ['blood pressure systolic']\n",
"(2017-07-03 18:27:56)>>>>>> BLOOD PRESSURE SYSTOLIC: 1/1\n",
"(2017-07-03 18:28:01)>>>>>>>> Convert to dask - (628962, 40)\n",
"(2017-07-03 18:28:01)<<<<<<<< --- (0.0s)\n",
"(2017-07-03 18:28:01)>>>>>>>> Join to big DF\n",
"(2017-07-03 18:28:01)<<<<<<<< --- (0.0s)\n",
"(2017-07-03 18:28:01)<<<<<< --- (5.0s)\n",
"(2017-07-03 18:28:01)>>>>>> Dask DF back to pandas\n",
"(2017-07-03 18:28:02)<<<<<< --- (1.0s)\n",
"(2017-07-03 18:28:02)>>>>>> SORT Joined DF\n",
"(2017-07-03 18:28:02)<<<<<< --- (0.0s)\n",
"(2017-07-03 18:28:02)<<<< --- (6.0s)\n",
"(2017-07-03 18:28:02)>>>> *fit* Filter columns (DataNeedsFilter) (628962, 40)\n",
"(2017-07-03 18:28:02)<<<< --- (0.0s)\n",
"(2017-07-03 18:28:02)>>>> *transform* Filter columns (DataNeedsFilter) (628962, 40)\n",
"(2017-07-03 18:28:02)<<<< --- (0.0s)\n",
"(2017-07-03 18:28:02)>>>> Segment df (628962, 40)\n",
"(2017-07-03 18:28:02)>>>>>> Get Segments\n",
"(2017-07-03 18:28:14)<<<<<< --- (12.0s)\n",
"(2017-07-03 18:28:14)>>>>>> Apply n=130685 Segments to df.shape = (628962, 40)\n",
"(2017-07-03 19:03:24)<<<<<< --- (2110.0s)\n",
"(2017-07-03 19:03:24)<<<< --- (2122.0s)\n",
"(2017-07-03 19:03:24)>>>> *transform* Filter columns (remove_small_columns) (659841, 40)\n",
"(2017-07-03 19:03:24)<<<< --- (0.0s)\n",
"(2017-07-03 19:03:24)>>>> *transform* Filter columns (record_threshold) (659841, 39)\n",
"(2017-07-03 19:03:24)<<<< --- (0.0s)\n",
"(2017-07-03 19:03:24)>>>> *transform* Filter columns (filter_var_type) (659841, 39)\n",
"(2017-07-03 19:03:24)<<<< --- (0.0s)\n",
"(2017-07-03 19:03:24)>>>> TRANSFORM Combine like columns (659841, 13)\n",
"(2017-07-03 19:03:24)>>>>>> ('blood pressure systolic', 'unknown', 'qn', 'cc/min')\n",
"(2017-07-03 19:03:35)<<<<<< --- (11.0s)\n",
"(2017-07-03 19:03:35)>>>>>> ('blood pressure systolic', 'known', 'qn', 'mmHg')\n",
"(2017-07-03 19:03:47)<<<<<< --- (12.0s)\n",
"(2017-07-03 19:03:47)<<<< --- (23.0s)\n",
"(2017-07-03 19:03:47)>>>> transform features on DF (659841, 2)\n",
"(2017-07-03 19:03:47)>>>>>> STD\n",
"(2017-07-03 19:03:47)<<<<<< --- (0.0s)\n",
"(2017-07-03 19:03:47)>>>>>> *transform* Filter columns (filter_to_component) (659841, 2)\n",
"(2017-07-03 19:03:47)<<<<<< --- (0.0s)\n",
"(2017-07-03 19:03:47)>>>>>> COUNT\n",
"(2017-07-03 19:03:47)<<<<<< --- (0.0s)\n",
"(2017-07-03 19:03:47)>>>>>> *transform* Filter columns (filter_to_component) (659841, 2)\n",
"(2017-07-03 19:04:25)<<<<<< --- (38.0s)\n",
"(2017-07-03 19:04:25)>>>>>> LAST\n",
"(2017-07-03 19:04:25)<<<<<< --- (0.0s)\n",
"(2017-07-03 19:04:25)>>>>>> *transform* Filter columns (filter_to_component) (659841, 2)\n",
"(2017-07-03 19:06:42)<<<<<< --- (137.0s)\n",
"(2017-07-03 19:06:42)>>>>>> MEAN\n",
"(2017-07-03 19:06:42)<<<<<< --- (0.0s)\n",
"(2017-07-03 19:06:42)>>>>>> *transform* Filter columns (filter_to_component) (659841, 2)\n",
"(2017-07-03 19:06:42)<<<<<< --- (0.0s)\n",
"(2017-07-03 19:06:42)<<<< --- (175.0s)\n",
"(2017-07-03 19:06:42)<< --- (2326.0s)\n",
"(2017-07-03 19:06:42) --- (5146.0s)\n",
"(992482, 20)\n",
"(130695, 20)\n"
]
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th colspan=\"2\" halign=\"left\">STD</th>\n",
" <th colspan=\"2\" halign=\"left\">COUNT</th>\n",
" <th colspan=\"2\" halign=\"left\">LAST</th>\n",
" <th colspan=\"2\" halign=\"left\">MEAN</th>\n",
" <th colspan=\"2\" halign=\"left\">STD</th>\n",
" <th colspan=\"2\" halign=\"left\">COUNT</th>\n",
" <th colspan=\"2\" halign=\"left\">LAST</th>\n",
" <th colspan=\"2\" halign=\"left\">MEAN</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure diastolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure diastolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure diastolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure diastolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure systolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure systolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure systolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure systolic</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>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</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>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>qn</th>\n",
" <th>qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" </tr>\n",
" <tr>\n",
" <th>id</th>\n",
" <th>seg_id</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=\"5\" valign=\"top\">100001</th>\n",
" <th>0</th>\n",
" <td>17.577041</td>\n",
" <td>7.0</td>\n",
" <td>110.0</td>\n",
" <td>99.571429</td>\n",
" <td>13.597969</td>\n",
" <td>0.0</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" <td>88.0</td>\n",
" <td>38.610183</td>\n",
" <td>81.285714</td>\n",
" <td>38.565997</td>\n",
" <td>30.917710</td>\n",
" <td>0.0</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" <td>179.0</td>\n",
" <td>68.499851</td>\n",
" <td>157.714286</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>5.958188</td>\n",
" <td>6.0</td>\n",
" <td>118.0</td>\n",
" <td>117.500000</td>\n",
" <td>5.645057</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>94.0</td>\n",
" <td>38.610183</td>\n",
" <td>94.666667</td>\n",
" <td>38.565997</td>\n",
" <td>5.879342</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>187.0</td>\n",
" <td>68.499851</td>\n",
" <td>186.833333</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>4.438468</td>\n",
" <td>5.0</td>\n",
" <td>116.0</td>\n",
" <td>120.800000</td>\n",
" <td>5.830952</td>\n",
" <td>0.0</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" <td>92.0</td>\n",
" <td>38.610183</td>\n",
" <td>98.000000</td>\n",
" <td>38.565997</td>\n",
" <td>6.055301</td>\n",
" <td>0.0</td>\n",
" <td>7.0</td>\n",
" <td>0.0</td>\n",
" <td>195.0</td>\n",
" <td>68.499851</td>\n",
" <td>193.000000</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>9.914636</td>\n",
" <td>5.0</td>\n",
" <td>122.0</td>\n",
" <td>109.600000</td>\n",
" <td>7.496666</td>\n",
" <td>0.0</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>96.0</td>\n",
" <td>38.610183</td>\n",
" <td>89.800000</td>\n",
" <td>38.565997</td>\n",
" <td>20.501219</td>\n",
" <td>0.0</td>\n",
" <td>5.0</td>\n",
" <td>0.0</td>\n",
" <td>199.0</td>\n",
" <td>68.499851</td>\n",
" <td>174.400000</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>22.268064</td>\n",
" <td>6.0</td>\n",
" <td>97.0</td>\n",
" <td>108.333333</td>\n",
" <td>17.747300</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>85.0</td>\n",
" <td>38.610183</td>\n",
" <td>87.833333</td>\n",
" <td>38.565997</td>\n",
" <td>33.319164</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>151.0</td>\n",
" <td>68.499851</td>\n",
" <td>174.833333</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature STD COUNT LAST \\\n",
"component blood pressure mean blood pressure mean blood pressure mean \n",
"status known known known \n",
"variable_type qn qn qn \n",
"units mmHg mmHg mmHg \n",
"description all all all \n",
"id seg_id \n",
"100001 0 17.577041 7.0 110.0 \n",
" 1 5.958188 6.0 118.0 \n",
" 2 4.438468 5.0 116.0 \n",
" 3 9.914636 5.0 122.0 \n",
" 4 22.268064 6.0 97.0 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure mean blood pressure diastolic \n",
"status known known unknown \n",
"variable_type qn qn qn \n",
"units mmHg mmHg cc/min \n",
"description all all all \n",
"id seg_id \n",
"100001 0 99.571429 13.597969 0.0 \n",
" 1 117.500000 5.645057 0.0 \n",
" 2 120.800000 5.830952 0.0 \n",
" 3 109.600000 7.496666 0.0 \n",
" 4 108.333333 17.747300 0.0 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure diastolic blood pressure diastolic \n",
"status known unknown known \n",
"variable_type qn qn qn \n",
"units mmHg cc/min mmHg \n",
"description all all all \n",
"id seg_id \n",
"100001 0 7.0 0.0 88.0 \n",
" 1 6.0 0.0 94.0 \n",
" 2 7.0 0.0 92.0 \n",
" 3 5.0 0.0 96.0 \n",
" 4 6.0 0.0 85.0 \n",
"\n",
"feature MEAN \\\n",
"component blood pressure diastolic \n",
"status unknown known unknown \n",
"variable_type qn qn qn \n",
"units cc/min mmHg cc/min \n",
"description all all all \n",
"id seg_id \n",
"100001 0 38.610183 81.285714 38.565997 \n",
" 1 38.610183 94.666667 38.565997 \n",
" 2 38.610183 98.000000 38.565997 \n",
" 3 38.610183 89.800000 38.565997 \n",
" 4 38.610183 87.833333 38.565997 \n",
"\n",
"feature STD COUNT \\\n",
"component blood pressure systolic blood pressure systolic \n",
"status known unknown known unknown \n",
"variable_type qn qn qn qn \n",
"units mmHg cc/min mmHg cc/min \n",
"description all all all all \n",
"id seg_id \n",
"100001 0 30.917710 0.0 7.0 0.0 \n",
" 1 5.879342 0.0 6.0 0.0 \n",
" 2 6.055301 0.0 7.0 0.0 \n",
" 3 20.501219 0.0 5.0 0.0 \n",
" 4 33.319164 0.0 6.0 0.0 \n",
"\n",
"feature LAST MEAN \\\n",
"component blood pressure systolic blood pressure systolic \n",
"status known unknown known \n",
"variable_type qn qn qn \n",
"units mmHg cc/min mmHg \n",
"description all all all \n",
"id seg_id \n",
"100001 0 179.0 68.499851 157.714286 \n",
" 1 187.0 68.499851 186.833333 \n",
" 2 195.0 68.499851 193.000000 \n",
" 3 199.0 68.499851 174.400000 \n",
" 4 151.0 68.499851 174.833333 \n",
"\n",
"feature \n",
"component \n",
"status unknown \n",
"variable_type qn \n",
"units cc/min \n",
"description all \n",
"id seg_id \n",
"100001 0 68.501586 \n",
" 1 68.501586 \n",
" 2 68.501586 \n",
" 3 68.501586 \n",
" 4 68.501586 "
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<div>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr>\n",
" <th></th>\n",
" <th>feature</th>\n",
" <th>STD</th>\n",
" <th>COUNT</th>\n",
" <th>LAST</th>\n",
" <th>MEAN</th>\n",
" <th colspan=\"2\" halign=\"left\">STD</th>\n",
" <th colspan=\"2\" halign=\"left\">COUNT</th>\n",
" <th colspan=\"2\" halign=\"left\">LAST</th>\n",
" <th colspan=\"2\" halign=\"left\">MEAN</th>\n",
" <th colspan=\"2\" halign=\"left\">STD</th>\n",
" <th colspan=\"2\" halign=\"left\">COUNT</th>\n",
" <th colspan=\"2\" halign=\"left\">LAST</th>\n",
" <th colspan=\"2\" halign=\"left\">MEAN</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>component</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th>blood pressure mean</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure diastolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure diastolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure diastolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure diastolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure systolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure systolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure systolic</th>\n",
" <th colspan=\"2\" halign=\"left\">blood pressure systolic</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>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</th>\n",
" <th>known</th>\n",
" <th>unknown</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>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>qn</th>\n",
" <th>qn</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>units</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" <th>mmHg</th>\n",
" <th>cc/min</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th>description</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" <th>all</th>\n",
" </tr>\n",
" <tr>\n",
" <th>id</th>\n",
" <th>seg_id</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=\"5\" valign=\"top\">100028</th>\n",
" <th>0</th>\n",
" <td>7.250287</td>\n",
" <td>6.0</td>\n",
" <td>53.0</td>\n",
" <td>49.166667</td>\n",
" <td>5.009990</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>41.0</td>\n",
" <td>38.610183</td>\n",
" <td>38.500000</td>\n",
" <td>38.565997</td>\n",
" <td>13.452385</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>92.0</td>\n",
" <td>68.499851</td>\n",
" <td>85.166667</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>11.644741</td>\n",
" <td>6.0</td>\n",
" <td>33.0</td>\n",
" <td>55.000000</td>\n",
" <td>11.373947</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>23.0</td>\n",
" <td>38.610183</td>\n",
" <td>43.833333</td>\n",
" <td>38.565997</td>\n",
" <td>6.615638</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>87.0</td>\n",
" <td>68.499851</td>\n",
" <td>92.833333</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>14.459138</td>\n",
" <td>6.0</td>\n",
" <td>89.0</td>\n",
" <td>65.666667</td>\n",
" <td>18.192489</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>85.0</td>\n",
" <td>38.610183</td>\n",
" <td>54.833333</td>\n",
" <td>38.565997</td>\n",
" <td>14.148027</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>101.0</td>\n",
" <td>68.499851</td>\n",
" <td>100.166667</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>6.968979</td>\n",
" <td>6.0</td>\n",
" <td>48.0</td>\n",
" <td>57.166667</td>\n",
" <td>9.973298</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>32.0</td>\n",
" <td>38.610183</td>\n",
" <td>42.333333</td>\n",
" <td>38.565997</td>\n",
" <td>10.206207</td>\n",
" <td>0.0</td>\n",
" <td>6.0</td>\n",
" <td>0.0</td>\n",
" <td>95.0</td>\n",
" <td>68.499851</td>\n",
" <td>104.833333</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>9.086882</td>\n",
" <td>8.0</td>\n",
" <td>65.0</td>\n",
" <td>62.000000</td>\n",
" <td>11.795883</td>\n",
" <td>0.0</td>\n",
" <td>8.0</td>\n",
" <td>0.0</td>\n",
" <td>49.0</td>\n",
" <td>38.610183</td>\n",
" <td>51.000000</td>\n",
" <td>38.565997</td>\n",
" <td>9.852483</td>\n",
" <td>0.0</td>\n",
" <td>8.0</td>\n",
" <td>0.0</td>\n",
" <td>113.0</td>\n",
" <td>68.499851</td>\n",
" <td>101.750000</td>\n",
" <td>68.501586</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"feature STD COUNT LAST \\\n",
"component blood pressure mean blood pressure mean blood pressure mean \n",
"status known known known \n",
"variable_type qn qn qn \n",
"units mmHg mmHg mmHg \n",
"description all all all \n",
"id seg_id \n",
"100028 0 7.250287 6.0 53.0 \n",
" 1 11.644741 6.0 33.0 \n",
" 2 14.459138 6.0 89.0 \n",
" 3 6.968979 6.0 48.0 \n",
" 4 9.086882 8.0 65.0 \n",
"\n",
"feature MEAN STD \\\n",
"component blood pressure mean blood pressure diastolic \n",
"status known known unknown \n",
"variable_type qn qn qn \n",
"units mmHg mmHg cc/min \n",
"description all all all \n",
"id seg_id \n",
"100028 0 49.166667 5.009990 0.0 \n",
" 1 55.000000 11.373947 0.0 \n",
" 2 65.666667 18.192489 0.0 \n",
" 3 57.166667 9.973298 0.0 \n",
" 4 62.000000 11.795883 0.0 \n",
"\n",
"feature COUNT LAST \\\n",
"component blood pressure diastolic blood pressure diastolic \n",
"status known unknown known \n",
"variable_type qn qn qn \n",
"units mmHg cc/min mmHg \n",
"description all all all \n",
"id seg_id \n",
"100028 0 6.0 0.0 41.0 \n",
" 1 6.0 0.0 23.0 \n",
" 2 6.0 0.0 85.0 \n",
" 3 6.0 0.0 32.0 \n",
" 4 8.0 0.0 49.0 \n",
"\n",
"feature MEAN \\\n",
"component blood pressure diastolic \n",
"status unknown known unknown \n",
"variable_type qn qn qn \n",
"units cc/min mmHg cc/min \n",
"description all all all \n",
"id seg_id \n",
"100028 0 38.610183 38.500000 38.565997 \n",
" 1 38.610183 43.833333 38.565997 \n",
" 2 38.610183 54.833333 38.565997 \n",
" 3 38.610183 42.333333 38.565997 \n",
" 4 38.610183 51.000000 38.565997 \n",
"\n",
"feature STD COUNT \\\n",
"component blood pressure systolic blood pressure systolic \n",
"status known unknown known unknown \n",
"variable_type qn qn qn qn \n",
"units mmHg cc/min mmHg cc/min \n",
"description all all all all \n",
"id seg_id \n",
"100028 0 13.452385 0.0 6.0 0.0 \n",
" 1 6.615638 0.0 6.0 0.0 \n",
" 2 14.148027 0.0 6.0 0.0 \n",
" 3 10.206207 0.0 6.0 0.0 \n",
" 4 9.852483 0.0 8.0 0.0 \n",
"\n",
"feature LAST MEAN \\\n",
"component blood pressure systolic blood pressure systolic \n",
"status known unknown known \n",
"variable_type qn qn qn \n",
"units mmHg cc/min mmHg \n",
"description all all all \n",
"id seg_id \n",
"100028 0 92.0 68.499851 85.166667 \n",
" 1 87.0 68.499851 92.833333 \n",
" 2 101.0 68.499851 100.166667 \n",
" 3 95.0 68.499851 104.833333 \n",
" 4 113.0 68.499851 101.750000 \n",
"\n",
"feature \n",
"component \n",
"status unknown \n",
"variable_type qn \n",
"units cc/min \n",
"description all \n",
"id seg_id \n",
"100028 0 68.501586 \n",
" 1 68.501586 \n",
" 2 68.501586 \n",
" 3 68.501586 \n",
" 4 68.501586 "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"labelizer = None #We need to make this labelizer\n",
"featurizer = bp_featurizer\n",
"featurizer.loader.segmenter = load_and_segment.periodic(n_hrs=6)\n",
"\n",
"X_train3 = featurizer.fit_transform(X=train_ids)\n",
"X_validate3 = featurizer.transform(X=validate_ids)\n",
"\n",
"\n",
"print X_train3.shape\n",
"print X_validate3.shape\n",
"display(X_train3.head())\n",
"display(X_validate3.head())\n",
"\n",
"# print X_train1.shape,y_train1.shape\n",
"# print X_validate1.shape,y_validate1.shape\n",
"# display(X_train1.head())\n",
"# display(y_train1.head())\n",
"# display(X_validate1.head())\n",
"# display(y_validate1.head())"
]
}
],
"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
}