Datasets
Models
Downloads: 1
2116 lines (2115 with data), 90.0 kB
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
" <script type=\"text/javascript\">\n",
" window.PlotlyConfig = {MathJaxConfig: 'local'};\n",
" if (window.MathJax) {MathJax.Hub.Config({SVG: {font: \"STIX-Web\"}});}\n",
" if (typeof require !== 'undefined') {\n",
" require.undef(\"plotly\");\n",
" requirejs.config({\n",
" paths: {\n",
" 'plotly': ['https://cdn.plot.ly/plotly-latest.min']\n",
" }\n",
" });\n",
" require(['plotly'], function(Plotly) {\n",
" window._Plotly = Plotly;\n",
" });\n",
" }\n",
" </script>\n",
" "
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Import libraries\n",
"import numpy as np\n",
"import pandas as pd\n",
"import matplotlib.pyplot as plt\n",
"import getpass\n",
"import pdvega\n",
"import plotly.graph_objs as go\n",
"\n",
"from plotly.offline import iplot, init_notebook_mode\n",
"import plotly.io as pio\n",
"from plotly.graph_objs import *\n",
"\n",
"# for configuring connection \n",
"from configobj import ConfigObj\n",
"import os\n",
"\n",
"%matplotlib inline\n",
"\n",
"\n",
"import os\n",
"\n",
"\n",
"from sklearn import linear_model\n",
"from sklearn import metrics\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"#configure the notebook for use in offline mode\n",
"init_notebook_mode(connected=True)"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Unnamed: 0</th>\n",
" <th>hospitalid</th>\n",
" <th>sodium</th>\n",
" <th>electivesurgery</th>\n",
" <th>vent</th>\n",
" <th>dialysis</th>\n",
" <th>gcs</th>\n",
" <th>urine</th>\n",
" <th>wbc</th>\n",
" <th>temperature</th>\n",
" <th>...</th>\n",
" <th>m11_True</th>\n",
" <th>m12_True</th>\n",
" <th>m13_True</th>\n",
" <th>m14_True</th>\n",
" <th>m15_True</th>\n",
" <th>m16_True</th>\n",
" <th>m17_True</th>\n",
" <th>m18_True</th>\n",
" <th>m19_True</th>\n",
" <th>m20_True</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>59.0</td>\n",
" <td>139.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>15.0</td>\n",
" <td>-1.0</td>\n",
" <td>14.7</td>\n",
" <td>36.1</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>1</td>\n",
" <td>73.0</td>\n",
" <td>134.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>13.0</td>\n",
" <td>-1.0</td>\n",
" <td>14.1</td>\n",
" <td>39.3</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>2</td>\n",
" <td>73.0</td>\n",
" <td>-1.0</td>\n",
" <td>1.0</td>\n",
" <td>1.0</td>\n",
" <td>0.0</td>\n",
" <td>15.0</td>\n",
" <td>-1.0</td>\n",
" <td>8.0</td>\n",
" <td>34.8</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>3</td>\n",
" <td>63.0</td>\n",
" <td>137.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>15.0</td>\n",
" <td>-1.0</td>\n",
" <td>10.9</td>\n",
" <td>36.6</td>\n",
" <td>...</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>4</td>\n",
" <td>63.0</td>\n",
" <td>135.0</td>\n",
" <td>-1.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>15.0</td>\n",
" <td>-1.0</td>\n",
" <td>5.9</td>\n",
" <td>35.0</td>\n",
" <td>...</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" <td>1</td>\n",
" <td>0</td>\n",
" <td>0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 85 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 hospitalid sodium electivesurgery vent dialysis gcs \\\n",
"0 0 59.0 139.0 -1.0 0.0 0.0 15.0 \n",
"1 1 73.0 134.0 -1.0 0.0 0.0 13.0 \n",
"2 2 73.0 -1.0 1.0 1.0 0.0 15.0 \n",
"3 3 63.0 137.0 -1.0 0.0 0.0 15.0 \n",
"4 4 63.0 135.0 -1.0 0.0 0.0 15.0 \n",
"\n",
" urine wbc temperature ... m11_True m12_True m13_True m14_True \\\n",
"0 -1.0 14.7 36.1 ... 1 0 0 1 \n",
"1 -1.0 14.1 39.3 ... 1 0 0 1 \n",
"2 -1.0 8.0 34.8 ... 0 0 1 0 \n",
"3 -1.0 10.9 36.6 ... 1 0 1 1 \n",
"4 -1.0 5.9 35.0 ... 0 0 1 0 \n",
"\n",
" m15_True m16_True m17_True m18_True m19_True m20_True \n",
"0 1 0 0 0 1 0 \n",
"1 1 0 0 0 1 0 \n",
"2 0 1 0 1 0 0 \n",
"3 1 0 0 1 1 0 \n",
"4 0 0 0 1 0 0 \n",
"\n",
"[5 rows x 85 columns]"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df= pd.read_csv(\"analysis.csv\")\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(95148, 85)"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [],
"source": [
"del df['hospitalid']\n",
"\n",
"df = df.drop(df.columns[[0]], axis=1)\n",
"df = df.drop(df.columns[[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82]], axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"sodium 18244\n",
"electivesurgery 74997\n",
"vent 0\n",
"dialysis 0\n",
"gcs 1728\n",
"urine 45829\n",
"wbc 22141\n",
"temperature 4139\n",
"respiratoryrate 582\n",
"heartrate 188\n",
"meanbp 263\n",
"creatinine 18332\n",
"ph 73474\n",
"hematocrit 20021\n",
"albumin 58143\n",
"pao2 73474\n",
"pco2 73474\n",
"bun 18774\n",
"glucose 10909\n",
"bilirubin 60797\n",
"fio2 73474\n",
"age 3356\n",
"thrombolytics 0\n",
"aids 0\n",
"hepaticfailure 0\n",
"lymphoma 0\n",
"metastaticcancer 0\n",
"leukemia 0\n",
"immunosuppression 0\n",
"cirrhosis 0\n",
" ... \n",
"admitsource_1.0 0\n",
"admitsource_2.0 0\n",
"admitsource_3.0 0\n",
"admitsource_4.0 0\n",
"admitsource_5.0 0\n",
"admitsource_6.0 0\n",
"admitsource_7.0 0\n",
"admitsource_8.0 0\n",
"diaggroup_ARF 0\n",
"diaggroup_Asthma-Emphys 0\n",
"diaggroup_CABG 0\n",
"diaggroup_CHF 0\n",
"diaggroup_CVA 0\n",
"diaggroup_CVOther 0\n",
"diaggroup_CardiacArrest 0\n",
"diaggroup_ChestPainUnknown 0\n",
"diaggroup_Coma 0\n",
"diaggroup_DKA 0\n",
"diaggroup_GIBleed 0\n",
"diaggroup_GIObstruction 0\n",
"diaggroup_Neuro 0\n",
"diaggroup_Other 0\n",
"diaggroup_Overdose 0\n",
"diaggroup_PNA 0\n",
"diaggroup_RespMedOther 0\n",
"diaggroup_Sepsis 0\n",
"diaggroup_Trauma 0\n",
"diaggroup_ValveDz 0\n",
"gender_Male 0\n",
"gender_Other 0\n",
"Length: 63, dtype: int64"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"missing_values_count = df.isnull().sum()\n",
"#df.replace('-1.0', np.nan)\n",
"df = df.replace({-1.0:np.nan, -1.0:np.nan})\n",
"df.head()\n",
"missing_values_count = df.isnull().sum()\n",
"missing_values_count"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**We moved all the pre-processing including splitting>imputation>Standardization to the CV iterations**"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"cols_to_norm=['gcs', 'urine', 'wbc', 'sodium',\n",
" 'temperature', 'respiratoryrate', 'heartrate', 'meanbp', 'creatinine',\n",
" 'ph', 'hematocrit', 'albumin', 'pao2', 'pco2', 'bun', 'glucose',\n",
" 'bilirubin', 'fio2', 'age', 'offset']\n",
"\n",
"X=df.drop('destcopy', 1)\n",
"y=df['destcopy']\n",
"df_cols = list(X) #fancy impute removes column names."
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Index(['sodium', 'electivesurgery', 'vent', 'dialysis', 'gcs', 'urine', 'wbc',\n",
" 'temperature', 'respiratoryrate', 'heartrate', 'meanbp', 'creatinine',\n",
" 'ph', 'hematocrit', 'albumin', 'pao2', 'pco2', 'bun', 'glucose',\n",
" 'bilirubin', 'fio2', 'age', 'thrombolytics', 'aids', 'hepaticfailure',\n",
" 'lymphoma', 'metastaticcancer', 'leukemia', 'immunosuppression',\n",
" 'cirrhosis', 'readmit', 'offset', 'destcopy', 'admitsource_1.0',\n",
" 'admitsource_2.0', 'admitsource_3.0', 'admitsource_4.0',\n",
" 'admitsource_5.0', 'admitsource_6.0', 'admitsource_7.0',\n",
" 'admitsource_8.0', 'diaggroup_ARF', 'diaggroup_Asthma-Emphys',\n",
" 'diaggroup_CABG', 'diaggroup_CHF', 'diaggroup_CVA', 'diaggroup_CVOther',\n",
" 'diaggroup_CardiacArrest', 'diaggroup_ChestPainUnknown',\n",
" 'diaggroup_Coma', 'diaggroup_DKA', 'diaggroup_GIBleed',\n",
" 'diaggroup_GIObstruction', 'diaggroup_Neuro', 'diaggroup_Other',\n",
" 'diaggroup_Overdose', 'diaggroup_PNA', 'diaggroup_RespMedOther',\n",
" 'diaggroup_Sepsis', 'diaggroup_Trauma', 'diaggroup_ValveDz',\n",
" 'gender_Male', 'gender_Other'],\n",
" dtype='object')"
]
},
"execution_count": 7,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.columns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**XGB**"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 1:\n",
"Accuracy: 0.7585916973200211\n",
"f-score: 0.7585916973200211\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.54 0.48 0.97 0.51 0.68 0.45 642\n",
" 2 0.79 0.96 0.37 0.87 0.59 0.37 6776\n",
" 3 0.58 0.24 0.96 0.34 0.48 0.21 1716\n",
" 4 0.31 0.01 1.00 0.02 0.10 0.01 381\n",
"\n",
"avg / total 0.72 0.76 0.54 0.71 0.56 0.33 9515\n",
"\n",
"[[ 310 239 89 4]\n",
" [ 102 6493 176 5]\n",
" [ 137 1168 411 0]\n",
" [ 21 325 31 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 2:\n",
"Accuracy: 0.7777193904361535\n",
"f-score: 0.7777193904361535\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.60 0.49 0.96 0.54 0.69 0.45 974\n",
" 2 0.87 0.90 0.48 0.88 0.66 0.45 7520\n",
" 3 0.20 0.27 0.92 0.23 0.49 0.23 697\n",
" 4 0.09 0.01 1.00 0.01 0.08 0.01 324\n",
"\n",
"avg / total 0.76 0.78 0.58 0.77 0.63 0.42 9515\n",
"\n",
"[[ 477 347 149 1]\n",
" [ 199 6735 567 19]\n",
" [ 99 412 186 0]\n",
" [ 17 272 33 2]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 3:\n",
"Accuracy: 0.7480819758276406\n",
"f-score: 0.7480819758276406\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.67 0.56 0.96 0.61 0.73 0.52 1247\n",
" 2 0.80 0.92 0.49 0.86 0.67 0.47 6585\n",
" 3 0.40 0.24 0.93 0.30 0.47 0.21 1462\n",
" 4 0.08 0.00 1.00 0.01 0.07 0.00 221\n",
"\n",
"avg / total 0.70 0.75 0.63 0.72 0.63 0.42 9515\n",
"\n",
"[[ 701 380 162 4]\n",
" [ 194 6066 317 8]\n",
" [ 143 969 350 0]\n",
" [ 16 158 46 1]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 4:\n",
"Accuracy: 0.7147661586967945\n",
"f-score: 0.7147661586967945\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.67 0.51 0.97 0.58 0.70 0.47 1129\n",
" 2 0.74 0.95 0.35 0.83 0.57 0.35 6348\n",
" 3 0.35 0.15 0.96 0.21 0.38 0.14 1285\n",
" 4 0.36 0.01 1.00 0.01 0.07 0.00 753\n",
"\n",
"avg / total 0.65 0.71 0.56 0.66 0.52 0.31 9515\n",
"\n",
"[[ 573 433 122 1]\n",
" [ 118 6026 202 2]\n",
" [ 124 959 198 4]\n",
" [ 38 672 39 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 5:\n",
"Accuracy: 0.7389385181292696\n",
"f-score: 0.7389385181292696\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.64 0.50 0.96 0.56 0.69 0.46 1085\n",
" 2 0.77 0.95 0.41 0.85 0.63 0.41 6437\n",
" 3 0.50 0.21 0.96 0.29 0.45 0.18 1657\n",
" 4 0.14 0.01 1.00 0.02 0.09 0.01 336\n",
"\n",
"avg / total 0.69 0.74 0.59 0.69 0.58 0.36 9515\n",
"\n",
"[[ 538 391 148 8]\n",
" [ 123 6145 164 5]\n",
" [ 154 1152 345 6]\n",
" [ 26 272 35 3]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 6:\n",
"Accuracy: 0.7128744088281661\n",
"f-score: 0.7128744088281661\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.56 0.50 0.96 0.53 0.70 0.46 785\n",
" 2 0.74 0.96 0.36 0.84 0.59 0.37 6224\n",
" 3 0.57 0.19 0.96 0.29 0.43 0.17 2026\n",
" 4 0.26 0.02 1.00 0.03 0.13 0.01 480\n",
"\n",
"avg / total 0.66 0.71 0.57 0.65 0.54 0.32 9515\n",
"\n",
"[[ 395 284 100 6]\n",
" [ 86 5994 137 7]\n",
" [ 193 1437 386 10]\n",
" [ 35 382 55 8]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 7:\n",
"Accuracy: 0.7487125591171834\n",
"f-score: 0.7487125591171834\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.63 0.45 0.97 0.53 0.67 0.42 853\n",
" 2 0.79 0.95 0.42 0.86 0.63 0.42 6684\n",
" 3 0.44 0.33 0.94 0.37 0.55 0.29 1209\n",
" 4 0.64 0.01 1.00 0.02 0.10 0.01 769\n",
"\n",
"avg / total 0.72 0.75 0.58 0.70 0.58 0.37 9515\n",
"\n",
"[[ 388 305 159 1]\n",
" [ 114 6336 231 3]\n",
" [ 68 748 393 0]\n",
" [ 45 600 117 7]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 8:\n",
"Accuracy: 0.7407251707829743\n",
"f-score: 0.7407251707829743\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.65 0.42 0.98 0.51 0.64 0.39 933\n",
" 2 0.78 0.95 0.38 0.85 0.60 0.38 6645\n",
" 3 0.46 0.22 0.94 0.30 0.46 0.19 1675\n",
" 4 0.13 0.02 1.00 0.03 0.12 0.01 262\n",
"\n",
"avg / total 0.69 0.74 0.55 0.70 0.56 0.33 9515\n",
"\n",
"[[ 395 364 168 6]\n",
" [ 107 6280 245 13]\n",
" [ 91 1208 369 7]\n",
" [ 12 219 27 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 9:\n",
"Accuracy: 0.7276644944292622\n",
"f-score: 0.7276644944292622\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.69 0.47 0.97 0.56 0.68 0.44 1031\n",
" 2 0.76 0.96 0.36 0.85 0.59 0.37 6399\n",
" 3 0.44 0.19 0.95 0.26 0.42 0.17 1495\n",
" 4 0.18 0.01 1.00 0.01 0.08 0.01 589\n",
"\n",
"avg / total 0.66 0.73 0.56 0.67 0.54 0.32 9514\n",
"\n",
"[[ 489 388 150 4]\n",
" [ 88 6150 156 5]\n",
" [ 99 1107 280 9]\n",
" [ 31 497 57 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 10:\n",
"Accuracy: 0.7419592179945343\n",
"f-score: 0.7419592179945343\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.66 0.53 0.96 0.59 0.71 0.49 1157\n",
" 2 0.78 0.95 0.41 0.86 0.62 0.40 6600\n",
" 3 0.34 0.17 0.95 0.23 0.40 0.15 1156\n",
" 4 0.14 0.01 1.00 0.01 0.08 0.01 601\n",
"\n",
"avg / total 0.67 0.74 0.58 0.69 0.57 0.36 9514\n",
"\n",
"[[ 614 393 143 7]\n",
" [ 144 6245 198 13]\n",
" [ 125 831 196 4]\n",
" [ 45 509 43 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 1:\n",
"Accuracy: 0.7585916973200211\n",
"f-score: 0.7585916973200211\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.54 0.48 0.97 0.51 0.68 0.45 642\n",
" 2 0.79 0.96 0.37 0.87 0.59 0.37 6776\n",
" 3 0.58 0.24 0.96 0.34 0.48 0.21 1716\n",
" 4 0.31 0.01 1.00 0.02 0.10 0.01 381\n",
"\n",
"avg / total 0.72 0.76 0.54 0.71 0.56 0.33 9515\n",
"\n",
"[[ 310 239 89 4]\n",
" [ 102 6493 176 5]\n",
" [ 137 1168 411 0]\n",
" [ 21 325 31 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 2:\n",
"Accuracy: 0.7777193904361535\n",
"f-score: 0.7777193904361535\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.60 0.49 0.96 0.54 0.69 0.45 974\n",
" 2 0.87 0.90 0.48 0.88 0.66 0.45 7520\n",
" 3 0.20 0.27 0.92 0.23 0.49 0.23 697\n",
" 4 0.09 0.01 1.00 0.01 0.08 0.01 324\n",
"\n",
"avg / total 0.76 0.78 0.58 0.77 0.63 0.42 9515\n",
"\n",
"[[ 477 347 149 1]\n",
" [ 199 6735 567 19]\n",
" [ 99 412 186 0]\n",
" [ 17 272 33 2]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 3:\n",
"Accuracy: 0.7480819758276406\n",
"f-score: 0.7480819758276406\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.67 0.56 0.96 0.61 0.73 0.52 1247\n",
" 2 0.80 0.92 0.49 0.86 0.67 0.47 6585\n",
" 3 0.40 0.24 0.93 0.30 0.47 0.21 1462\n",
" 4 0.08 0.00 1.00 0.01 0.07 0.00 221\n",
"\n",
"avg / total 0.70 0.75 0.63 0.72 0.63 0.42 9515\n",
"\n",
"[[ 701 380 162 4]\n",
" [ 194 6066 317 8]\n",
" [ 143 969 350 0]\n",
" [ 16 158 46 1]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 4:\n",
"Accuracy: 0.7147661586967945\n",
"f-score: 0.7147661586967945\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.67 0.51 0.97 0.58 0.70 0.47 1129\n",
" 2 0.74 0.95 0.35 0.83 0.57 0.35 6348\n",
" 3 0.35 0.15 0.96 0.21 0.38 0.14 1285\n",
" 4 0.36 0.01 1.00 0.01 0.07 0.00 753\n",
"\n",
"avg / total 0.65 0.71 0.56 0.66 0.52 0.31 9515\n",
"\n",
"[[ 573 433 122 1]\n",
" [ 118 6026 202 2]\n",
" [ 124 959 198 4]\n",
" [ 38 672 39 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 5:\n",
"Accuracy: 0.7389385181292696\n",
"f-score: 0.7389385181292696\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.64 0.50 0.96 0.56 0.69 0.46 1085\n",
" 2 0.77 0.95 0.41 0.85 0.63 0.41 6437\n",
" 3 0.50 0.21 0.96 0.29 0.45 0.18 1657\n",
" 4 0.14 0.01 1.00 0.02 0.09 0.01 336\n",
"\n",
"avg / total 0.69 0.74 0.59 0.69 0.58 0.36 9515\n",
"\n",
"[[ 538 391 148 8]\n",
" [ 123 6145 164 5]\n",
" [ 154 1152 345 6]\n",
" [ 26 272 35 3]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 6:\n",
"Accuracy: 0.7128744088281661\n",
"f-score: 0.7128744088281661\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.56 0.50 0.96 0.53 0.70 0.46 785\n",
" 2 0.74 0.96 0.36 0.84 0.59 0.37 6224\n",
" 3 0.57 0.19 0.96 0.29 0.43 0.17 2026\n",
" 4 0.26 0.02 1.00 0.03 0.13 0.01 480\n",
"\n",
"avg / total 0.66 0.71 0.57 0.65 0.54 0.32 9515\n",
"\n",
"[[ 395 284 100 6]\n",
" [ 86 5994 137 7]\n",
" [ 193 1437 386 10]\n",
" [ 35 382 55 8]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 7:\n",
"Accuracy: 0.7487125591171834\n",
"f-score: 0.7487125591171834\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.63 0.45 0.97 0.53 0.67 0.42 853\n",
" 2 0.79 0.95 0.42 0.86 0.63 0.42 6684\n",
" 3 0.44 0.33 0.94 0.37 0.55 0.29 1209\n",
" 4 0.64 0.01 1.00 0.02 0.10 0.01 769\n",
"\n",
"avg / total 0.72 0.75 0.58 0.70 0.58 0.37 9515\n",
"\n",
"[[ 388 305 159 1]\n",
" [ 114 6336 231 3]\n",
" [ 68 748 393 0]\n",
" [ 45 600 117 7]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 8:\n",
"Accuracy: 0.7407251707829743\n",
"f-score: 0.7407251707829743\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.65 0.42 0.98 0.51 0.64 0.39 933\n",
" 2 0.78 0.95 0.38 0.85 0.60 0.38 6645\n",
" 3 0.46 0.22 0.94 0.30 0.46 0.19 1675\n",
" 4 0.13 0.02 1.00 0.03 0.12 0.01 262\n",
"\n",
"avg / total 0.69 0.74 0.55 0.70 0.56 0.33 9515\n",
"\n",
"[[ 395 364 168 6]\n",
" [ 107 6280 245 13]\n",
" [ 91 1208 369 7]\n",
" [ 12 219 27 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 9:\n",
"Accuracy: 0.7276644944292622\n",
"f-score: 0.7276644944292622\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.69 0.47 0.97 0.56 0.68 0.44 1031\n",
" 2 0.76 0.96 0.36 0.85 0.59 0.37 6399\n",
" 3 0.44 0.19 0.95 0.26 0.42 0.17 1495\n",
" 4 0.18 0.01 1.00 0.01 0.08 0.01 589\n",
"\n",
"avg / total 0.66 0.73 0.56 0.67 0.54 0.32 9514\n",
"\n",
"[[ 489 388 150 4]\n",
" [ 88 6150 156 5]\n",
" [ 99 1107 280 9]\n",
" [ 31 497 57 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 10:\n",
"Accuracy: 0.7419592179945343\n",
"f-score: 0.7419592179945343\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.66 0.53 0.96 0.59 0.71 0.49 1157\n",
" 2 0.78 0.95 0.41 0.86 0.62 0.40 6600\n",
" 3 0.34 0.17 0.95 0.23 0.40 0.15 1156\n",
" 4 0.14 0.01 1.00 0.01 0.08 0.01 601\n",
"\n",
"avg / total 0.67 0.74 0.58 0.69 0.57 0.36 9514\n",
"\n",
"[[ 614 393 143 7]\n",
" [ 144 6245 198 13]\n",
" [ 125 831 196 4]\n",
" [ 45 509 43 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 1:\n",
"Accuracy: 0.7585916973200211\n",
"f-score: 0.7585916973200211\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.54 0.48 0.97 0.51 0.68 0.45 642\n",
" 2 0.79 0.96 0.37 0.87 0.59 0.37 6776\n",
" 3 0.58 0.24 0.96 0.34 0.48 0.21 1716\n",
" 4 0.31 0.01 1.00 0.02 0.10 0.01 381\n",
"\n",
"avg / total 0.72 0.76 0.54 0.71 0.56 0.33 9515\n",
"\n",
"[[ 310 239 89 4]\n",
" [ 102 6493 176 5]\n",
" [ 137 1168 411 0]\n",
" [ 21 325 31 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 2:\n",
"Accuracy: 0.7777193904361535\n",
"f-score: 0.7777193904361535\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.60 0.49 0.96 0.54 0.69 0.45 974\n",
" 2 0.87 0.90 0.48 0.88 0.66 0.45 7520\n",
" 3 0.20 0.27 0.92 0.23 0.49 0.23 697\n",
" 4 0.09 0.01 1.00 0.01 0.08 0.01 324\n",
"\n",
"avg / total 0.76 0.78 0.58 0.77 0.63 0.42 9515\n",
"\n",
"[[ 477 347 149 1]\n",
" [ 199 6735 567 19]\n",
" [ 99 412 186 0]\n",
" [ 17 272 33 2]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 3:\n",
"Accuracy: 0.7480819758276406\n",
"f-score: 0.7480819758276406\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.67 0.56 0.96 0.61 0.73 0.52 1247\n",
" 2 0.80 0.92 0.49 0.86 0.67 0.47 6585\n",
" 3 0.40 0.24 0.93 0.30 0.47 0.21 1462\n",
" 4 0.08 0.00 1.00 0.01 0.07 0.00 221\n",
"\n",
"avg / total 0.70 0.75 0.63 0.72 0.63 0.42 9515\n",
"\n",
"[[ 701 380 162 4]\n",
" [ 194 6066 317 8]\n",
" [ 143 969 350 0]\n",
" [ 16 158 46 1]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 4:\n",
"Accuracy: 0.7147661586967945\n",
"f-score: 0.7147661586967945\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.67 0.51 0.97 0.58 0.70 0.47 1129\n",
" 2 0.74 0.95 0.35 0.83 0.57 0.35 6348\n",
" 3 0.35 0.15 0.96 0.21 0.38 0.14 1285\n",
" 4 0.36 0.01 1.00 0.01 0.07 0.00 753\n",
"\n",
"avg / total 0.65 0.71 0.56 0.66 0.52 0.31 9515\n",
"\n",
"[[ 573 433 122 1]\n",
" [ 118 6026 202 2]\n",
" [ 124 959 198 4]\n",
" [ 38 672 39 4]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"For fold 5:\n",
"Accuracy: 0.7389385181292696\n",
"f-score: 0.7389385181292696\n",
" pre rec spe f1 geo iba sup\n",
"\n",
" 1 0.64 0.50 0.96 0.56 0.69 0.46 1085\n",
" 2 0.77 0.95 0.41 0.85 0.63 0.41 6437\n",
" 3 0.50 0.21 0.96 0.29 0.45 0.18 1657\n",
" 4 0.14 0.01 1.00 0.02 0.09 0.01 336\n",
"\n",
"avg / total 0.69 0.74 0.59 0.69 0.58 0.36 9515\n",
"\n",
"[[ 538 391 148 8]\n",
" [ 123 6145 164 5]\n",
" [ 154 1152 345 6]\n",
" [ 26 272 35 3]]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:42: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/ipykernel_launcher.py:43: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n",
"/anaconda3/lib/python3.7/site-packages/pandas/core/indexing.py:543: SettingWithCopyWarning:\n",
"\n",
"\n",
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
"\n"
]
}
],
"source": [
"%matplotlib inline\n",
"from sklearn.model_selection import KFold\n",
"from sklearn import preprocessing\n",
"from imblearn.over_sampling import SMOTE\n",
"from sklearn.metrics import f1_score\n",
"from imblearn.metrics import classification_report_imbalanced\n",
"# explicitly require this experimental feature\n",
"\n",
"from yellowbrick.classifier import ROCAUC\n",
"from sklearn.linear_model import LogisticRegression\n",
"from numpy import loadtxt\n",
"import os\n",
"os.environ['KMP_DUPLICATE_LIB_OK']='True'\n",
"from xgboost import XGBClassifier\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.metrics import accuracy_score\n",
"import io \n",
"\n",
"\n",
"classes=['Death','Home','Nursing Home','Rehabilitation']\n",
"\n",
"\n",
"kf = KFold(n_splits=10)\n",
"\n",
"\n",
"for i in range (1,11):\n",
"\n",
" for fold, (train_index, test_index) in enumerate(kf.split(X), 1):\n",
" X_train = X.iloc[train_index]\n",
" y_train = y.iloc[train_index] # Based on your code, you might need a ravel call here, but I would look into how you're generating your y\n",
" X_test = X.iloc[test_index]\n",
" y_test = y.iloc[test_index] # See comment on ravel and y_train\n",
"\n",
"\n",
" #------------------------------IMPUTE Training Set------------------------------------\n",
"\n",
" \n",
"\n",
" #------------------------------Standardize Testing Set------------------------------------\n",
"\n",
" std_scale = preprocessing.StandardScaler().fit(X_train[cols_to_norm])\n",
" X_train[cols_to_norm] = std_scale.transform(X_train[cols_to_norm])\n",
" X_test[cols_to_norm] = std_scale.transform(X_test[cols_to_norm])\n",
" #------------------------------------------------------------------------------------------\n",
"\n",
" # Hyperparameters are optimized using hyperopt\n",
"\n",
" #sm = SMOTE()\n",
" #X_train_oversampled, y_train_oversampled = sm.fit_sample(X_train, y_train)\n",
" model = XGBClassifier(max_depth=8, gamma=0.063, colsample_bytree=0.71)\n",
" model.fit(X_train, y_train) \n",
" y_pred = model.predict(X_test)\n",
" visualizer = ROCAUC(model, classes=classes)\n",
" visualizer.fit(X_train, y_train) # Fit the training data to the visualizer\n",
" visualizer.score(X_test, y_test) # Evaluate the model on the test data\n",
" visualizer.poof(\"XGB_Unbalanced_{}_{}.pdf\".format(i, fold), clear_figure=True) \n",
" print(f'For fold {fold}:')\n",
" print(f'Accuracy: {model.score(X_test, y_test)}')\n",
" f1=f1_score(y_test, y_pred, average='micro')\n",
" print(f'f-score: {f1}')\n",
" print(classification_report_imbalanced(y_test, y_pred))\n",
" K= classification_report_imbalanced(y_test, y_pred)\n",
" df = pd.read_fwf(io.StringIO(K))\n",
" df.loc[\"1\":\"1\",\"pre\":\"sup\"].to_csv(\"XGB-U-D.csv\" , sep=',', encoding='utf-8', doublequote=False, index=False, mode=\"a\", header=False)\n",
" df.loc[\"2\":\"2\",\"pre\":\"sup\"].to_csv(\"XGB-U-H.csv\" , sep=',', encoding='utf-8', doublequote=False, index=False, mode=\"a\", header=False)\n",
" df.loc[\"3\":\"3\",\"pre\":\"sup\"].to_csv(\"XGB-U-N.csv\" , sep=',', encoding='utf-8', doublequote=False, index=False, mode=\"a\", header=False)\n",
" df.loc[\"4\":\"4\",\"pre\":\"sup\"].to_csv(\"XGB-U-R.csv\" , sep=',', encoding='utf-8', doublequote=False, index=False, mode=\"a\", header=False)\n",
" df.iloc[6:7,:].to_csv(\"XGB-U-avg.csv\" , sep=',', encoding='utf-8', doublequote=False, index=False, mode=\"a\", header=False)\n",
" from sklearn.metrics import confusion_matrix\n",
" print(confusion_matrix(y_test, y_pred))\n",
"\n",
" #\n",
"\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.3"
}
},
"nbformat": 4,
"nbformat_minor": 4
}