Datasets
Models
Downloads: 1
Diff of
/Feature Importance for 15 subjects.ipynb
[000000]
..
[d8f241]
Switch to side-by-side view
--- a +++ b/Feature Importance for 15 subjects.ipynb @@ -0,0 +1,1802 @@ +{ + "cells": [ + { + "cell_type": "code", + "execution_count": 26, + "metadata": {}, + "outputs": [], + "source": [ + "import pandas as pd\n", + "from sklearn.ensemble import RandomForestClassifier \n", + "from sklearn.model_selection import train_test_split\n", + "from sklearn.metrics import classification_report" + ] + }, + { + "cell_type": "code", + "execution_count": 3, + "metadata": {}, + "outputs": [], + "source": [ + "df = pd.read_csv(\"master_data.csv\")" + ] + }, + { + "cell_type": "code", + "execution_count": 4, + "metadata": {}, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "<class 'pandas.core.frame.DataFrame'>\n", + "RangeIndex: 59125500 entries, 0 to 59125499\n", + "Data columns (total 10 columns):\n", + "target int64\n", + "subject int64\n", + "chest_ACC_x float64\n", + "chest_ACC_y float64\n", + "chest_ACC_z float64\n", + "chest_ECG float64\n", + "chest_EMG float64\n", + "chest_EDA float64\n", + "chest_Temp float64\n", + "chest_Resp float64\n", + "dtypes: float64(8), int64(2)\n", + "memory usage: 4.4 GB\n" + ] + } + ], + "source": [ + "df.info()" + ] + }, + { + "cell_type": "code", + "execution_count": 5, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "6 4825799\n", + "3 4400200\n", + "4 4393200\n", + "5 4250400\n", + "2 4165000\n", + "17 4022201\n", + "16 3826200\n", + "13 3794000\n", + "14 3763200\n", + "10 3740100\n", + "8 3719799\n", + "15 3576300\n", + "7 3563700\n", + "11 3556701\n", + "9 3528700\n", + "Name: subject, dtype: int64" + ] + }, + "execution_count": 5, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "df['subject'].value_counts()" + ] + }, + { + "cell_type": "code", + "execution_count": 6, + "metadata": {}, + "outputs": [], + "source": [ + "feature_importances_list = []" + ] + }, + { + "cell_type": "code", + "execution_count": 27, + "metadata": { + "scrolled": false + }, + "outputs": [ + { + "name": "stdout", + "output_type": "stream", + "text": [ + "6\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9981689328947815\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 1.00 1.00 902929\n", + " 1 1.00 1.00 1.00 271725\n", + " 2 1.00 1.00 1.00 150059\n", + " 3 1.00 0.99 1.00 86152\n", + " 4 1.00 1.00 1.00 181649\n", + "\n", + " accuracy 1.00 1592514\n", + " macro avg 1.00 1.00 1.00 1592514\n", + "weighted avg 1.00 1.00 1.00 1592514\n", + "\n", + "11\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9880933312430988\n", + " precision recall f1-score support\n", + "\n", + " 0 0.99 0.99 0.99 475759\n", + " 1 1.00 1.00 1.00 272833\n", + " 2 1.00 0.99 1.00 157039\n", + " 3 0.98 0.98 0.98 85341\n", + " 4 0.98 0.98 0.98 182740\n", + "\n", + " accuracy 0.99 1173712\n", + " macro avg 0.99 0.99 0.99 1173712\n", + "weighted avg 0.99 0.99 0.99 1173712\n", + "\n", + "14\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9876434948979592\n", + " precision recall f1-score support\n", + "\n", + " 0 0.99 0.99 0.99 543791\n", + " 1 1.00 1.00 1.00 272719\n", + " 2 0.98 0.98 0.98 155792\n", + " 3 0.98 0.97 0.97 85954\n", + " 4 0.99 0.99 0.99 183600\n", + "\n", + " accuracy 0.99 1241856\n", + " macro avg 0.99 0.98 0.98 1241856\n", + "weighted avg 0.99 0.99 0.99 1241856\n", + "\n", + "8\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.99311057779255\n", + " precision recall f1-score support\n", + "\n", + " 0 0.99 0.99 0.99 533239\n", + " 1 1.00 1.00 1.00 270630\n", + " 2 0.99 0.99 0.99 155051\n", + " 3 0.99 0.99 0.99 85349\n", + " 4 0.99 0.99 0.99 183265\n", + "\n", + " accuracy 0.99 1227534\n", + " macro avg 0.99 0.99 0.99 1227534\n", + "weighted avg 0.99 0.99 0.99 1227534\n", + "\n", + "15\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9935704668529096\n", + " precision recall f1-score support\n", + "\n", + " 0 0.99 0.99 0.99 481153\n", + " 1 1.00 1.00 1.00 271736\n", + " 2 1.00 1.00 1.00 158288\n", + " 3 0.99 0.99 0.99 85801\n", + " 4 1.00 1.00 1.00 183201\n", + "\n", + " accuracy 0.99 1180179\n", + " macro avg 0.99 0.99 0.99 1180179\n", + "weighted avg 0.99 0.99 0.99 1180179\n", + "\n", + "9\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9942205516496332\n", + " precision recall f1-score support\n", + "\n", + " 0 0.99 0.99 0.99 473496\n", + " 1 1.00 1.00 1.00 272821\n", + " 2 1.00 1.00 1.00 148833\n", + " 3 0.98 0.99 0.99 86077\n", + " 4 0.99 0.99 0.99 183244\n", + "\n", + " accuracy 0.99 1164471\n", + " macro avg 0.99 0.99 0.99 1164471\n", + "weighted avg 0.99 0.99 0.99 1164471\n", + "\n", + "10\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9887095872497332\n", + " precision recall f1-score support\n", + "\n", + " 0 0.99 0.98 0.99 524557\n", + " 1 1.00 1.00 1.00 272919\n", + " 2 0.99 0.99 0.99 167514\n", + " 3 0.97 0.98 0.98 85925\n", + " 4 0.98 0.99 0.99 183318\n", + "\n", + " accuracy 0.99 1234233\n", + " macro avg 0.99 0.99 0.99 1234233\n", + "weighted avg 0.99 0.99 0.99 1234233\n", + "\n", + "2\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9942551566080978\n", + " precision recall f1-score support\n", + "\n", + " 0 0.99 0.99 0.99 707930\n", + " 1 1.00 1.00 1.00 264291\n", + " 2 0.99 0.99 0.99 141472\n", + " 3 0.99 0.99 0.99 83882\n", + " 4 0.99 0.99 0.99 176875\n", + "\n", + " accuracy 0.99 1374450\n", + " macro avg 0.99 0.99 0.99 1374450\n", + "weighted avg 0.99 0.99 0.99 1374450\n", + "\n", + "16\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9909420375940683\n", + " precision recall f1-score support\n", + "\n", + " 0 0.99 0.99 0.99 566286\n", + " 1 1.00 1.00 1.00 273173\n", + " 2 1.00 0.99 1.00 155403\n", + " 3 0.97 0.97 0.97 84900\n", + " 4 0.99 0.99 0.99 182884\n", + "\n", + " accuracy 0.99 1262646\n", + " macro avg 0.99 0.99 0.99 1262646\n", + "weighted avg 0.99 0.99 0.99 1262646\n", + "\n", + "4\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9948501678903209\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 0.99 1.00 763459\n", + " 1 1.00 1.00 1.00 267545\n", + " 2 1.00 1.00 1.00 147129\n", + " 3 0.97 0.99 0.98 86069\n", + " 4 1.00 1.00 1.00 185554\n", + "\n", + " accuracy 0.99 1449756\n", + " macro avg 0.99 0.99 0.99 1449756\n", + "weighted avg 0.99 0.99 0.99 1449756\n", + "\n", + "13\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9953618951773934\n", + " precision recall f1-score support\n", + "\n", + " 0 0.99 1.00 0.99 554003\n", + " 1 1.00 1.00 1.00 273008\n", + " 2 1.00 1.00 1.00 153832\n", + " 3 0.99 0.99 0.99 88025\n", + " 4 1.00 0.99 1.00 183152\n", + "\n", + " accuracy 1.00 1252020\n", + " macro avg 1.00 0.99 0.99 1252020\n", + "weighted avg 1.00 1.00 1.00 1252020\n", + "\n", + "3\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9984215593506081\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 1.00 1.00 774757\n", + " 1 1.00 1.00 1.00 263230\n", + " 2 1.00 1.00 1.00 147381\n", + " 3 1.00 1.00 1.00 86832\n", + " 4 1.00 1.00 1.00 179866\n", + "\n", + " accuracy 1.00 1452066\n", + " macro avg 1.00 1.00 1.00 1452066\n", + "weighted avg 1.00 1.00 1.00 1452066\n", + "\n", + "17\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9960514628271707\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 1.00 1.00 632614\n", + " 1 1.00 1.00 1.00 273250\n", + " 2 1.00 1.00 1.00 167191\n", + " 3 0.99 0.99 0.99 85889\n", + " 4 0.99 0.99 0.99 168383\n", + "\n", + " accuracy 1.00 1327327\n", + " macro avg 0.99 1.00 1.00 1327327\n", + "weighted avg 1.00 1.00 1.00 1327327\n", + "\n", + "5\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9962292319011686\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 1.00 1.00 706523\n", + " 1 1.00 1.00 1.00 276704\n", + " 2 0.99 0.99 0.99 149255\n", + " 3 1.00 1.00 1.00 86753\n", + " 4 1.00 1.00 1.00 183397\n", + "\n", + " accuracy 1.00 1402632\n", + " macro avg 1.00 1.00 1.00 1402632\n", + "weighted avg 1.00 1.00 1.00 1402632\n", + "\n", + "7\n" + ] + }, + { + "name": "stderr", + "output_type": "stream", + "text": [ + "/home/sf/.local/lib/python3.6/site-packages/sklearn/ensemble/forest.py:245: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.\n", + " \"10 in version 0.20 to 100 in 0.22.\", FutureWarning)\n" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + "0.9961871429166657\n", + " precision recall f1-score support\n", + "\n", + " 0 1.00 1.00 1.00 486045\n", + " 1 1.00 1.00 1.00 274312\n", + " 2 1.00 1.00 1.00 147644\n", + " 3 0.99 0.99 0.99 85832\n", + " 4 1.00 1.00 1.00 182188\n", + "\n", + " accuracy 1.00 1176021\n", + " macro avg 1.00 1.00 1.00 1176021\n", + "weighted avg 1.00 1.00 1.00 1176021\n", + "\n", + "CPU times: user 1h 2min 21s, sys: 35.1 s, total: 1h 2min 56s\n", + "Wall time: 1h 2min 56s\n" + ] + } + ], + "source": [ + "%%time\n", + "for subject in df['subject'].unique():\n", + " print (subject)\n", + " temp = df[df['subject'] == subject]\n", + " y = temp['target']\n", + " X = temp.drop('target', 1)\n", + " \n", + " rf = RandomForestClassifier() \n", + " \n", + " X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.33, random_state=42)\n", + " \n", + " rf.fit(X_train, y_train)\n", + " print (rf.score(X_test, y_test))\n", + " \n", + " print(classification_report(y_test, rf.predict(X_test)))\n", + " \n", + " feature_importances = pd.DataFrame(rf.feature_importances_,index = X_train.columns,columns=[str(subject)])\n", + " feature_importances_dict = feature_importances.to_dict()\n", + " feature_importances_list.append(feature_importances_dict)\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": 8, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[{'6': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.1300669764504841,\n", + " 'chest_ACC_y': 0.1968860170043269,\n", + " 'chest_ACC_z': 0.24581151008517166,\n", + " 'chest_ECG': 0.0032265901153278563,\n", + " 'chest_EMG': 0.0036803586156519685,\n", + " 'chest_EDA': 0.24669042461389065,\n", + " 'chest_Temp': 0.15944455526109153,\n", + " 'chest_Resp': 0.014193567854055431}},\n", + " {'11': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.04024757292461694,\n", + " 'chest_ACC_y': 0.1565318618203392,\n", + " 'chest_ACC_z': 0.11830625071942938,\n", + " 'chest_ECG': 0.007922838269133713,\n", + " 'chest_EMG': 0.006348978002092723,\n", + " 'chest_EDA': 0.36328293249601246,\n", + " 'chest_Temp': 0.2618496659465971,\n", + " 'chest_Resp': 0.045509899821778596}},\n", + " {'14': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.10375227203200195,\n", + " 'chest_ACC_y': 0.1853095383931324,\n", + " 'chest_ACC_z': 0.215453524103329,\n", + " 'chest_ECG': 0.008595033425546683,\n", + " 'chest_EMG': 0.0051670030825727055,\n", + " 'chest_EDA': 0.25382475947777666,\n", + " 'chest_Temp': 0.2077869105964587,\n", + " 'chest_Resp': 0.020110958889181855}},\n", + " {'8': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.14347363122864362,\n", + " 'chest_ACC_y': 0.24065811924766892,\n", + " 'chest_ACC_z': 0.267762938257923,\n", + " 'chest_ECG': 0.005711548638591734,\n", + " 'chest_EMG': 0.003918487469962929,\n", + " 'chest_EDA': 0.2387070057305599,\n", + " 'chest_Temp': 0.08413531983996998,\n", + " 'chest_Resp': 0.01563294958667973}},\n", + " {'15': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.11231814251034679,\n", + " 'chest_ACC_y': 0.08220255608689836,\n", + " 'chest_ACC_z': 0.20822479510318542,\n", + " 'chest_ECG': 0.0030866105842708154,\n", + " 'chest_EMG': 0.002597678771338352,\n", + " 'chest_EDA': 0.41319383692544054,\n", + " 'chest_Temp': 0.1684332696165509,\n", + " 'chest_Resp': 0.009943110401968736}},\n", + " {'9': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.12561607603440622,\n", + " 'chest_ACC_y': 0.09702573688756252,\n", + " 'chest_ACC_z': 0.24384679962004108,\n", + " 'chest_ECG': 0.003995169023835594,\n", + " 'chest_EMG': 0.0054176080210714085,\n", + " 'chest_EDA': 0.36880376616830607,\n", + " 'chest_Temp': 0.14303779961937815,\n", + " 'chest_Resp': 0.012257044625398936}},\n", + " {'10': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.22882102161026965,\n", + " 'chest_ACC_y': 0.04732657436997019,\n", + " 'chest_ACC_z': 0.2322145246566627,\n", + " 'chest_ECG': 0.004801462002461738,\n", + " 'chest_EMG': 0.0045123477972814855,\n", + " 'chest_EDA': 0.31158122644140307,\n", + " 'chest_Temp': 0.1581155419253945,\n", + " 'chest_Resp': 0.012627301196556704}},\n", + " {'2': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.11668464543524892,\n", + " 'chest_ACC_y': 0.13597111186938743,\n", + " 'chest_ACC_z': 0.24675670252898294,\n", + " 'chest_ECG': 0.0049927372104148,\n", + " 'chest_EMG': 0.0024869718274109194,\n", + " 'chest_EDA': 0.22587860975496904,\n", + " 'chest_Temp': 0.25156271388019963,\n", + " 'chest_Resp': 0.015666507493386436}},\n", + " {'16': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.07922301732289758,\n", + " 'chest_ACC_y': 0.06155434121985866,\n", + " 'chest_ACC_z': 0.2439000711979064,\n", + " 'chest_ECG': 0.012125844832497342,\n", + " 'chest_EMG': 0.003252002142311649,\n", + " 'chest_EDA': 0.4108674411007088,\n", + " 'chest_Temp': 0.1740060304072016,\n", + " 'chest_Resp': 0.0150712517766179}},\n", + " {'4': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.1888912770202422,\n", + " 'chest_ACC_y': 0.1515329160303108,\n", + " 'chest_ACC_z': 0.23782728420548904,\n", + " 'chest_ECG': 0.003605102562460383,\n", + " 'chest_EMG': 0.002869069393522499,\n", + " 'chest_EDA': 0.2525019555539589,\n", + " 'chest_Temp': 0.1498092548768111,\n", + " 'chest_Resp': 0.012963140357205296}},\n", + " {'13': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.07803417203388363,\n", + " 'chest_ACC_y': 0.09974802002465204,\n", + " 'chest_ACC_z': 0.1777006613688301,\n", + " 'chest_ECG': 0.0034168687514631547,\n", + " 'chest_EMG': 0.0034440563788113777,\n", + " 'chest_EDA': 0.37400948926186695,\n", + " 'chest_Temp': 0.2460262689411883,\n", + " 'chest_Resp': 0.017620463239304454}},\n", + " {'3': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.07188722001251066,\n", + " 'chest_ACC_y': 0.061859702055979716,\n", + " 'chest_ACC_z': 0.33898272660534673,\n", + " 'chest_ECG': 0.002533408376087527,\n", + " 'chest_EMG': 0.012332865584837815,\n", + " 'chest_EDA': 0.22347187550642342,\n", + " 'chest_Temp': 0.2792589111675616,\n", + " 'chest_Resp': 0.009673290691252574}},\n", + " {'17': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.18044989325378819,\n", + " 'chest_ACC_y': 0.07736863340070056,\n", + " 'chest_ACC_z': 0.20479809095955676,\n", + " 'chest_ECG': 0.003415233725763734,\n", + " 'chest_EMG': 0.0025323836092819166,\n", + " 'chest_EDA': 0.39464251796388494,\n", + " 'chest_Temp': 0.12339909371098787,\n", + " 'chest_Resp': 0.013394153376035991}},\n", + " {'5': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.20167807887040695,\n", + " 'chest_ACC_y': 0.08914038474449766,\n", + " 'chest_ACC_z': 0.2014025757829614,\n", + " 'chest_ECG': 0.004351308801137371,\n", + " 'chest_EMG': 0.004152757849246086,\n", + " 'chest_EDA': 0.37152507620617825,\n", + " 'chest_Temp': 0.10902969536748346,\n", + " 'chest_Resp': 0.01872012237808883}},\n", + " {'7': {'subject': 0.0,\n", + " 'chest_ACC_x': 0.07199023148411884,\n", + " 'chest_ACC_y': 0.0738758141531722,\n", + " 'chest_ACC_z': 0.2306827752142297,\n", + " 'chest_ECG': 0.004528291130553968,\n", + " 'chest_EMG': 0.003471923752608401,\n", + " 'chest_EDA': 0.22224281102614607,\n", + " 'chest_Temp': 0.3742280348025795,\n", + " 'chest_Resp': 0.0189801184365914}}]" + ] + }, + "execution_count": 8, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "feature_importances_list" + ] + }, + { + "cell_type": "code", + "execution_count": 9, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "15" + ] + }, + "execution_count": 9, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "len(feature_importances_list)" + ] + }, + { + "cell_type": "code", + "execution_count": 15, + "metadata": {}, + "outputs": [], + "source": [ + "list_df = []\n", + "for val in feature_importances_list:\n", + " list_df.append(pd.DataFrame.from_dict(val).T)\n", + " " + ] + }, + { + "cell_type": "code", + "execution_count": 16, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "[ chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 6 0.130067 0.196886 0.245812 0.003227 0.24669 0.00368 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 6 0.014194 0.159445 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 11 0.040248 0.156532 0.118306 0.007923 0.363283 0.006349 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 11 0.04551 0.26185 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 14 0.103752 0.18531 0.215454 0.008595 0.253825 0.005167 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 14 0.020111 0.207787 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 8 0.143474 0.240658 0.267763 0.005712 0.238707 0.003918 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 8 0.015633 0.084135 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 15 0.112318 0.082203 0.208225 0.003087 0.413194 0.002598 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 15 0.009943 0.168433 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 9 0.125616 0.097026 0.243847 0.003995 0.368804 0.005418 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 9 0.012257 0.143038 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 10 0.228821 0.047327 0.232215 0.004801 0.311581 0.004512 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 10 0.012627 0.158116 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 2 0.116685 0.135971 0.246757 0.004993 0.225879 0.002487 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 2 0.015667 0.251563 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 16 0.079223 0.061554 0.2439 0.012126 0.410867 0.003252 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 16 0.015071 0.174006 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 4 0.188891 0.151533 0.237827 0.003605 0.252502 0.002869 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 4 0.012963 0.149809 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 13 0.078034 0.099748 0.177701 0.003417 0.374009 0.003444 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 13 0.01762 0.246026 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 3 0.071887 0.06186 0.338983 0.002533 0.223472 0.012333 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 3 0.009673 0.279259 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 17 0.18045 0.077369 0.204798 0.003415 0.394643 0.002532 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 17 0.013394 0.123399 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 5 0.201678 0.08914 0.201403 0.004351 0.371525 0.004153 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 5 0.01872 0.10903 0.0 ,\n", + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + " 7 0.07199 0.073876 0.230683 0.004528 0.222243 0.003472 \n", + " \n", + " chest_Resp chest_Temp subject \n", + " 7 0.01898 0.374228 0.0 ]" + ] + }, + "execution_count": 16, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "list_df" + ] + }, + { + "cell_type": "code", + "execution_count": 18, + "metadata": {}, + "outputs": [], + "source": [ + "feature_importance_all_subjects = pd.concat(list_df)" + ] + }, + { + "cell_type": "code", + "execution_count": 19, + "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>chest_ACC_x</th>\n", + " <th>chest_ACC_y</th>\n", + " <th>chest_ACC_z</th>\n", + " <th>chest_ECG</th>\n", + " <th>chest_EDA</th>\n", + " <th>chest_EMG</th>\n", + " <th>chest_Resp</th>\n", + " <th>chest_Temp</th>\n", + " <th>subject</th>\n", + " </tr>\n", + " </thead>\n", + " <tbody>\n", + " <tr>\n", + " <th>6</th>\n", + " <td>0.130067</td>\n", + " <td>0.196886</td>\n", + " <td>0.245812</td>\n", + " <td>0.003227</td>\n", + " <td>0.246690</td>\n", + " <td>0.003680</td>\n", + " <td>0.014194</td>\n", + " <td>0.159445</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>11</th>\n", + " <td>0.040248</td>\n", + " <td>0.156532</td>\n", + " <td>0.118306</td>\n", + " <td>0.007923</td>\n", + " <td>0.363283</td>\n", + " <td>0.006349</td>\n", + " <td>0.045510</td>\n", + " <td>0.261850</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>14</th>\n", + " <td>0.103752</td>\n", + " <td>0.185310</td>\n", + " <td>0.215454</td>\n", + " <td>0.008595</td>\n", + " <td>0.253825</td>\n", + " <td>0.005167</td>\n", + " <td>0.020111</td>\n", + " <td>0.207787</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>8</th>\n", + " <td>0.143474</td>\n", + " <td>0.240658</td>\n", + " <td>0.267763</td>\n", + " <td>0.005712</td>\n", + " <td>0.238707</td>\n", + " <td>0.003918</td>\n", + " <td>0.015633</td>\n", + " <td>0.084135</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>15</th>\n", + " <td>0.112318</td>\n", + " <td>0.082203</td>\n", + " <td>0.208225</td>\n", + " <td>0.003087</td>\n", + " <td>0.413194</td>\n", + " <td>0.002598</td>\n", + " <td>0.009943</td>\n", + " <td>0.168433</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>9</th>\n", + " <td>0.125616</td>\n", + " <td>0.097026</td>\n", + " <td>0.243847</td>\n", + " <td>0.003995</td>\n", + " <td>0.368804</td>\n", + " <td>0.005418</td>\n", + " <td>0.012257</td>\n", + " <td>0.143038</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>10</th>\n", + " <td>0.228821</td>\n", + " <td>0.047327</td>\n", + " <td>0.232215</td>\n", + " <td>0.004801</td>\n", + " <td>0.311581</td>\n", + " <td>0.004512</td>\n", + " <td>0.012627</td>\n", + " <td>0.158116</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>2</th>\n", + " <td>0.116685</td>\n", + " <td>0.135971</td>\n", + " <td>0.246757</td>\n", + " <td>0.004993</td>\n", + " <td>0.225879</td>\n", + " <td>0.002487</td>\n", + " <td>0.015667</td>\n", + " <td>0.251563</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>16</th>\n", + " <td>0.079223</td>\n", + " <td>0.061554</td>\n", + " <td>0.243900</td>\n", + " <td>0.012126</td>\n", + " <td>0.410867</td>\n", + " <td>0.003252</td>\n", + " <td>0.015071</td>\n", + " <td>0.174006</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>4</th>\n", + " <td>0.188891</td>\n", + " <td>0.151533</td>\n", + " <td>0.237827</td>\n", + " <td>0.003605</td>\n", + " <td>0.252502</td>\n", + " <td>0.002869</td>\n", + " <td>0.012963</td>\n", + " <td>0.149809</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>13</th>\n", + " <td>0.078034</td>\n", + " <td>0.099748</td>\n", + " <td>0.177701</td>\n", + " <td>0.003417</td>\n", + " <td>0.374009</td>\n", + " <td>0.003444</td>\n", + " <td>0.017620</td>\n", + " <td>0.246026</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>3</th>\n", + " <td>0.071887</td>\n", + " <td>0.061860</td>\n", + " <td>0.338983</td>\n", + " <td>0.002533</td>\n", + " <td>0.223472</td>\n", + " <td>0.012333</td>\n", + " <td>0.009673</td>\n", + " <td>0.279259</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>17</th>\n", + " <td>0.180450</td>\n", + " <td>0.077369</td>\n", + " <td>0.204798</td>\n", + " <td>0.003415</td>\n", + " <td>0.394643</td>\n", + " <td>0.002532</td>\n", + " <td>0.013394</td>\n", + " <td>0.123399</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>5</th>\n", + " <td>0.201678</td>\n", + " <td>0.089140</td>\n", + " <td>0.201403</td>\n", + " <td>0.004351</td>\n", + " <td>0.371525</td>\n", + " <td>0.004153</td>\n", + " <td>0.018720</td>\n", + " <td>0.109030</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " <tr>\n", + " <th>7</th>\n", + " <td>0.071990</td>\n", + " <td>0.073876</td>\n", + " <td>0.230683</td>\n", + " <td>0.004528</td>\n", + " <td>0.222243</td>\n", + " <td>0.003472</td>\n", + " <td>0.018980</td>\n", + " <td>0.374228</td>\n", + " <td>0.0</td>\n", + " </tr>\n", + " </tbody>\n", + "</table>\n", + "</div>" + ], + "text/plain": [ + " chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG chest_EDA chest_EMG \\\n", + "6 0.130067 0.196886 0.245812 0.003227 0.246690 0.003680 \n", + "11 0.040248 0.156532 0.118306 0.007923 0.363283 0.006349 \n", + "14 0.103752 0.185310 0.215454 0.008595 0.253825 0.005167 \n", + "8 0.143474 0.240658 0.267763 0.005712 0.238707 0.003918 \n", + "15 0.112318 0.082203 0.208225 0.003087 0.413194 0.002598 \n", + "9 0.125616 0.097026 0.243847 0.003995 0.368804 0.005418 \n", + "10 0.228821 0.047327 0.232215 0.004801 0.311581 0.004512 \n", + "2 0.116685 0.135971 0.246757 0.004993 0.225879 0.002487 \n", + "16 0.079223 0.061554 0.243900 0.012126 0.410867 0.003252 \n", + "4 0.188891 0.151533 0.237827 0.003605 0.252502 0.002869 \n", + "13 0.078034 0.099748 0.177701 0.003417 0.374009 0.003444 \n", + "3 0.071887 0.061860 0.338983 0.002533 0.223472 0.012333 \n", + "17 0.180450 0.077369 0.204798 0.003415 0.394643 0.002532 \n", + "5 0.201678 0.089140 0.201403 0.004351 0.371525 0.004153 \n", + "7 0.071990 0.073876 0.230683 0.004528 0.222243 0.003472 \n", + "\n", + " chest_Resp chest_Temp subject \n", + "6 0.014194 0.159445 0.0 \n", + "11 0.045510 0.261850 0.0 \n", + "14 0.020111 0.207787 0.0 \n", + "8 0.015633 0.084135 0.0 \n", + "15 0.009943 0.168433 0.0 \n", + "9 0.012257 0.143038 0.0 \n", + "10 0.012627 0.158116 0.0 \n", + "2 0.015667 0.251563 0.0 \n", + "16 0.015071 0.174006 0.0 \n", + "4 0.012963 0.149809 0.0 \n", + "13 0.017620 0.246026 0.0 \n", + "3 0.009673 0.279259 0.0 \n", + "17 0.013394 0.123399 0.0 \n", + "5 0.018720 0.109030 0.0 \n", + "7 0.018980 0.374228 0.0 " + ] + }, + "execution_count": 19, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "feature_importance_all_subjects" + ] + }, + { + "cell_type": "code", + "execution_count": 21, + "metadata": {}, + "outputs": [ + { + "data": { + "text/plain": [ + "6 1.0\n", + "11 1.0\n", + "14 1.0\n", + "8 1.0\n", + "15 1.0\n", + "9 1.0\n", + "10 1.0\n", + "2 1.0\n", + "16 1.0\n", + "4 1.0\n", + "13 1.0\n", + "3 1.0\n", + "17 1.0\n", + "5 1.0\n", + "7 1.0\n", + "dtype: float64" + ] + }, + "execution_count": 21, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "feature_importance_all_subjects.sum(axis = 1, skipna = True) " + ] + }, + { + "cell_type": "code", + "execution_count": 23, + "metadata": {}, + "outputs": [ + { + "data": { + "text/html": [ + "<style type=\"text/css\" >\n", + " #T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col0 {\n", + " background-color: #6dbc6d;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col1 {\n", + " background-color: #2e992e;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col2 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col3 {\n", + " background-color: #e3fee3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col5 {\n", + " background-color: #e3fee3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col6 {\n", + " background-color: #d9f8d9;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col7 {\n", + " background-color: #51ad51;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col0 {\n", + " background-color: #ccf1cc;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col1 {\n", + " background-color: #82c882;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col2 {\n", + " background-color: #9bd69b;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col3 {\n", + " background-color: #e1fde1;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col5 {\n", + " background-color: #e2fde2;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col6 {\n", + " background-color: #c9efc9;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col7 {\n", + " background-color: #40a340;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col0 {\n", + " background-color: #88cb88;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col1 {\n", + " background-color: #3ea23e;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col2 {\n", + " background-color: #229322;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col3 {\n", + " background-color: #defbde;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col5 {\n", + " background-color: #e1fde1;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col6 {\n", + " background-color: #d3f5d3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col7 {\n", + " background-color: #299729;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col0 {\n", + " background-color: #6abb6a;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col1 {\n", + " background-color: #178c17;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col2 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col3 {\n", + " background-color: #e1fde1;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col4 {\n", + " background-color: #188d18;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col5 {\n", + " background-color: #e3fee3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col6 {\n", + " background-color: #d9f8d9;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col7 {\n", + " background-color: #9ed79e;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col0 {\n", + " background-color: #a7dda7;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col1 {\n", + " background-color: #b8e6b8;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col2 {\n", + " background-color: #71bf71;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col3 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col5 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col6 {\n", + " background-color: #e0fce0;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col7 {\n", + " background-color: #88cb88;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col0 {\n", + " background-color: #97d497;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col1 {\n", + " background-color: #a9dea9;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col2 {\n", + " background-color: #4dab4d;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col3 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col5 {\n", + " background-color: #e3fee3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col6 {\n", + " background-color: #defbde;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col7 {\n", + " background-color: #8cce8c;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col0 {\n", + " background-color: #3ca13c;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col1 {\n", + " background-color: #c3ecc3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col2 {\n", + " background-color: #3aa03a;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col3 {\n", + " background-color: #e3fee3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col5 {\n", + " background-color: #e3fee3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col6 {\n", + " background-color: #dcfadc;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col7 {\n", + " background-color: #71bf71;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col0 {\n", + " background-color: #7bc47b;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col1 {\n", + " background-color: #69ba69;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col2 {\n", + " background-color: #048204;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col3 {\n", + " background-color: #e1fde1;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col4 {\n", + " background-color: #178d17;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col5 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col6 {\n", + " background-color: #d8f8d8;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col7 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col0 {\n", + " background-color: #b9e7b9;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col1 {\n", + " background-color: #c3ecc3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col2 {\n", + " background-color: #5eb45e;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col3 {\n", + " background-color: #dffcdf;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col5 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col6 {\n", + " background-color: #ddfbdd;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col7 {\n", + " background-color: #84c984;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col0 {\n", + " background-color: #3aa03a;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col1 {\n", + " background-color: #5cb35c;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col2 {\n", + " background-color: #0d870d;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col3 {\n", + " background-color: #e3fee3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col5 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col6 {\n", + " background-color: #daf9da;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col7 {\n", + " background-color: #5eb45e;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col0 {\n", + " background-color: #b6e5b6;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col1 {\n", + " background-color: #a8dda8;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col2 {\n", + " background-color: #79c379;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col3 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col5 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col6 {\n", + " background-color: #dbf9db;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col7 {\n", + " background-color: #4eab4e;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col0 {\n", + " background-color: #b5e4b5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col1 {\n", + " background-color: #bce8bc;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col2 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col3 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col4 {\n", + " background-color: #4eab4e;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col5 {\n", + " background-color: #ddfbdd;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col6 {\n", + " background-color: #dffcdf;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col7 {\n", + " background-color: #289628;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col0 {\n", + " background-color: #7cc57c;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col1 {\n", + " background-color: #b8e6b8;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col2 {\n", + " background-color: #6fbd6f;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col3 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col5 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col6 {\n", + " background-color: #defbde;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col7 {\n", + " background-color: #9ed79e;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col0 {\n", + " background-color: #69ba69;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col1 {\n", + " background-color: #afe1af;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col2 {\n", + " background-color: #69ba69;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col3 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col4 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col5 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col6 {\n", + " background-color: #dbf9db;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col7 {\n", + " background-color: #a2daa2;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col0 {\n", + " background-color: #b9e7b9;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col1 {\n", + " background-color: #b8e6b8;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col2 {\n", + " background-color: #58b158;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col3 {\n", + " background-color: #e3fee3;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col4 {\n", + " background-color: #5db35d;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col5 {\n", + " background-color: #e4fee4;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col6 {\n", + " background-color: #dbf9db;\n", + " color: #000000;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col7 {\n", + " background-color: #008000;\n", + " color: #f1f1f1;\n", + " } #T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col8 {\n", + " background-color: #e5ffe5;\n", + " color: #000000;\n", + " }</style><table id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002\" ><thead> <tr> <th class=\"blank level0\" ></th> <th class=\"col_heading level0 col0\" >chest_ACC_x</th> <th class=\"col_heading level0 col1\" >chest_ACC_y</th> <th class=\"col_heading level0 col2\" >chest_ACC_z</th> <th class=\"col_heading level0 col3\" >chest_ECG</th> <th class=\"col_heading level0 col4\" >chest_EDA</th> <th class=\"col_heading level0 col5\" >chest_EMG</th> <th class=\"col_heading level0 col6\" >chest_Resp</th> <th class=\"col_heading level0 col7\" >chest_Temp</th> <th class=\"col_heading level0 col8\" >subject</th> </tr></thead><tbody>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row0\" class=\"row_heading level0 row0\" >6</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col0\" class=\"data row0 col0\" >0.130067</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col1\" class=\"data row0 col1\" >0.196886</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col2\" class=\"data row0 col2\" >0.245812</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col3\" class=\"data row0 col3\" >0.00322659</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col4\" class=\"data row0 col4\" >0.24669</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col5\" class=\"data row0 col5\" >0.00368036</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col6\" class=\"data row0 col6\" >0.0141936</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col7\" class=\"data row0 col7\" >0.159445</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row0_col8\" class=\"data row0 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row1\" class=\"row_heading level0 row1\" >11</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col0\" class=\"data row1 col0\" >0.0402476</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col1\" class=\"data row1 col1\" >0.156532</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col2\" class=\"data row1 col2\" >0.118306</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col3\" class=\"data row1 col3\" >0.00792284</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col4\" class=\"data row1 col4\" >0.363283</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col5\" class=\"data row1 col5\" >0.00634898</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col6\" class=\"data row1 col6\" >0.0455099</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col7\" class=\"data row1 col7\" >0.26185</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row1_col8\" class=\"data row1 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row2\" class=\"row_heading level0 row2\" >14</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col0\" class=\"data row2 col0\" >0.103752</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col1\" class=\"data row2 col1\" >0.18531</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col2\" class=\"data row2 col2\" >0.215454</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col3\" class=\"data row2 col3\" >0.00859503</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col4\" class=\"data row2 col4\" >0.253825</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col5\" class=\"data row2 col5\" >0.005167</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col6\" class=\"data row2 col6\" >0.020111</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col7\" class=\"data row2 col7\" >0.207787</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row2_col8\" class=\"data row2 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row3\" class=\"row_heading level0 row3\" >8</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col0\" class=\"data row3 col0\" >0.143474</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col1\" class=\"data row3 col1\" >0.240658</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col2\" class=\"data row3 col2\" >0.267763</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col3\" class=\"data row3 col3\" >0.00571155</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col4\" class=\"data row3 col4\" >0.238707</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col5\" class=\"data row3 col5\" >0.00391849</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col6\" class=\"data row3 col6\" >0.0156329</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col7\" class=\"data row3 col7\" >0.0841353</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row3_col8\" class=\"data row3 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row4\" class=\"row_heading level0 row4\" >15</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col0\" class=\"data row4 col0\" >0.112318</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col1\" class=\"data row4 col1\" >0.0822026</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col2\" class=\"data row4 col2\" >0.208225</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col3\" class=\"data row4 col3\" >0.00308661</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col4\" class=\"data row4 col4\" >0.413194</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col5\" class=\"data row4 col5\" >0.00259768</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col6\" class=\"data row4 col6\" >0.00994311</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col7\" class=\"data row4 col7\" >0.168433</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row4_col8\" class=\"data row4 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row5\" class=\"row_heading level0 row5\" >9</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col0\" class=\"data row5 col0\" >0.125616</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col1\" class=\"data row5 col1\" >0.0970257</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col2\" class=\"data row5 col2\" >0.243847</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col3\" class=\"data row5 col3\" >0.00399517</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col4\" class=\"data row5 col4\" >0.368804</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col5\" class=\"data row5 col5\" >0.00541761</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col6\" class=\"data row5 col6\" >0.012257</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col7\" class=\"data row5 col7\" >0.143038</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row5_col8\" class=\"data row5 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row6\" class=\"row_heading level0 row6\" >10</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col0\" class=\"data row6 col0\" >0.228821</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col1\" class=\"data row6 col1\" >0.0473266</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col2\" class=\"data row6 col2\" >0.232215</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col3\" class=\"data row6 col3\" >0.00480146</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col4\" class=\"data row6 col4\" >0.311581</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col5\" class=\"data row6 col5\" >0.00451235</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col6\" class=\"data row6 col6\" >0.0126273</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col7\" class=\"data row6 col7\" >0.158116</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row6_col8\" class=\"data row6 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row7\" class=\"row_heading level0 row7\" >2</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col0\" class=\"data row7 col0\" >0.116685</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col1\" class=\"data row7 col1\" >0.135971</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col2\" class=\"data row7 col2\" >0.246757</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col3\" class=\"data row7 col3\" >0.00499274</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col4\" class=\"data row7 col4\" >0.225879</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col5\" class=\"data row7 col5\" >0.00248697</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col6\" class=\"data row7 col6\" >0.0156665</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col7\" class=\"data row7 col7\" >0.251563</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row7_col8\" class=\"data row7 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row8\" class=\"row_heading level0 row8\" >16</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col0\" class=\"data row8 col0\" >0.079223</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col1\" class=\"data row8 col1\" >0.0615543</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col2\" class=\"data row8 col2\" >0.2439</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col3\" class=\"data row8 col3\" >0.0121258</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col4\" class=\"data row8 col4\" >0.410867</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col5\" class=\"data row8 col5\" >0.003252</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col6\" class=\"data row8 col6\" >0.0150713</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col7\" class=\"data row8 col7\" >0.174006</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row8_col8\" class=\"data row8 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row9\" class=\"row_heading level0 row9\" >4</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col0\" class=\"data row9 col0\" >0.188891</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col1\" class=\"data row9 col1\" >0.151533</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col2\" class=\"data row9 col2\" >0.237827</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col3\" class=\"data row9 col3\" >0.0036051</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col4\" class=\"data row9 col4\" >0.252502</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col5\" class=\"data row9 col5\" >0.00286907</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col6\" class=\"data row9 col6\" >0.0129631</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col7\" class=\"data row9 col7\" >0.149809</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row9_col8\" class=\"data row9 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row10\" class=\"row_heading level0 row10\" >13</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col0\" class=\"data row10 col0\" >0.0780342</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col1\" class=\"data row10 col1\" >0.099748</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col2\" class=\"data row10 col2\" >0.177701</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col3\" class=\"data row10 col3\" >0.00341687</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col4\" class=\"data row10 col4\" >0.374009</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col5\" class=\"data row10 col5\" >0.00344406</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col6\" class=\"data row10 col6\" >0.0176205</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col7\" class=\"data row10 col7\" >0.246026</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row10_col8\" class=\"data row10 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row11\" class=\"row_heading level0 row11\" >3</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col0\" class=\"data row11 col0\" >0.0718872</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col1\" class=\"data row11 col1\" >0.0618597</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col2\" class=\"data row11 col2\" >0.338983</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col3\" class=\"data row11 col3\" >0.00253341</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col4\" class=\"data row11 col4\" >0.223472</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col5\" class=\"data row11 col5\" >0.0123329</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col6\" class=\"data row11 col6\" >0.00967329</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col7\" class=\"data row11 col7\" >0.279259</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row11_col8\" class=\"data row11 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row12\" class=\"row_heading level0 row12\" >17</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col0\" class=\"data row12 col0\" >0.18045</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col1\" class=\"data row12 col1\" >0.0773686</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col2\" class=\"data row12 col2\" >0.204798</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col3\" class=\"data row12 col3\" >0.00341523</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col4\" class=\"data row12 col4\" >0.394643</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col5\" class=\"data row12 col5\" >0.00253238</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col6\" class=\"data row12 col6\" >0.0133942</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col7\" class=\"data row12 col7\" >0.123399</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row12_col8\" class=\"data row12 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row13\" class=\"row_heading level0 row13\" >5</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col0\" class=\"data row13 col0\" >0.201678</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col1\" class=\"data row13 col1\" >0.0891404</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col2\" class=\"data row13 col2\" >0.201403</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col3\" class=\"data row13 col3\" >0.00435131</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col4\" class=\"data row13 col4\" >0.371525</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col5\" class=\"data row13 col5\" >0.00415276</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col6\" class=\"data row13 col6\" >0.0187201</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col7\" class=\"data row13 col7\" >0.10903</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row13_col8\" class=\"data row13 col8\" >0</td>\n", + " </tr>\n", + " <tr>\n", + " <th id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002level0_row14\" class=\"row_heading level0 row14\" >7</th>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col0\" class=\"data row14 col0\" >0.0719902</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col1\" class=\"data row14 col1\" >0.0738758</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col2\" class=\"data row14 col2\" >0.230683</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col3\" class=\"data row14 col3\" >0.00452829</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col4\" class=\"data row14 col4\" >0.222243</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col5\" class=\"data row14 col5\" >0.00347192</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col6\" class=\"data row14 col6\" >0.0189801</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col7\" class=\"data row14 col7\" >0.374228</td>\n", + " <td id=\"T_cf1e75b6_c071_11e9_a2b0_42010a800002row14_col8\" class=\"data row14 col8\" >0</td>\n", + " </tr>\n", + " </tbody></table>" + ], + "text/plain": [ + "<pandas.io.formats.style.Styler at 0x7fa017af0898>" + ] + }, + "execution_count": 23, + "metadata": {}, + "output_type": "execute_result" + } + ], + "source": [ + "import seaborn as sns\n", + "\n", + "cm = sns.light_palette(\"green\", as_cmap=True)\n", + "\n", + "s = feature_importance_all_subjects.style.background_gradient(cmap=cm,axis = 1)\n", + "s" + ] + }, + { + "cell_type": "code", + "execution_count": 25, + "metadata": {}, + "outputs": [], + "source": [ + "feature_importance_all_subjects.to_csv('feature_importance_all_subjects.csv' )" + ] + }, + { + "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": "3.6.8" + } + }, + "nbformat": 4, + "nbformat_minor": 2 +}