Datasets
Models
Downloads: 1
2507 lines (2506 with data), 78.0 kB
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 1.02 s, sys: 617 ms, total: 1.64 s\n",
"Wall time: 818 ms\n"
]
}
],
"source": [
"%%time\n",
"import pandas as pd\n",
"import numpy as np\n",
"from sklearn.ensemble import ExtraTreesClassifier\n",
"from sklearn.metrics import classification_report\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.linear_model import LogisticRegression\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 43.3 s, sys: 6.23 s, total: 49.5 s\n",
"Wall time: 49.5 s\n"
]
}
],
"source": [
"%%time\n",
"df = pd.read_csv(\"master_data.csv\")"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(31470603, 10)"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.shape"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"[2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['subject'].unique()\n",
"list_of_subjects=list(df['subject'].unique())\n",
"list_of_subjects.sort()\n",
"list_of_subjects"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['chest_ACC_x',\n",
" 'chest_ACC_y',\n",
" 'chest_ACC_z',\n",
" 'chest_ECG',\n",
" 'chest_EMG',\n",
" 'chest_EDA',\n",
" 'chest_Temp',\n",
" 'chest_Resp']"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"features=df.columns.tolist()\n",
"to_remove = [fea for fea in features if \"target\" in fea or \"subject\" in fea]\n",
"feature = [x for x in features if x not in to_remove]\n",
"feature"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"array([1, 2, 4, 3])"
]
},
"execution_count": 6,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df['target'].unique()"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"6\n",
"11\n",
"14\n",
"8\n",
"15\n",
"9\n",
"10\n",
"2\n",
"16\n",
"4\n",
"13\n",
"3\n",
"17\n",
"5\n",
"7\n",
"CPU times: user 2.25 s, sys: 814 ms, total: 3.06 s\n",
"Wall time: 3.04 s\n"
]
}
],
"source": [
"%%time\n",
"test_subject=list(df['subject'].unique())\n",
"for i in test_subject:\n",
" print(i)\n",
" globals()['subject_%s' % i]=df[df['subject'] == i]\n",
"# globals()['subject_%s_train' % i],globals()['subject_%s_test' % i]=train_test_split(globals()['subject_%s' % i], test_size=test_shape)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"subject_list=[subject_2,subject_3,subject_4,subject_5,subject_6,subject_7,subject_8,subject_9,subject_10,subject_11,subject_13,subject_14,subject_15,subject_16,subject_17]"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"x=[2,3,4,5,6,7,8,9,10,11,13,14,15,16,17]"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"\n",
"for i in range(len(x)):\n",
" \n",
" globals()['df_1_%s' % x[i]]=subject_list[i][subject_list[i]['target']==1]\n",
" globals()['df_2_%s' % x[i]]=subject_list[i][subject_list[i]['target']==2]\n",
" globals()['df_3_%s' % x[i]]=subject_list[i][subject_list[i]['target']==3]\n",
" globals()['df_4_%s' % x[i]]=subject_list[i][subject_list[i]['target']==4]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ExtraTreesClassifier\t LogisticRegression\t RandomForestClassifier\t classification_report\t df\t df_1_10\t df_1_11\t df_1_13\t df_1_14\t \n",
"df_1_15\t df_1_16\t df_1_17\t df_1_2\t df_1_3\t df_1_4\t df_1_5\t df_1_6\t df_1_7\t \n",
"df_1_8\t df_1_9\t df_2_10\t df_2_11\t df_2_13\t df_2_14\t df_2_15\t df_2_16\t df_2_17\t \n",
"df_2_2\t df_2_3\t df_2_4\t df_2_5\t df_2_6\t df_2_7\t df_2_8\t df_2_9\t df_3_10\t \n",
"df_3_11\t df_3_13\t df_3_14\t df_3_15\t df_3_16\t df_3_17\t df_3_2\t df_3_3\t df_3_4\t \n",
"df_3_5\t df_3_6\t df_3_7\t df_3_8\t df_3_9\t df_4_10\t df_4_11\t df_4_13\t df_4_14\t \n",
"df_4_15\t df_4_16\t df_4_17\t df_4_2\t df_4_3\t df_4_4\t df_4_5\t df_4_6\t df_4_7\t \n",
"df_4_8\t df_4_9\t feature\t features\t i\t list_of_subjects\t np\t pd\t subject_10\t \n",
"subject_11\t subject_13\t subject_14\t subject_15\t subject_16\t subject_17\t subject_2\t subject_3\t subject_4\t \n",
"subject_5\t subject_6\t subject_7\t subject_8\t subject_9\t subject_list\t test_subject\t to_remove\t train_test_split\t \n",
"x\t \n"
]
}
],
"source": [
"who"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"x=[2,3,4,5,6,7,8,9,10,11,13,14,15,16,17]\n",
"cls=[1,2,3,4]"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"21000"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"no_of_rows=int(700*60*0.5)\n",
"no_of_rows"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"for i in cls:\n",
" for j in x:\n",
" globals()['df_{}_train_{}'.format(i,j)] = globals()['df_{}_{}'.format(i,j)].iloc[:no_of_rows]\n",
" #globals()['df_{}_train_{}'.format(i,j)],globals()['df_{}_test_{}'.format(i,j)]=train_test_split(globals()['df_{}_{}'.format(i,j)], test_size=0.3)\n",
" #print('subject_'+str(i))\n",
" globals()['df_{}_test_{}'.format(i,j)] = globals()['df_{}_{}'.format(i,j)].iloc[no_of_rows:] "
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"concat_list=[]\n",
"for i in cls:\n",
" for j in x:\n",
" concat_list.append(globals()['df_{}_train_{}'.format(i,j)])\n",
"#concat_list[0]"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {
"scrolled": true
},
"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>target</th>\n",
" <th>subject</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_EMG</th>\n",
" <th>chest_EDA</th>\n",
" <th>chest_Temp</th>\n",
" <th>chest_Resp</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>14786800</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8914</td>\n",
" <td>-0.1102</td>\n",
" <td>-0.2576</td>\n",
" <td>0.030945</td>\n",
" <td>-0.003708</td>\n",
" <td>5.710983</td>\n",
" <td>29.083618</td>\n",
" <td>1.191711</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786801</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8926</td>\n",
" <td>-0.1086</td>\n",
" <td>-0.2544</td>\n",
" <td>0.033646</td>\n",
" <td>-0.014145</td>\n",
" <td>5.719376</td>\n",
" <td>29.122437</td>\n",
" <td>1.139832</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786802</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8930</td>\n",
" <td>-0.1094</td>\n",
" <td>-0.2580</td>\n",
" <td>0.033005</td>\n",
" <td>0.010208</td>\n",
" <td>5.706406</td>\n",
" <td>29.115234</td>\n",
" <td>1.141357</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786803</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8934</td>\n",
" <td>-0.1082</td>\n",
" <td>-0.2538</td>\n",
" <td>0.031815</td>\n",
" <td>0.012634</td>\n",
" <td>5.712509</td>\n",
" <td>29.126709</td>\n",
" <td>1.155090</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786804</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8930</td>\n",
" <td>-0.1096</td>\n",
" <td>-0.2570</td>\n",
" <td>0.030350</td>\n",
" <td>0.002060</td>\n",
" <td>5.727005</td>\n",
" <td>29.100861</td>\n",
" <td>1.133728</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786805</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8906</td>\n",
" <td>-0.1078</td>\n",
" <td>-0.2538</td>\n",
" <td>0.030350</td>\n",
" <td>-0.002792</td>\n",
" <td>5.707550</td>\n",
" <td>29.126709</td>\n",
" <td>1.136780</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786806</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8906</td>\n",
" <td>-0.1082</td>\n",
" <td>-0.2566</td>\n",
" <td>0.032639</td>\n",
" <td>-0.001968</td>\n",
" <td>5.715561</td>\n",
" <td>29.116699</td>\n",
" <td>1.115417</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786807</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8906</td>\n",
" <td>-0.1080</td>\n",
" <td>-0.2600</td>\n",
" <td>0.029572</td>\n",
" <td>0.007919</td>\n",
" <td>5.706406</td>\n",
" <td>29.106628</td>\n",
" <td>1.136780</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786808</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8872</td>\n",
" <td>-0.1062</td>\n",
" <td>-0.2586</td>\n",
" <td>0.026138</td>\n",
" <td>-0.007050</td>\n",
" <td>5.708313</td>\n",
" <td>29.121002</td>\n",
" <td>1.106262</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786809</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8862</td>\n",
" <td>-0.1068</td>\n",
" <td>-0.2616</td>\n",
" <td>0.027649</td>\n",
" <td>-0.013870</td>\n",
" <td>5.715561</td>\n",
" <td>29.108063</td>\n",
" <td>1.081848</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786810</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8862</td>\n",
" <td>-0.1090</td>\n",
" <td>-0.2614</td>\n",
" <td>0.035477</td>\n",
" <td>0.008102</td>\n",
" <td>5.705261</td>\n",
" <td>29.118103</td>\n",
" <td>1.100159</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786811</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8872</td>\n",
" <td>-0.1058</td>\n",
" <td>-0.2642</td>\n",
" <td>0.042709</td>\n",
" <td>0.009567</td>\n",
" <td>5.715179</td>\n",
" <td>29.126709</td>\n",
" <td>1.081848</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786812</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8894</td>\n",
" <td>-0.1066</td>\n",
" <td>-0.2686</td>\n",
" <td>0.047012</td>\n",
" <td>-0.016068</td>\n",
" <td>5.704880</td>\n",
" <td>29.095123</td>\n",
" <td>1.055908</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786813</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8874</td>\n",
" <td>-0.1074</td>\n",
" <td>-0.2606</td>\n",
" <td>0.050583</td>\n",
" <td>-0.014877</td>\n",
" <td>5.711746</td>\n",
" <td>29.122437</td>\n",
" <td>1.057434</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786814</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8886</td>\n",
" <td>-0.1062</td>\n",
" <td>-0.2632</td>\n",
" <td>0.052597</td>\n",
" <td>-0.017624</td>\n",
" <td>5.721283</td>\n",
" <td>29.132477</td>\n",
" <td>1.081848</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786815</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8866</td>\n",
" <td>-0.1034</td>\n",
" <td>-0.2598</td>\n",
" <td>0.057358</td>\n",
" <td>-0.015106</td>\n",
" <td>5.702972</td>\n",
" <td>29.119537</td>\n",
" <td>1.060486</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786816</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8858</td>\n",
" <td>-0.1026</td>\n",
" <td>-0.2620</td>\n",
" <td>0.063675</td>\n",
" <td>-0.016479</td>\n",
" <td>5.710983</td>\n",
" <td>29.115234</td>\n",
" <td>0.718689</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786817</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8874</td>\n",
" <td>-0.1030</td>\n",
" <td>-0.2590</td>\n",
" <td>0.067154</td>\n",
" <td>-0.016891</td>\n",
" <td>5.713272</td>\n",
" <td>29.123871</td>\n",
" <td>1.026917</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786818</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8874</td>\n",
" <td>-0.1020</td>\n",
" <td>-0.2616</td>\n",
" <td>0.064270</td>\n",
" <td>0.013046</td>\n",
" <td>5.734253</td>\n",
" <td>29.108063</td>\n",
" <td>1.020813</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786819</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8890</td>\n",
" <td>-0.1022</td>\n",
" <td>-0.2594</td>\n",
" <td>0.061844</td>\n",
" <td>0.023254</td>\n",
" <td>5.710220</td>\n",
" <td>29.109497</td>\n",
" <td>1.026917</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786820</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8874</td>\n",
" <td>-0.1006</td>\n",
" <td>-0.2568</td>\n",
" <td>0.058777</td>\n",
" <td>0.039825</td>\n",
" <td>5.728531</td>\n",
" <td>29.121002</td>\n",
" <td>1.043701</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786821</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8872</td>\n",
" <td>-0.1026</td>\n",
" <td>-0.2524</td>\n",
" <td>0.056717</td>\n",
" <td>0.038040</td>\n",
" <td>5.706406</td>\n",
" <td>29.115234</td>\n",
" <td>0.994873</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786822</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8874</td>\n",
" <td>-0.1018</td>\n",
" <td>-0.2494</td>\n",
" <td>0.058914</td>\n",
" <td>0.005173</td>\n",
" <td>5.712128</td>\n",
" <td>29.108063</td>\n",
" <td>0.979614</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786823</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8906</td>\n",
" <td>-0.1030</td>\n",
" <td>-0.2510</td>\n",
" <td>0.060699</td>\n",
" <td>-0.027283</td>\n",
" <td>5.726624</td>\n",
" <td>29.123871</td>\n",
" <td>1.004028</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786824</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8898</td>\n",
" <td>-0.1030</td>\n",
" <td>-0.2502</td>\n",
" <td>0.059784</td>\n",
" <td>-0.040146</td>\n",
" <td>5.709457</td>\n",
" <td>29.126709</td>\n",
" <td>0.965881</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786825</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8894</td>\n",
" <td>-0.1006</td>\n",
" <td>-0.2502</td>\n",
" <td>0.060379</td>\n",
" <td>-0.025955</td>\n",
" <td>5.723953</td>\n",
" <td>29.200073</td>\n",
" <td>0.982666</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786826</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8890</td>\n",
" <td>-0.0996</td>\n",
" <td>-0.2498</td>\n",
" <td>0.063950</td>\n",
" <td>-0.037216</td>\n",
" <td>5.702209</td>\n",
" <td>29.092224</td>\n",
" <td>0.964355</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786827</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8894</td>\n",
" <td>-0.0998</td>\n",
" <td>-0.2472</td>\n",
" <td>0.067429</td>\n",
" <td>-0.012497</td>\n",
" <td>5.711365</td>\n",
" <td>29.129608</td>\n",
" <td>0.950623</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786828</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8896</td>\n",
" <td>-0.1014</td>\n",
" <td>-0.2456</td>\n",
" <td>0.068893</td>\n",
" <td>-0.019455</td>\n",
" <td>5.718613</td>\n",
" <td>29.115234</td>\n",
" <td>0.958252</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14786829</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8866</td>\n",
" <td>-0.1014</td>\n",
" <td>-0.2464</td>\n",
" <td>0.066422</td>\n",
" <td>0.011398</td>\n",
" <td>5.702209</td>\n",
" <td>29.103729</td>\n",
" <td>0.917053</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809069</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4378</td>\n",
" <td>-0.2318</td>\n",
" <td>-0.8414</td>\n",
" <td>-0.179581</td>\n",
" <td>-0.005081</td>\n",
" <td>0.448990</td>\n",
" <td>31.927704</td>\n",
" <td>-1.399231</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809070</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4378</td>\n",
" <td>-0.2328</td>\n",
" <td>-0.8398</td>\n",
" <td>-0.179077</td>\n",
" <td>-0.000595</td>\n",
" <td>0.542450</td>\n",
" <td>31.941071</td>\n",
" <td>-1.437378</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809071</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4394</td>\n",
" <td>-0.2360</td>\n",
" <td>-0.8376</td>\n",
" <td>-0.180313</td>\n",
" <td>-0.000137</td>\n",
" <td>0.449371</td>\n",
" <td>32.031494</td>\n",
" <td>-1.441956</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809072</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4406</td>\n",
" <td>-0.2382</td>\n",
" <td>-0.8438</td>\n",
" <td>-0.186447</td>\n",
" <td>0.002975</td>\n",
" <td>0.512695</td>\n",
" <td>31.920319</td>\n",
" <td>-1.438904</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809073</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4398</td>\n",
" <td>-0.2386</td>\n",
" <td>-0.8454</td>\n",
" <td>-0.194504</td>\n",
" <td>-0.004211</td>\n",
" <td>0.494003</td>\n",
" <td>31.930664</td>\n",
" <td>-1.551819</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809074</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4416</td>\n",
" <td>-0.2390</td>\n",
" <td>-0.8454</td>\n",
" <td>-0.200455</td>\n",
" <td>0.004349</td>\n",
" <td>0.479126</td>\n",
" <td>31.927704</td>\n",
" <td>-1.473999</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809075</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4402</td>\n",
" <td>-0.2382</td>\n",
" <td>-0.8450</td>\n",
" <td>-0.205902</td>\n",
" <td>-0.012955</td>\n",
" <td>0.472641</td>\n",
" <td>31.930664</td>\n",
" <td>-1.493835</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809076</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4378</td>\n",
" <td>-0.2366</td>\n",
" <td>-0.8472</td>\n",
" <td>-0.210983</td>\n",
" <td>0.002289</td>\n",
" <td>0.456238</td>\n",
" <td>31.909912</td>\n",
" <td>-1.487732</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809077</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4362</td>\n",
" <td>-0.2364</td>\n",
" <td>-0.8502</td>\n",
" <td>-0.212311</td>\n",
" <td>0.005722</td>\n",
" <td>0.454330</td>\n",
" <td>31.930664</td>\n",
" <td>-1.522827</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809078</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4374</td>\n",
" <td>-0.2354</td>\n",
" <td>-0.8438</td>\n",
" <td>-0.211716</td>\n",
" <td>-0.007233</td>\n",
" <td>0.450516</td>\n",
" <td>31.924744</td>\n",
" <td>-1.507568</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809079</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4380</td>\n",
" <td>-0.2360</td>\n",
" <td>-0.8450</td>\n",
" <td>-0.207596</td>\n",
" <td>0.000229</td>\n",
" <td>0.532150</td>\n",
" <td>31.920319</td>\n",
" <td>-1.483154</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809080</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4386</td>\n",
" <td>-0.2376</td>\n",
" <td>-0.8424</td>\n",
" <td>-0.199173</td>\n",
" <td>-0.005997</td>\n",
" <td>0.493622</td>\n",
" <td>31.921814</td>\n",
" <td>-1.519775</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809081</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4410</td>\n",
" <td>-0.2386</td>\n",
" <td>-0.8412</td>\n",
" <td>-0.189011</td>\n",
" <td>0.002518</td>\n",
" <td>0.466537</td>\n",
" <td>31.923248</td>\n",
" <td>-1.501465</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809082</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4454</td>\n",
" <td>-0.2392</td>\n",
" <td>-0.8320</td>\n",
" <td>-0.180496</td>\n",
" <td>-0.000504</td>\n",
" <td>0.460052</td>\n",
" <td>31.924744</td>\n",
" <td>-1.539612</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809083</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4470</td>\n",
" <td>-0.2390</td>\n",
" <td>-0.8342</td>\n",
" <td>-0.175186</td>\n",
" <td>-0.008743</td>\n",
" <td>0.453568</td>\n",
" <td>31.918823</td>\n",
" <td>-1.524353</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809084</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4440</td>\n",
" <td>-0.2384</td>\n",
" <td>-0.8358</td>\n",
" <td>-0.171799</td>\n",
" <td>0.002426</td>\n",
" <td>0.449371</td>\n",
" <td>31.936615</td>\n",
" <td>-1.548767</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809085</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4454</td>\n",
" <td>-0.2388</td>\n",
" <td>-0.8354</td>\n",
" <td>-0.170013</td>\n",
" <td>-0.000549</td>\n",
" <td>0.501633</td>\n",
" <td>31.927704</td>\n",
" <td>-1.564026</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809086</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4430</td>\n",
" <td>-0.2378</td>\n",
" <td>-0.8322</td>\n",
" <td>-0.172348</td>\n",
" <td>-0.009201</td>\n",
" <td>0.494003</td>\n",
" <td>31.926239</td>\n",
" <td>-1.542664</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809087</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4424</td>\n",
" <td>-0.2394</td>\n",
" <td>-0.8342</td>\n",
" <td>-0.176834</td>\n",
" <td>0.001144</td>\n",
" <td>0.482178</td>\n",
" <td>31.912903</td>\n",
" <td>-2.137756</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809088</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4436</td>\n",
" <td>-0.2402</td>\n",
" <td>-0.8342</td>\n",
" <td>-0.182648</td>\n",
" <td>0.002975</td>\n",
" <td>0.468826</td>\n",
" <td>31.924744</td>\n",
" <td>-1.579285</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809089</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4414</td>\n",
" <td>-0.2394</td>\n",
" <td>-0.8322</td>\n",
" <td>-0.190567</td>\n",
" <td>-0.012222</td>\n",
" <td>0.453949</td>\n",
" <td>31.927704</td>\n",
" <td>-1.564026</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809090</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4414</td>\n",
" <td>-0.2376</td>\n",
" <td>-0.8330</td>\n",
" <td>-0.194962</td>\n",
" <td>0.001602</td>\n",
" <td>0.453186</td>\n",
" <td>31.933655</td>\n",
" <td>-2.027893</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809091</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4388</td>\n",
" <td>-0.2374</td>\n",
" <td>-0.8334</td>\n",
" <td>-0.196793</td>\n",
" <td>0.001236</td>\n",
" <td>0.450897</td>\n",
" <td>31.904022</td>\n",
" <td>-1.606750</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809092</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4394</td>\n",
" <td>-0.2374</td>\n",
" <td>-0.8370</td>\n",
" <td>-0.196426</td>\n",
" <td>-0.001511</td>\n",
" <td>0.508118</td>\n",
" <td>31.933655</td>\n",
" <td>-1.585388</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809093</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4386</td>\n",
" <td>-0.2344</td>\n",
" <td>-0.8382</td>\n",
" <td>-0.192764</td>\n",
" <td>-0.000687</td>\n",
" <td>0.508881</td>\n",
" <td>31.929199</td>\n",
" <td>-1.631165</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809094</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4378</td>\n",
" <td>-0.2348</td>\n",
" <td>-0.8380</td>\n",
" <td>-0.182602</td>\n",
" <td>-0.015793</td>\n",
" <td>0.484085</td>\n",
" <td>31.926239</td>\n",
" <td>-1.609802</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809095</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4378</td>\n",
" <td>-0.2338</td>\n",
" <td>-0.8394</td>\n",
" <td>-0.170609</td>\n",
" <td>0.000687</td>\n",
" <td>0.473404</td>\n",
" <td>31.932190</td>\n",
" <td>-1.646423</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809096</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4388</td>\n",
" <td>-0.2338</td>\n",
" <td>-0.8386</td>\n",
" <td>-0.160812</td>\n",
" <td>0.004532</td>\n",
" <td>0.463486</td>\n",
" <td>31.918823</td>\n",
" <td>-1.643372</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809097</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4398</td>\n",
" <td>-0.2374</td>\n",
" <td>-0.8390</td>\n",
" <td>-0.156326</td>\n",
" <td>0.000595</td>\n",
" <td>0.459290</td>\n",
" <td>31.932190</td>\n",
" <td>-1.661682</td>\n",
" </tr>\n",
" <tr>\n",
" <th>16809098</th>\n",
" <td>4</td>\n",
" <td>2</td>\n",
" <td>0.4386</td>\n",
" <td>-0.2366</td>\n",
" <td>-0.8408</td>\n",
" <td>-0.154312</td>\n",
" <td>-0.009201</td>\n",
" <td>0.455475</td>\n",
" <td>31.927704</td>\n",
" <td>-1.646423</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2022299 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" target subject chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG \\\n",
"14786800 1 2 0.8914 -0.1102 -0.2576 0.030945 \n",
"14786801 1 2 0.8926 -0.1086 -0.2544 0.033646 \n",
"14786802 1 2 0.8930 -0.1094 -0.2580 0.033005 \n",
"14786803 1 2 0.8934 -0.1082 -0.2538 0.031815 \n",
"14786804 1 2 0.8930 -0.1096 -0.2570 0.030350 \n",
"... ... ... ... ... ... ... \n",
"16809094 4 2 0.4378 -0.2348 -0.8380 -0.182602 \n",
"16809095 4 2 0.4378 -0.2338 -0.8394 -0.170609 \n",
"16809096 4 2 0.4388 -0.2338 -0.8386 -0.160812 \n",
"16809097 4 2 0.4398 -0.2374 -0.8390 -0.156326 \n",
"16809098 4 2 0.4386 -0.2366 -0.8408 -0.154312 \n",
"\n",
" chest_EMG chest_EDA chest_Temp chest_Resp \n",
"14786800 -0.003708 5.710983 29.083618 1.191711 \n",
"14786801 -0.014145 5.719376 29.122437 1.139832 \n",
"14786802 0.010208 5.706406 29.115234 1.141357 \n",
"14786803 0.012634 5.712509 29.126709 1.155090 \n",
"14786804 0.002060 5.727005 29.100861 1.133728 \n",
"... ... ... ... ... \n",
"16809094 -0.015793 0.484085 31.926239 -1.609802 \n",
"16809095 0.000687 0.473404 31.932190 -1.646423 \n",
"16809096 0.004532 0.463486 31.918823 -1.643372 \n",
"16809097 0.000595 0.459290 31.932190 -1.661682 \n",
"16809098 -0.009201 0.455475 31.927704 -1.646423 \n",
"\n",
"[2022299 rows x 10 columns]"
]
},
"execution_count": 18,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"subject_2"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {
"scrolled": true
},
"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>target</th>\n",
" <th>subject</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_EMG</th>\n",
" <th>chest_EDA</th>\n",
" <th>chest_Temp</th>\n",
" <th>chest_Resp</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>14807800</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8334</td>\n",
" <td>-0.0422</td>\n",
" <td>-0.4328</td>\n",
" <td>0.153305</td>\n",
" <td>-0.009659</td>\n",
" <td>4.866028</td>\n",
" <td>29.234650</td>\n",
" <td>-7.191467</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807801</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8346</td>\n",
" <td>-0.0392</td>\n",
" <td>-0.4312</td>\n",
" <td>0.155319</td>\n",
" <td>0.004257</td>\n",
" <td>4.887772</td>\n",
" <td>29.237518</td>\n",
" <td>-7.179260</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807802</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8328</td>\n",
" <td>-0.0412</td>\n",
" <td>-0.4306</td>\n",
" <td>0.148911</td>\n",
" <td>0.003525</td>\n",
" <td>4.865265</td>\n",
" <td>29.226013</td>\n",
" <td>-7.179260</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807803</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8354</td>\n",
" <td>-0.0418</td>\n",
" <td>-0.4376</td>\n",
" <td>0.138016</td>\n",
" <td>-0.013687</td>\n",
" <td>4.876328</td>\n",
" <td>29.230316</td>\n",
" <td>-7.171631</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807804</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8366</td>\n",
" <td>-0.0446</td>\n",
" <td>-0.4416</td>\n",
" <td>0.130600</td>\n",
" <td>-0.012131</td>\n",
" <td>4.893494</td>\n",
" <td>29.221680</td>\n",
" <td>-7.147217</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807805</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8346</td>\n",
" <td>-0.0442</td>\n",
" <td>-0.4446</td>\n",
" <td>0.127213</td>\n",
" <td>0.002518</td>\n",
" <td>4.875183</td>\n",
" <td>29.279236</td>\n",
" <td>-7.124329</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807806</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8318</td>\n",
" <td>-0.0434</td>\n",
" <td>-0.4434</td>\n",
" <td>0.126526</td>\n",
" <td>0.011581</td>\n",
" <td>4.880142</td>\n",
" <td>29.234650</td>\n",
" <td>-7.127380</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807807</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8322</td>\n",
" <td>-0.0466</td>\n",
" <td>-0.4424</td>\n",
" <td>0.120438</td>\n",
" <td>-0.007004</td>\n",
" <td>4.867554</td>\n",
" <td>29.198639</td>\n",
" <td>-7.127380</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807808</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8314</td>\n",
" <td>-0.0454</td>\n",
" <td>-0.4406</td>\n",
" <td>0.108994</td>\n",
" <td>-0.026871</td>\n",
" <td>4.872513</td>\n",
" <td>29.312378</td>\n",
" <td>-7.237244</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807809</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8322</td>\n",
" <td>-0.0454</td>\n",
" <td>-0.4406</td>\n",
" <td>0.098648</td>\n",
" <td>-0.037399</td>\n",
" <td>4.884720</td>\n",
" <td>29.238953</td>\n",
" <td>-7.106018</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807810</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8318</td>\n",
" <td>-0.0466</td>\n",
" <td>-0.4370</td>\n",
" <td>0.093201</td>\n",
" <td>-0.013000</td>\n",
" <td>4.866028</td>\n",
" <td>29.204376</td>\n",
" <td>-7.081604</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807811</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8302</td>\n",
" <td>-0.0454</td>\n",
" <td>-0.4438</td>\n",
" <td>0.091049</td>\n",
" <td>0.017166</td>\n",
" <td>4.871368</td>\n",
" <td>29.290771</td>\n",
" <td>-7.098389</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807812</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8290</td>\n",
" <td>-0.0430</td>\n",
" <td>-0.4460</td>\n",
" <td>0.088806</td>\n",
" <td>0.023300</td>\n",
" <td>4.887009</td>\n",
" <td>29.233185</td>\n",
" <td>-7.072449</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807813</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8290</td>\n",
" <td>-0.0438</td>\n",
" <td>-0.4418</td>\n",
" <td>0.086105</td>\n",
" <td>0.011307</td>\n",
" <td>4.864883</td>\n",
" <td>29.217346</td>\n",
" <td>-7.070923</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807814</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8298</td>\n",
" <td>-0.0478</td>\n",
" <td>-0.4418</td>\n",
" <td>0.086472</td>\n",
" <td>0.008972</td>\n",
" <td>4.875565</td>\n",
" <td>29.215912</td>\n",
" <td>-7.044983</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807815</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8266</td>\n",
" <td>-0.0498</td>\n",
" <td>-0.4392</td>\n",
" <td>0.078690</td>\n",
" <td>0.008377</td>\n",
" <td>4.867172</td>\n",
" <td>29.230316</td>\n",
" <td>-7.041931</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807816</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8250</td>\n",
" <td>-0.0530</td>\n",
" <td>-0.4358</td>\n",
" <td>0.069168</td>\n",
" <td>0.000504</td>\n",
" <td>4.864883</td>\n",
" <td>29.207275</td>\n",
" <td>-7.048035</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807817</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8258</td>\n",
" <td>-0.0542</td>\n",
" <td>-0.4322</td>\n",
" <td>0.062073</td>\n",
" <td>-0.004166</td>\n",
" <td>4.873276</td>\n",
" <td>29.259094</td>\n",
" <td>-7.011414</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807818</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8250</td>\n",
" <td>-0.0534</td>\n",
" <td>-0.4274</td>\n",
" <td>0.054794</td>\n",
" <td>-0.002747</td>\n",
" <td>4.883957</td>\n",
" <td>29.230316</td>\n",
" <td>-7.025146</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807819</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8226</td>\n",
" <td>-0.0582</td>\n",
" <td>-0.4210</td>\n",
" <td>0.048843</td>\n",
" <td>-0.010574</td>\n",
" <td>4.892349</td>\n",
" <td>29.227417</td>\n",
" <td>-6.993103</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807820</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8218</td>\n",
" <td>-0.0624</td>\n",
" <td>-0.4244</td>\n",
" <td>0.046234</td>\n",
" <td>-0.006363</td>\n",
" <td>4.864883</td>\n",
" <td>29.233185</td>\n",
" <td>-6.977844</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807821</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8194</td>\n",
" <td>-0.0642</td>\n",
" <td>-0.4244</td>\n",
" <td>0.044724</td>\n",
" <td>-0.005905</td>\n",
" <td>4.865265</td>\n",
" <td>29.200073</td>\n",
" <td>-6.971741</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807822</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8188</td>\n",
" <td>-0.0678</td>\n",
" <td>-0.4200</td>\n",
" <td>0.042068</td>\n",
" <td>-0.000641</td>\n",
" <td>4.874420</td>\n",
" <td>29.290771</td>\n",
" <td>-6.959534</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807823</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8174</td>\n",
" <td>-0.0704</td>\n",
" <td>-0.4178</td>\n",
" <td>0.037170</td>\n",
" <td>0.004807</td>\n",
" <td>4.890823</td>\n",
" <td>29.224548</td>\n",
" <td>-6.956482</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807824</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8148</td>\n",
" <td>-0.0744</td>\n",
" <td>-0.4234</td>\n",
" <td>0.030533</td>\n",
" <td>0.003113</td>\n",
" <td>4.863739</td>\n",
" <td>29.226013</td>\n",
" <td>-6.932068</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807825</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8118</td>\n",
" <td>-0.0776</td>\n",
" <td>-0.4182</td>\n",
" <td>0.022888</td>\n",
" <td>-0.002243</td>\n",
" <td>4.870987</td>\n",
" <td>29.218811</td>\n",
" <td>-6.929016</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807826</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8114</td>\n",
" <td>-0.0806</td>\n",
" <td>-0.4210</td>\n",
" <td>0.016342</td>\n",
" <td>0.009109</td>\n",
" <td>4.890442</td>\n",
" <td>29.220215</td>\n",
" <td>-6.912231</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807827</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8074</td>\n",
" <td>-0.0840</td>\n",
" <td>-0.4172</td>\n",
" <td>0.007462</td>\n",
" <td>0.013596</td>\n",
" <td>4.864502</td>\n",
" <td>29.221680</td>\n",
" <td>-6.898499</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807828</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8030</td>\n",
" <td>-0.0838</td>\n",
" <td>-0.4166</td>\n",
" <td>-0.000046</td>\n",
" <td>-0.005539</td>\n",
" <td>4.878998</td>\n",
" <td>29.218811</td>\n",
" <td>-6.892395</td>\n",
" </tr>\n",
" <tr>\n",
" <th>14807829</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.8014</td>\n",
" <td>-0.0902</td>\n",
" <td>-0.4178</td>\n",
" <td>-0.007874</td>\n",
" <td>-0.004807</td>\n",
" <td>4.863739</td>\n",
" <td>29.211609</td>\n",
" <td>-6.878662</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587570</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7886</td>\n",
" <td>0.1476</td>\n",
" <td>0.1152</td>\n",
" <td>-0.083038</td>\n",
" <td>-0.000504</td>\n",
" <td>1.179504</td>\n",
" <td>29.723724</td>\n",
" <td>-2.064514</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587571</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7866</td>\n",
" <td>0.1450</td>\n",
" <td>0.1198</td>\n",
" <td>-0.061203</td>\n",
" <td>0.002747</td>\n",
" <td>1.181793</td>\n",
" <td>29.723724</td>\n",
" <td>-2.049255</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587572</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7826</td>\n",
" <td>0.1444</td>\n",
" <td>0.1274</td>\n",
" <td>-0.028152</td>\n",
" <td>-0.005859</td>\n",
" <td>1.183319</td>\n",
" <td>29.762756</td>\n",
" <td>-1.989746</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587573</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7768</td>\n",
" <td>0.1442</td>\n",
" <td>0.1374</td>\n",
" <td>0.030945</td>\n",
" <td>0.000961</td>\n",
" <td>1.187134</td>\n",
" <td>29.712128</td>\n",
" <td>-1.959229</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587574</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7704</td>\n",
" <td>0.1430</td>\n",
" <td>0.1428</td>\n",
" <td>0.068848</td>\n",
" <td>-0.005676</td>\n",
" <td>1.192474</td>\n",
" <td>29.712128</td>\n",
" <td>-1.901245</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587575</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7662</td>\n",
" <td>0.1416</td>\n",
" <td>0.1472</td>\n",
" <td>0.084961</td>\n",
" <td>0.001694</td>\n",
" <td>1.193619</td>\n",
" <td>29.726593</td>\n",
" <td>-1.884460</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587576</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7608</td>\n",
" <td>0.1428</td>\n",
" <td>0.1566</td>\n",
" <td>0.084045</td>\n",
" <td>0.011215</td>\n",
" <td>1.198959</td>\n",
" <td>29.712128</td>\n",
" <td>-1.856995</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587577</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7598</td>\n",
" <td>0.1432</td>\n",
" <td>0.1578</td>\n",
" <td>0.081665</td>\n",
" <td>-0.000320</td>\n",
" <td>1.212311</td>\n",
" <td>29.722229</td>\n",
" <td>-1.799011</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587578</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7550</td>\n",
" <td>0.1432</td>\n",
" <td>0.1562</td>\n",
" <td>0.084091</td>\n",
" <td>0.001968</td>\n",
" <td>1.214218</td>\n",
" <td>29.723724</td>\n",
" <td>-1.776123</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587579</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7474</td>\n",
" <td>0.1406</td>\n",
" <td>0.1494</td>\n",
" <td>0.086380</td>\n",
" <td>-0.001740</td>\n",
" <td>1.204300</td>\n",
" <td>29.765656</td>\n",
" <td>-1.727295</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587580</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7410</td>\n",
" <td>0.1422</td>\n",
" <td>0.1390</td>\n",
" <td>0.098282</td>\n",
" <td>-0.007919</td>\n",
" <td>1.205826</td>\n",
" <td>29.715027</td>\n",
" <td>-1.702881</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587581</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7362</td>\n",
" <td>0.1370</td>\n",
" <td>0.1314</td>\n",
" <td>0.109543</td>\n",
" <td>-0.005081</td>\n",
" <td>1.202011</td>\n",
" <td>29.709229</td>\n",
" <td>-1.661682</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587582</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7304</td>\n",
" <td>0.1322</td>\n",
" <td>0.1266</td>\n",
" <td>0.129227</td>\n",
" <td>0.009842</td>\n",
" <td>1.199722</td>\n",
" <td>29.720825</td>\n",
" <td>-1.640320</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587583</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7270</td>\n",
" <td>0.1250</td>\n",
" <td>0.1202</td>\n",
" <td>0.187042</td>\n",
" <td>-0.001511</td>\n",
" <td>1.190948</td>\n",
" <td>29.771454</td>\n",
" <td>-1.588440</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587584</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7234</td>\n",
" <td>0.1224</td>\n",
" <td>0.1106</td>\n",
" <td>0.203568</td>\n",
" <td>-0.003250</td>\n",
" <td>1.194000</td>\n",
" <td>29.700562</td>\n",
" <td>-1.551819</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587585</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7206</td>\n",
" <td>0.1210</td>\n",
" <td>0.0986</td>\n",
" <td>0.202515</td>\n",
" <td>0.010941</td>\n",
" <td>1.185608</td>\n",
" <td>29.726593</td>\n",
" <td>-1.513672</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587586</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7170</td>\n",
" <td>0.1178</td>\n",
" <td>0.0866</td>\n",
" <td>0.198166</td>\n",
" <td>-0.000687</td>\n",
" <td>1.184082</td>\n",
" <td>29.801849</td>\n",
" <td>-1.606750</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587587</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7128</td>\n",
" <td>0.1146</td>\n",
" <td>0.0714</td>\n",
" <td>0.199905</td>\n",
" <td>-0.017899</td>\n",
" <td>1.185226</td>\n",
" <td>29.735260</td>\n",
" <td>-1.445007</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587588</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7128</td>\n",
" <td>0.1118</td>\n",
" <td>0.0552</td>\n",
" <td>0.204208</td>\n",
" <td>-0.010757</td>\n",
" <td>1.272202</td>\n",
" <td>29.728058</td>\n",
" <td>-1.393127</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587589</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7146</td>\n",
" <td>0.1146</td>\n",
" <td>0.0390</td>\n",
" <td>0.208603</td>\n",
" <td>-0.023209</td>\n",
" <td>1.227570</td>\n",
" <td>29.729492</td>\n",
" <td>-1.380920</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587590</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7162</td>\n",
" <td>0.1122</td>\n",
" <td>0.0198</td>\n",
" <td>0.214554</td>\n",
" <td>-0.005814</td>\n",
" <td>1.220322</td>\n",
" <td>29.723724</td>\n",
" <td>-1.335144</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587591</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7182</td>\n",
" <td>0.1082</td>\n",
" <td>0.0062</td>\n",
" <td>0.228470</td>\n",
" <td>-0.003708</td>\n",
" <td>1.217270</td>\n",
" <td>29.712128</td>\n",
" <td>-1.303101</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587592</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7182</td>\n",
" <td>0.1010</td>\n",
" <td>-0.0054</td>\n",
" <td>0.244858</td>\n",
" <td>0.008102</td>\n",
" <td>1.217270</td>\n",
" <td>29.723724</td>\n",
" <td>-1.252747</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587593</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7194</td>\n",
" <td>0.0962</td>\n",
" <td>-0.0142</td>\n",
" <td>0.265045</td>\n",
" <td>0.008011</td>\n",
" <td>1.222992</td>\n",
" <td>29.754089</td>\n",
" <td>-1.229858</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587594</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7186</td>\n",
" <td>0.0882</td>\n",
" <td>-0.0274</td>\n",
" <td>0.287659</td>\n",
" <td>0.016068</td>\n",
" <td>1.215363</td>\n",
" <td>29.703461</td>\n",
" <td>-1.167297</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587595</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7148</td>\n",
" <td>0.0758</td>\n",
" <td>-0.0428</td>\n",
" <td>0.308167</td>\n",
" <td>0.016617</td>\n",
" <td>1.204681</td>\n",
" <td>29.716492</td>\n",
" <td>-1.144409</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587596</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7144</td>\n",
" <td>0.0670</td>\n",
" <td>-0.0618</td>\n",
" <td>0.332840</td>\n",
" <td>-0.001740</td>\n",
" <td>1.197052</td>\n",
" <td>29.762756</td>\n",
" <td>-1.118469</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587597</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7146</td>\n",
" <td>0.0642</td>\n",
" <td>-0.0726</td>\n",
" <td>0.359528</td>\n",
" <td>-0.005814</td>\n",
" <td>1.200104</td>\n",
" <td>29.715027</td>\n",
" <td>-1.078796</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587598</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7244</td>\n",
" <td>0.0606</td>\n",
" <td>-0.0818</td>\n",
" <td>0.387680</td>\n",
" <td>-0.001602</td>\n",
" <td>1.190948</td>\n",
" <td>29.717896</td>\n",
" <td>-1.025391</td>\n",
" </tr>\n",
" <tr>\n",
" <th>15587599</th>\n",
" <td>1</td>\n",
" <td>2</td>\n",
" <td>0.7282</td>\n",
" <td>0.0506</td>\n",
" <td>-0.0948</td>\n",
" <td>0.415009</td>\n",
" <td>-0.028244</td>\n",
" <td>1.198959</td>\n",
" <td>29.717896</td>\n",
" <td>-0.996399</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>779800 rows × 10 columns</p>\n",
"</div>"
],
"text/plain": [
" target subject chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG \\\n",
"14807800 1 2 0.8334 -0.0422 -0.4328 0.153305 \n",
"14807801 1 2 0.8346 -0.0392 -0.4312 0.155319 \n",
"14807802 1 2 0.8328 -0.0412 -0.4306 0.148911 \n",
"14807803 1 2 0.8354 -0.0418 -0.4376 0.138016 \n",
"14807804 1 2 0.8366 -0.0446 -0.4416 0.130600 \n",
"... ... ... ... ... ... ... \n",
"15587595 1 2 0.7148 0.0758 -0.0428 0.308167 \n",
"15587596 1 2 0.7144 0.0670 -0.0618 0.332840 \n",
"15587597 1 2 0.7146 0.0642 -0.0726 0.359528 \n",
"15587598 1 2 0.7244 0.0606 -0.0818 0.387680 \n",
"15587599 1 2 0.7282 0.0506 -0.0948 0.415009 \n",
"\n",
" chest_EMG chest_EDA chest_Temp chest_Resp \n",
"14807800 -0.009659 4.866028 29.234650 -7.191467 \n",
"14807801 0.004257 4.887772 29.237518 -7.179260 \n",
"14807802 0.003525 4.865265 29.226013 -7.179260 \n",
"14807803 -0.013687 4.876328 29.230316 -7.171631 \n",
"14807804 -0.012131 4.893494 29.221680 -7.147217 \n",
"... ... ... ... ... \n",
"15587595 0.016617 1.204681 29.716492 -1.144409 \n",
"15587596 -0.001740 1.197052 29.762756 -1.118469 \n",
"15587597 -0.005814 1.200104 29.715027 -1.078796 \n",
"15587598 -0.001602 1.190948 29.717896 -1.025391 \n",
"15587599 -0.028244 1.198959 29.717896 -0.996399 \n",
"\n",
"[779800 rows x 10 columns]"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"concat_list1=[]\n",
"for i in cls:\n",
" for j in x:\n",
" concat_list1.append(globals()['df_{}_test_{}'.format(i,j)])\n",
"concat_list1[0]"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"(1260000, 10)"
]
},
"execution_count": 20,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_df=pd.concat(concat_list)\n",
"train_df.shape"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"4 315000\n",
"3 315000\n",
"2 315000\n",
"1 315000\n",
"Name: target, dtype: int64"
]
},
"execution_count": 21,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_df.target.value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"scrolled": true
},
"outputs": [
{
"data": {
"text/plain": [
"17 84000\n",
"16 84000\n",
"15 84000\n",
"14 84000\n",
"13 84000\n",
"11 84000\n",
"10 84000\n",
"9 84000\n",
"8 84000\n",
"7 84000\n",
"6 84000\n",
"5 84000\n",
"4 84000\n",
"3 84000\n",
"2 84000\n",
"Name: subject, dtype: int64"
]
},
"execution_count": 22,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_df.subject.value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"(30210603, 10)"
]
},
"execution_count": 23,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"test_df=pd.concat(concat_list1)\n",
"test_df.shape"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"for i in test_subject:\n",
" del(globals()['subject_%s' % i])\n",
" \n",
"for i in range(len(x)): \n",
" del(globals()['df_1_%s' % x[i]])\n",
" del(globals()['df_2_%s' % x[i]])\n",
" del(globals()['df_3_%s' % x[i]])\n",
" del(globals()['df_4_%s' % x[i]])\n",
"for i in cls:\n",
" for j in x:\n",
" del(globals()['df_{}_train_{}'.format(i,j)])\n",
" del(globals()['df_{}_test_{}'.format(i,j)])\n",
"del df"
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ExtraTreesClassifier\t LogisticRegression\t RandomForestClassifier\t classification_report\t cls\t concat_list\t concat_list1\t feature\t features\t \n",
"i\t j\t list_of_subjects\t no_of_rows\t np\t pd\t subject_list\t test_df\t test_subject\t \n",
"to_remove\t train_df\t train_test_split\t x\t \n"
]
}
],
"source": [
"who"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 112 µs, sys: 27 µs, total: 139 µs\n",
"Wall time: 144 µs\n"
]
}
],
"source": [
"%%time\n",
"et = ExtraTreesClassifier(n_estimators=50, n_jobs=10, verbose=2,random_state=0)"
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"#et = RandomForestClassifier(n_estimators=100, n_jobs=10, verbose=2,random_state=0)"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"building tree 1 of 50\n",
"building tree 2 of 50\n",
"building tree 3 of 50\n",
"building tree 4 of 50\n",
"building tree 5 of 50\n",
"building tree 6 of 50\n",
"building tree 7 of 50\n",
"building tree 8 of 50\n",
"building tree 9 of 50\n",
"building tree 10 of 50\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[Parallel(n_jobs=10)]: Using backend ThreadingBackend with 10 concurrent workers.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"building tree 11 of 50\n",
"building tree 12 of 50\n",
"building tree 13 of 50\n",
"building tree 14 of 50\n",
"building tree 15 of 50\n",
"building tree 16 of 50\n",
"building tree 17 of 50\n",
"building tree 18 of 50\n",
"building tree 19 of 50\n",
"building tree 20 of 50\n",
"building tree 21 of 50\n",
"building tree 22 of 50\n",
"building tree 23 of 50\n",
"building tree 24 of 50\n",
"building tree 25 of 50\n",
"building tree 26 of 50\n",
"building tree 27 of 50\n",
"building tree 28 of 50\n",
"building tree 29 of 50\n",
"building tree 30 of 50\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 2.2s\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"building tree 31 of 50\n",
"building tree 32 of 50\n",
"building tree 33 of 50\n",
"building tree 34 of 50\n",
"building tree 35 of 50\n",
"building tree 36 of 50\n",
"building tree 37 of 50\n",
"building tree 38 of 50\n",
"building tree 39 of 50\n",
"building tree 40 of 50\n",
"building tree 41 of 50\n",
"building tree 42 of 50\n",
"building tree 43 of 50\n",
"building tree 44 of 50\n",
"building tree 45 of 50\n",
"building tree 46 of 50\n",
"building tree 47 of 50\n",
"building tree 48 of 50\n",
"building tree 49 of 50\n",
"building tree 50 of 50\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 4.9s finished\n"
]
},
{
"data": {
"text/plain": [
"ExtraTreesClassifier(bootstrap=False, class_weight=None, criterion='gini',\n",
" max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
" min_impurity_decrease=0.0, min_impurity_split=None,\n",
" min_samples_leaf=1, min_samples_split=2,\n",
" min_weight_fraction_leaf=0.0, n_estimators=50, n_jobs=10,\n",
" oob_score=False, random_state=0, verbose=2,\n",
" warm_start=False)"
]
},
"execution_count": 29,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"et.fit(train_df[feature],train_df['target'])"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[Parallel(n_jobs=10)]: Using backend ThreadingBackend with 10 concurrent workers.\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 22.6s\n",
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 40.6s finished\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"CPU times: user 3min 41s, sys: 58.9 s, total: 4min 40s\n",
"Wall time: 44.2 s\n"
]
}
],
"source": [
"%%time \n",
"y_pred=et.predict(test_df[feature])"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" 1 0.87 0.60 0.71 12012702\n",
" 2 0.67 0.83 0.74 6661201\n",
" 3 0.66 0.82 0.73 3587501\n",
" 4 0.65 0.76 0.70 7949199\n",
"\n",
" accuracy 0.72 30210603\n",
" macro avg 0.71 0.75 0.72 30210603\n",
"weighted avg 0.75 0.72 0.72 30210603\n",
"\n"
]
}
],
"source": [
"print(classification_report(test_df['target'], y_pred))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"#train_df.to_csv('1_min_train.csv')"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"#test_df.to_csv('1_min_test.csv')"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 4.4s\n",
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 6.3s finished\n",
"[Parallel(n_jobs=10)]: Using backend ThreadingBackend with 10 concurrent workers.\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 0.1s\n",
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 0.2s finished\n",
"[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 1.9s\n",
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 3.8s finished\n",
"[Parallel(n_jobs=10)]: Using backend ThreadingBackend with 10 concurrent workers.\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 0.1s\n",
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 0.3s finished\n",
"[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 1.7s\n",
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 3.7s finished\n",
"[Parallel(n_jobs=10)]: Using backend ThreadingBackend with 10 concurrent workers.\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 0.2s\n",
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 0.3s finished\n",
"[Parallel(n_jobs=10)]: Using backend LokyBackend with 10 concurrent workers.\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 1.9s\n",
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 3.8s finished\n",
"[Parallel(n_jobs=10)]: Using backend ThreadingBackend with 10 concurrent workers.\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 0.2s\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[0.39672381 0.42419048 0.43319683 0.5674381 ]\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 0.3s finished\n"
]
}
],
"source": [
"from sklearn.model_selection import cross_val_score\n",
"scores = cross_val_score(et, train_df[feature],train_df['target'], cv=4)\n",
"print(scores)"
]
},
{
"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
}