Datasets
Models
Downloads: 1
[d8f241]:
/
Dependent Vs Independent.ipynb
746 lines (745 with data), 28.3 kB
{
"cells": [
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T03:28:20.614469Z",
"start_time": "2019-07-21T03:28:19.208340Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using TensorFlow backend.\n"
]
}
],
"source": [
"#This code is for adaptive GPU usage\n",
"import keras.backend as K\n",
"cfg = K.tf.ConfigProto()\n",
"cfg.gpu_options.allow_growth = True\n",
"K.set_session(K.tf.Session(config=cfg))"
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-23T12:10:14.715612Z",
"start_time": "2019-07-23T12:10:14.196989Z"
}
},
"outputs": [],
"source": [
"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"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-23T13:09:10.760608Z",
"start_time": "2019-07-23T13:09:10.743179Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"15"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"subject=[2,3,4,5,6,7,8,9,10,11,13,14,15,16,17]\n",
"len(subject)"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-23T12:10:50.414237Z",
"start_time": "2019-07-23T12:10:23.407112Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"subject_2\n",
"subject_3\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m<ipython-input-3-8c3302bbf9e7>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0msubject\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mglobals\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'subject_%s'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpd\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread_csv\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"Sub_\"\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0;34m\".csv\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0mglobals\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'subject_%s'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mglobals\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'subject_%s'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mglobals\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'subject_%s'\u001b[0m \u001b[0;34m%\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'label'\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m<=\u001b[0m \u001b[0;36m4\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0msubject_2_train\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0msubject_2_test\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtrain_test_split\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msubject_2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtest_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.3\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'subject_'\u001b[0m\u001b[0;34m+\u001b[0m\u001b[0mstr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/anaconda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mparser_f\u001b[0;34m(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, squeeze, prefix, mangle_dupe_cols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, dayfirst, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, escapechar, comment, encoding, dialect, tupleize_cols, error_bad_lines, warn_bad_lines, skipfooter, doublequote, delim_whitespace, low_memory, memory_map, float_precision)\u001b[0m\n\u001b[1;32m 676\u001b[0m skip_blank_lines=skip_blank_lines)\n\u001b[1;32m 677\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 678\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0m_read\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfilepath_or_buffer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkwds\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 679\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 680\u001b[0m \u001b[0mparser_f\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__name__\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/anaconda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36m_read\u001b[0;34m(filepath_or_buffer, kwds)\u001b[0m\n\u001b[1;32m 444\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 445\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 446\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 447\u001b[0m \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 448\u001b[0m \u001b[0mparser\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/anaconda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, nrows)\u001b[0m\n\u001b[1;32m 1034\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'skipfooter not supported for iteration'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1035\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1036\u001b[0;31m \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1037\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1038\u001b[0m \u001b[0;31m# May alter columns / col_dict\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/opt/anaconda/lib/python3.6/site-packages/pandas/io/parsers.py\u001b[0m in \u001b[0;36mread\u001b[0;34m(self, nrows)\u001b[0m\n\u001b[1;32m 1846\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnrows\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1847\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1848\u001b[0;31m \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_reader\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mread\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnrows\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1849\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mStopIteration\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1850\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_first_chunk\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader.read\u001b[0;34m()\u001b[0m\n",
"\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._read_low_memory\u001b[0;34m()\u001b[0m\n",
"\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers._concatenate_chunks\u001b[0;34m()\u001b[0m\n",
"\u001b[0;32m/opt/anaconda/lib/python3.6/site-packages/pandas/core/dtypes/common.py\u001b[0m in \u001b[0;36mis_categorical_dtype\u001b[0;34m(arr_or_dtype)\u001b[0m\n\u001b[1;32m 511\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 512\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 513\u001b[0;31m \u001b[0;32mdef\u001b[0m \u001b[0mis_categorical_dtype\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0marr_or_dtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 514\u001b[0m \"\"\"\n\u001b[1;32m 515\u001b[0m \u001b[0mCheck\u001b[0m \u001b[0mwhether\u001b[0m \u001b[0man\u001b[0m \u001b[0marray\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0mlike\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mdtype\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0mof\u001b[0m \u001b[0mthe\u001b[0m \u001b[0mCategorical\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"for i in subject:\n",
" globals()['subject_%s' % i] = pd.read_csv(\"Sub_\"+str(i)+\".csv\")\n",
" globals()['subject_%s' % i]=globals()['subject_%s' % i][globals()['subject_%s' % i]['label'] <= 4]\n",
" #subject_2_train,subject_2_test=train_test_split(subject_2, test_size=0.3)\n",
" print('subject_'+str(i))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"%%time\n",
"df = pd.read_csv(\"master_data.csv\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"df=df[df['target']!=0]\n",
"df"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T03:48:13.626469Z",
"start_time": "2019-07-21T03:48:11.630785Z"
}
},
"outputs": [],
"source": [
"train=pd.concat([subject_2,subject_3,subject_4,subject_5,subject_6,subject_7,subject_8,subject_9,subject_10,subject_11])"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T03:48:14.534888Z",
"start_time": "2019-07-21T03:48:13.628414Z"
}
},
"outputs": [],
"source": [
"test=pd.concat([subject_13,subject_14,subject_15,subject_16,subject_17])"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T03:48:14.544552Z",
"start_time": "2019-07-21T03:48:14.536781Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Index 321148792\n",
"subject 321148792\n",
"ACC_x 321148792\n",
"ACC_y 321148792\n",
"ACC_z 321148792\n",
"ECG 321148792\n",
"EMG 321148792\n",
"EDA 321148792\n",
"Temp 321148792\n",
"Resp 321148792\n",
"label 321148792\n",
"dtype: int64\n",
"Index 151855208\n",
"subject 151855208\n",
"ACC_x 151855208\n",
"ACC_y 151855208\n",
"ACC_z 151855208\n",
"ECG 151855208\n",
"EMG 151855208\n",
"EDA 151855208\n",
"Temp 151855208\n",
"Resp 151855208\n",
"label 151855208\n",
"dtype: int64\n"
]
}
],
"source": [
"print(train.memory_usage(index=True, deep=False))\n",
"print(test.memory_usage(index=True, deep=False))"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T03:48:15.689593Z",
"start_time": "2019-07-21T03:48:14.546129Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"Int64Index: 40143599 entries, 0 to 3663099\n",
"Data columns (total 10 columns):\n",
"subject int64\n",
"ACC_x float64\n",
"ACC_y float64\n",
"ACC_z float64\n",
"ECG float64\n",
"EMG float64\n",
"EDA float64\n",
"Temp float64\n",
"Resp float64\n",
"label int64\n",
"dtypes: float64(8), int64(2)\n",
"memory usage: 3.3 GB\n",
"None\n",
"<class 'pandas.core.frame.DataFrame'>\n",
"Int64Index: 18981901 entries, 0 to 4143999\n",
"Data columns (total 10 columns):\n",
"subject int64\n",
"ACC_x float64\n",
"ACC_y float64\n",
"ACC_z float64\n",
"ECG float64\n",
"EMG float64\n",
"EDA float64\n",
"Temp float64\n",
"Resp float64\n",
"label int64\n",
"dtypes: float64(8), int64(2)\n",
"memory usage: 1.6 GB\n",
"None\n"
]
}
],
"source": [
"print(train.info(memory_usage='deep'))\n",
"print(test.info(memory_usage='deep'))"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-23T13:09:21.798204Z",
"start_time": "2019-07-23T13:09:21.793394Z"
}
},
"outputs": [],
"source": [
"features=['subject','ACC_x','ACC_y','ACC_z','ECG','EMG','EDA','Temp','Resp']\n",
"target=['label']"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T03:57:26.901617Z",
"start_time": "2019-07-21T03:50:57.031138Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/anaconda/lib/python3.6/site-packages/ipykernel_launcher.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
" \n"
]
},
{
"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",
"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",
"building tree 31 of 50\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 3.0min\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"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 50building tree 38 of 50\n",
"\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: 5.9min finished\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 12.6s\n",
"[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 24.5s finished\n"
]
}
],
"source": [
"et = ExtraTreesClassifier(n_estimators=50, n_jobs=10, verbose=2)\n",
"et.fit(train[features],train[target])\n",
"y_pred=et.predict(test[features])"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T03:57:45.807406Z",
"start_time": "2019-07-21T03:57:40.672071Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" 0 0.43 0.75 0.55 8419601\n",
" 1 0.04 0.04 0.04 4127201\n",
" 2 0.15 0.01 0.03 2394701\n",
" 3 0.00 0.00 0.00 1306201\n",
" 4 0.00 0.00 0.00 2734197\n",
"\n",
"avg / total 0.22 0.34 0.25 18981901\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/anaconda/lib/python3.6/site-packages/sklearn/metrics/classification.py:1135: UndefinedMetricWarning: Precision and F-score are ill-defined and being set to 0.0 in labels with no predicted samples.\n",
" 'precision', 'predicted', average, warn_for)\n"
]
}
],
"source": [
"print(classification_report(test[target],y_pred ))"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T03:57:54.022571Z",
"start_time": "2019-07-21T03:57:53.711601Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"array([0.08156137, 0.10834554, 0.12135855, 0.19428681, 0.0057354 ,\n",
" 0.00575368, 0.24000214, 0.21983822, 0.02311827])"
]
},
"execution_count": 16,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"et.feature_importances_"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-23T13:09:31.720954Z",
"start_time": "2019-07-23T13:09:31.713668Z"
}
},
"outputs": [
{
"data": {
"text/plain": [
"['subject', 'ACC_x', 'ACC_y', 'ACC_z', 'ECG', 'EMG', 'EDA', 'Temp', 'Resp']"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"features"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# 70-30 all subject"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T04:03:43.043681Z",
"start_time": "2019-07-21T04:01:34.361732Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"subject_2\n",
"subject_3\n",
"subject_4\n",
"subject_5\n",
"subject_6\n",
"subject_7\n",
"subject_8\n",
"subject_9\n",
"subject_10\n",
"subject_11\n",
"subject_13\n",
"subject_14\n",
"subject_15\n",
"subject_16\n",
"subject_17\n"
]
}
],
"source": [
"for i in subject:\n",
" globals()['subject_%s' % i] = pd.read_csv(\"Sub_\"+str(i)+\".csv\")\n",
" globals()['subject_%s' % i]=globals()['subject_%s' % i][globals()['subject_%s' % i]['label'] <= 4]\n",
" globals()['subject_%s_train' % i],globals()['subject_%s_test' % i]=train_test_split(globals()['subject_%s' % i], test_size=0.3)\n",
" print('subject_'+str(i))"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T04:01:07.867253Z",
"start_time": "2019-07-21T04:01:07.861501Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ExtraTreesClassifier\t autopep8\t classification_report\t features\t i\t json\t np\t pd\t subject\t \n",
"subject_10\t subject_11\t subject_13\t subject_14\t subject_15\t subject_16\t subject_17\t subject_2\t subject_2_test\t \n",
"subject_2_train\t subject_3\t subject_4\t subject_5\t subject_6\t subject_7\t subject_8\t subject_9\t target\t \n",
"test\t train\t train_test_split\t y_pred\t \n"
]
}
],
"source": [
"who"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T04:03:53.417465Z",
"start_time": "2019-07-21T04:03:50.257592Z"
}
},
"outputs": [],
"source": [
"train=pd.concat([subject_2_train,subject_3_train,subject_4_train,subject_5_train,subject_6_train,subject_7_train,subject_8_train,subject_9_train,subject_10_train,subject_11_train,subject_13_train,subject_14_train,subject_15_train,subject_16_train,subject_17_train])\n",
"test=pd.concat([subject_2_test,subject_3_test,subject_4_test,subject_5_test,subject_6_test,subject_7_test,subject_8_test,subject_9_test,subject_10_test,subject_11_test,subject_13_test,subject_14_test,subject_15_test,subject_16_test,subject_17_test])"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T04:04:12.276243Z",
"start_time": "2019-07-21T04:04:12.271442Z"
}
},
"outputs": [],
"source": [
"features=['subject','ACC_x','ACC_y','ACC_z','ECG','EMG','EDA','Temp','Resp']\n",
"target=['label']"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"ExecuteTime": {
"start_time": "2019-07-21T04:04:25.485Z"
}
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/opt/anaconda/lib/python3.6/site-packages/ipykernel_launcher.py:2: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples,), for example using ravel().\n",
" \n"
]
},
{
"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",
"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",
"building tree 31 of 50\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 10.6min\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"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: 18.3min finished\n",
"[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 26.6s\n"
]
}
],
"source": [
"et = ExtraTreesClassifier(n_estimators=50, n_jobs=10, verbose=2)\n",
"et.fit(train[features],train[target])\n",
"y_pred=et.predict(test[features])"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {
"ExecuteTime": {
"end_time": "2019-07-21T04:40:10.287166Z",
"start_time": "2019-07-21T04:40:03.793730Z"
}
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" precision recall f1-score support\n",
"\n",
" 0 1.00 0.99 1.00 8296151\n",
" 1 1.00 1.00 1.00 3699449\n",
" 2 1.00 1.00 1.00 2093592\n",
" 3 0.98 0.99 0.99 1169776\n",
" 4 0.99 1.00 0.99 2478684\n",
"\n",
"avg / total 1.00 1.00 1.00 17737652\n",
"\n"
]
}
],
"source": [
"print(classification_report(test[target],y_pred ))"
]
},
{
"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
}