Datasets
Models
Downloads: 1
Diff of
/Dependent Vs Independent.ipynb
[000000]
..
[d8f241]
Switch to unified view
| a | b/Dependent Vs Independent.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 2, |
||
| 6 | "metadata": { |
||
| 7 | "ExecuteTime": { |
||
| 8 | "end_time": "2019-07-21T03:28:20.614469Z", |
||
| 9 | "start_time": "2019-07-21T03:28:19.208340Z" |
||
| 10 | } |
||
| 11 | }, |
||
| 12 | "outputs": [ |
||
| 13 | { |
||
| 14 | "name": "stderr", |
||
| 15 | "output_type": "stream", |
||
| 16 | "text": [ |
||
| 17 | "Using TensorFlow backend.\n" |
||
| 18 | ] |
||
| 19 | } |
||
| 20 | ], |
||
| 21 | "source": [ |
||
| 22 | "#This code is for adaptive GPU usage\n", |
||
| 23 | "import keras.backend as K\n", |
||
| 24 | "cfg = K.tf.ConfigProto()\n", |
||
| 25 | "cfg.gpu_options.allow_growth = True\n", |
||
| 26 | "K.set_session(K.tf.Session(config=cfg))" |
||
| 27 | ] |
||
| 28 | }, |
||
| 29 | { |
||
| 30 | "cell_type": "code", |
||
| 31 | "execution_count": 1, |
||
| 32 | "metadata": { |
||
| 33 | "ExecuteTime": { |
||
| 34 | "end_time": "2019-07-23T12:10:14.715612Z", |
||
| 35 | "start_time": "2019-07-23T12:10:14.196989Z" |
||
| 36 | } |
||
| 37 | }, |
||
| 38 | "outputs": [], |
||
| 39 | "source": [ |
||
| 40 | "import pandas as pd\n", |
||
| 41 | "import numpy as np\n", |
||
| 42 | "from sklearn.ensemble import ExtraTreesClassifier\n", |
||
| 43 | "from sklearn.metrics import classification_report\n", |
||
| 44 | "from sklearn.model_selection import train_test_split" |
||
| 45 | ] |
||
| 46 | }, |
||
| 47 | { |
||
| 48 | "cell_type": "code", |
||
| 49 | "execution_count": 2, |
||
| 50 | "metadata": { |
||
| 51 | "ExecuteTime": { |
||
| 52 | "end_time": "2019-07-23T13:09:10.760608Z", |
||
| 53 | "start_time": "2019-07-23T13:09:10.743179Z" |
||
| 54 | } |
||
| 55 | }, |
||
| 56 | "outputs": [ |
||
| 57 | { |
||
| 58 | "data": { |
||
| 59 | "text/plain": [ |
||
| 60 | "15" |
||
| 61 | ] |
||
| 62 | }, |
||
| 63 | "execution_count": 2, |
||
| 64 | "metadata": {}, |
||
| 65 | "output_type": "execute_result" |
||
| 66 | } |
||
| 67 | ], |
||
| 68 | "source": [ |
||
| 69 | "subject=[2,3,4,5,6,7,8,9,10,11,13,14,15,16,17]\n", |
||
| 70 | "len(subject)" |
||
| 71 | ] |
||
| 72 | }, |
||
| 73 | { |
||
| 74 | "cell_type": "code", |
||
| 75 | "execution_count": 3, |
||
| 76 | "metadata": { |
||
| 77 | "ExecuteTime": { |
||
| 78 | "end_time": "2019-07-23T12:10:50.414237Z", |
||
| 79 | "start_time": "2019-07-23T12:10:23.407112Z" |
||
| 80 | } |
||
| 81 | }, |
||
| 82 | "outputs": [ |
||
| 83 | { |
||
| 84 | "name": "stdout", |
||
| 85 | "output_type": "stream", |
||
| 86 | "text": [ |
||
| 87 | "subject_2\n", |
||
| 88 | "subject_3\n" |
||
| 89 | ] |
||
| 90 | }, |
||
| 91 | { |
||
| 92 | "ename": "KeyboardInterrupt", |
||
| 93 | "evalue": "", |
||
| 94 | "output_type": "error", |
||
| 95 | "traceback": [ |
||
| 96 | "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", |
||
| 97 | "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", |
||
| 98 | "\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", |
||
| 99 | "\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", |
||
| 100 | "\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", |
||
| 101 | "\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", |
||
| 102 | "\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", |
||
| 103 | "\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader.read\u001b[0;34m()\u001b[0m\n", |
||
| 104 | "\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers.TextReader._read_low_memory\u001b[0;34m()\u001b[0m\n", |
||
| 105 | "\u001b[0;32mpandas/_libs/parsers.pyx\u001b[0m in \u001b[0;36mpandas._libs.parsers._concatenate_chunks\u001b[0;34m()\u001b[0m\n", |
||
| 106 | "\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", |
||
| 107 | "\u001b[0;31mKeyboardInterrupt\u001b[0m: " |
||
| 108 | ] |
||
| 109 | } |
||
| 110 | ], |
||
| 111 | "source": [ |
||
| 112 | "for i in subject:\n", |
||
| 113 | " globals()['subject_%s' % i] = pd.read_csv(\"Sub_\"+str(i)+\".csv\")\n", |
||
| 114 | " globals()['subject_%s' % i]=globals()['subject_%s' % i][globals()['subject_%s' % i]['label'] <= 4]\n", |
||
| 115 | " #subject_2_train,subject_2_test=train_test_split(subject_2, test_size=0.3)\n", |
||
| 116 | " print('subject_'+str(i))" |
||
| 117 | ] |
||
| 118 | }, |
||
| 119 | { |
||
| 120 | "cell_type": "code", |
||
| 121 | "execution_count": null, |
||
| 122 | "metadata": {}, |
||
| 123 | "outputs": [], |
||
| 124 | "source": [ |
||
| 125 | "%%time\n", |
||
| 126 | "df = pd.read_csv(\"master_data.csv\")\n" |
||
| 127 | ] |
||
| 128 | }, |
||
| 129 | { |
||
| 130 | "cell_type": "code", |
||
| 131 | "execution_count": null, |
||
| 132 | "metadata": {}, |
||
| 133 | "outputs": [], |
||
| 134 | "source": [ |
||
| 135 | "df=df[df['target']!=0]\n", |
||
| 136 | "df" |
||
| 137 | ] |
||
| 138 | }, |
||
| 139 | { |
||
| 140 | "cell_type": "code", |
||
| 141 | "execution_count": 4, |
||
| 142 | "metadata": { |
||
| 143 | "ExecuteTime": { |
||
| 144 | "end_time": "2019-07-21T03:48:13.626469Z", |
||
| 145 | "start_time": "2019-07-21T03:48:11.630785Z" |
||
| 146 | } |
||
| 147 | }, |
||
| 148 | "outputs": [], |
||
| 149 | "source": [ |
||
| 150 | "train=pd.concat([subject_2,subject_3,subject_4,subject_5,subject_6,subject_7,subject_8,subject_9,subject_10,subject_11])" |
||
| 151 | ] |
||
| 152 | }, |
||
| 153 | { |
||
| 154 | "cell_type": "code", |
||
| 155 | "execution_count": 5, |
||
| 156 | "metadata": { |
||
| 157 | "ExecuteTime": { |
||
| 158 | "end_time": "2019-07-21T03:48:14.534888Z", |
||
| 159 | "start_time": "2019-07-21T03:48:13.628414Z" |
||
| 160 | } |
||
| 161 | }, |
||
| 162 | "outputs": [], |
||
| 163 | "source": [ |
||
| 164 | "test=pd.concat([subject_13,subject_14,subject_15,subject_16,subject_17])" |
||
| 165 | ] |
||
| 166 | }, |
||
| 167 | { |
||
| 168 | "cell_type": "code", |
||
| 169 | "execution_count": 6, |
||
| 170 | "metadata": { |
||
| 171 | "ExecuteTime": { |
||
| 172 | "end_time": "2019-07-21T03:48:14.544552Z", |
||
| 173 | "start_time": "2019-07-21T03:48:14.536781Z" |
||
| 174 | } |
||
| 175 | }, |
||
| 176 | "outputs": [ |
||
| 177 | { |
||
| 178 | "name": "stdout", |
||
| 179 | "output_type": "stream", |
||
| 180 | "text": [ |
||
| 181 | "Index 321148792\n", |
||
| 182 | "subject 321148792\n", |
||
| 183 | "ACC_x 321148792\n", |
||
| 184 | "ACC_y 321148792\n", |
||
| 185 | "ACC_z 321148792\n", |
||
| 186 | "ECG 321148792\n", |
||
| 187 | "EMG 321148792\n", |
||
| 188 | "EDA 321148792\n", |
||
| 189 | "Temp 321148792\n", |
||
| 190 | "Resp 321148792\n", |
||
| 191 | "label 321148792\n", |
||
| 192 | "dtype: int64\n", |
||
| 193 | "Index 151855208\n", |
||
| 194 | "subject 151855208\n", |
||
| 195 | "ACC_x 151855208\n", |
||
| 196 | "ACC_y 151855208\n", |
||
| 197 | "ACC_z 151855208\n", |
||
| 198 | "ECG 151855208\n", |
||
| 199 | "EMG 151855208\n", |
||
| 200 | "EDA 151855208\n", |
||
| 201 | "Temp 151855208\n", |
||
| 202 | "Resp 151855208\n", |
||
| 203 | "label 151855208\n", |
||
| 204 | "dtype: int64\n" |
||
| 205 | ] |
||
| 206 | } |
||
| 207 | ], |
||
| 208 | "source": [ |
||
| 209 | "print(train.memory_usage(index=True, deep=False))\n", |
||
| 210 | "print(test.memory_usage(index=True, deep=False))" |
||
| 211 | ] |
||
| 212 | }, |
||
| 213 | { |
||
| 214 | "cell_type": "code", |
||
| 215 | "execution_count": 7, |
||
| 216 | "metadata": { |
||
| 217 | "ExecuteTime": { |
||
| 218 | "end_time": "2019-07-21T03:48:15.689593Z", |
||
| 219 | "start_time": "2019-07-21T03:48:14.546129Z" |
||
| 220 | } |
||
| 221 | }, |
||
| 222 | "outputs": [ |
||
| 223 | { |
||
| 224 | "name": "stdout", |
||
| 225 | "output_type": "stream", |
||
| 226 | "text": [ |
||
| 227 | "<class 'pandas.core.frame.DataFrame'>\n", |
||
| 228 | "Int64Index: 40143599 entries, 0 to 3663099\n", |
||
| 229 | "Data columns (total 10 columns):\n", |
||
| 230 | "subject int64\n", |
||
| 231 | "ACC_x float64\n", |
||
| 232 | "ACC_y float64\n", |
||
| 233 | "ACC_z float64\n", |
||
| 234 | "ECG float64\n", |
||
| 235 | "EMG float64\n", |
||
| 236 | "EDA float64\n", |
||
| 237 | "Temp float64\n", |
||
| 238 | "Resp float64\n", |
||
| 239 | "label int64\n", |
||
| 240 | "dtypes: float64(8), int64(2)\n", |
||
| 241 | "memory usage: 3.3 GB\n", |
||
| 242 | "None\n", |
||
| 243 | "<class 'pandas.core.frame.DataFrame'>\n", |
||
| 244 | "Int64Index: 18981901 entries, 0 to 4143999\n", |
||
| 245 | "Data columns (total 10 columns):\n", |
||
| 246 | "subject int64\n", |
||
| 247 | "ACC_x float64\n", |
||
| 248 | "ACC_y float64\n", |
||
| 249 | "ACC_z float64\n", |
||
| 250 | "ECG float64\n", |
||
| 251 | "EMG float64\n", |
||
| 252 | "EDA float64\n", |
||
| 253 | "Temp float64\n", |
||
| 254 | "Resp float64\n", |
||
| 255 | "label int64\n", |
||
| 256 | "dtypes: float64(8), int64(2)\n", |
||
| 257 | "memory usage: 1.6 GB\n", |
||
| 258 | "None\n" |
||
| 259 | ] |
||
| 260 | } |
||
| 261 | ], |
||
| 262 | "source": [ |
||
| 263 | "print(train.info(memory_usage='deep'))\n", |
||
| 264 | "print(test.info(memory_usage='deep'))" |
||
| 265 | ] |
||
| 266 | }, |
||
| 267 | { |
||
| 268 | "cell_type": "code", |
||
| 269 | "execution_count": 2, |
||
| 270 | "metadata": { |
||
| 271 | "ExecuteTime": { |
||
| 272 | "end_time": "2019-07-23T13:09:21.798204Z", |
||
| 273 | "start_time": "2019-07-23T13:09:21.793394Z" |
||
| 274 | } |
||
| 275 | }, |
||
| 276 | "outputs": [], |
||
| 277 | "source": [ |
||
| 278 | "features=['subject','ACC_x','ACC_y','ACC_z','ECG','EMG','EDA','Temp','Resp']\n", |
||
| 279 | "target=['label']" |
||
| 280 | ] |
||
| 281 | }, |
||
| 282 | { |
||
| 283 | "cell_type": "code", |
||
| 284 | "execution_count": 12, |
||
| 285 | "metadata": { |
||
| 286 | "ExecuteTime": { |
||
| 287 | "end_time": "2019-07-21T03:57:26.901617Z", |
||
| 288 | "start_time": "2019-07-21T03:50:57.031138Z" |
||
| 289 | } |
||
| 290 | }, |
||
| 291 | "outputs": [ |
||
| 292 | { |
||
| 293 | "name": "stderr", |
||
| 294 | "output_type": "stream", |
||
| 295 | "text": [ |
||
| 296 | "/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", |
||
| 297 | " \n" |
||
| 298 | ] |
||
| 299 | }, |
||
| 300 | { |
||
| 301 | "name": "stdout", |
||
| 302 | "output_type": "stream", |
||
| 303 | "text": [ |
||
| 304 | "building tree 1 of 50\n", |
||
| 305 | "building tree 2 of 50\n", |
||
| 306 | "building tree 3 of 50\n", |
||
| 307 | "building tree 4 of 50\n", |
||
| 308 | "building tree 5 of 50\n", |
||
| 309 | "building tree 6 of 50\n", |
||
| 310 | "building tree 7 of 50\n", |
||
| 311 | "building tree 8 of 50\n", |
||
| 312 | "building tree 9 of 50\n", |
||
| 313 | "building tree 10 of 50\n", |
||
| 314 | "building tree 11 of 50\n", |
||
| 315 | "building tree 12 of 50\n", |
||
| 316 | "building tree 13 of 50\n", |
||
| 317 | "building tree 14 of 50\n", |
||
| 318 | "building tree 15 of 50\n", |
||
| 319 | "building tree 16 of 50\n", |
||
| 320 | "building tree 17 of 50\n", |
||
| 321 | "building tree 18 of 50\n", |
||
| 322 | "building tree 19 of 50\n", |
||
| 323 | "building tree 20 of 50\n", |
||
| 324 | "building tree 21 of 50\n", |
||
| 325 | "building tree 22 of 50\n", |
||
| 326 | "building tree 23 of 50\n", |
||
| 327 | "building tree 24 of 50\n", |
||
| 328 | "building tree 25 of 50\n", |
||
| 329 | "building tree 26 of 50\n", |
||
| 330 | "building tree 27 of 50\n", |
||
| 331 | "building tree 28 of 50\n", |
||
| 332 | "building tree 29 of 50\n", |
||
| 333 | "building tree 30 of 50\n", |
||
| 334 | "building tree 31 of 50\n" |
||
| 335 | ] |
||
| 336 | }, |
||
| 337 | { |
||
| 338 | "name": "stderr", |
||
| 339 | "output_type": "stream", |
||
| 340 | "text": [ |
||
| 341 | "[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 3.0min\n" |
||
| 342 | ] |
||
| 343 | }, |
||
| 344 | { |
||
| 345 | "name": "stdout", |
||
| 346 | "output_type": "stream", |
||
| 347 | "text": [ |
||
| 348 | "building tree 32 of 50\n", |
||
| 349 | "building tree 33 of 50\n", |
||
| 350 | "building tree 34 of 50\n", |
||
| 351 | "building tree 35 of 50\n", |
||
| 352 | "building tree 36 of 50\n", |
||
| 353 | "building tree 37 of 50building tree 38 of 50\n", |
||
| 354 | "\n", |
||
| 355 | "building tree 39 of 50\n", |
||
| 356 | "building tree 40 of 50\n", |
||
| 357 | "building tree 41 of 50\n", |
||
| 358 | "building tree 42 of 50\n", |
||
| 359 | "building tree 43 of 50\n", |
||
| 360 | "building tree 44 of 50\n", |
||
| 361 | "building tree 45 of 50\n", |
||
| 362 | "building tree 46 of 50\n", |
||
| 363 | "building tree 47 of 50\n", |
||
| 364 | "building tree 48 of 50\n", |
||
| 365 | "building tree 49 of 50\n", |
||
| 366 | "building tree 50 of 50\n" |
||
| 367 | ] |
||
| 368 | }, |
||
| 369 | { |
||
| 370 | "name": "stderr", |
||
| 371 | "output_type": "stream", |
||
| 372 | "text": [ |
||
| 373 | "[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 5.9min finished\n", |
||
| 374 | "[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 12.6s\n", |
||
| 375 | "[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 24.5s finished\n" |
||
| 376 | ] |
||
| 377 | } |
||
| 378 | ], |
||
| 379 | "source": [ |
||
| 380 | "et = ExtraTreesClassifier(n_estimators=50, n_jobs=10, verbose=2)\n", |
||
| 381 | "et.fit(train[features],train[target])\n", |
||
| 382 | "y_pred=et.predict(test[features])" |
||
| 383 | ] |
||
| 384 | }, |
||
| 385 | { |
||
| 386 | "cell_type": "code", |
||
| 387 | "execution_count": 15, |
||
| 388 | "metadata": { |
||
| 389 | "ExecuteTime": { |
||
| 390 | "end_time": "2019-07-21T03:57:45.807406Z", |
||
| 391 | "start_time": "2019-07-21T03:57:40.672071Z" |
||
| 392 | } |
||
| 393 | }, |
||
| 394 | "outputs": [ |
||
| 395 | { |
||
| 396 | "name": "stdout", |
||
| 397 | "output_type": "stream", |
||
| 398 | "text": [ |
||
| 399 | " precision recall f1-score support\n", |
||
| 400 | "\n", |
||
| 401 | " 0 0.43 0.75 0.55 8419601\n", |
||
| 402 | " 1 0.04 0.04 0.04 4127201\n", |
||
| 403 | " 2 0.15 0.01 0.03 2394701\n", |
||
| 404 | " 3 0.00 0.00 0.00 1306201\n", |
||
| 405 | " 4 0.00 0.00 0.00 2734197\n", |
||
| 406 | "\n", |
||
| 407 | "avg / total 0.22 0.34 0.25 18981901\n", |
||
| 408 | "\n" |
||
| 409 | ] |
||
| 410 | }, |
||
| 411 | { |
||
| 412 | "name": "stderr", |
||
| 413 | "output_type": "stream", |
||
| 414 | "text": [ |
||
| 415 | "/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", |
||
| 416 | " 'precision', 'predicted', average, warn_for)\n" |
||
| 417 | ] |
||
| 418 | } |
||
| 419 | ], |
||
| 420 | "source": [ |
||
| 421 | "print(classification_report(test[target],y_pred ))" |
||
| 422 | ] |
||
| 423 | }, |
||
| 424 | { |
||
| 425 | "cell_type": "code", |
||
| 426 | "execution_count": 16, |
||
| 427 | "metadata": { |
||
| 428 | "ExecuteTime": { |
||
| 429 | "end_time": "2019-07-21T03:57:54.022571Z", |
||
| 430 | "start_time": "2019-07-21T03:57:53.711601Z" |
||
| 431 | } |
||
| 432 | }, |
||
| 433 | "outputs": [ |
||
| 434 | { |
||
| 435 | "data": { |
||
| 436 | "text/plain": [ |
||
| 437 | "array([0.08156137, 0.10834554, 0.12135855, 0.19428681, 0.0057354 ,\n", |
||
| 438 | " 0.00575368, 0.24000214, 0.21983822, 0.02311827])" |
||
| 439 | ] |
||
| 440 | }, |
||
| 441 | "execution_count": 16, |
||
| 442 | "metadata": {}, |
||
| 443 | "output_type": "execute_result" |
||
| 444 | } |
||
| 445 | ], |
||
| 446 | "source": [ |
||
| 447 | "et.feature_importances_" |
||
| 448 | ] |
||
| 449 | }, |
||
| 450 | { |
||
| 451 | "cell_type": "code", |
||
| 452 | "execution_count": 3, |
||
| 453 | "metadata": { |
||
| 454 | "ExecuteTime": { |
||
| 455 | "end_time": "2019-07-23T13:09:31.720954Z", |
||
| 456 | "start_time": "2019-07-23T13:09:31.713668Z" |
||
| 457 | } |
||
| 458 | }, |
||
| 459 | "outputs": [ |
||
| 460 | { |
||
| 461 | "data": { |
||
| 462 | "text/plain": [ |
||
| 463 | "['subject', 'ACC_x', 'ACC_y', 'ACC_z', 'ECG', 'EMG', 'EDA', 'Temp', 'Resp']" |
||
| 464 | ] |
||
| 465 | }, |
||
| 466 | "execution_count": 3, |
||
| 467 | "metadata": {}, |
||
| 468 | "output_type": "execute_result" |
||
| 469 | } |
||
| 470 | ], |
||
| 471 | "source": [ |
||
| 472 | "features" |
||
| 473 | ] |
||
| 474 | }, |
||
| 475 | { |
||
| 476 | "cell_type": "markdown", |
||
| 477 | "metadata": {}, |
||
| 478 | "source": [ |
||
| 479 | "# 70-30 all subject" |
||
| 480 | ] |
||
| 481 | }, |
||
| 482 | { |
||
| 483 | "cell_type": "code", |
||
| 484 | "execution_count": 21, |
||
| 485 | "metadata": { |
||
| 486 | "ExecuteTime": { |
||
| 487 | "end_time": "2019-07-21T04:03:43.043681Z", |
||
| 488 | "start_time": "2019-07-21T04:01:34.361732Z" |
||
| 489 | } |
||
| 490 | }, |
||
| 491 | "outputs": [ |
||
| 492 | { |
||
| 493 | "name": "stdout", |
||
| 494 | "output_type": "stream", |
||
| 495 | "text": [ |
||
| 496 | "subject_2\n", |
||
| 497 | "subject_3\n", |
||
| 498 | "subject_4\n", |
||
| 499 | "subject_5\n", |
||
| 500 | "subject_6\n", |
||
| 501 | "subject_7\n", |
||
| 502 | "subject_8\n", |
||
| 503 | "subject_9\n", |
||
| 504 | "subject_10\n", |
||
| 505 | "subject_11\n", |
||
| 506 | "subject_13\n", |
||
| 507 | "subject_14\n", |
||
| 508 | "subject_15\n", |
||
| 509 | "subject_16\n", |
||
| 510 | "subject_17\n" |
||
| 511 | ] |
||
| 512 | } |
||
| 513 | ], |
||
| 514 | "source": [ |
||
| 515 | "for i in subject:\n", |
||
| 516 | " globals()['subject_%s' % i] = pd.read_csv(\"Sub_\"+str(i)+\".csv\")\n", |
||
| 517 | " globals()['subject_%s' % i]=globals()['subject_%s' % i][globals()['subject_%s' % i]['label'] <= 4]\n", |
||
| 518 | " globals()['subject_%s_train' % i],globals()['subject_%s_test' % i]=train_test_split(globals()['subject_%s' % i], test_size=0.3)\n", |
||
| 519 | " print('subject_'+str(i))" |
||
| 520 | ] |
||
| 521 | }, |
||
| 522 | { |
||
| 523 | "cell_type": "code", |
||
| 524 | "execution_count": 20, |
||
| 525 | "metadata": { |
||
| 526 | "ExecuteTime": { |
||
| 527 | "end_time": "2019-07-21T04:01:07.867253Z", |
||
| 528 | "start_time": "2019-07-21T04:01:07.861501Z" |
||
| 529 | } |
||
| 530 | }, |
||
| 531 | "outputs": [ |
||
| 532 | { |
||
| 533 | "name": "stdout", |
||
| 534 | "output_type": "stream", |
||
| 535 | "text": [ |
||
| 536 | "ExtraTreesClassifier\t autopep8\t classification_report\t features\t i\t json\t np\t pd\t subject\t \n", |
||
| 537 | "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", |
||
| 538 | "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", |
||
| 539 | "test\t train\t train_test_split\t y_pred\t \n" |
||
| 540 | ] |
||
| 541 | } |
||
| 542 | ], |
||
| 543 | "source": [ |
||
| 544 | "who" |
||
| 545 | ] |
||
| 546 | }, |
||
| 547 | { |
||
| 548 | "cell_type": "code", |
||
| 549 | "execution_count": 22, |
||
| 550 | "metadata": { |
||
| 551 | "ExecuteTime": { |
||
| 552 | "end_time": "2019-07-21T04:03:53.417465Z", |
||
| 553 | "start_time": "2019-07-21T04:03:50.257592Z" |
||
| 554 | } |
||
| 555 | }, |
||
| 556 | "outputs": [], |
||
| 557 | "source": [ |
||
| 558 | "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", |
||
| 559 | "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])" |
||
| 560 | ] |
||
| 561 | }, |
||
| 562 | { |
||
| 563 | "cell_type": "code", |
||
| 564 | "execution_count": 23, |
||
| 565 | "metadata": { |
||
| 566 | "ExecuteTime": { |
||
| 567 | "end_time": "2019-07-21T04:04:12.276243Z", |
||
| 568 | "start_time": "2019-07-21T04:04:12.271442Z" |
||
| 569 | } |
||
| 570 | }, |
||
| 571 | "outputs": [], |
||
| 572 | "source": [ |
||
| 573 | "features=['subject','ACC_x','ACC_y','ACC_z','ECG','EMG','EDA','Temp','Resp']\n", |
||
| 574 | "target=['label']" |
||
| 575 | ] |
||
| 576 | }, |
||
| 577 | { |
||
| 578 | "cell_type": "code", |
||
| 579 | "execution_count": null, |
||
| 580 | "metadata": {}, |
||
| 581 | "outputs": [], |
||
| 582 | "source": [] |
||
| 583 | }, |
||
| 584 | { |
||
| 585 | "cell_type": "code", |
||
| 586 | "execution_count": null, |
||
| 587 | "metadata": { |
||
| 588 | "ExecuteTime": { |
||
| 589 | "start_time": "2019-07-21T04:04:25.485Z" |
||
| 590 | } |
||
| 591 | }, |
||
| 592 | "outputs": [ |
||
| 593 | { |
||
| 594 | "name": "stderr", |
||
| 595 | "output_type": "stream", |
||
| 596 | "text": [ |
||
| 597 | "/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", |
||
| 598 | " \n" |
||
| 599 | ] |
||
| 600 | }, |
||
| 601 | { |
||
| 602 | "name": "stdout", |
||
| 603 | "output_type": "stream", |
||
| 604 | "text": [ |
||
| 605 | "building tree 1 of 50\n", |
||
| 606 | "building tree 2 of 50\n", |
||
| 607 | "building tree 3 of 50\n", |
||
| 608 | "building tree 4 of 50\n", |
||
| 609 | "building tree 5 of 50\n", |
||
| 610 | "building tree 6 of 50\n", |
||
| 611 | "building tree 7 of 50\n", |
||
| 612 | "building tree 8 of 50\n", |
||
| 613 | "building tree 9 of 50\n", |
||
| 614 | "building tree 10 of 50\n", |
||
| 615 | "building tree 11 of 50\n", |
||
| 616 | "building tree 12 of 50\n", |
||
| 617 | "building tree 13 of 50\n", |
||
| 618 | "building tree 14 of 50\n", |
||
| 619 | "building tree 15 of 50\n", |
||
| 620 | "building tree 16 of 50\n", |
||
| 621 | "building tree 17 of 50\n", |
||
| 622 | "building tree 18 of 50\n", |
||
| 623 | "building tree 19 of 50\n", |
||
| 624 | "building tree 20 of 50\n", |
||
| 625 | "building tree 21 of 50\n", |
||
| 626 | "building tree 22 of 50\n", |
||
| 627 | "building tree 23 of 50\n", |
||
| 628 | "building tree 24 of 50\n", |
||
| 629 | "building tree 25 of 50\n", |
||
| 630 | "building tree 26 of 50\n", |
||
| 631 | "building tree 27 of 50\n", |
||
| 632 | "building tree 28 of 50\n", |
||
| 633 | "building tree 29 of 50\n", |
||
| 634 | "building tree 30 of 50\n", |
||
| 635 | "building tree 31 of 50\n" |
||
| 636 | ] |
||
| 637 | }, |
||
| 638 | { |
||
| 639 | "name": "stderr", |
||
| 640 | "output_type": "stream", |
||
| 641 | "text": [ |
||
| 642 | "[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 10.6min\n" |
||
| 643 | ] |
||
| 644 | }, |
||
| 645 | { |
||
| 646 | "name": "stdout", |
||
| 647 | "output_type": "stream", |
||
| 648 | "text": [ |
||
| 649 | "building tree 32 of 50\n", |
||
| 650 | "building tree 33 of 50\n", |
||
| 651 | "building tree 34 of 50\n", |
||
| 652 | "building tree 35 of 50\n", |
||
| 653 | "building tree 36 of 50\n", |
||
| 654 | "building tree 37 of 50\n", |
||
| 655 | "building tree 38 of 50\n", |
||
| 656 | "building tree 39 of 50\n", |
||
| 657 | "building tree 40 of 50\n", |
||
| 658 | "building tree 41 of 50\n", |
||
| 659 | "building tree 42 of 50\n", |
||
| 660 | "building tree 43 of 50\n", |
||
| 661 | "building tree 44 of 50\n", |
||
| 662 | "building tree 45 of 50\n", |
||
| 663 | "building tree 46 of 50\n", |
||
| 664 | "building tree 47 of 50\n", |
||
| 665 | "building tree 48 of 50\n", |
||
| 666 | "building tree 49 of 50\n", |
||
| 667 | "building tree 50 of 50\n" |
||
| 668 | ] |
||
| 669 | }, |
||
| 670 | { |
||
| 671 | "name": "stderr", |
||
| 672 | "output_type": "stream", |
||
| 673 | "text": [ |
||
| 674 | "[Parallel(n_jobs=10)]: Done 50 out of 50 | elapsed: 18.3min finished\n", |
||
| 675 | "[Parallel(n_jobs=10)]: Done 21 tasks | elapsed: 26.6s\n" |
||
| 676 | ] |
||
| 677 | } |
||
| 678 | ], |
||
| 679 | "source": [ |
||
| 680 | "et = ExtraTreesClassifier(n_estimators=50, n_jobs=10, verbose=2)\n", |
||
| 681 | "et.fit(train[features],train[target])\n", |
||
| 682 | "y_pred=et.predict(test[features])" |
||
| 683 | ] |
||
| 684 | }, |
||
| 685 | { |
||
| 686 | "cell_type": "code", |
||
| 687 | "execution_count": 27, |
||
| 688 | "metadata": { |
||
| 689 | "ExecuteTime": { |
||
| 690 | "end_time": "2019-07-21T04:40:10.287166Z", |
||
| 691 | "start_time": "2019-07-21T04:40:03.793730Z" |
||
| 692 | } |
||
| 693 | }, |
||
| 694 | "outputs": [ |
||
| 695 | { |
||
| 696 | "name": "stdout", |
||
| 697 | "output_type": "stream", |
||
| 698 | "text": [ |
||
| 699 | " precision recall f1-score support\n", |
||
| 700 | "\n", |
||
| 701 | " 0 1.00 0.99 1.00 8296151\n", |
||
| 702 | " 1 1.00 1.00 1.00 3699449\n", |
||
| 703 | " 2 1.00 1.00 1.00 2093592\n", |
||
| 704 | " 3 0.98 0.99 0.99 1169776\n", |
||
| 705 | " 4 0.99 1.00 0.99 2478684\n", |
||
| 706 | "\n", |
||
| 707 | "avg / total 1.00 1.00 1.00 17737652\n", |
||
| 708 | "\n" |
||
| 709 | ] |
||
| 710 | } |
||
| 711 | ], |
||
| 712 | "source": [ |
||
| 713 | "print(classification_report(test[target],y_pred ))" |
||
| 714 | ] |
||
| 715 | }, |
||
| 716 | { |
||
| 717 | "cell_type": "code", |
||
| 718 | "execution_count": null, |
||
| 719 | "metadata": {}, |
||
| 720 | "outputs": [], |
||
| 721 | "source": [] |
||
| 722 | } |
||
| 723 | ], |
||
| 724 | "metadata": { |
||
| 725 | "kernelspec": { |
||
| 726 | "display_name": "Python 3", |
||
| 727 | "language": "python", |
||
| 728 | "name": "python3" |
||
| 729 | }, |
||
| 730 | "language_info": { |
||
| 731 | "codemirror_mode": { |
||
| 732 | "name": "ipython", |
||
| 733 | "version": 3 |
||
| 734 | }, |
||
| 735 | "file_extension": ".py", |
||
| 736 | "mimetype": "text/x-python", |
||
| 737 | "name": "python", |
||
| 738 | "nbconvert_exporter": "python", |
||
| 739 | "pygments_lexer": "ipython3", |
||
| 740 | "version": "3.6.8" |
||
| 741 | } |
||
| 742 | }, |
||
| 743 | "nbformat": 4, |
||
| 744 | "nbformat_minor": 2 |
||
| 745 | } |