Datasets
Models
Downloads: 1
Diff of
/Random/Random 4.ipynb
[000000]
..
[d8f241]
Switch to unified view
| a | b/Random/Random 4.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 3, |
||
| 6 | "metadata": {}, |
||
| 7 | "outputs": [ |
||
| 8 | { |
||
| 9 | "name": "stdout", |
||
| 10 | "output_type": "stream", |
||
| 11 | "text": [ |
||
| 12 | "CPU times: user 0 ns, sys: 37 µs, total: 37 µs\n", |
||
| 13 | "Wall time: 41 µs\n" |
||
| 14 | ] |
||
| 15 | } |
||
| 16 | ], |
||
| 17 | "source": [ |
||
| 18 | "%%time\n", |
||
| 19 | "import pandas as pd\n", |
||
| 20 | "import numpy as np\n", |
||
| 21 | "from sklearn.ensemble import ExtraTreesClassifier\n", |
||
| 22 | "from sklearn.metrics import classification_report\n", |
||
| 23 | "from sklearn.model_selection import train_test_split\n", |
||
| 24 | "from sklearn.ensemble import RandomForestClassifier\n", |
||
| 25 | "from sklearn.linear_model import LogisticRegression\n", |
||
| 26 | "\n" |
||
| 27 | ] |
||
| 28 | }, |
||
| 29 | { |
||
| 30 | "cell_type": "code", |
||
| 31 | "execution_count": 4, |
||
| 32 | "metadata": {}, |
||
| 33 | "outputs": [ |
||
| 34 | { |
||
| 35 | "name": "stdout", |
||
| 36 | "output_type": "stream", |
||
| 37 | "text": [ |
||
| 38 | "CPU times: user 1min 1s, sys: 4.38 s, total: 1min 5s\n", |
||
| 39 | "Wall time: 1min 18s\n" |
||
| 40 | ] |
||
| 41 | } |
||
| 42 | ], |
||
| 43 | "source": [ |
||
| 44 | "%%time\n", |
||
| 45 | "df = pd.read_csv(\"master_data.csv\")" |
||
| 46 | ] |
||
| 47 | }, |
||
| 48 | { |
||
| 49 | "cell_type": "code", |
||
| 50 | "execution_count": 5, |
||
| 51 | "metadata": {}, |
||
| 52 | "outputs": [ |
||
| 53 | { |
||
| 54 | "data": { |
||
| 55 | "text/plain": [ |
||
| 56 | "(31470603, 10)" |
||
| 57 | ] |
||
| 58 | }, |
||
| 59 | "execution_count": 5, |
||
| 60 | "metadata": {}, |
||
| 61 | "output_type": "execute_result" |
||
| 62 | } |
||
| 63 | ], |
||
| 64 | "source": [ |
||
| 65 | "df.shape" |
||
| 66 | ] |
||
| 67 | }, |
||
| 68 | { |
||
| 69 | "cell_type": "code", |
||
| 70 | "execution_count": 6, |
||
| 71 | "metadata": {}, |
||
| 72 | "outputs": [ |
||
| 73 | { |
||
| 74 | "data": { |
||
| 75 | "text/plain": [ |
||
| 76 | "[2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17]" |
||
| 77 | ] |
||
| 78 | }, |
||
| 79 | "execution_count": 6, |
||
| 80 | "metadata": {}, |
||
| 81 | "output_type": "execute_result" |
||
| 82 | } |
||
| 83 | ], |
||
| 84 | "source": [ |
||
| 85 | "df['subject'].unique()\n", |
||
| 86 | "list_of_subjects=list(df['subject'].unique())\n", |
||
| 87 | "list_of_subjects.sort()\n", |
||
| 88 | "list_of_subjects" |
||
| 89 | ] |
||
| 90 | }, |
||
| 91 | { |
||
| 92 | "cell_type": "code", |
||
| 93 | "execution_count": 7, |
||
| 94 | "metadata": {}, |
||
| 95 | "outputs": [ |
||
| 96 | { |
||
| 97 | "data": { |
||
| 98 | "text/plain": [ |
||
| 99 | "['chest_ACC_x',\n", |
||
| 100 | " 'chest_ACC_y',\n", |
||
| 101 | " 'chest_ACC_z',\n", |
||
| 102 | " 'chest_ECG',\n", |
||
| 103 | " 'chest_EMG',\n", |
||
| 104 | " 'chest_EDA',\n", |
||
| 105 | " 'chest_Temp',\n", |
||
| 106 | " 'chest_Resp']" |
||
| 107 | ] |
||
| 108 | }, |
||
| 109 | "execution_count": 7, |
||
| 110 | "metadata": {}, |
||
| 111 | "output_type": "execute_result" |
||
| 112 | } |
||
| 113 | ], |
||
| 114 | "source": [ |
||
| 115 | "features=df.columns.tolist()\n", |
||
| 116 | "to_remove = [fea for fea in features if \"target\" in fea or \"subject\" in fea]\n", |
||
| 117 | "feature = [x for x in features if x not in to_remove]\n", |
||
| 118 | "feature" |
||
| 119 | ] |
||
| 120 | }, |
||
| 121 | { |
||
| 122 | "cell_type": "code", |
||
| 123 | "execution_count": 8, |
||
| 124 | "metadata": {}, |
||
| 125 | "outputs": [ |
||
| 126 | { |
||
| 127 | "data": { |
||
| 128 | "text/plain": [ |
||
| 129 | "array([1, 2, 4, 3])" |
||
| 130 | ] |
||
| 131 | }, |
||
| 132 | "execution_count": 8, |
||
| 133 | "metadata": {}, |
||
| 134 | "output_type": "execute_result" |
||
| 135 | } |
||
| 136 | ], |
||
| 137 | "source": [ |
||
| 138 | "df['target'].unique()" |
||
| 139 | ] |
||
| 140 | }, |
||
| 141 | { |
||
| 142 | "cell_type": "code", |
||
| 143 | "execution_count": 9, |
||
| 144 | "metadata": {}, |
||
| 145 | "outputs": [ |
||
| 146 | { |
||
| 147 | "name": "stdout", |
||
| 148 | "output_type": "stream", |
||
| 149 | "text": [ |
||
| 150 | "6\n", |
||
| 151 | "11\n", |
||
| 152 | "14\n", |
||
| 153 | "8\n", |
||
| 154 | "15\n", |
||
| 155 | "9\n", |
||
| 156 | "10\n", |
||
| 157 | "2\n", |
||
| 158 | "16\n", |
||
| 159 | "4\n", |
||
| 160 | "13\n", |
||
| 161 | "3\n", |
||
| 162 | "17\n", |
||
| 163 | "5\n", |
||
| 164 | "7\n", |
||
| 165 | "CPU times: user 2.25 s, sys: 663 ms, total: 2.92 s\n", |
||
| 166 | "Wall time: 3.07 s\n" |
||
| 167 | ] |
||
| 168 | } |
||
| 169 | ], |
||
| 170 | "source": [ |
||
| 171 | "%%time\n", |
||
| 172 | "test_subject=list(df['subject'].unique())\n", |
||
| 173 | "for i in test_subject:\n", |
||
| 174 | " print(i)\n", |
||
| 175 | " globals()['subject_%s' % i]=df[df['subject'] == i]\n", |
||
| 176 | "# globals()['subject_%s_train' % i],globals()['subject_%s_test' % i]=train_test_split(globals()['subject_%s' % i], test_size=test_shape)" |
||
| 177 | ] |
||
| 178 | }, |
||
| 179 | { |
||
| 180 | "cell_type": "code", |
||
| 181 | "execution_count": 10, |
||
| 182 | "metadata": {}, |
||
| 183 | "outputs": [], |
||
| 184 | "source": [ |
||
| 185 | "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]" |
||
| 186 | ] |
||
| 187 | }, |
||
| 188 | { |
||
| 189 | "cell_type": "code", |
||
| 190 | "execution_count": 11, |
||
| 191 | "metadata": {}, |
||
| 192 | "outputs": [], |
||
| 193 | "source": [ |
||
| 194 | "x=[2,3,4,5,6,7,8,9,10,11,13,14,15,16,17]" |
||
| 195 | ] |
||
| 196 | }, |
||
| 197 | { |
||
| 198 | "cell_type": "code", |
||
| 199 | "execution_count": 12, |
||
| 200 | "metadata": {}, |
||
| 201 | "outputs": [], |
||
| 202 | "source": [ |
||
| 203 | "\n", |
||
| 204 | "for i in range(len(x)):\n", |
||
| 205 | " \n", |
||
| 206 | " globals()['df_1_%s' % x[i]]=subject_list[i][subject_list[i]['target']==1]\n", |
||
| 207 | " globals()['df_2_%s' % x[i]]=subject_list[i][subject_list[i]['target']==2]\n", |
||
| 208 | " globals()['df_3_%s' % x[i]]=subject_list[i][subject_list[i]['target']==3]\n", |
||
| 209 | " globals()['df_4_%s' % x[i]]=subject_list[i][subject_list[i]['target']==4]" |
||
| 210 | ] |
||
| 211 | }, |
||
| 212 | { |
||
| 213 | "cell_type": "code", |
||
| 214 | "execution_count": 13, |
||
| 215 | "metadata": {}, |
||
| 216 | "outputs": [ |
||
| 217 | { |
||
| 218 | "name": "stdout", |
||
| 219 | "output_type": "stream", |
||
| 220 | "text": [ |
||
| 221 | "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", |
||
| 222 | "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", |
||
| 223 | "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", |
||
| 224 | "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", |
||
| 225 | "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", |
||
| 226 | "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", |
||
| 227 | "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", |
||
| 228 | "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", |
||
| 229 | "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", |
||
| 230 | "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", |
||
| 231 | "x\t \n" |
||
| 232 | ] |
||
| 233 | } |
||
| 234 | ], |
||
| 235 | "source": [ |
||
| 236 | "who" |
||
| 237 | ] |
||
| 238 | }, |
||
| 239 | { |
||
| 240 | "cell_type": "code", |
||
| 241 | "execution_count": 14, |
||
| 242 | "metadata": {}, |
||
| 243 | "outputs": [], |
||
| 244 | "source": [ |
||
| 245 | "x=[2,3,4,5,6,7,8,9,10,11,13,14,15,16,17]\n", |
||
| 246 | "cls=[1,2,3,4]" |
||
| 247 | ] |
||
| 248 | }, |
||
| 249 | { |
||
| 250 | "cell_type": "code", |
||
| 251 | "execution_count": 15, |
||
| 252 | "metadata": {}, |
||
| 253 | "outputs": [ |
||
| 254 | { |
||
| 255 | "data": { |
||
| 256 | "text/plain": [ |
||
| 257 | "84000" |
||
| 258 | ] |
||
| 259 | }, |
||
| 260 | "execution_count": 15, |
||
| 261 | "metadata": {}, |
||
| 262 | "output_type": "execute_result" |
||
| 263 | } |
||
| 264 | ], |
||
| 265 | "source": [ |
||
| 266 | "no_of_rows=int(700*120)\n", |
||
| 267 | "no_of_rows" |
||
| 268 | ] |
||
| 269 | }, |
||
| 270 | { |
||
| 271 | "cell_type": "code", |
||
| 272 | "execution_count": 16, |
||
| 273 | "metadata": {}, |
||
| 274 | "outputs": [], |
||
| 275 | "source": [ |
||
| 276 | "for i in cls:\n", |
||
| 277 | " for j in x:\n", |
||
| 278 | " globals()['df_{}_train_{}'.format(i,j)] = globals()['df_{}_{}'.format(i,j)].iloc[:no_of_rows]\n", |
||
| 279 | " #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", |
||
| 280 | " #print('subject_'+str(i))\n", |
||
| 281 | " globals()['df_{}_test_{}'.format(i,j)] = globals()['df_{}_{}'.format(i,j)].iloc[no_of_rows:] " |
||
| 282 | ] |
||
| 283 | }, |
||
| 284 | { |
||
| 285 | "cell_type": "code", |
||
| 286 | "execution_count": 17, |
||
| 287 | "metadata": { |
||
| 288 | "scrolled": true |
||
| 289 | }, |
||
| 290 | "outputs": [], |
||
| 291 | "source": [ |
||
| 292 | "concat_list=[]\n", |
||
| 293 | "for i in cls:\n", |
||
| 294 | " for j in x:\n", |
||
| 295 | " concat_list.append(globals()['df_{}_train_{}'.format(i,j)])\n", |
||
| 296 | "#concat_list[0]" |
||
| 297 | ] |
||
| 298 | }, |
||
| 299 | { |
||
| 300 | "cell_type": "code", |
||
| 301 | "execution_count": 22, |
||
| 302 | "metadata": { |
||
| 303 | "collapsed": true |
||
| 304 | }, |
||
| 305 | "outputs": [ |
||
| 306 | { |
||
| 307 | "data": { |
||
| 308 | "text/html": [ |
||
| 309 | "<div>\n", |
||
| 310 | "<style scoped>\n", |
||
| 311 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 312 | " vertical-align: middle;\n", |
||
| 313 | " }\n", |
||
| 314 | "\n", |
||
| 315 | " .dataframe tbody tr th {\n", |
||
| 316 | " vertical-align: top;\n", |
||
| 317 | " }\n", |
||
| 318 | "\n", |
||
| 319 | " .dataframe thead th {\n", |
||
| 320 | " text-align: right;\n", |
||
| 321 | " }\n", |
||
| 322 | "</style>\n", |
||
| 323 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 324 | " <thead>\n", |
||
| 325 | " <tr style=\"text-align: right;\">\n", |
||
| 326 | " <th></th>\n", |
||
| 327 | " <th>target</th>\n", |
||
| 328 | " <th>subject</th>\n", |
||
| 329 | " <th>chest_ACC_x</th>\n", |
||
| 330 | " <th>chest_ACC_y</th>\n", |
||
| 331 | " <th>chest_ACC_z</th>\n", |
||
| 332 | " <th>chest_ECG</th>\n", |
||
| 333 | " <th>chest_EMG</th>\n", |
||
| 334 | " <th>chest_EDA</th>\n", |
||
| 335 | " <th>chest_Temp</th>\n", |
||
| 336 | " <th>chest_Resp</th>\n", |
||
| 337 | " </tr>\n", |
||
| 338 | " </thead>\n", |
||
| 339 | " <tbody>\n", |
||
| 340 | " <tr>\n", |
||
| 341 | " <td>14786800</td>\n", |
||
| 342 | " <td>1</td>\n", |
||
| 343 | " <td>2</td>\n", |
||
| 344 | " <td>0.8914</td>\n", |
||
| 345 | " <td>-0.1102</td>\n", |
||
| 346 | " <td>-0.2576</td>\n", |
||
| 347 | " <td>0.030945</td>\n", |
||
| 348 | " <td>-0.003708</td>\n", |
||
| 349 | " <td>5.710983</td>\n", |
||
| 350 | " <td>29.083618</td>\n", |
||
| 351 | " <td>1.191711</td>\n", |
||
| 352 | " </tr>\n", |
||
| 353 | " <tr>\n", |
||
| 354 | " <td>14786801</td>\n", |
||
| 355 | " <td>1</td>\n", |
||
| 356 | " <td>2</td>\n", |
||
| 357 | " <td>0.8926</td>\n", |
||
| 358 | " <td>-0.1086</td>\n", |
||
| 359 | " <td>-0.2544</td>\n", |
||
| 360 | " <td>0.033646</td>\n", |
||
| 361 | " <td>-0.014145</td>\n", |
||
| 362 | " <td>5.719376</td>\n", |
||
| 363 | " <td>29.122437</td>\n", |
||
| 364 | " <td>1.139832</td>\n", |
||
| 365 | " </tr>\n", |
||
| 366 | " <tr>\n", |
||
| 367 | " <td>14786802</td>\n", |
||
| 368 | " <td>1</td>\n", |
||
| 369 | " <td>2</td>\n", |
||
| 370 | " <td>0.8930</td>\n", |
||
| 371 | " <td>-0.1094</td>\n", |
||
| 372 | " <td>-0.2580</td>\n", |
||
| 373 | " <td>0.033005</td>\n", |
||
| 374 | " <td>0.010208</td>\n", |
||
| 375 | " <td>5.706406</td>\n", |
||
| 376 | " <td>29.115234</td>\n", |
||
| 377 | " <td>1.141357</td>\n", |
||
| 378 | " </tr>\n", |
||
| 379 | " <tr>\n", |
||
| 380 | " <td>14786803</td>\n", |
||
| 381 | " <td>1</td>\n", |
||
| 382 | " <td>2</td>\n", |
||
| 383 | " <td>0.8934</td>\n", |
||
| 384 | " <td>-0.1082</td>\n", |
||
| 385 | " <td>-0.2538</td>\n", |
||
| 386 | " <td>0.031815</td>\n", |
||
| 387 | " <td>0.012634</td>\n", |
||
| 388 | " <td>5.712509</td>\n", |
||
| 389 | " <td>29.126709</td>\n", |
||
| 390 | " <td>1.155090</td>\n", |
||
| 391 | " </tr>\n", |
||
| 392 | " <tr>\n", |
||
| 393 | " <td>14786804</td>\n", |
||
| 394 | " <td>1</td>\n", |
||
| 395 | " <td>2</td>\n", |
||
| 396 | " <td>0.8930</td>\n", |
||
| 397 | " <td>-0.1096</td>\n", |
||
| 398 | " <td>-0.2570</td>\n", |
||
| 399 | " <td>0.030350</td>\n", |
||
| 400 | " <td>0.002060</td>\n", |
||
| 401 | " <td>5.727005</td>\n", |
||
| 402 | " <td>29.100861</td>\n", |
||
| 403 | " <td>1.133728</td>\n", |
||
| 404 | " </tr>\n", |
||
| 405 | " <tr>\n", |
||
| 406 | " <td>...</td>\n", |
||
| 407 | " <td>...</td>\n", |
||
| 408 | " <td>...</td>\n", |
||
| 409 | " <td>...</td>\n", |
||
| 410 | " <td>...</td>\n", |
||
| 411 | " <td>...</td>\n", |
||
| 412 | " <td>...</td>\n", |
||
| 413 | " <td>...</td>\n", |
||
| 414 | " <td>...</td>\n", |
||
| 415 | " <td>...</td>\n", |
||
| 416 | " <td>...</td>\n", |
||
| 417 | " </tr>\n", |
||
| 418 | " <tr>\n", |
||
| 419 | " <td>16809094</td>\n", |
||
| 420 | " <td>4</td>\n", |
||
| 421 | " <td>2</td>\n", |
||
| 422 | " <td>0.4378</td>\n", |
||
| 423 | " <td>-0.2348</td>\n", |
||
| 424 | " <td>-0.8380</td>\n", |
||
| 425 | " <td>-0.182602</td>\n", |
||
| 426 | " <td>-0.015793</td>\n", |
||
| 427 | " <td>0.484085</td>\n", |
||
| 428 | " <td>31.926239</td>\n", |
||
| 429 | " <td>-1.609802</td>\n", |
||
| 430 | " </tr>\n", |
||
| 431 | " <tr>\n", |
||
| 432 | " <td>16809095</td>\n", |
||
| 433 | " <td>4</td>\n", |
||
| 434 | " <td>2</td>\n", |
||
| 435 | " <td>0.4378</td>\n", |
||
| 436 | " <td>-0.2338</td>\n", |
||
| 437 | " <td>-0.8394</td>\n", |
||
| 438 | " <td>-0.170609</td>\n", |
||
| 439 | " <td>0.000687</td>\n", |
||
| 440 | " <td>0.473404</td>\n", |
||
| 441 | " <td>31.932190</td>\n", |
||
| 442 | " <td>-1.646423</td>\n", |
||
| 443 | " </tr>\n", |
||
| 444 | " <tr>\n", |
||
| 445 | " <td>16809096</td>\n", |
||
| 446 | " <td>4</td>\n", |
||
| 447 | " <td>2</td>\n", |
||
| 448 | " <td>0.4388</td>\n", |
||
| 449 | " <td>-0.2338</td>\n", |
||
| 450 | " <td>-0.8386</td>\n", |
||
| 451 | " <td>-0.160812</td>\n", |
||
| 452 | " <td>0.004532</td>\n", |
||
| 453 | " <td>0.463486</td>\n", |
||
| 454 | " <td>31.918823</td>\n", |
||
| 455 | " <td>-1.643372</td>\n", |
||
| 456 | " </tr>\n", |
||
| 457 | " <tr>\n", |
||
| 458 | " <td>16809097</td>\n", |
||
| 459 | " <td>4</td>\n", |
||
| 460 | " <td>2</td>\n", |
||
| 461 | " <td>0.4398</td>\n", |
||
| 462 | " <td>-0.2374</td>\n", |
||
| 463 | " <td>-0.8390</td>\n", |
||
| 464 | " <td>-0.156326</td>\n", |
||
| 465 | " <td>0.000595</td>\n", |
||
| 466 | " <td>0.459290</td>\n", |
||
| 467 | " <td>31.932190</td>\n", |
||
| 468 | " <td>-1.661682</td>\n", |
||
| 469 | " </tr>\n", |
||
| 470 | " <tr>\n", |
||
| 471 | " <td>16809098</td>\n", |
||
| 472 | " <td>4</td>\n", |
||
| 473 | " <td>2</td>\n", |
||
| 474 | " <td>0.4386</td>\n", |
||
| 475 | " <td>-0.2366</td>\n", |
||
| 476 | " <td>-0.8408</td>\n", |
||
| 477 | " <td>-0.154312</td>\n", |
||
| 478 | " <td>-0.009201</td>\n", |
||
| 479 | " <td>0.455475</td>\n", |
||
| 480 | " <td>31.927704</td>\n", |
||
| 481 | " <td>-1.646423</td>\n", |
||
| 482 | " </tr>\n", |
||
| 483 | " </tbody>\n", |
||
| 484 | "</table>\n", |
||
| 485 | "<p>2022299 rows × 10 columns</p>\n", |
||
| 486 | "</div>" |
||
| 487 | ], |
||
| 488 | "text/plain": [ |
||
| 489 | " target subject chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG \\\n", |
||
| 490 | "14786800 1 2 0.8914 -0.1102 -0.2576 0.030945 \n", |
||
| 491 | "14786801 1 2 0.8926 -0.1086 -0.2544 0.033646 \n", |
||
| 492 | "14786802 1 2 0.8930 -0.1094 -0.2580 0.033005 \n", |
||
| 493 | "14786803 1 2 0.8934 -0.1082 -0.2538 0.031815 \n", |
||
| 494 | "14786804 1 2 0.8930 -0.1096 -0.2570 0.030350 \n", |
||
| 495 | "... ... ... ... ... ... ... \n", |
||
| 496 | "16809094 4 2 0.4378 -0.2348 -0.8380 -0.182602 \n", |
||
| 497 | "16809095 4 2 0.4378 -0.2338 -0.8394 -0.170609 \n", |
||
| 498 | "16809096 4 2 0.4388 -0.2338 -0.8386 -0.160812 \n", |
||
| 499 | "16809097 4 2 0.4398 -0.2374 -0.8390 -0.156326 \n", |
||
| 500 | "16809098 4 2 0.4386 -0.2366 -0.8408 -0.154312 \n", |
||
| 501 | "\n", |
||
| 502 | " chest_EMG chest_EDA chest_Temp chest_Resp \n", |
||
| 503 | "14786800 -0.003708 5.710983 29.083618 1.191711 \n", |
||
| 504 | "14786801 -0.014145 5.719376 29.122437 1.139832 \n", |
||
| 505 | "14786802 0.010208 5.706406 29.115234 1.141357 \n", |
||
| 506 | "14786803 0.012634 5.712509 29.126709 1.155090 \n", |
||
| 507 | "14786804 0.002060 5.727005 29.100861 1.133728 \n", |
||
| 508 | "... ... ... ... ... \n", |
||
| 509 | "16809094 -0.015793 0.484085 31.926239 -1.609802 \n", |
||
| 510 | "16809095 0.000687 0.473404 31.932190 -1.646423 \n", |
||
| 511 | "16809096 0.004532 0.463486 31.918823 -1.643372 \n", |
||
| 512 | "16809097 0.000595 0.459290 31.932190 -1.661682 \n", |
||
| 513 | "16809098 -0.009201 0.455475 31.927704 -1.646423 \n", |
||
| 514 | "\n", |
||
| 515 | "[2022299 rows x 10 columns]" |
||
| 516 | ] |
||
| 517 | }, |
||
| 518 | "execution_count": 22, |
||
| 519 | "metadata": {}, |
||
| 520 | "output_type": "execute_result" |
||
| 521 | } |
||
| 522 | ], |
||
| 523 | "source": [ |
||
| 524 | "subject_2" |
||
| 525 | ] |
||
| 526 | }, |
||
| 527 | { |
||
| 528 | "cell_type": "code", |
||
| 529 | "execution_count": 18, |
||
| 530 | "metadata": {}, |
||
| 531 | "outputs": [ |
||
| 532 | { |
||
| 533 | "data": { |
||
| 534 | "text/html": [ |
||
| 535 | "<div>\n", |
||
| 536 | "<style scoped>\n", |
||
| 537 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 538 | " vertical-align: middle;\n", |
||
| 539 | " }\n", |
||
| 540 | "\n", |
||
| 541 | " .dataframe tbody tr th {\n", |
||
| 542 | " vertical-align: top;\n", |
||
| 543 | " }\n", |
||
| 544 | "\n", |
||
| 545 | " .dataframe thead th {\n", |
||
| 546 | " text-align: right;\n", |
||
| 547 | " }\n", |
||
| 548 | "</style>\n", |
||
| 549 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 550 | " <thead>\n", |
||
| 551 | " <tr style=\"text-align: right;\">\n", |
||
| 552 | " <th></th>\n", |
||
| 553 | " <th>target</th>\n", |
||
| 554 | " <th>subject</th>\n", |
||
| 555 | " <th>chest_ACC_x</th>\n", |
||
| 556 | " <th>chest_ACC_y</th>\n", |
||
| 557 | " <th>chest_ACC_z</th>\n", |
||
| 558 | " <th>chest_ECG</th>\n", |
||
| 559 | " <th>chest_EMG</th>\n", |
||
| 560 | " <th>chest_EDA</th>\n", |
||
| 561 | " <th>chest_Temp</th>\n", |
||
| 562 | " <th>chest_Resp</th>\n", |
||
| 563 | " </tr>\n", |
||
| 564 | " </thead>\n", |
||
| 565 | " <tbody>\n", |
||
| 566 | " <tr>\n", |
||
| 567 | " <td>14870800</td>\n", |
||
| 568 | " <td>1</td>\n", |
||
| 569 | " <td>2</td>\n", |
||
| 570 | " <td>0.6296</td>\n", |
||
| 571 | " <td>-0.1086</td>\n", |
||
| 572 | " <td>-0.7042</td>\n", |
||
| 573 | " <td>0.126160</td>\n", |
||
| 574 | " <td>-0.005585</td>\n", |
||
| 575 | " <td>3.750992</td>\n", |
||
| 576 | " <td>28.752167</td>\n", |
||
| 577 | " <td>-2.301025</td>\n", |
||
| 578 | " </tr>\n", |
||
| 579 | " <tr>\n", |
||
| 580 | " <td>14870801</td>\n", |
||
| 581 | " <td>1</td>\n", |
||
| 582 | " <td>2</td>\n", |
||
| 583 | " <td>0.6296</td>\n", |
||
| 584 | " <td>-0.1058</td>\n", |
||
| 585 | " <td>-0.7094</td>\n", |
||
| 586 | " <td>0.124100</td>\n", |
||
| 587 | " <td>-0.007004</td>\n", |
||
| 588 | " <td>3.757477</td>\n", |
||
| 589 | " <td>28.765045</td>\n", |
||
| 590 | " <td>-2.740479</td>\n", |
||
| 591 | " </tr>\n", |
||
| 592 | " <tr>\n", |
||
| 593 | " <td>14870802</td>\n", |
||
| 594 | " <td>1</td>\n", |
||
| 595 | " <td>2</td>\n", |
||
| 596 | " <td>0.6292</td>\n", |
||
| 597 | " <td>-0.1042</td>\n", |
||
| 598 | " <td>-0.7086</td>\n", |
||
| 599 | " <td>0.120346</td>\n", |
||
| 600 | " <td>0.002335</td>\n", |
||
| 601 | " <td>3.776169</td>\n", |
||
| 602 | " <td>28.745026</td>\n", |
||
| 603 | " <td>-2.276611</td>\n", |
||
| 604 | " </tr>\n", |
||
| 605 | " <tr>\n", |
||
| 606 | " <td>14870803</td>\n", |
||
| 607 | " <td>1</td>\n", |
||
| 608 | " <td>2</td>\n", |
||
| 609 | " <td>0.6266</td>\n", |
||
| 610 | " <td>-0.1022</td>\n", |
||
| 611 | " <td>-0.7086</td>\n", |
||
| 612 | " <td>0.113754</td>\n", |
||
| 613 | " <td>-0.012863</td>\n", |
||
| 614 | " <td>3.753662</td>\n", |
||
| 615 | " <td>28.766479</td>\n", |
||
| 616 | " <td>-2.287292</td>\n", |
||
| 617 | " </tr>\n", |
||
| 618 | " <tr>\n", |
||
| 619 | " <td>14870804</td>\n", |
||
| 620 | " <td>1</td>\n", |
||
| 621 | " <td>2</td>\n", |
||
| 622 | " <td>0.6258</td>\n", |
||
| 623 | " <td>-0.1022</td>\n", |
||
| 624 | " <td>-0.7106</td>\n", |
||
| 625 | " <td>0.109909</td>\n", |
||
| 626 | " <td>-0.002975</td>\n", |
||
| 627 | " <td>3.759766</td>\n", |
||
| 628 | " <td>28.737854</td>\n", |
||
| 629 | " <td>-2.284241</td>\n", |
||
| 630 | " </tr>\n", |
||
| 631 | " <tr>\n", |
||
| 632 | " <td>...</td>\n", |
||
| 633 | " <td>...</td>\n", |
||
| 634 | " <td>...</td>\n", |
||
| 635 | " <td>...</td>\n", |
||
| 636 | " <td>...</td>\n", |
||
| 637 | " <td>...</td>\n", |
||
| 638 | " <td>...</td>\n", |
||
| 639 | " <td>...</td>\n", |
||
| 640 | " <td>...</td>\n", |
||
| 641 | " <td>...</td>\n", |
||
| 642 | " <td>...</td>\n", |
||
| 643 | " </tr>\n", |
||
| 644 | " <tr>\n", |
||
| 645 | " <td>15587595</td>\n", |
||
| 646 | " <td>1</td>\n", |
||
| 647 | " <td>2</td>\n", |
||
| 648 | " <td>0.7148</td>\n", |
||
| 649 | " <td>0.0758</td>\n", |
||
| 650 | " <td>-0.0428</td>\n", |
||
| 651 | " <td>0.308167</td>\n", |
||
| 652 | " <td>0.016617</td>\n", |
||
| 653 | " <td>1.204681</td>\n", |
||
| 654 | " <td>29.716492</td>\n", |
||
| 655 | " <td>-1.144409</td>\n", |
||
| 656 | " </tr>\n", |
||
| 657 | " <tr>\n", |
||
| 658 | " <td>15587596</td>\n", |
||
| 659 | " <td>1</td>\n", |
||
| 660 | " <td>2</td>\n", |
||
| 661 | " <td>0.7144</td>\n", |
||
| 662 | " <td>0.0670</td>\n", |
||
| 663 | " <td>-0.0618</td>\n", |
||
| 664 | " <td>0.332840</td>\n", |
||
| 665 | " <td>-0.001740</td>\n", |
||
| 666 | " <td>1.197052</td>\n", |
||
| 667 | " <td>29.762756</td>\n", |
||
| 668 | " <td>-1.118469</td>\n", |
||
| 669 | " </tr>\n", |
||
| 670 | " <tr>\n", |
||
| 671 | " <td>15587597</td>\n", |
||
| 672 | " <td>1</td>\n", |
||
| 673 | " <td>2</td>\n", |
||
| 674 | " <td>0.7146</td>\n", |
||
| 675 | " <td>0.0642</td>\n", |
||
| 676 | " <td>-0.0726</td>\n", |
||
| 677 | " <td>0.359528</td>\n", |
||
| 678 | " <td>-0.005814</td>\n", |
||
| 679 | " <td>1.200104</td>\n", |
||
| 680 | " <td>29.715027</td>\n", |
||
| 681 | " <td>-1.078796</td>\n", |
||
| 682 | " </tr>\n", |
||
| 683 | " <tr>\n", |
||
| 684 | " <td>15587598</td>\n", |
||
| 685 | " <td>1</td>\n", |
||
| 686 | " <td>2</td>\n", |
||
| 687 | " <td>0.7244</td>\n", |
||
| 688 | " <td>0.0606</td>\n", |
||
| 689 | " <td>-0.0818</td>\n", |
||
| 690 | " <td>0.387680</td>\n", |
||
| 691 | " <td>-0.001602</td>\n", |
||
| 692 | " <td>1.190948</td>\n", |
||
| 693 | " <td>29.717896</td>\n", |
||
| 694 | " <td>-1.025391</td>\n", |
||
| 695 | " </tr>\n", |
||
| 696 | " <tr>\n", |
||
| 697 | " <td>15587599</td>\n", |
||
| 698 | " <td>1</td>\n", |
||
| 699 | " <td>2</td>\n", |
||
| 700 | " <td>0.7282</td>\n", |
||
| 701 | " <td>0.0506</td>\n", |
||
| 702 | " <td>-0.0948</td>\n", |
||
| 703 | " <td>0.415009</td>\n", |
||
| 704 | " <td>-0.028244</td>\n", |
||
| 705 | " <td>1.198959</td>\n", |
||
| 706 | " <td>29.717896</td>\n", |
||
| 707 | " <td>-0.996399</td>\n", |
||
| 708 | " </tr>\n", |
||
| 709 | " </tbody>\n", |
||
| 710 | "</table>\n", |
||
| 711 | "<p>716800 rows × 10 columns</p>\n", |
||
| 712 | "</div>" |
||
| 713 | ], |
||
| 714 | "text/plain": [ |
||
| 715 | " target subject chest_ACC_x chest_ACC_y chest_ACC_z chest_ECG \\\n", |
||
| 716 | "14870800 1 2 0.6296 -0.1086 -0.7042 0.126160 \n", |
||
| 717 | "14870801 1 2 0.6296 -0.1058 -0.7094 0.124100 \n", |
||
| 718 | "14870802 1 2 0.6292 -0.1042 -0.7086 0.120346 \n", |
||
| 719 | "14870803 1 2 0.6266 -0.1022 -0.7086 0.113754 \n", |
||
| 720 | "14870804 1 2 0.6258 -0.1022 -0.7106 0.109909 \n", |
||
| 721 | "... ... ... ... ... ... ... \n", |
||
| 722 | "15587595 1 2 0.7148 0.0758 -0.0428 0.308167 \n", |
||
| 723 | "15587596 1 2 0.7144 0.0670 -0.0618 0.332840 \n", |
||
| 724 | "15587597 1 2 0.7146 0.0642 -0.0726 0.359528 \n", |
||
| 725 | "15587598 1 2 0.7244 0.0606 -0.0818 0.387680 \n", |
||
| 726 | "15587599 1 2 0.7282 0.0506 -0.0948 0.415009 \n", |
||
| 727 | "\n", |
||
| 728 | " chest_EMG chest_EDA chest_Temp chest_Resp \n", |
||
| 729 | "14870800 -0.005585 3.750992 28.752167 -2.301025 \n", |
||
| 730 | "14870801 -0.007004 3.757477 28.765045 -2.740479 \n", |
||
| 731 | "14870802 0.002335 3.776169 28.745026 -2.276611 \n", |
||
| 732 | "14870803 -0.012863 3.753662 28.766479 -2.287292 \n", |
||
| 733 | "14870804 -0.002975 3.759766 28.737854 -2.284241 \n", |
||
| 734 | "... ... ... ... ... \n", |
||
| 735 | "15587595 0.016617 1.204681 29.716492 -1.144409 \n", |
||
| 736 | "15587596 -0.001740 1.197052 29.762756 -1.118469 \n", |
||
| 737 | "15587597 -0.005814 1.200104 29.715027 -1.078796 \n", |
||
| 738 | "15587598 -0.001602 1.190948 29.717896 -1.025391 \n", |
||
| 739 | "15587599 -0.028244 1.198959 29.717896 -0.996399 \n", |
||
| 740 | "\n", |
||
| 741 | "[716800 rows x 10 columns]" |
||
| 742 | ] |
||
| 743 | }, |
||
| 744 | "execution_count": 18, |
||
| 745 | "metadata": {}, |
||
| 746 | "output_type": "execute_result" |
||
| 747 | } |
||
| 748 | ], |
||
| 749 | "source": [ |
||
| 750 | "concat_list1=[]\n", |
||
| 751 | "for i in cls:\n", |
||
| 752 | " for j in x:\n", |
||
| 753 | " concat_list1.append(globals()['df_{}_test_{}'.format(i,j)])\n", |
||
| 754 | "concat_list1[0]" |
||
| 755 | ] |
||
| 756 | }, |
||
| 757 | { |
||
| 758 | "cell_type": "code", |
||
| 759 | "execution_count": 19, |
||
| 760 | "metadata": { |
||
| 761 | "scrolled": true |
||
| 762 | }, |
||
| 763 | "outputs": [ |
||
| 764 | { |
||
| 765 | "data": { |
||
| 766 | "text/plain": [ |
||
| 767 | "(5040000, 10)" |
||
| 768 | ] |
||
| 769 | }, |
||
| 770 | "execution_count": 19, |
||
| 771 | "metadata": {}, |
||
| 772 | "output_type": "execute_result" |
||
| 773 | } |
||
| 774 | ], |
||
| 775 | "source": [ |
||
| 776 | "train_df=pd.concat(concat_list)\n", |
||
| 777 | "train_df.shape" |
||
| 778 | ] |
||
| 779 | }, |
||
| 780 | { |
||
| 781 | "cell_type": "code", |
||
| 782 | "execution_count": 20, |
||
| 783 | "metadata": {}, |
||
| 784 | "outputs": [ |
||
| 785 | { |
||
| 786 | "data": { |
||
| 787 | "text/plain": [ |
||
| 788 | "4 1260000\n", |
||
| 789 | "3 1260000\n", |
||
| 790 | "2 1260000\n", |
||
| 791 | "1 1260000\n", |
||
| 792 | "Name: target, dtype: int64" |
||
| 793 | ] |
||
| 794 | }, |
||
| 795 | "execution_count": 20, |
||
| 796 | "metadata": {}, |
||
| 797 | "output_type": "execute_result" |
||
| 798 | } |
||
| 799 | ], |
||
| 800 | "source": [ |
||
| 801 | "train_df.target.value_counts()" |
||
| 802 | ] |
||
| 803 | }, |
||
| 804 | { |
||
| 805 | "cell_type": "code", |
||
| 806 | "execution_count": 21, |
||
| 807 | "metadata": { |
||
| 808 | "scrolled": true |
||
| 809 | }, |
||
| 810 | "outputs": [ |
||
| 811 | { |
||
| 812 | "data": { |
||
| 813 | "text/plain": [ |
||
| 814 | "15" |
||
| 815 | ] |
||
| 816 | }, |
||
| 817 | "execution_count": 21, |
||
| 818 | "metadata": {}, |
||
| 819 | "output_type": "execute_result" |
||
| 820 | } |
||
| 821 | ], |
||
| 822 | "source": [ |
||
| 823 | "len(train_df.subject.unique())" |
||
| 824 | ] |
||
| 825 | }, |
||
| 826 | { |
||
| 827 | "cell_type": "code", |
||
| 828 | "execution_count": 22, |
||
| 829 | "metadata": {}, |
||
| 830 | "outputs": [ |
||
| 831 | { |
||
| 832 | "data": { |
||
| 833 | "text/plain": [ |
||
| 834 | "(26430603, 10)" |
||
| 835 | ] |
||
| 836 | }, |
||
| 837 | "execution_count": 22, |
||
| 838 | "metadata": {}, |
||
| 839 | "output_type": "execute_result" |
||
| 840 | } |
||
| 841 | ], |
||
| 842 | "source": [ |
||
| 843 | "test_df=pd.concat(concat_list1)\n", |
||
| 844 | "test_df.shape" |
||
| 845 | ] |
||
| 846 | }, |
||
| 847 | { |
||
| 848 | "cell_type": "code", |
||
| 849 | "execution_count": 23, |
||
| 850 | "metadata": {}, |
||
| 851 | "outputs": [], |
||
| 852 | "source": [ |
||
| 853 | "for i in test_subject:\n", |
||
| 854 | " del(globals()['subject_%s' % i])\n", |
||
| 855 | " \n", |
||
| 856 | "for i in range(len(x)): \n", |
||
| 857 | " del(globals()['df_1_%s' % x[i]])\n", |
||
| 858 | " del(globals()['df_2_%s' % x[i]])\n", |
||
| 859 | " del(globals()['df_3_%s' % x[i]])\n", |
||
| 860 | " del(globals()['df_4_%s' % x[i]])\n", |
||
| 861 | "for i in cls:\n", |
||
| 862 | " for j in x:\n", |
||
| 863 | " del(globals()['df_{}_train_{}'.format(i,j)])\n", |
||
| 864 | " del(globals()['df_{}_test_{}'.format(i,j)])\n", |
||
| 865 | "del df" |
||
| 866 | ] |
||
| 867 | }, |
||
| 868 | { |
||
| 869 | "cell_type": "code", |
||
| 870 | "execution_count": null, |
||
| 871 | "metadata": {}, |
||
| 872 | "outputs": [], |
||
| 873 | "source": [ |
||
| 874 | "who" |
||
| 875 | ] |
||
| 876 | }, |
||
| 877 | { |
||
| 878 | "cell_type": "code", |
||
| 879 | "execution_count": null, |
||
| 880 | "metadata": {}, |
||
| 881 | "outputs": [], |
||
| 882 | "source": [ |
||
| 883 | "%%time\n", |
||
| 884 | "et = ExtraTreesClassifier(n_estimators=50, n_jobs=10, verbose=2,random_state=0)" |
||
| 885 | ] |
||
| 886 | }, |
||
| 887 | { |
||
| 888 | "cell_type": "code", |
||
| 889 | "execution_count": null, |
||
| 890 | "metadata": {}, |
||
| 891 | "outputs": [], |
||
| 892 | "source": [ |
||
| 893 | "#et = RandomForestClassifier(n_estimators=100, n_jobs=10, verbose=2,random_state=0)" |
||
| 894 | ] |
||
| 895 | }, |
||
| 896 | { |
||
| 897 | "cell_type": "code", |
||
| 898 | "execution_count": null, |
||
| 899 | "metadata": { |
||
| 900 | "scrolled": true |
||
| 901 | }, |
||
| 902 | "outputs": [], |
||
| 903 | "source": [ |
||
| 904 | "et.fit(train_df[feature],train_df['target'])" |
||
| 905 | ] |
||
| 906 | }, |
||
| 907 | { |
||
| 908 | "cell_type": "code", |
||
| 909 | "execution_count": null, |
||
| 910 | "metadata": {}, |
||
| 911 | "outputs": [], |
||
| 912 | "source": [ |
||
| 913 | "%%time \n", |
||
| 914 | "y_pred=et.predict(test_df[feature])" |
||
| 915 | ] |
||
| 916 | }, |
||
| 917 | { |
||
| 918 | "cell_type": "code", |
||
| 919 | "execution_count": null, |
||
| 920 | "metadata": {}, |
||
| 921 | "outputs": [], |
||
| 922 | "source": [ |
||
| 923 | "print(classification_report(test_df['target'], y_pred))" |
||
| 924 | ] |
||
| 925 | }, |
||
| 926 | { |
||
| 927 | "cell_type": "code", |
||
| 928 | "execution_count": null, |
||
| 929 | "metadata": {}, |
||
| 930 | "outputs": [], |
||
| 931 | "source": [ |
||
| 932 | "#train_df.to_csv('1_min_train.csv')" |
||
| 933 | ] |
||
| 934 | }, |
||
| 935 | { |
||
| 936 | "cell_type": "code", |
||
| 937 | "execution_count": null, |
||
| 938 | "metadata": {}, |
||
| 939 | "outputs": [], |
||
| 940 | "source": [ |
||
| 941 | "#test_df.to_csv('1_min_test.csv')" |
||
| 942 | ] |
||
| 943 | }, |
||
| 944 | { |
||
| 945 | "cell_type": "code", |
||
| 946 | "execution_count": 33, |
||
| 947 | "metadata": {}, |
||
| 948 | "outputs": [], |
||
| 949 | "source": [ |
||
| 950 | "# train_df.to_csv('30_sec_train.csv')" |
||
| 951 | ] |
||
| 952 | }, |
||
| 953 | { |
||
| 954 | "cell_type": "code", |
||
| 955 | "execution_count": 34, |
||
| 956 | "metadata": {}, |
||
| 957 | "outputs": [], |
||
| 958 | "source": [ |
||
| 959 | "# test_df.to_csv('30_sec_test.csv')" |
||
| 960 | ] |
||
| 961 | }, |
||
| 962 | { |
||
| 963 | "cell_type": "code", |
||
| 964 | "execution_count": 24, |
||
| 965 | "metadata": {}, |
||
| 966 | "outputs": [], |
||
| 967 | "source": [ |
||
| 968 | "train_df.to_csv('2_min_train.csv')" |
||
| 969 | ] |
||
| 970 | }, |
||
| 971 | { |
||
| 972 | "cell_type": "code", |
||
| 973 | "execution_count": 25, |
||
| 974 | "metadata": {}, |
||
| 975 | "outputs": [], |
||
| 976 | "source": [ |
||
| 977 | "test_df.to_csv('2_min_test.csv')s" |
||
| 978 | ] |
||
| 979 | }, |
||
| 980 | { |
||
| 981 | "cell_type": "code", |
||
| 982 | "execution_count": null, |
||
| 983 | "metadata": {}, |
||
| 984 | "outputs": [], |
||
| 985 | "source": [ |
||
| 986 | "from sklearn.model_selection import cross_val_score\n", |
||
| 987 | "scores = cross_val_score(et, train_df[feature],train_df['target'], cv=4)\n", |
||
| 988 | "print(scores)" |
||
| 989 | ] |
||
| 990 | }, |
||
| 991 | { |
||
| 992 | "cell_type": "code", |
||
| 993 | "execution_count": 27, |
||
| 994 | "metadata": { |
||
| 995 | "scrolled": true |
||
| 996 | }, |
||
| 997 | "outputs": [ |
||
| 998 | { |
||
| 999 | "name": "stdout", |
||
| 1000 | "output_type": "stream", |
||
| 1001 | "text": [ |
||
| 1002 | "Fitting 10 folds for each of 6 candidates, totalling 60 fits\n" |
||
| 1003 | ] |
||
| 1004 | }, |
||
| 1005 | { |
||
| 1006 | "name": "stderr", |
||
| 1007 | "output_type": "stream", |
||
| 1008 | "text": [ |
||
| 1009 | "[Parallel(n_jobs=1)]: Using backend SequentialBackend with 1 concurrent workers.\n" |
||
| 1010 | ] |
||
| 1011 | }, |
||
| 1012 | { |
||
| 1013 | "name": "stdout", |
||
| 1014 | "output_type": "stream", |
||
| 1015 | "text": [ |
||
| 1016 | "[CV] n_neighbors=1 ...................................................\n", |
||
| 1017 | "[CV] .................................... n_neighbors=1, total= 17.2s\n", |
||
| 1018 | "[CV] n_neighbors=1 ...................................................\n" |
||
| 1019 | ] |
||
| 1020 | }, |
||
| 1021 | { |
||
| 1022 | "name": "stderr", |
||
| 1023 | "output_type": "stream", |
||
| 1024 | "text": [ |
||
| 1025 | "[Parallel(n_jobs=1)]: Done 1 out of 1 | elapsed: 17.2s remaining: 0.0s\n" |
||
| 1026 | ] |
||
| 1027 | }, |
||
| 1028 | { |
||
| 1029 | "name": "stdout", |
||
| 1030 | "output_type": "stream", |
||
| 1031 | "text": [ |
||
| 1032 | "[CV] .................................... n_neighbors=1, total= 22.0s\n", |
||
| 1033 | "[CV] n_neighbors=1 ...................................................\n", |
||
| 1034 | "[CV] .................................... n_neighbors=1, total= 18.1s\n", |
||
| 1035 | "[CV] n_neighbors=1 ...................................................\n", |
||
| 1036 | "[CV] .................................... n_neighbors=1, total= 13.1s\n", |
||
| 1037 | "[CV] n_neighbors=1 ...................................................\n", |
||
| 1038 | "[CV] .................................... n_neighbors=1, total= 21.9s\n", |
||
| 1039 | "[CV] n_neighbors=1 ...................................................\n", |
||
| 1040 | "[CV] .................................... n_neighbors=1, total= 30.5s\n", |
||
| 1041 | "[CV] n_neighbors=1 ...................................................\n", |
||
| 1042 | "[CV] .................................... n_neighbors=1, total= 17.4s\n", |
||
| 1043 | "[CV] n_neighbors=1 ...................................................\n", |
||
| 1044 | "[CV] .................................... n_neighbors=1, total= 19.3s\n", |
||
| 1045 | "[CV] n_neighbors=1 ...................................................\n", |
||
| 1046 | "[CV] .................................... n_neighbors=1, total= 21.8s\n", |
||
| 1047 | "[CV] n_neighbors=1 ...................................................\n", |
||
| 1048 | "[CV] .................................... n_neighbors=1, total= 21.4s\n", |
||
| 1049 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1050 | "[CV] .................................... n_neighbors=3, total= 21.4s\n", |
||
| 1051 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1052 | "[CV] .................................... n_neighbors=3, total= 28.9s\n", |
||
| 1053 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1054 | "[CV] .................................... n_neighbors=3, total= 20.3s\n", |
||
| 1055 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1056 | "[CV] .................................... n_neighbors=3, total= 15.2s\n", |
||
| 1057 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1058 | "[CV] .................................... n_neighbors=3, total= 21.3s\n", |
||
| 1059 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1060 | "[CV] .................................... n_neighbors=3, total= 24.5s\n", |
||
| 1061 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1062 | "[CV] .................................... n_neighbors=3, total= 19.0s\n", |
||
| 1063 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1064 | "[CV] .................................... n_neighbors=3, total= 20.7s\n", |
||
| 1065 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1066 | "[CV] .................................... n_neighbors=3, total= 24.1s\n", |
||
| 1067 | "[CV] n_neighbors=3 ...................................................\n", |
||
| 1068 | "[CV] .................................... n_neighbors=3, total= 23.5s\n", |
||
| 1069 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1070 | "[CV] .................................... n_neighbors=5, total= 22.2s\n", |
||
| 1071 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1072 | "[CV] .................................... n_neighbors=5, total= 24.9s\n", |
||
| 1073 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1074 | "[CV] .................................... n_neighbors=5, total= 21.1s\n", |
||
| 1075 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1076 | "[CV] .................................... n_neighbors=5, total= 13.9s\n", |
||
| 1077 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1078 | "[CV] .................................... n_neighbors=5, total= 22.0s\n", |
||
| 1079 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1080 | "[CV] .................................... n_neighbors=5, total= 27.2s\n", |
||
| 1081 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1082 | "[CV] .................................... n_neighbors=5, total= 19.0s\n", |
||
| 1083 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1084 | "[CV] .................................... n_neighbors=5, total= 21.3s\n", |
||
| 1085 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1086 | "[CV] .................................... n_neighbors=5, total= 25.0s\n", |
||
| 1087 | "[CV] n_neighbors=5 ...................................................\n", |
||
| 1088 | "[CV] .................................... n_neighbors=5, total= 24.3s\n", |
||
| 1089 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1090 | "[CV] .................................... n_neighbors=7, total= 22.7s\n", |
||
| 1091 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1092 | "[CV] .................................... n_neighbors=7, total= 25.2s\n", |
||
| 1093 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1094 | "[CV] .................................... n_neighbors=7, total= 21.6s\n", |
||
| 1095 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1096 | "[CV] .................................... n_neighbors=7, total= 13.8s\n", |
||
| 1097 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1098 | "[CV] .................................... n_neighbors=7, total= 22.1s\n", |
||
| 1099 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1100 | "[CV] .................................... n_neighbors=7, total= 28.4s\n", |
||
| 1101 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1102 | "[CV] .................................... n_neighbors=7, total= 19.4s\n", |
||
| 1103 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1104 | "[CV] .................................... n_neighbors=7, total= 21.6s\n", |
||
| 1105 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1106 | "[CV] .................................... n_neighbors=7, total= 25.3s\n", |
||
| 1107 | "[CV] n_neighbors=7 ...................................................\n", |
||
| 1108 | "[CV] .................................... n_neighbors=7, total= 24.4s\n", |
||
| 1109 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1110 | "[CV] .................................... n_neighbors=9, total= 23.3s\n", |
||
| 1111 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1112 | "[CV] .................................... n_neighbors=9, total= 25.8s\n", |
||
| 1113 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1114 | "[CV] .................................... n_neighbors=9, total= 22.1s\n", |
||
| 1115 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1116 | "[CV] .................................... n_neighbors=9, total= 13.8s\n", |
||
| 1117 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1118 | "[CV] .................................... n_neighbors=9, total= 22.5s\n", |
||
| 1119 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1120 | "[CV] .................................... n_neighbors=9, total= 28.0s\n", |
||
| 1121 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1122 | "[CV] .................................... n_neighbors=9, total= 21.1s\n", |
||
| 1123 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1124 | "[CV] .................................... n_neighbors=9, total= 22.1s\n", |
||
| 1125 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1126 | "[CV] .................................... n_neighbors=9, total= 26.2s\n", |
||
| 1127 | "[CV] n_neighbors=9 ...................................................\n", |
||
| 1128 | "[CV] .................................... n_neighbors=9, total= 24.9s\n", |
||
| 1129 | "[CV] n_neighbors=11 ..................................................\n", |
||
| 1130 | "[CV] ................................... n_neighbors=11, total= 24.0s\n", |
||
| 1131 | "[CV] n_neighbors=11 ..................................................\n", |
||
| 1132 | "[CV] ................................... n_neighbors=11, total= 26.5s\n", |
||
| 1133 | "[CV] n_neighbors=11 ..................................................\n", |
||
| 1134 | "[CV] ................................... n_neighbors=11, total= 29.7s\n", |
||
| 1135 | "[CV] n_neighbors=11 ..................................................\n", |
||
| 1136 | "[CV] ................................... n_neighbors=11, total= 14.2s\n", |
||
| 1137 | "[CV] n_neighbors=11 ..................................................\n", |
||
| 1138 | "[CV] ................................... n_neighbors=11, total= 23.2s\n", |
||
| 1139 | "[CV] n_neighbors=11 ..................................................\n", |
||
| 1140 | "[CV] ................................... n_neighbors=11, total= 28.7s\n", |
||
| 1141 | "[CV] n_neighbors=11 ..................................................\n", |
||
| 1142 | "[CV] ................................... n_neighbors=11, total= 21.7s\n", |
||
| 1143 | "[CV] n_neighbors=11 ..................................................\n", |
||
| 1144 | "[CV] ................................... n_neighbors=11, total= 22.7s\n", |
||
| 1145 | "[CV] n_neighbors=11 ..................................................\n", |
||
| 1146 | "[CV] ................................... n_neighbors=11, total= 27.1s\n", |
||
| 1147 | "[CV] n_neighbors=11 ..................................................\n" |
||
| 1148 | ] |
||
| 1149 | }, |
||
| 1150 | { |
||
| 1151 | "name": "stdout", |
||
| 1152 | "output_type": "stream", |
||
| 1153 | "text": [ |
||
| 1154 | "[CV] ................................... n_neighbors=11, total= 25.6s\n" |
||
| 1155 | ] |
||
| 1156 | }, |
||
| 1157 | { |
||
| 1158 | "name": "stderr", |
||
| 1159 | "output_type": "stream", |
||
| 1160 | "text": [ |
||
| 1161 | "[Parallel(n_jobs=1)]: Done 60 out of 60 | elapsed: 22.4min finished\n" |
||
| 1162 | ] |
||
| 1163 | }, |
||
| 1164 | { |
||
| 1165 | "data": { |
||
| 1166 | "text/plain": [ |
||
| 1167 | "GridSearchCV(cv=10, error_score='raise-deprecating',\n", |
||
| 1168 | " estimator=KNeighborsClassifier(algorithm='auto', leaf_size=30,\n", |
||
| 1169 | " metric='minkowski',\n", |
||
| 1170 | " metric_params=None, n_jobs=None,\n", |
||
| 1171 | " n_neighbors=5, p=2,\n", |
||
| 1172 | " weights='uniform'),\n", |
||
| 1173 | " iid='warn', n_jobs=None,\n", |
||
| 1174 | " param_grid={'n_neighbors': [1, 3, 5, 7, 9, 11]},\n", |
||
| 1175 | " pre_dispatch='2*n_jobs', refit=True, return_train_score=False,\n", |
||
| 1176 | " scoring=None, verbose=2)" |
||
| 1177 | ] |
||
| 1178 | }, |
||
| 1179 | "execution_count": 27, |
||
| 1180 | "metadata": {}, |
||
| 1181 | "output_type": "execute_result" |
||
| 1182 | } |
||
| 1183 | ], |
||
| 1184 | "source": [ |
||
| 1185 | "from sklearn.model_selection import GridSearchCV\n", |
||
| 1186 | "from sklearn.neighbors import KNeighborsClassifier\n", |
||
| 1187 | "# param_grid = { \n", |
||
| 1188 | "# 'n_estimators': [20],\n", |
||
| 1189 | "# 'max_features': ['auto'],\n", |
||
| 1190 | "# # 'max_depth' : [4,5,6,7,8],\n", |
||
| 1191 | "# 'criterion' :['gini', 'entropy']\n", |
||
| 1192 | "# }\n", |
||
| 1193 | "\n", |
||
| 1194 | "param_grid = { \n", |
||
| 1195 | " 'n_neighbors': [1,3,5,7,9,11]\n", |
||
| 1196 | "}\n", |
||
| 1197 | "\n", |
||
| 1198 | "clf = KNeighborsClassifier()\n", |
||
| 1199 | "\n", |
||
| 1200 | "CV_rfc = GridSearchCV(estimator=clf, param_grid=param_grid, cv= 10,verbose=2)\n", |
||
| 1201 | "CV_rfc.fit(train_df[feature],train_df['target'])" |
||
| 1202 | ] |
||
| 1203 | }, |
||
| 1204 | { |
||
| 1205 | "cell_type": "code", |
||
| 1206 | "execution_count": 28, |
||
| 1207 | "metadata": {}, |
||
| 1208 | "outputs": [ |
||
| 1209 | { |
||
| 1210 | "data": { |
||
| 1211 | "text/plain": [ |
||
| 1212 | "{'n_neighbors': 1}" |
||
| 1213 | ] |
||
| 1214 | }, |
||
| 1215 | "execution_count": 28, |
||
| 1216 | "metadata": {}, |
||
| 1217 | "output_type": "execute_result" |
||
| 1218 | } |
||
| 1219 | ], |
||
| 1220 | "source": [ |
||
| 1221 | "CV_rfc.best_params_" |
||
| 1222 | ] |
||
| 1223 | }, |
||
| 1224 | { |
||
| 1225 | "cell_type": "code", |
||
| 1226 | "execution_count": null, |
||
| 1227 | "metadata": {}, |
||
| 1228 | "outputs": [], |
||
| 1229 | "source": [ |
||
| 1230 | "%%time\n", |
||
| 1231 | "et = ExtraTreesClassifier(n_estimators=20, n_jobs=10, verbose=2,random_state=0)" |
||
| 1232 | ] |
||
| 1233 | }, |
||
| 1234 | { |
||
| 1235 | "cell_type": "code", |
||
| 1236 | "execution_count": null, |
||
| 1237 | "metadata": {}, |
||
| 1238 | "outputs": [], |
||
| 1239 | "source": [ |
||
| 1240 | "et.fit(train_df[feature],train_df['target'])" |
||
| 1241 | ] |
||
| 1242 | }, |
||
| 1243 | { |
||
| 1244 | "cell_type": "code", |
||
| 1245 | "execution_count": null, |
||
| 1246 | "metadata": {}, |
||
| 1247 | "outputs": [], |
||
| 1248 | "source": [ |
||
| 1249 | "%%time \n", |
||
| 1250 | "y_pred=et.predict(test_df[feature])" |
||
| 1251 | ] |
||
| 1252 | }, |
||
| 1253 | { |
||
| 1254 | "cell_type": "code", |
||
| 1255 | "execution_count": null, |
||
| 1256 | "metadata": {}, |
||
| 1257 | "outputs": [], |
||
| 1258 | "source": [ |
||
| 1259 | "print(classification_report(test_df['target'], y_pred))" |
||
| 1260 | ] |
||
| 1261 | }, |
||
| 1262 | { |
||
| 1263 | "cell_type": "code", |
||
| 1264 | "execution_count": null, |
||
| 1265 | "metadata": {}, |
||
| 1266 | "outputs": [], |
||
| 1267 | "source": [ |
||
| 1268 | "clf = KNeighborsClassifier(n_neighbors=1)\n", |
||
| 1269 | "clf.fit(train_df[feature],train_df['target'])\n", |
||
| 1270 | "y_pred=clf.predict(test_df[feature])" |
||
| 1271 | ] |
||
| 1272 | }, |
||
| 1273 | { |
||
| 1274 | "cell_type": "code", |
||
| 1275 | "execution_count": null, |
||
| 1276 | "metadata": {}, |
||
| 1277 | "outputs": [], |
||
| 1278 | "source": [ |
||
| 1279 | "print(classification_report(test_df['target'], y_pred))" |
||
| 1280 | ] |
||
| 1281 | }, |
||
| 1282 | { |
||
| 1283 | "cell_type": "code", |
||
| 1284 | "execution_count": null, |
||
| 1285 | "metadata": {}, |
||
| 1286 | "outputs": [], |
||
| 1287 | "source": [] |
||
| 1288 | } |
||
| 1289 | ], |
||
| 1290 | "metadata": { |
||
| 1291 | "kernelspec": { |
||
| 1292 | "display_name": "Python 3", |
||
| 1293 | "language": "python", |
||
| 1294 | "name": "python3" |
||
| 1295 | }, |
||
| 1296 | "language_info": { |
||
| 1297 | "codemirror_mode": { |
||
| 1298 | "name": "ipython", |
||
| 1299 | "version": 3 |
||
| 1300 | }, |
||
| 1301 | "file_extension": ".py", |
||
| 1302 | "mimetype": "text/x-python", |
||
| 1303 | "name": "python", |
||
| 1304 | "nbconvert_exporter": "python", |
||
| 1305 | "pygments_lexer": "ipython3", |
||
| 1306 | "version": "3.6.8" |
||
| 1307 | } |
||
| 1308 | }, |
||
| 1309 | "nbformat": 4, |
||
| 1310 | "nbformat_minor": 2 |
||
| 1311 | } |