File size: 34,240 Bytes
0ab7b0c |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"# import seaborn as sns\n",
"# import matplotlib.pyplot as plt\n",
"import os\n",
"from sklearn.model_selection import train_test_split\n",
"from sklearn.feature_selection import SelectFromModel\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"# plt.style.use('seaborn-colorblind')\n",
"# %matplotlib inline\n",
"from sklearn.feature_selection import RFE\n",
"from feature_selection import hybrid\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Load Dataset"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from sklearn.datasets import load_breast_cancer\n",
"data = load_breast_cancer()\n",
"data = pd.DataFrame(np.c_[data['data'], data['target']],\n",
" columns= np.append(data['feature_names'], ['target']))"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>mean radius</th>\n",
" <th>mean texture</th>\n",
" <th>mean perimeter</th>\n",
" <th>mean area</th>\n",
" <th>mean smoothness</th>\n",
" <th>mean compactness</th>\n",
" <th>mean concavity</th>\n",
" <th>mean concave points</th>\n",
" <th>mean symmetry</th>\n",
" <th>mean fractal dimension</th>\n",
" <th>...</th>\n",
" <th>worst texture</th>\n",
" <th>worst perimeter</th>\n",
" <th>worst area</th>\n",
" <th>worst smoothness</th>\n",
" <th>worst compactness</th>\n",
" <th>worst concavity</th>\n",
" <th>worst concave points</th>\n",
" <th>worst symmetry</th>\n",
" <th>worst fractal dimension</th>\n",
" <th>target</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>17.99</td>\n",
" <td>10.38</td>\n",
" <td>122.80</td>\n",
" <td>1001.0</td>\n",
" <td>0.11840</td>\n",
" <td>0.27760</td>\n",
" <td>0.3001</td>\n",
" <td>0.14710</td>\n",
" <td>0.2419</td>\n",
" <td>0.07871</td>\n",
" <td>...</td>\n",
" <td>17.33</td>\n",
" <td>184.60</td>\n",
" <td>2019.0</td>\n",
" <td>0.1622</td>\n",
" <td>0.6656</td>\n",
" <td>0.7119</td>\n",
" <td>0.2654</td>\n",
" <td>0.4601</td>\n",
" <td>0.11890</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>20.57</td>\n",
" <td>17.77</td>\n",
" <td>132.90</td>\n",
" <td>1326.0</td>\n",
" <td>0.08474</td>\n",
" <td>0.07864</td>\n",
" <td>0.0869</td>\n",
" <td>0.07017</td>\n",
" <td>0.1812</td>\n",
" <td>0.05667</td>\n",
" <td>...</td>\n",
" <td>23.41</td>\n",
" <td>158.80</td>\n",
" <td>1956.0</td>\n",
" <td>0.1238</td>\n",
" <td>0.1866</td>\n",
" <td>0.2416</td>\n",
" <td>0.1860</td>\n",
" <td>0.2750</td>\n",
" <td>0.08902</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>19.69</td>\n",
" <td>21.25</td>\n",
" <td>130.00</td>\n",
" <td>1203.0</td>\n",
" <td>0.10960</td>\n",
" <td>0.15990</td>\n",
" <td>0.1974</td>\n",
" <td>0.12790</td>\n",
" <td>0.2069</td>\n",
" <td>0.05999</td>\n",
" <td>...</td>\n",
" <td>25.53</td>\n",
" <td>152.50</td>\n",
" <td>1709.0</td>\n",
" <td>0.1444</td>\n",
" <td>0.4245</td>\n",
" <td>0.4504</td>\n",
" <td>0.2430</td>\n",
" <td>0.3613</td>\n",
" <td>0.08758</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>11.42</td>\n",
" <td>20.38</td>\n",
" <td>77.58</td>\n",
" <td>386.1</td>\n",
" <td>0.14250</td>\n",
" <td>0.28390</td>\n",
" <td>0.2414</td>\n",
" <td>0.10520</td>\n",
" <td>0.2597</td>\n",
" <td>0.09744</td>\n",
" <td>...</td>\n",
" <td>26.50</td>\n",
" <td>98.87</td>\n",
" <td>567.7</td>\n",
" <td>0.2098</td>\n",
" <td>0.8663</td>\n",
" <td>0.6869</td>\n",
" <td>0.2575</td>\n",
" <td>0.6638</td>\n",
" <td>0.17300</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>20.29</td>\n",
" <td>14.34</td>\n",
" <td>135.10</td>\n",
" <td>1297.0</td>\n",
" <td>0.10030</td>\n",
" <td>0.13280</td>\n",
" <td>0.1980</td>\n",
" <td>0.10430</td>\n",
" <td>0.1809</td>\n",
" <td>0.05883</td>\n",
" <td>...</td>\n",
" <td>16.67</td>\n",
" <td>152.20</td>\n",
" <td>1575.0</td>\n",
" <td>0.1374</td>\n",
" <td>0.2050</td>\n",
" <td>0.4000</td>\n",
" <td>0.1625</td>\n",
" <td>0.2364</td>\n",
" <td>0.07678</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 31 columns</p>\n",
"</div>"
],
"text/plain": [
" mean radius mean texture mean perimeter mean area mean smoothness \\\n",
"0 17.99 10.38 122.80 1001.0 0.11840 \n",
"1 20.57 17.77 132.90 1326.0 0.08474 \n",
"2 19.69 21.25 130.00 1203.0 0.10960 \n",
"3 11.42 20.38 77.58 386.1 0.14250 \n",
"4 20.29 14.34 135.10 1297.0 0.10030 \n",
"\n",
" mean compactness mean concavity mean concave points mean symmetry \\\n",
"0 0.27760 0.3001 0.14710 0.2419 \n",
"1 0.07864 0.0869 0.07017 0.1812 \n",
"2 0.15990 0.1974 0.12790 0.2069 \n",
"3 0.28390 0.2414 0.10520 0.2597 \n",
"4 0.13280 0.1980 0.10430 0.1809 \n",
"\n",
" mean fractal dimension ... worst texture worst perimeter worst area \\\n",
"0 0.07871 ... 17.33 184.60 2019.0 \n",
"1 0.05667 ... 23.41 158.80 1956.0 \n",
"2 0.05999 ... 25.53 152.50 1709.0 \n",
"3 0.09744 ... 26.50 98.87 567.7 \n",
"4 0.05883 ... 16.67 152.20 1575.0 \n",
"\n",
" worst smoothness worst compactness worst concavity worst concave points \\\n",
"0 0.1622 0.6656 0.7119 0.2654 \n",
"1 0.1238 0.1866 0.2416 0.1860 \n",
"2 0.1444 0.4245 0.4504 0.2430 \n",
"3 0.2098 0.8663 0.6869 0.2575 \n",
"4 0.1374 0.2050 0.4000 0.1625 \n",
"\n",
" worst symmetry worst fractal dimension target \n",
"0 0.4601 0.11890 0.0 \n",
"1 0.2750 0.08902 0.0 \n",
"2 0.3613 0.08758 0.0 \n",
"3 0.6638 0.17300 0.0 \n",
"4 0.2364 0.07678 0.0 \n",
"\n",
"[5 rows x 31 columns]"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"data.head(5)"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"((455, 30), (114, 30))"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"X_train, X_test, y_train, y_test = train_test_split(data.drop(labels=['target'], axis=1), \n",
" data.target, test_size=0.2,\n",
" random_state=0)\n",
"X_train.shape, X_test.shape"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Recursive Feature Elimination \n",
"### with Random Forests Importance\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Example 1\n",
"This method is slightly **different from the guide**, as it use a different stopping criterion: the desired number of features to select is eventually reached."
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"RFE(estimator=RandomForestClassifier(bootstrap=True, class_weight=None, criterion='gini',\n",
" max_depth=None, max_features='auto', max_leaf_nodes=None,\n",
" min_impurity_decrease=0.0, min_impurity_split=None,\n",
" min_samples_leaf=1, min_samples_split=2,\n",
" min_weight_fraction_leaf=0.0, n_estimators=20, n_jobs=None,\n",
" oob_score=False, random_state=None, verbose=0,\n",
" warm_start=False),\n",
" n_features_to_select=10, step=1, verbose=0)"
]
},
"execution_count": 5,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# n_features_to_select decide the stopping criterion\n",
"# we stop till 10 features remaining\n",
"\n",
"sel_ = RFE(RandomForestClassifier(n_estimators=20), n_features_to_select=10)\n",
"sel_.fit(X_train.fillna(0), y_train)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Index(['mean texture', 'mean perimeter', 'mean area', 'mean concavity',\n",
" 'mean concave points', 'worst radius', 'worst perimeter', 'worst area',\n",
" 'worst concave points', 'worst symmetry'],\n",
" dtype='object')\n"
]
}
],
"source": [
"selected_feat = X_train.columns[(sel_.get_support())]\n",
"print(selected_feat)"
]
},
{
"cell_type": "markdown",
"metadata": {
"collapsed": true
},
"source": [
"### Example 2\n",
"recursive feature elimination with RandomForest\n",
"with the method same as the guide\n",
"1. Rank the features according to their importance derived from a machine learning algorithm: it can be tree importance, or LASSO / Ridge, or the linear / logistic regression coefficients.\n",
"2. Remove one feature -the least important- and build a machine learning algorithm utilizing the remaining features.\n",
"3. Calculate a performance metric of your choice: roc-auc, mse, rmse, accuracy.\n",
"4. If the metric decreases by more of an arbitrarily set threshold, then that feature is important and should be kept. Otherwise, we can remove that feature.\n",
"5. Repeat steps 2-4 until all features have been removed (and therefore evaluated) and the drop in performance assessed.\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"testing feature: mean radius which is feature 1 out of 30\n",
"New Test ROC AUC=0.9941251190854239\n",
"All features Test ROC AUC=0.9968243886948238\n",
"Drop in ROC AUC=0.0026992696093999236\n",
"keep: mean radius\n",
"\n",
"testing feature: mean texture which is feature 2 out of 30\n",
"New Test ROC AUC=0.9936487773896475\n",
"All features Test ROC AUC=0.9968243886948238\n",
"Drop in ROC AUC=0.0031756113051762958\n",
"keep: mean texture\n",
"\n",
"testing feature: mean perimeter which is feature 3 out of 30\n",
"New Test ROC AUC=0.9968243886948238\n",
"All features Test ROC AUC=0.9968243886948238\n",
"Drop in ROC AUC=0.0\n",
"remove: mean perimeter\n",
"\n",
"testing feature: mean area which is feature 4 out of 30\n",
"New Test ROC AUC=0.9960304858685297\n",
"All features Test ROC AUC=0.9968243886948238\n",
"Drop in ROC AUC=0.0007939028262941017\n",
"remove: mean area\n",
"\n",
"testing feature: mean smoothness which is feature 5 out of 30\n",
"New Test ROC AUC=0.9965068275643061\n",
"All features Test ROC AUC=0.9960304858685297\n",
"Drop in ROC AUC=-0.0004763416957763722\n",
"remove: mean smoothness\n",
"\n",
"testing feature: mean compactness which is feature 6 out of 30\n",
"New Test ROC AUC=0.9942838996506828\n",
"All features Test ROC AUC=0.9965068275643061\n",
"Drop in ROC AUC=0.0022229279136233293\n",
"keep: mean compactness\n",
"\n",
"testing feature: mean concavity which is feature 7 out of 30\n",
"New Test ROC AUC=0.9957129247380121\n",
"All features Test ROC AUC=0.9965068275643061\n",
"Drop in ROC AUC=0.0007939028262939907\n",
"remove: mean concavity\n",
"\n",
"testing feature: mean concave points which is feature 8 out of 30\n",
"New Test ROC AUC=0.9976182915211178\n",
"All features Test ROC AUC=0.9957129247380121\n",
"Drop in ROC AUC=-0.0019053667831057108\n",
"remove: mean concave points\n",
"\n",
"testing feature: mean symmetry which is feature 9 out of 30\n",
"New Test ROC AUC=0.9953953636074945\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.0022229279136233293\n",
"keep: mean symmetry\n",
"\n",
"testing feature: mean fractal dimension which is feature 10 out of 30\n",
"New Test ROC AUC=0.9949190219117181\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.0026992696093997015\n",
"keep: mean fractal dimension\n",
"\n",
"testing feature: radius error which is feature 11 out of 30\n",
"New Test ROC AUC=0.9952365830422356\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.002381708478882194\n",
"keep: radius error\n",
"\n",
"testing feature: texture error which is feature 12 out of 30\n",
"New Test ROC AUC=0.9952365830422356\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.002381708478882194\n",
"keep: texture error\n",
"\n",
"testing feature: perimeter error which is feature 13 out of 30\n",
"New Test ROC AUC=0.9939663385201651\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.003651953000952668\n",
"keep: perimeter error\n",
"\n",
"testing feature: area error which is feature 14 out of 30\n",
"New Test ROC AUC=0.994919021911718\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.0026992696093998125\n",
"keep: area error\n",
"\n",
"testing feature: smoothness error which is feature 15 out of 30\n",
"New Test ROC AUC=0.995871705303271\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.001746586217846846\n",
"keep: smoothness error\n",
"\n",
"testing feature: compactness error which is feature 16 out of 30\n",
"New Test ROC AUC=0.9958717053032708\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.0017465862178469571\n",
"keep: compactness error\n",
"\n",
"testing feature: concavity error which is feature 17 out of 30\n",
"New Test ROC AUC=0.9961892664337886\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.0014290250873292276\n",
"keep: concavity error\n",
"\n",
"testing feature: concave points error which is feature 18 out of 30\n",
"New Test ROC AUC=0.9961892664337885\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.0014290250873293386\n",
"keep: concave points error\n",
"\n",
"testing feature: symmetry error which is feature 19 out of 30\n",
"New Test ROC AUC=0.9968243886948238\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.0007939028262939907\n",
"remove: symmetry error\n",
"\n",
"testing feature: fractal dimension error which is feature 20 out of 30\n",
"New Test ROC AUC=0.9946014607812005\n",
"All features Test ROC AUC=0.9968243886948238\n",
"Drop in ROC AUC=0.0022229279136233293\n",
"keep: fractal dimension error\n",
"\n",
"testing feature: worst radius which is feature 21 out of 30\n",
"New Test ROC AUC=0.9955541441727532\n",
"All features Test ROC AUC=0.9968243886948238\n",
"Drop in ROC AUC=0.001270244522070585\n",
"keep: worst radius\n",
"\n",
"testing feature: worst texture which is feature 22 out of 30\n",
"New Test ROC AUC=0.9958717053032708\n",
"All features Test ROC AUC=0.9968243886948238\n",
"Drop in ROC AUC=0.0009526833915529664\n",
"remove: worst texture\n",
"\n",
"testing feature: worst perimeter which is feature 23 out of 30\n",
"New Test ROC AUC=0.995871705303271\n",
"All features Test ROC AUC=0.9958717053032708\n",
"Drop in ROC AUC=-1.1102230246251565e-16\n",
"remove: worst perimeter\n",
"\n",
"testing feature: worst area which is feature 24 out of 30\n",
"New Test ROC AUC=0.9938075579549063\n",
"All features Test ROC AUC=0.995871705303271\n",
"Drop in ROC AUC=0.0020641473483646866\n",
"keep: worst area\n",
"\n",
"testing feature: worst smoothness which is feature 25 out of 30\n",
"New Test ROC AUC=0.9939663385201651\n",
"All features Test ROC AUC=0.995871705303271\n",
"Drop in ROC AUC=0.0019053667831058219\n",
"keep: worst smoothness\n",
"\n",
"testing feature: worst compactness which is feature 26 out of 30\n",
"New Test ROC AUC=0.9960304858685296\n",
"All features Test ROC AUC=0.995871705303271\n",
"Drop in ROC AUC=-0.0001587805652586427\n",
"remove: worst compactness\n",
"\n",
"testing feature: worst concavity which is feature 27 out of 30\n",
"New Test ROC AUC=0.9966656081295648\n",
"All features Test ROC AUC=0.9960304858685296\n",
"Drop in ROC AUC=-0.0006351222610352369\n",
"remove: worst concavity\n",
"\n",
"testing feature: worst concave points which is feature 28 out of 30\n",
"New Test ROC AUC=0.9936487773896475\n",
"All features Test ROC AUC=0.9966656081295648\n",
"Drop in ROC AUC=0.00301683073991732\n",
"keep: worst concave points\n",
"\n",
"testing feature: worst symmetry which is feature 29 out of 30\n",
"New Test ROC AUC=0.9976182915211178\n",
"All features Test ROC AUC=0.9966656081295648\n",
"Drop in ROC AUC=-0.0009526833915529664\n",
"remove: worst symmetry\n",
"\n",
"testing feature: worst fractal dimension which is feature 30 out of 30\n",
"New Test ROC AUC=0.9973007303906002\n",
"All features Test ROC AUC=0.9976182915211178\n",
"Drop in ROC AUC=0.00031756113051761847\n",
"remove: worst fractal dimension\n",
"DONE!!\n",
"total features to remove: 12\n",
"total features to keep: 18\n"
]
}
],
"source": [
"# tol decide whether we should drop or keep the feature in current round\n",
"features_to_keep = hybrid.recursive_feature_elimination_rf(X_train=X_train,\n",
" y_train=y_train,\n",
" X_test=X_test,\n",
" y_test=y_test,\n",
" tol=0.001)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['mean radius',\n",
" 'mean texture',\n",
" 'mean compactness',\n",
" 'mean symmetry',\n",
" 'mean fractal dimension',\n",
" 'radius error',\n",
" 'texture error',\n",
" 'perimeter error',\n",
" 'area error',\n",
" 'smoothness error',\n",
" 'compactness error',\n",
" 'concavity error',\n",
" 'concave points error',\n",
" 'fractal dimension error',\n",
" 'worst radius',\n",
" 'worst area',\n",
" 'worst smoothness',\n",
" 'worst concave points']"
]
},
"execution_count": 8,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"features_to_keep"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Recursive Feature Addition\n",
"### with Random Forests Importance"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Example 1\n",
"recursive feature addition with RandomForest\n",
"with the method same as the guide\n",
"1. Rank the features according to their importance derived from a machine learning algorithm: it can be tree importance, or LASSO / Ridge, or the linear / logistic regression coefficients.\n",
"2. Build a machine learning model with only 1 feature, the most important one, and calculate the model metric for performance.\n",
"3. Add one feature -the most important- and build a machine learning algorithm utilizing the added and any feature from previous rounds.\n",
"4. Calculate a performance metric of your choice: roc-auc, mse, rmse, accuracy.\n",
"5. If the metric increases by more than an arbitrarily set threshold, then that feature is important and should be kept. Otherwise, we can remove that feature.\n",
"6. Repeat steps 2-5 until all features have been removed (and therefore evaluated) and the drop in performance assessed.\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"testing feature: mean texture which is feature 1 out of 30\n",
"New Test ROC AUC=0.9558590028580501\n",
"All features Test ROC AUC=0.9009209272785013\n",
"Increase in ROC AUC=0.054938075579548884\n",
"keep: mean texture\n",
"\n",
"testing feature: mean perimeter which is feature 2 out of 30\n",
"New Test ROC AUC=0.9609399809463322\n",
"All features Test ROC AUC=0.9558590028580501\n",
"Increase in ROC AUC=0.005080978088282007\n",
"keep: mean perimeter\n",
"\n",
"testing feature: mean area which is feature 3 out of 30\n",
"New Test ROC AUC=0.9609399809463322\n",
"All features Test ROC AUC=0.9609399809463322\n",
"Increase in ROC AUC=0.0\n",
"remove: mean area\n",
"\n",
"testing feature: mean smoothness which is feature 4 out of 30\n",
"New Test ROC AUC=0.9684026675134964\n",
"All features Test ROC AUC=0.9609399809463322\n",
"Increase in ROC AUC=0.007462686567164201\n",
"keep: mean smoothness\n",
"\n",
"testing feature: mean compactness which is feature 5 out of 30\n",
"New Test ROC AUC=0.9750714512543665\n",
"All features Test ROC AUC=0.9684026675134964\n",
"Increase in ROC AUC=0.006668783740870099\n",
"keep: mean compactness\n",
"\n",
"testing feature: mean concavity which is feature 6 out of 30\n",
"New Test ROC AUC=0.9933312162591298\n",
"All features Test ROC AUC=0.9750714512543665\n",
"Increase in ROC AUC=0.01825976500476334\n",
"keep: mean concavity\n",
"\n",
"testing feature: mean concave points which is feature 7 out of 30\n",
"New Test ROC AUC=0.9925373134328358\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0007939028262939907\n",
"remove: mean concave points\n",
"\n",
"testing feature: mean symmetry which is feature 8 out of 30\n",
"New Test ROC AUC=0.9895204826929185\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0038107335662113107\n",
"remove: mean symmetry\n",
"\n",
"testing feature: mean fractal dimension which is feature 9 out of 30\n",
"New Test ROC AUC=0.9892029215624007\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.00412829469672904\n",
"remove: mean fractal dimension\n",
"\n",
"testing feature: radius error which is feature 10 out of 30\n",
"New Test ROC AUC=0.9895204826929184\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0038107335662114217\n",
"remove: radius error\n",
"\n",
"testing feature: texture error which is feature 11 out of 30\n",
"New Test ROC AUC=0.9868212130835186\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.006510003175611234\n",
"remove: texture error\n",
"\n",
"testing feature: perimeter error which is feature 12 out of 30\n",
"New Test ROC AUC=0.9890441409971419\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.004287075261987905\n",
"remove: perimeter error\n",
"\n",
"testing feature: area error which is feature 13 out of 30\n",
"New Test ROC AUC=0.989044140997142\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.004287075261987794\n",
"remove: area error\n",
"\n",
"testing feature: smoothness error which is feature 14 out of 30\n",
"New Test ROC AUC=0.988091457605589\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.00523975865354076\n",
"remove: smoothness error\n",
"\n",
"testing feature: compactness error which is feature 15 out of 30\n",
"New Test ROC AUC=0.9895204826929184\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0038107335662114217\n",
"remove: compactness error\n",
"\n",
"testing feature: concavity error which is feature 16 out of 30\n",
"New Test ROC AUC=0.9911082883455065\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0022229279136233293\n",
"remove: concavity error\n",
"\n",
"testing feature: concave points error which is feature 17 out of 30\n",
"New Test ROC AUC=0.9906319466497301\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0026992696093997015\n",
"remove: concave points error\n",
"\n",
"testing feature: symmetry error which is feature 18 out of 30\n",
"New Test ROC AUC=0.9876151159098127\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0057161003493171325\n",
"remove: symmetry error\n",
"\n",
"testing feature: fractal dimension error which is feature 19 out of 30\n",
"New Test ROC AUC=0.9896792632581772\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.003651953000952557\n",
"remove: fractal dimension error\n",
"\n",
"testing feature: worst radius which is feature 20 out of 30\n",
"New Test ROC AUC=0.994125119085424\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=0.0007939028262942127\n",
"remove: worst radius\n",
"\n",
"testing feature: worst texture which is feature 21 out of 30\n",
"New Test ROC AUC=0.9906319466497301\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0026992696093997015\n",
"remove: worst texture\n",
"\n",
"testing feature: worst perimeter which is feature 22 out of 30\n",
"New Test ROC AUC=0.9933312162591299\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=1.1102230246251565e-16\n",
"remove: worst perimeter\n",
"\n",
"testing feature: worst area which is feature 23 out of 30\n",
"New Test ROC AUC=0.9931724356938711\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0001587805652586427\n",
"remove: worst area\n",
"\n",
"testing feature: worst smoothness which is feature 24 out of 30\n",
"New Test ROC AUC=0.9933312162591299\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=1.1102230246251565e-16\n",
"remove: worst smoothness\n",
"\n",
"testing feature: worst compactness which is feature 25 out of 30\n",
"New Test ROC AUC=0.9895204826929184\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=-0.0038107335662114217\n",
"remove: worst compactness\n",
"\n",
"testing feature: worst concavity which is feature 26 out of 30\n",
"New Test ROC AUC=0.9938075579549063\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=0.0004763416957764832\n",
"remove: worst concavity\n",
"\n",
"testing feature: worst concave points which is feature 27 out of 30\n",
"New Test ROC AUC=0.9971419498253413\n",
"All features Test ROC AUC=0.9933312162591298\n",
"Increase in ROC AUC=0.0038107335662115327\n",
"keep: worst concave points\n",
"\n",
"testing feature: worst symmetry which is feature 28 out of 30\n",
"New Test ROC AUC=0.9957129247380121\n",
"All features Test ROC AUC=0.9971419498253413\n",
"Increase in ROC AUC=-0.0014290250873292276\n",
"remove: worst symmetry\n",
"\n",
"testing feature: worst fractal dimension which is feature 29 out of 30\n",
"New Test ROC AUC=0.9950778024769769\n",
"All features Test ROC AUC=0.9971419498253413\n",
"Increase in ROC AUC=-0.0020641473483644646\n",
"remove: worst fractal dimension\n",
"DONE!!\n",
"total features to keep: 7\n"
]
}
],
"source": [
"features_to_keep = hybrid.recursive_feature_addition_rf(X_train=X_train,\n",
" y_train=y_train,\n",
" X_test=X_test,\n",
" y_test=y_test,\n",
" tol=0.001)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['mean radius',\n",
" 'mean texture',\n",
" 'mean perimeter',\n",
" 'mean smoothness',\n",
" 'mean compactness',\n",
" 'mean concavity',\n",
" 'worst concave points']"
]
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"features_to_keep"
]
}
],
"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": "3.6.1"
}
},
"nbformat": 4,
"nbformat_minor": 2
}
|