層化 k 分割交差検証の実装
以下のリンクの続き
StratifiedKFold を使った場合。kfold からどのような組み合わせか確認できる
import numpy as np from sklearn.model_selection import StratifiedKFold kfold = StratifiedKFold(n_splits=10, random_state=1).split(X_train, y_train) scores = [] for k, (train, test) in enumerate(kfold): pipe_lr.fit(X_train[train], y_train[train]) score = pipe_lr.score(X_train[test], y_train[test]) scores.append(score) ## np.bincount で [0,0,1,1,1] => [2, 3] と回数を数える print('Fold: %2d, Class dist, : %s, Acc: %.3f' % (k+1, np.bincount(y_train[train]), score) ) print('\nCV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))
Fold: 1, Class dist, : [256 153], Acc: 0.935 Fold: 2, Class dist, : [256 153], Acc: 0.935 Fold: 3, Class dist, : [256 153], Acc: 0.957 Fold: 4, Class dist, : [256 153], Acc: 0.957 Fold: 5, Class dist, : [256 153], Acc: 0.935 Fold: 6, Class dist, : [257 153], Acc: 0.956 Fold: 7, Class dist, : [257 153], Acc: 0.978 Fold: 8, Class dist, : [257 153], Acc: 0.933 Fold: 9, Class dist, : [257 153], Acc: 0.956 Fold: 10, Class dist, : [257 153], Acc: 0.956 CV accuracy: 0.950 +/- 0.014
kfold の中身を見てみる
kfold = StratifiedKFold(n_splits=10, random_state=1).split(X_train, y_train) next(kfold) =============== (array([ 45, 46, 47, 48, 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]), array([ 0, 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, 49])) ===============
cross_val_score を使った場合、効率よく検証できる
from sklearn.model_selection import cross_val_score score = cross_val_score(estimator=pipe_lr, X=X_train, y=y_train, n_jobs=1) print('CV accuracy scores: %s' % scores) print('\nCV accuracy: %.3f +/- %.3f' % (np.mean(scores), np.std(scores)))
CV accuracy scores: [0.9347826086956522, 0.9347826086956522, 0.9565217391304348, 0.9565217391304348, 0.9347826086956522, 0.9555555555555556, 0.9777777777777777, 0.9333333333333333, 0.9555555555555556, 0.9555555555555556] CV accuracy: 0.950 +/- 0.014
