This repository was archived by the owner on Jan 25, 2023. It is now read-only.
forked from scikit-learn/scikit-learn
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathtest_data.py
More file actions
709 lines (552 loc) · 24.7 KB
/
test_data.py
File metadata and controls
709 lines (552 loc) · 24.7 KB
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
import warnings
import numpy as np
import numpy.linalg as la
from scipy import sparse
from sklearn.utils.testing import assert_almost_equal
from sklearn.utils.testing import assert_array_almost_equal
from sklearn.utils.testing import assert_array_equal
from sklearn.utils.testing import assert_equal
from sklearn.utils.testing import assert_raises
from sklearn.utils.testing import assert_true
from sklearn.utils.testing import assert_false
from sklearn.utils.testing import assert_warns
from sklearn.utils.sparsefuncs import mean_variance_axis0
from sklearn.preprocessing.data import _transform_selected
from sklearn.preprocessing.data import Binarizer
from sklearn.preprocessing.data import KernelCenterer
from sklearn.preprocessing.data import Normalizer
from sklearn.preprocessing.data import normalize
from sklearn.preprocessing.data import OneHotEncoder
from sklearn.preprocessing.data import StandardScaler
from sklearn.preprocessing.data import scale
from sklearn.preprocessing.data import MinMaxScaler
from sklearn.preprocessing.data import add_dummy_feature
from sklearn import datasets
iris = datasets.load_iris()
def toarray(a):
if hasattr(a, "toarray"):
a = a.toarray()
return a
def test_scaler_1d():
"""Test scaling of dataset along single axis"""
rng = np.random.RandomState(0)
X = rng.randn(5)
X_orig_copy = X.copy()
scaler = StandardScaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
# check inverse transform
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_array_almost_equal(X_scaled_back, X_orig_copy)
# Test with 1D list
X = [0., 1., 2, 0.4, 1.]
scaler = StandardScaler()
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
X_scaled = scale(X)
assert_array_almost_equal(X_scaled.mean(axis=0), 0.0)
assert_array_almost_equal(X_scaled.std(axis=0), 1.0)
def test_scaler_2d_arrays():
"""Test scaling of 2d array along first axis"""
rng = np.random.RandomState(0)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
scaler = StandardScaler()
X_scaled = scaler.fit(X).transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has been copied
assert_true(X_scaled is not X)
# check inverse transform
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_true(X_scaled_back is not X)
assert_true(X_scaled_back is not X_scaled)
assert_array_almost_equal(X_scaled_back, X)
X_scaled = scale(X, axis=1, with_std=False)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=1), 4 * [0.0])
X_scaled = scale(X, axis=1, with_std=True)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=1), 4 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=1), 4 * [1.0])
# Check that the data hasn't been modified
assert_true(X_scaled is not X)
X_scaled = scaler.fit(X).transform(X, copy=False)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert_true(X_scaled is X)
X = rng.randn(4, 5)
X[:, 0] = 1.0 # first feature is a constant, non zero feature
scaler = StandardScaler()
X_scaled = scaler.fit(X).transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
assert_array_almost_equal(X_scaled.mean(axis=0), 5 * [0.0])
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert_true(X_scaled is not X)
def test_min_max_scaler_iris():
X = iris.data
scaler = MinMaxScaler()
# default params
X_trans = scaler.fit_transform(X)
assert_array_almost_equal(X_trans.min(axis=0), 0)
assert_array_almost_equal(X_trans.min(axis=0), 0)
assert_array_almost_equal(X_trans.max(axis=0), 1)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
# not default params: min=1, max=2
scaler = MinMaxScaler(feature_range=(1, 2))
X_trans = scaler.fit_transform(X)
assert_array_almost_equal(X_trans.min(axis=0), 1)
assert_array_almost_equal(X_trans.max(axis=0), 2)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
# min=-.5, max=.6
scaler = MinMaxScaler(feature_range=(-.5, .6))
X_trans = scaler.fit_transform(X)
assert_array_almost_equal(X_trans.min(axis=0), -.5)
assert_array_almost_equal(X_trans.max(axis=0), .6)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
# raises on invalid range
scaler = MinMaxScaler(feature_range=(2, 1))
assert_raises(ValueError, scaler.fit, X)
def test_min_max_scaler_zero_variance_features():
"""Check min max scaler on toy data with zero variance features"""
X = [[0., 1., +0.5],
[0., 1., -0.1],
[0., 1., +1.1]]
X_new = [[+0., 2., 0.5],
[-1., 1., 0.0],
[+0., 1., 1.5]]
# default params
scaler = MinMaxScaler()
X_trans = scaler.fit_transform(X)
X_expected_0_1 = [[0., 0., 0.5],
[0., 0., 0.0],
[0., 0., 1.0]]
assert_array_almost_equal(X_trans, X_expected_0_1)
X_trans_inv = scaler.inverse_transform(X_trans)
assert_array_almost_equal(X, X_trans_inv)
X_trans_new = scaler.transform(X_new)
X_expected_0_1_new = [[+0., 1., 0.500],
[-1., 0., 0.083],
[+0., 0., 1.333]]
assert_array_almost_equal(X_trans_new, X_expected_0_1_new, decimal=2)
# not default params
scaler = MinMaxScaler(feature_range=(1, 2))
X_trans = scaler.fit_transform(X)
X_expected_1_2 = [[1., 1., 1.5],
[1., 1., 1.0],
[1., 1., 2.0]]
assert_array_almost_equal(X_trans, X_expected_1_2)
def test_scaler_without_centering():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
X_csr = sparse.csr_matrix(X)
X_csc = sparse.csc_matrix(X)
assert_raises(ValueError, StandardScaler().fit, X_csr)
null_transform = StandardScaler(with_mean=False, with_std=False, copy=True)
X_null = null_transform.fit_transform(X_csr)
assert_array_equal(X_null.data, X_csr.data)
X_orig = null_transform.inverse_transform(X_null)
assert_array_equal(X_orig.data, X_csr.data)
scaler = StandardScaler(with_mean=False).fit(X)
X_scaled = scaler.transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
scaler_csr = StandardScaler(with_mean=False).fit(X_csr)
X_csr_scaled = scaler_csr.transform(X_csr, copy=True)
assert_false(np.any(np.isnan(X_csr_scaled.data)))
scaler_csc = StandardScaler(with_mean=False).fit(X_csc)
X_csc_scaled = scaler_csr.transform(X_csc, copy=True)
assert_false(np.any(np.isnan(X_csc_scaled.data)))
assert_equal(scaler.mean_, scaler_csr.mean_)
assert_array_almost_equal(scaler.std_, scaler_csr.std_)
assert_equal(scaler.mean_, scaler_csc.mean_)
assert_array_almost_equal(scaler.std_, scaler_csc.std_)
assert_array_almost_equal(
X_scaled.mean(axis=0), [0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
X_csr_scaled_mean, X_csr_scaled_std = mean_variance_axis0(X_csr_scaled)
assert_array_almost_equal(X_csr_scaled_mean, X_scaled.mean(axis=0))
assert_array_almost_equal(X_csr_scaled_std, X_scaled.std(axis=0))
# Check that X has not been modified (copy)
assert_true(X_scaled is not X)
assert_true(X_csr_scaled is not X_csr)
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_true(X_scaled_back is not X)
assert_true(X_scaled_back is not X_scaled)
assert_array_almost_equal(X_scaled_back, X)
X_csr_scaled_back = scaler_csr.inverse_transform(X_csr_scaled)
assert_true(X_csr_scaled_back is not X_csr)
assert_true(X_csr_scaled_back is not X_csr_scaled)
assert_array_almost_equal(X_csr_scaled_back.toarray(), X)
X_csc_scaled_back = scaler_csr.inverse_transform(X_csc_scaled.tocsc())
assert_true(X_csc_scaled_back is not X_csc)
assert_true(X_csc_scaled_back is not X_csc_scaled)
assert_array_almost_equal(X_csc_scaled_back.toarray(), X)
def test_scaler_int():
# test that scaler converts integer input to floating
# for both sparse and dense matrices
rng = np.random.RandomState(42)
X = rng.randint(20, size=(4, 5))
X[:, 0] = 0 # first feature is always of zero
X_csr = sparse.csr_matrix(X)
X_csc = sparse.csc_matrix(X)
null_transform = StandardScaler(with_mean=False, with_std=False, copy=True)
with warnings.catch_warnings(record=True):
X_null = null_transform.fit_transform(X_csr)
assert_array_equal(X_null.data, X_csr.data)
X_orig = null_transform.inverse_transform(X_null)
assert_array_equal(X_orig.data, X_csr.data)
with warnings.catch_warnings(record=True):
scaler = StandardScaler(with_mean=False).fit(X)
X_scaled = scaler.transform(X, copy=True)
assert_false(np.any(np.isnan(X_scaled)))
with warnings.catch_warnings(record=True):
scaler_csr = StandardScaler(with_mean=False).fit(X_csr)
X_csr_scaled = scaler_csr.transform(X_csr, copy=True)
assert_false(np.any(np.isnan(X_csr_scaled.data)))
with warnings.catch_warnings(record=True):
scaler_csc = StandardScaler(with_mean=False).fit(X_csc)
X_csc_scaled = scaler_csr.transform(X_csc, copy=True)
assert_false(np.any(np.isnan(X_csc_scaled.data)))
assert_equal(scaler.mean_, scaler_csr.mean_)
assert_array_almost_equal(scaler.std_, scaler_csr.std_)
assert_equal(scaler.mean_, scaler_csc.mean_)
assert_array_almost_equal(scaler.std_, scaler_csc.std_)
assert_array_almost_equal(
X_scaled.mean(axis=0),
[0., 1.109, 1.856, 21., 1.559], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
X_csr_scaled_mean, X_csr_scaled_std = mean_variance_axis0(
X_csr_scaled.astype(np.float))
assert_array_almost_equal(X_csr_scaled_mean, X_scaled.mean(axis=0))
assert_array_almost_equal(X_csr_scaled_std, X_scaled.std(axis=0))
# Check that X has not been modified (copy)
assert_true(X_scaled is not X)
assert_true(X_csr_scaled is not X_csr)
X_scaled_back = scaler.inverse_transform(X_scaled)
assert_true(X_scaled_back is not X)
assert_true(X_scaled_back is not X_scaled)
assert_array_almost_equal(X_scaled_back, X)
X_csr_scaled_back = scaler_csr.inverse_transform(X_csr_scaled)
assert_true(X_csr_scaled_back is not X_csr)
assert_true(X_csr_scaled_back is not X_csr_scaled)
assert_array_almost_equal(X_csr_scaled_back.toarray(), X)
X_csc_scaled_back = scaler_csr.inverse_transform(X_csc_scaled.tocsc())
assert_true(X_csc_scaled_back is not X_csc)
assert_true(X_csc_scaled_back is not X_csc_scaled)
assert_array_almost_equal(X_csc_scaled_back.toarray(), X)
def test_scaler_without_copy():
"""Check that StandardScaler.fit does not change input"""
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
X_csr = sparse.csr_matrix(X)
X_copy = X.copy()
StandardScaler(copy=False).fit(X)
assert_array_equal(X, X_copy)
X_csr_copy = X_csr.copy()
StandardScaler(with_mean=False, copy=False).fit(X_csr)
assert_array_equal(X_csr.toarray(), X_csr_copy.toarray())
def test_scale_sparse_with_mean_raise_exception():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X_csr = sparse.csr_matrix(X)
# check scaling and fit with direct calls on sparse data
assert_raises(ValueError, scale, X_csr, with_mean=True)
assert_raises(ValueError, StandardScaler(with_mean=True).fit, X_csr)
# check transform and inverse_transform after a fit on a dense array
scaler = StandardScaler(with_mean=True).fit(X)
assert_raises(ValueError, scaler.transform, X_csr)
X_transformed_csr = sparse.csr_matrix(scaler.transform(X))
assert_raises(ValueError, scaler.inverse_transform, X_transformed_csr)
def test_scale_function_without_centering():
rng = np.random.RandomState(42)
X = rng.randn(4, 5)
X[:, 0] = 0.0 # first feature is always of zero
X_csr = sparse.csr_matrix(X)
X_scaled = scale(X, with_mean=False)
assert_false(np.any(np.isnan(X_scaled)))
X_csr_scaled = scale(X_csr, with_mean=False)
assert_false(np.any(np.isnan(X_csr_scaled.data)))
# test csc has same outcome
X_csc_scaled = scale(X_csr.tocsc(), with_mean=False)
assert_array_almost_equal(X_scaled, X_csc_scaled.toarray())
# raises value error on axis != 0
assert_raises(ValueError, scale, X_csr, with_mean=False, axis=1)
assert_array_almost_equal(X_scaled.mean(axis=0),
[0., -0.01, 2.24, -0.35, -0.78], 2)
assert_array_almost_equal(X_scaled.std(axis=0), [0., 1., 1., 1., 1.])
# Check that X has not been copied
assert_true(X_scaled is not X)
X_csr_scaled_mean, X_csr_scaled_std = mean_variance_axis0(X_csr_scaled)
assert_array_almost_equal(X_csr_scaled_mean, X_scaled.mean(axis=0))
assert_array_almost_equal(X_csr_scaled_std, X_scaled.std(axis=0))
def test_warning_scaling_integers():
"""Check warning when scaling integer data"""
X = np.array([[1, 2, 0],
[0, 0, 0]], dtype=np.uint8)
with warnings.catch_warnings(record=True):
warnings.simplefilter("always")
assert_warns(UserWarning, StandardScaler().fit, X)
with warnings.catch_warnings(record=True):
warnings.simplefilter("always")
assert_warns(UserWarning, MinMaxScaler().fit, X)
def test_normalizer_l1():
rng = np.random.RandomState(0)
X_dense = rng.randn(4, 5)
X_sparse_unpruned = sparse.csr_matrix(X_dense)
# set the row number 3 to zero
X_dense[3, :] = 0.0
# set the row number 3 to zero without pruning (can happen in real life)
indptr_3 = X_sparse_unpruned.indptr[3]
indptr_4 = X_sparse_unpruned.indptr[4]
X_sparse_unpruned.data[indptr_3:indptr_4] = 0.0
# build the pruned variant using the regular constructor
X_sparse_pruned = sparse.csr_matrix(X_dense)
# check inputs that support the no-copy optim
for X in (X_dense, X_sparse_pruned, X_sparse_unpruned):
normalizer = Normalizer(norm='l1', copy=True)
X_norm = normalizer.transform(X)
assert_true(X_norm is not X)
X_norm1 = toarray(X_norm)
normalizer = Normalizer(norm='l1', copy=False)
X_norm = normalizer.transform(X)
assert_true(X_norm is X)
X_norm2 = toarray(X_norm)
for X_norm in (X_norm1, X_norm2):
row_sums = np.abs(X_norm).sum(axis=1)
for i in range(3):
assert_almost_equal(row_sums[i], 1.0)
assert_almost_equal(row_sums[3], 0.0)
# check input for which copy=False won't prevent a copy
for init in (sparse.coo_matrix, sparse.csc_matrix, sparse.lil_matrix):
X = init(X_dense)
X_norm = normalizer = Normalizer(norm='l2', copy=False).transform(X)
assert_true(X_norm is not X)
assert_true(isinstance(X_norm, sparse.csr_matrix))
X_norm = toarray(X_norm)
for i in range(3):
assert_almost_equal(row_sums[i], 1.0)
assert_almost_equal(la.norm(X_norm[3]), 0.0)
def test_normalizer_l2():
rng = np.random.RandomState(0)
X_dense = rng.randn(4, 5)
X_sparse_unpruned = sparse.csr_matrix(X_dense)
# set the row number 3 to zero
X_dense[3, :] = 0.0
# set the row number 3 to zero without pruning (can happen in real life)
indptr_3 = X_sparse_unpruned.indptr[3]
indptr_4 = X_sparse_unpruned.indptr[4]
X_sparse_unpruned.data[indptr_3:indptr_4] = 0.0
# build the pruned variant using the regular constructor
X_sparse_pruned = sparse.csr_matrix(X_dense)
# check inputs that support the no-copy optim
for X in (X_dense, X_sparse_pruned, X_sparse_unpruned):
normalizer = Normalizer(norm='l2', copy=True)
X_norm1 = normalizer.transform(X)
assert_true(X_norm1 is not X)
X_norm1 = toarray(X_norm1)
normalizer = Normalizer(norm='l2', copy=False)
X_norm2 = normalizer.transform(X)
assert_true(X_norm2 is X)
X_norm2 = toarray(X_norm2)
for X_norm in (X_norm1, X_norm2):
for i in range(3):
assert_almost_equal(la.norm(X_norm[i]), 1.0)
assert_almost_equal(la.norm(X_norm[3]), 0.0)
# check input for which copy=False won't prevent a copy
for init in (sparse.coo_matrix, sparse.csc_matrix, sparse.lil_matrix):
X = init(X_dense)
X_norm = normalizer = Normalizer(norm='l2', copy=False).transform(X)
assert_true(X_norm is not X)
assert_true(isinstance(X_norm, sparse.csr_matrix))
X_norm = toarray(X_norm)
for i in range(3):
assert_almost_equal(la.norm(X_norm[i]), 1.0)
assert_almost_equal(la.norm(X_norm[3]), 0.0)
def test_normalize_errors():
"""Check that invalid arguments yield ValueError"""
assert_raises(ValueError, normalize, [[0]], axis=2)
assert_raises(ValueError, normalize, [[0]], norm='l3')
def test_binarizer():
X_ = np.array([[1, 0, 5], [2, 3, -1]])
for init in (np.array, list, sparse.csr_matrix, sparse.csc_matrix):
X = init(X_.copy())
binarizer = Binarizer(threshold=2.0, copy=True)
X_bin = toarray(binarizer.transform(X))
assert_equal(np.sum(X_bin == 0), 4)
assert_equal(np.sum(X_bin == 1), 2)
X_bin = binarizer.transform(X)
assert_equal(sparse.issparse(X), sparse.issparse(X_bin))
binarizer = Binarizer(copy=True).fit(X)
X_bin = toarray(binarizer.transform(X))
assert_true(X_bin is not X)
assert_equal(np.sum(X_bin == 0), 2)
assert_equal(np.sum(X_bin == 1), 4)
binarizer = Binarizer(copy=True)
X_bin = binarizer.transform(X)
assert_true(X_bin is not X)
X_bin = toarray(X_bin)
assert_equal(np.sum(X_bin == 0), 2)
assert_equal(np.sum(X_bin == 1), 4)
binarizer = Binarizer(copy=False)
X_bin = binarizer.transform(X)
if init is not list:
assert_true(X_bin is X)
X_bin = toarray(X_bin)
assert_equal(np.sum(X_bin == 0), 2)
assert_equal(np.sum(X_bin == 1), 4)
binarizer = Binarizer(threshold=-0.5, copy=True)
for init in (np.array, list):
X = init(X_.copy())
X_bin = toarray(binarizer.transform(X))
assert_equal(np.sum(X_bin == 0), 1)
assert_equal(np.sum(X_bin == 1), 5)
X_bin = binarizer.transform(X)
# Cannot use threshold < 0 for sparse
assert_raises(ValueError, binarizer.transform, sparse.csc_matrix(X))
def test_center_kernel():
"""Test that KernelCenterer is equivalent to StandardScaler
in feature space"""
rng = np.random.RandomState(0)
X_fit = rng.random_sample((5, 4))
scaler = StandardScaler(with_std=False)
scaler.fit(X_fit)
X_fit_centered = scaler.transform(X_fit)
K_fit = np.dot(X_fit, X_fit.T)
# center fit time matrix
centerer = KernelCenterer()
K_fit_centered = np.dot(X_fit_centered, X_fit_centered.T)
K_fit_centered2 = centerer.fit_transform(K_fit)
assert_array_almost_equal(K_fit_centered, K_fit_centered2)
# center predict time matrix
X_pred = rng.random_sample((2, 4))
K_pred = np.dot(X_pred, X_fit.T)
X_pred_centered = scaler.transform(X_pred)
K_pred_centered = np.dot(X_pred_centered, X_fit_centered.T)
K_pred_centered2 = centerer.transform(K_pred)
assert_array_almost_equal(K_pred_centered, K_pred_centered2)
def test_fit_transform():
rng = np.random.RandomState(0)
X = rng.random_sample((5, 4))
for obj in ((StandardScaler(), Normalizer(), Binarizer())):
X_transformed = obj.fit(X).transform(X)
X_transformed2 = obj.fit_transform(X)
assert_array_equal(X_transformed, X_transformed2)
def test_add_dummy_feature():
X = [[1, 0], [0, 1], [0, 1]]
X = add_dummy_feature(X)
assert_array_equal(X, [[1, 1, 0], [1, 0, 1], [1, 0, 1]])
def test_add_dummy_feature_coo():
X = sparse.coo_matrix([[1, 0], [0, 1], [0, 1]])
X = add_dummy_feature(X)
assert_true(sparse.isspmatrix_coo(X), X)
assert_array_equal(X.toarray(), [[1, 1, 0], [1, 0, 1], [1, 0, 1]])
def test_add_dummy_feature_csc():
X = sparse.csc_matrix([[1, 0], [0, 1], [0, 1]])
X = add_dummy_feature(X)
assert_true(sparse.isspmatrix_csc(X), X)
assert_array_equal(X.toarray(), [[1, 1, 0], [1, 0, 1], [1, 0, 1]])
def test_add_dummy_feature_csr():
X = sparse.csr_matrix([[1, 0], [0, 1], [0, 1]])
X = add_dummy_feature(X)
assert_true(sparse.isspmatrix_csr(X), X)
assert_array_equal(X.toarray(), [[1, 1, 0], [1, 0, 1], [1, 0, 1]])
def test_one_hot_encoder():
"""Test OneHotEncoder's fit and transform."""
X = [[3, 2, 1], [0, 1, 1]]
enc = OneHotEncoder()
# discover max values automatically
X_trans = enc.fit_transform(X).toarray()
assert_equal(X_trans.shape, (2, 5))
assert_array_equal(enc.active_features_,
np.where([1, 0, 0, 1, 0, 1, 1, 0, 1])[0])
assert_array_equal(enc.feature_indices_, [0, 4, 7, 9])
# check outcome
assert_array_equal(X_trans,
[[0., 1., 0., 1., 1.],
[1., 0., 1., 0., 1.]])
# max value given as 3
enc = OneHotEncoder(n_values=4)
X_trans = enc.fit_transform(X)
assert_equal(X_trans.shape, (2, 4 * 3))
assert_array_equal(enc.feature_indices_, [0, 4, 8, 12])
# max value given per feature
enc = OneHotEncoder(n_values=[3, 2, 2])
X = [[1, 0, 1], [0, 1, 1]]
X_trans = enc.fit_transform(X)
assert_equal(X_trans.shape, (2, 3 + 2 + 2))
assert_array_equal(enc.n_values_, [3, 2, 2])
# check that testing with larger feature works:
X = np.array([[2, 0, 1], [0, 1, 1]])
enc.transform(X)
# test that an error is raise when out of bounds:
X_too_large = [[0, 2, 1], [0, 1, 1]]
assert_raises(ValueError, enc.transform, X_too_large)
# test that error is raised when wrong number of features
assert_raises(ValueError, enc.transform, X[:, :-1])
# test that error is raised when wrong number of features in fit
# with prespecified n_values
assert_raises(ValueError, enc.fit, X[:, :-1])
# test exception on wrong init param
assert_raises(TypeError, OneHotEncoder(n_values=np.int).fit, X)
enc = OneHotEncoder()
# test negative input to fit
assert_raises(ValueError, enc.fit, [[0], [-1]])
# test negative input to transform
enc.fit([[0], [1]])
assert_raises(ValueError, enc.transform, [[0], [-1]])
def _check_transform_selected(X, X_expected, sel):
for M in (X, sparse.csr_matrix(X)):
Xtr = _transform_selected(M, Binarizer().transform, sel)
assert_array_equal(toarray(Xtr), X_expected)
def test_transform_selected():
X = [[3, 2, 1], [0, 1, 1]]
X_expected = [[1, 2, 1], [0, 1, 1]]
_check_transform_selected(X, X_expected, [0])
_check_transform_selected(X, X_expected, [True, False, False])
X_expected = [[1, 1, 1], [0, 1, 1]]
_check_transform_selected(X, X_expected, [0, 1, 2])
_check_transform_selected(X, X_expected, [True, True, True])
_check_transform_selected(X, X_expected, "all")
_check_transform_selected(X, X, [])
_check_transform_selected(X, X, [False, False, False])
def _run_one_hot(X, X2, cat):
enc = OneHotEncoder(categorical_features=cat)
Xtr = enc.fit_transform(X)
X2tr = enc.transform(X2)
return Xtr, X2tr
def _check_one_hot(X, X2, cat, n_features):
ind = np.where(cat)[0]
# With mask
A, B = _run_one_hot(X, X2, cat)
# With indices
C, D = _run_one_hot(X, X2, ind)
# Check shape
assert_equal(A.shape, (2, n_features))
assert_equal(B.shape, (1, n_features))
assert_equal(C.shape, (2, n_features))
assert_equal(D.shape, (1, n_features))
# Check that mask and indices give the same results
assert_array_equal(toarray(A), toarray(C))
assert_array_equal(toarray(B), toarray(D))
def test_one_hot_encoder_categorical_features():
X = np.array([[3, 2, 1], [0, 1, 1]])
X2 = np.array([[1, 1, 1]])
cat = [True, False, False]
_check_one_hot(X, X2, cat, 4)
# Edge case: all non-categorical
cat = [False, False, False]
_check_one_hot(X, X2, cat, 3)
# Edge case: all categorical
cat = [True, True, True]
_check_one_hot(X, X2, cat, 5)