forked from scikit-learn/scikit-learn
/
test_validation.py
1727 lines (1443 loc) · 56.4 KB
/
test_validation.py
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
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
"""Tests for input validation functions"""
import numbers
import warnings
import re
from tempfile import NamedTemporaryFile
from itertools import product
from operator import itemgetter
import pytest
from pytest import importorskip
import numpy as np
import scipy.sparse as sp
from sklearn.utils._testing import assert_no_warnings
from sklearn.utils._testing import ignore_warnings
from sklearn.utils._testing import SkipTest
from sklearn.utils._testing import assert_array_equal
from sklearn.utils._testing import assert_allclose_dense_sparse
from sklearn.utils._testing import assert_allclose
from sklearn.utils._testing import _convert_container
from sklearn.utils import as_float_array, check_array, check_symmetric
from sklearn.utils import check_X_y
from sklearn.utils import deprecated
from sklearn.utils._mocking import MockDataFrame
from sklearn.utils.fixes import parse_version
from sklearn.utils.estimator_checks import _NotAnArray
from sklearn.random_projection import _sparse_random_matrix
from sklearn.linear_model import ARDRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.ensemble import RandomForestRegressor
from sklearn.svm import SVR
from sklearn.datasets import make_blobs
from sklearn.utils import _safe_indexing
from sklearn.utils.validation import (
has_fit_parameter,
check_is_fitted,
check_consistent_length,
assert_all_finite,
check_memory,
check_non_negative,
_num_samples,
check_scalar,
_check_psd_eigenvalues,
_check_y,
_deprecate_positional_args,
_check_sample_weight,
_allclose_dense_sparse,
_num_features,
FLOAT_DTYPES,
_get_feature_names,
_check_feature_names_in,
_check_fit_params,
)
from sklearn.base import BaseEstimator
import sklearn
from sklearn.exceptions import NotFittedError, PositiveSpectrumWarning
from sklearn.utils._testing import TempMemmap
def test_as_float_array():
# Test function for as_float_array
X = np.ones((3, 10), dtype=np.int32)
X = X + np.arange(10, dtype=np.int32)
X2 = as_float_array(X, copy=False)
assert X2.dtype == np.float32
# Another test
X = X.astype(np.int64)
X2 = as_float_array(X, copy=True)
# Checking that the array wasn't overwritten
assert as_float_array(X, copy=False) is not X
assert X2.dtype == np.float64
# Test int dtypes <= 32bit
tested_dtypes = [bool, np.int8, np.int16, np.int32, np.uint8, np.uint16, np.uint32]
for dtype in tested_dtypes:
X = X.astype(dtype)
X2 = as_float_array(X)
assert X2.dtype == np.float32
# Test object dtype
X = X.astype(object)
X2 = as_float_array(X, copy=True)
assert X2.dtype == np.float64
# Here, X is of the right type, it shouldn't be modified
X = np.ones((3, 2), dtype=np.float32)
assert as_float_array(X, copy=False) is X
# Test that if X is fortran ordered it stays
X = np.asfortranarray(X)
assert np.isfortran(as_float_array(X, copy=True))
# Test the copy parameter with some matrices
matrices = [
sp.csc_matrix(np.arange(5)).toarray(),
_sparse_random_matrix(10, 10, density=0.10).toarray(),
]
for M in matrices:
N = as_float_array(M, copy=True)
N[0, 0] = np.nan
assert not np.isnan(M).any()
@pytest.mark.parametrize("X", [(np.random.random((10, 2))), (sp.rand(10, 2).tocsr())])
def test_as_float_array_nan(X):
X[5, 0] = np.nan
X[6, 1] = np.nan
X_converted = as_float_array(X, force_all_finite="allow-nan")
assert_allclose_dense_sparse(X_converted, X)
def test_np_matrix():
# Confirm that input validation code does not return np.matrix
X = np.arange(12).reshape(3, 4)
assert not isinstance(as_float_array(X), np.matrix)
assert not isinstance(as_float_array(sp.csc_matrix(X)), np.matrix)
def test_memmap():
# Confirm that input validation code doesn't copy memory mapped arrays
asflt = lambda x: as_float_array(x, copy=False)
with NamedTemporaryFile(prefix="sklearn-test") as tmp:
M = np.memmap(tmp, shape=(10, 10), dtype=np.float32)
M[:] = 0
for f in (check_array, np.asarray, asflt):
X = f(M)
X[:] = 1
assert_array_equal(X.ravel(), M.ravel())
X[:] = 0
def test_ordering():
# Check that ordering is enforced correctly by validation utilities.
# We need to check each validation utility, because a 'copy' without
# 'order=K' will kill the ordering.
X = np.ones((10, 5))
for A in X, X.T:
for copy in (True, False):
B = check_array(A, order="C", copy=copy)
assert B.flags["C_CONTIGUOUS"]
B = check_array(A, order="F", copy=copy)
assert B.flags["F_CONTIGUOUS"]
if copy:
assert A is not B
X = sp.csr_matrix(X)
X.data = X.data[::-1]
assert not X.data.flags["C_CONTIGUOUS"]
@pytest.mark.parametrize(
"value, force_all_finite", [(np.inf, False), (np.nan, "allow-nan"), (np.nan, False)]
)
@pytest.mark.parametrize("retype", [np.asarray, sp.csr_matrix])
def test_check_array_force_all_finite_valid(value, force_all_finite, retype):
X = retype(np.arange(4).reshape(2, 2).astype(float))
X[0, 0] = value
X_checked = check_array(X, force_all_finite=force_all_finite, accept_sparse=True)
assert_allclose_dense_sparse(X, X_checked)
@pytest.mark.parametrize(
"value, input_name, force_all_finite, match_msg",
[
(np.inf, "", True, "Input contains infinity"),
(np.inf, "X", True, "Input X contains infinity"),
(np.inf, "sample_weight", True, "Input sample_weight contains infinity"),
(np.inf, "X", "allow-nan", "Input X contains infinity"),
(np.nan, "", True, "Input contains NaN"),
(np.nan, "X", True, "Input X contains NaN"),
(np.nan, "y", True, "Input y contains NaN"),
(
np.nan,
"",
"allow-inf",
'force_all_finite should be a bool or "allow-nan"',
),
(np.nan, "", 1, "Input contains NaN"),
],
)
@pytest.mark.parametrize("retype", [np.asarray, sp.csr_matrix])
def test_check_array_force_all_finiteinvalid(
value, input_name, force_all_finite, match_msg, retype
):
X = retype(np.arange(4).reshape(2, 2).astype(np.float64))
X[0, 0] = value
with pytest.raises(ValueError, match=match_msg):
check_array(
X,
input_name=input_name,
force_all_finite=force_all_finite,
accept_sparse=True,
)
@pytest.mark.parametrize("input_name", ["X", "y", "sample_weight"])
@pytest.mark.parametrize("retype", [np.asarray, sp.csr_matrix])
def test_check_array_links_to_imputer_doc_only_for_X(input_name, retype):
data = retype(np.arange(4).reshape(2, 2).astype(np.float64))
data[0, 0] = np.nan
estimator = SVR()
extended_msg = (
f"\n{estimator.__class__.__name__} does not accept missing values"
" encoded as NaN natively. For supervised learning, you might want"
" to consider sklearn.ensemble.HistGradientBoostingClassifier and Regressor"
" which accept missing values encoded as NaNs natively."
" Alternatively, it is possible to preprocess the"
" data, for instance by using an imputer transformer in a pipeline"
" or drop samples with missing values. See"
" https://scikit-learn.org/stable/modules/impute.html"
" You can find a list of all estimators that handle NaN values"
" at the following page:"
" https://scikit-learn.org/stable/modules/impute.html"
"#estimators-that-handle-nan-values"
)
with pytest.raises(ValueError, match=f"Input {input_name} contains NaN") as ctx:
check_array(
data,
estimator=estimator,
input_name=input_name,
accept_sparse=True,
)
if input_name == "X":
assert extended_msg in ctx.value.args[0]
else:
assert extended_msg not in ctx.value.args[0]
if input_name == "X":
# Veriy that _validate_data is automatically called with the right argument
# to generate the same exception:
with pytest.raises(ValueError, match=f"Input {input_name} contains NaN") as ctx:
SVR().fit(data, np.ones(data.shape[0]))
assert extended_msg in ctx.value.args[0]
def test_check_array_force_all_finite_object():
X = np.array([["a", "b", np.nan]], dtype=object).T
X_checked = check_array(X, dtype=None, force_all_finite="allow-nan")
assert X is X_checked
X_checked = check_array(X, dtype=None, force_all_finite=False)
assert X is X_checked
with pytest.raises(ValueError, match="Input contains NaN"):
check_array(X, dtype=None, force_all_finite=True)
@pytest.mark.parametrize(
"X, err_msg",
[
(
np.array([[1, np.nan]]),
"Input contains NaN.",
),
(
np.array([[1, np.nan]]),
"Input contains NaN.",
),
(
np.array([[1, np.inf]]),
"Input contains infinity or a value too large for.*int",
),
(np.array([[1, np.nan]], dtype=object), "cannot convert float NaN to integer"),
],
)
@pytest.mark.parametrize("force_all_finite", [True, False])
def test_check_array_force_all_finite_object_unsafe_casting(
X, err_msg, force_all_finite
):
# casting a float array containing NaN or inf to int dtype should
# raise an error irrespective of the force_all_finite parameter.
with pytest.raises(ValueError, match=err_msg):
check_array(X, dtype=int, force_all_finite=force_all_finite)
@ignore_warnings
def test_check_array():
# accept_sparse == False
# raise error on sparse inputs
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
with pytest.raises(TypeError):
check_array(X_csr)
# ensure_2d=False
X_array = check_array([0, 1, 2], ensure_2d=False)
assert X_array.ndim == 1
# ensure_2d=True with 1d array
with pytest.raises(ValueError, match="Expected 2D array, got 1D array instead"):
check_array([0, 1, 2], ensure_2d=True)
# ensure_2d=True with scalar array
with pytest.raises(ValueError, match="Expected 2D array, got scalar array instead"):
check_array(10, ensure_2d=True)
# don't allow ndim > 3
X_ndim = np.arange(8).reshape(2, 2, 2)
with pytest.raises(ValueError):
check_array(X_ndim)
check_array(X_ndim, allow_nd=True) # doesn't raise
# dtype and order enforcement.
X_C = np.arange(4).reshape(2, 2).copy("C")
X_F = X_C.copy("F")
X_int = X_C.astype(int)
X_float = X_C.astype(float)
Xs = [X_C, X_F, X_int, X_float]
dtypes = [np.int32, int, float, np.float32, None, bool, object]
orders = ["C", "F", None]
copys = [True, False]
for X, dtype, order, copy in product(Xs, dtypes, orders, copys):
X_checked = check_array(X, dtype=dtype, order=order, copy=copy)
if dtype is not None:
assert X_checked.dtype == dtype
else:
assert X_checked.dtype == X.dtype
if order == "C":
assert X_checked.flags["C_CONTIGUOUS"]
assert not X_checked.flags["F_CONTIGUOUS"]
elif order == "F":
assert X_checked.flags["F_CONTIGUOUS"]
assert not X_checked.flags["C_CONTIGUOUS"]
if copy:
assert X is not X_checked
else:
# doesn't copy if it was already good
if (
X.dtype == X_checked.dtype
and X_checked.flags["C_CONTIGUOUS"] == X.flags["C_CONTIGUOUS"]
and X_checked.flags["F_CONTIGUOUS"] == X.flags["F_CONTIGUOUS"]
):
assert X is X_checked
# allowed sparse != None
X_csc = sp.csc_matrix(X_C)
X_coo = X_csc.tocoo()
X_dok = X_csc.todok()
X_int = X_csc.astype(int)
X_float = X_csc.astype(float)
Xs = [X_csc, X_coo, X_dok, X_int, X_float]
accept_sparses = [["csr", "coo"], ["coo", "dok"]]
# scipy sparse matrices do not support the object dtype so
# this dtype is skipped in this loop
non_object_dtypes = [dt for dt in dtypes if dt is not object]
for X, dtype, accept_sparse, copy in product(
Xs, non_object_dtypes, accept_sparses, copys
):
X_checked = check_array(X, dtype=dtype, accept_sparse=accept_sparse, copy=copy)
if dtype is not None:
assert X_checked.dtype == dtype
else:
assert X_checked.dtype == X.dtype
if X.format in accept_sparse:
# no change if allowed
assert X.format == X_checked.format
else:
# got converted
assert X_checked.format == accept_sparse[0]
if copy:
assert X is not X_checked
else:
# doesn't copy if it was already good
if X.dtype == X_checked.dtype and X.format == X_checked.format:
assert X is X_checked
# other input formats
# convert lists to arrays
X_dense = check_array([[1, 2], [3, 4]])
assert isinstance(X_dense, np.ndarray)
# raise on too deep lists
with pytest.raises(ValueError):
check_array(X_ndim.tolist())
check_array(X_ndim.tolist(), allow_nd=True) # doesn't raise
# convert weird stuff to arrays
X_no_array = _NotAnArray(X_dense)
result = check_array(X_no_array)
assert isinstance(result, np.ndarray)
@pytest.mark.parametrize(
"X",
[
[["1", "2"], ["3", "4"]],
np.array([["1", "2"], ["3", "4"]], dtype="U"),
np.array([["1", "2"], ["3", "4"]], dtype="S"),
[[b"1", b"2"], [b"3", b"4"]],
np.array([[b"1", b"2"], [b"3", b"4"]], dtype="V1"),
],
)
def test_check_array_numeric_error(X):
"""Test that check_array errors when it receives an array of bytes/string
while a numeric dtype is required."""
expected_msg = r"dtype='numeric' is not compatible with arrays of bytes/strings"
with pytest.raises(ValueError, match=expected_msg):
check_array(X, dtype="numeric")
@pytest.mark.parametrize(
"pd_dtype", ["Int8", "Int16", "UInt8", "UInt16", "Float32", "Float64"]
)
@pytest.mark.parametrize(
"dtype, expected_dtype",
[
([np.float32, np.float64], np.float32),
(np.float64, np.float64),
("numeric", np.float64),
],
)
def test_check_array_pandas_na_support(pd_dtype, dtype, expected_dtype):
# Test pandas numerical extension arrays with pd.NA
pd = pytest.importorskip("pandas")
if pd_dtype in {"Float32", "Float64"}:
# Extension dtypes with Floats was added in 1.2
pd = pytest.importorskip("pandas", minversion="1.2")
X_np = np.array(
[[1, 2, 3, np.nan, np.nan], [np.nan, np.nan, 8, 4, 6], [1, 2, 3, 4, 5]]
).T
# Creates dataframe with numerical extension arrays with pd.NA
X = pd.DataFrame(X_np, dtype=pd_dtype, columns=["a", "b", "c"])
# column c has no nans
X["c"] = X["c"].astype("float")
X_checked = check_array(X, force_all_finite="allow-nan", dtype=dtype)
assert_allclose(X_checked, X_np)
assert X_checked.dtype == expected_dtype
X_checked = check_array(X, force_all_finite=False, dtype=dtype)
assert_allclose(X_checked, X_np)
assert X_checked.dtype == expected_dtype
msg = "Input contains NaN"
with pytest.raises(ValueError, match=msg):
check_array(X, force_all_finite=True)
def test_check_array_pandas_dtype_casting():
# test that data-frames with homogeneous dtype are not upcast
pd = pytest.importorskip("pandas")
X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]], dtype=np.float32)
X_df = pd.DataFrame(X)
assert check_array(X_df).dtype == np.float32
assert check_array(X_df, dtype=FLOAT_DTYPES).dtype == np.float32
X_df = X_df.astype({0: np.float16})
assert_array_equal(X_df.dtypes, (np.float16, np.float32, np.float32))
assert check_array(X_df).dtype == np.float32
assert check_array(X_df, dtype=FLOAT_DTYPES).dtype == np.float32
X_df = X_df.astype({0: np.int16})
# float16, int16, float32 casts to float32
assert check_array(X_df).dtype == np.float32
assert check_array(X_df, dtype=FLOAT_DTYPES).dtype == np.float32
X_df = X_df.astype({2: np.float16})
# float16, int16, float16 casts to float32
assert check_array(X_df).dtype == np.float32
assert check_array(X_df, dtype=FLOAT_DTYPES).dtype == np.float32
X_df = X_df.astype(np.int16)
assert check_array(X_df).dtype == np.int16
# we're not using upcasting rules for determining
# the target type yet, so we cast to the default of float64
assert check_array(X_df, dtype=FLOAT_DTYPES).dtype == np.float64
# check that we handle pandas dtypes in a semi-reasonable way
# this is actually tricky because we can't really know that this
# should be integer ahead of converting it.
cat_df = pd.DataFrame({"cat_col": pd.Categorical([1, 2, 3])})
assert check_array(cat_df).dtype == np.int64
assert check_array(cat_df, dtype=FLOAT_DTYPES).dtype == np.float64
def test_check_array_on_mock_dataframe():
arr = np.array([[0.2, 0.7], [0.6, 0.5], [0.4, 0.1], [0.7, 0.2]])
mock_df = MockDataFrame(arr)
checked_arr = check_array(mock_df)
assert checked_arr.dtype == arr.dtype
checked_arr = check_array(mock_df, dtype=np.float32)
assert checked_arr.dtype == np.dtype(np.float32)
def test_check_array_dtype_stability():
# test that lists with ints don't get converted to floats
X = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
assert check_array(X).dtype.kind == "i"
assert check_array(X, ensure_2d=False).dtype.kind == "i"
def test_check_array_dtype_warning():
X_int_list = [[1, 2, 3], [4, 5, 6], [7, 8, 9]]
X_float32 = np.asarray(X_int_list, dtype=np.float32)
X_int64 = np.asarray(X_int_list, dtype=np.int64)
X_csr_float32 = sp.csr_matrix(X_float32)
X_csc_float32 = sp.csc_matrix(X_float32)
X_csc_int32 = sp.csc_matrix(X_int64, dtype=np.int32)
integer_data = [X_int64, X_csc_int32]
float32_data = [X_float32, X_csr_float32, X_csc_float32]
for X in integer_data:
X_checked = assert_no_warnings(
check_array, X, dtype=np.float64, accept_sparse=True
)
assert X_checked.dtype == np.float64
for X in float32_data:
X_checked = assert_no_warnings(
check_array, X, dtype=[np.float64, np.float32], accept_sparse=True
)
assert X_checked.dtype == np.float32
assert X_checked is X
X_checked = assert_no_warnings(
check_array,
X,
dtype=[np.float64, np.float32],
accept_sparse=["csr", "dok"],
copy=True,
)
assert X_checked.dtype == np.float32
assert X_checked is not X
X_checked = assert_no_warnings(
check_array,
X_csc_float32,
dtype=[np.float64, np.float32],
accept_sparse=["csr", "dok"],
copy=False,
)
assert X_checked.dtype == np.float32
assert X_checked is not X_csc_float32
assert X_checked.format == "csr"
def test_check_array_accept_sparse_type_exception():
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
invalid_type = SVR()
msg = (
"A sparse matrix was passed, but dense data is required. "
r"Use X.toarray\(\) to convert to a dense numpy array."
)
with pytest.raises(TypeError, match=msg):
check_array(X_csr, accept_sparse=False)
msg = (
"Parameter 'accept_sparse' should be a string, "
"boolean or list of strings. You provided 'accept_sparse=.*'."
)
with pytest.raises(ValueError, match=msg):
check_array(X_csr, accept_sparse=invalid_type)
msg = (
"When providing 'accept_sparse' as a tuple or list, "
"it must contain at least one string value."
)
with pytest.raises(ValueError, match=msg):
check_array(X_csr, accept_sparse=[])
with pytest.raises(ValueError, match=msg):
check_array(X_csr, accept_sparse=())
with pytest.raises(TypeError, match="SVR"):
check_array(X_csr, accept_sparse=[invalid_type])
def test_check_array_accept_sparse_no_exception():
X = [[1, 2], [3, 4]]
X_csr = sp.csr_matrix(X)
check_array(X_csr, accept_sparse=True)
check_array(X_csr, accept_sparse="csr")
check_array(X_csr, accept_sparse=["csr"])
check_array(X_csr, accept_sparse=("csr",))
@pytest.fixture(params=["csr", "csc", "coo", "bsr"])
def X_64bit(request):
X = sp.rand(20, 10, format=request.param)
for attr in ["indices", "indptr", "row", "col"]:
if hasattr(X, attr):
setattr(X, attr, getattr(X, attr).astype("int64"))
yield X
def test_check_array_accept_large_sparse_no_exception(X_64bit):
# When large sparse are allowed
check_array(X_64bit, accept_large_sparse=True, accept_sparse=True)
def test_check_array_accept_large_sparse_raise_exception(X_64bit):
# When large sparse are not allowed
msg = (
"Only sparse matrices with 32-bit integer indices "
"are accepted. Got int64 indices."
)
with pytest.raises(ValueError, match=msg):
check_array(X_64bit, accept_sparse=True, accept_large_sparse=False)
def test_check_array_min_samples_and_features_messages():
# empty list is considered 2D by default:
msg = r"0 feature\(s\) \(shape=\(1, 0\)\) while a minimum of 1 is" " required."
with pytest.raises(ValueError, match=msg):
check_array([[]])
# If considered a 1D collection when ensure_2d=False, then the minimum
# number of samples will break:
msg = r"0 sample\(s\) \(shape=\(0,\)\) while a minimum of 1 is required."
with pytest.raises(ValueError, match=msg):
check_array([], ensure_2d=False)
# Invalid edge case when checking the default minimum sample of a scalar
msg = r"Singleton array array\(42\) cannot be considered a valid" " collection."
with pytest.raises(TypeError, match=msg):
check_array(42, ensure_2d=False)
# Simulate a model that would need at least 2 samples to be well defined
X = np.ones((1, 10))
y = np.ones(1)
msg = r"1 sample\(s\) \(shape=\(1, 10\)\) while a minimum of 2 is" " required."
with pytest.raises(ValueError, match=msg):
check_X_y(X, y, ensure_min_samples=2)
# The same message is raised if the data has 2 dimensions even if this is
# not mandatory
with pytest.raises(ValueError, match=msg):
check_X_y(X, y, ensure_min_samples=2, ensure_2d=False)
# Simulate a model that would require at least 3 features (e.g. SelectKBest
# with k=3)
X = np.ones((10, 2))
y = np.ones(2)
msg = r"2 feature\(s\) \(shape=\(10, 2\)\) while a minimum of 3 is" " required."
with pytest.raises(ValueError, match=msg):
check_X_y(X, y, ensure_min_features=3)
# Only the feature check is enabled whenever the number of dimensions is 2
# even if allow_nd is enabled:
with pytest.raises(ValueError, match=msg):
check_X_y(X, y, ensure_min_features=3, allow_nd=True)
# Simulate a case where a pipeline stage as trimmed all the features of a
# 2D dataset.
X = np.empty(0).reshape(10, 0)
y = np.ones(10)
msg = r"0 feature\(s\) \(shape=\(10, 0\)\) while a minimum of 1 is" " required."
with pytest.raises(ValueError, match=msg):
check_X_y(X, y)
# nd-data is not checked for any minimum number of features by default:
X = np.ones((10, 0, 28, 28))
y = np.ones(10)
X_checked, y_checked = check_X_y(X, y, allow_nd=True)
assert_array_equal(X, X_checked)
assert_array_equal(y, y_checked)
def test_check_array_complex_data_error():
X = np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]])
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# list of lists
X = [[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# tuple of tuples
X = ((1 + 2j, 3 + 4j, 5 + 7j), (2 + 3j, 4 + 5j, 6 + 7j))
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# list of np arrays
X = [np.array([1 + 2j, 3 + 4j, 5 + 7j]), np.array([2 + 3j, 4 + 5j, 6 + 7j])]
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# tuple of np arrays
X = (np.array([1 + 2j, 3 + 4j, 5 + 7j]), np.array([2 + 3j, 4 + 5j, 6 + 7j]))
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# dataframe
X = MockDataFrame(np.array([[1 + 2j, 3 + 4j, 5 + 7j], [2 + 3j, 4 + 5j, 6 + 7j]]))
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# sparse matrix
X = sp.coo_matrix([[0, 1 + 2j], [0, 0]])
with pytest.raises(ValueError, match="Complex data not supported"):
check_array(X)
# target variable does not always go through check_array but should
# never accept complex data either.
y = np.array([1 + 2j, 3 + 4j, 5 + 7j, 2 + 3j, 4 + 5j, 6 + 7j])
with pytest.raises(ValueError, match="Complex data not supported"):
_check_y(y)
def test_has_fit_parameter():
assert not has_fit_parameter(KNeighborsClassifier, "sample_weight")
assert has_fit_parameter(RandomForestRegressor, "sample_weight")
assert has_fit_parameter(SVR, "sample_weight")
assert has_fit_parameter(SVR(), "sample_weight")
class TestClassWithDeprecatedFitMethod:
@deprecated("Deprecated for the purpose of testing has_fit_parameter")
def fit(self, X, y, sample_weight=None):
pass
assert has_fit_parameter(
TestClassWithDeprecatedFitMethod, "sample_weight"
), "has_fit_parameter fails for class with deprecated fit method."
def test_check_symmetric():
arr_sym = np.array([[0, 1], [1, 2]])
arr_bad = np.ones(2)
arr_asym = np.array([[0, 2], [0, 2]])
test_arrays = {
"dense": arr_asym,
"dok": sp.dok_matrix(arr_asym),
"csr": sp.csr_matrix(arr_asym),
"csc": sp.csc_matrix(arr_asym),
"coo": sp.coo_matrix(arr_asym),
"lil": sp.lil_matrix(arr_asym),
"bsr": sp.bsr_matrix(arr_asym),
}
# check error for bad inputs
with pytest.raises(ValueError):
check_symmetric(arr_bad)
# check that asymmetric arrays are properly symmetrized
for arr_format, arr in test_arrays.items():
# Check for warnings and errors
with pytest.warns(UserWarning):
check_symmetric(arr)
with pytest.raises(ValueError):
check_symmetric(arr, raise_exception=True)
output = check_symmetric(arr, raise_warning=False)
if sp.issparse(output):
assert output.format == arr_format
assert_array_equal(output.toarray(), arr_sym)
else:
assert_array_equal(output, arr_sym)
def test_check_is_fitted_with_is_fitted():
class Estimator(BaseEstimator):
def fit(self, **kwargs):
self._is_fitted = True
return self
def __sklearn_is_fitted__(self):
return hasattr(self, "_is_fitted") and self._is_fitted
with pytest.raises(NotFittedError):
check_is_fitted(Estimator())
check_is_fitted(Estimator().fit())
def test_check_is_fitted():
# Check is TypeError raised when non estimator instance passed
with pytest.raises(TypeError):
check_is_fitted(ARDRegression)
with pytest.raises(TypeError):
check_is_fitted("SVR")
ard = ARDRegression()
svr = SVR()
try:
with pytest.raises(NotFittedError):
check_is_fitted(ard)
with pytest.raises(NotFittedError):
check_is_fitted(svr)
except ValueError:
assert False, "check_is_fitted failed with ValueError"
# NotFittedError is a subclass of both ValueError and AttributeError
msg = "Random message %(name)s, %(name)s"
match = "Random message ARDRegression, ARDRegression"
with pytest.raises(ValueError, match=match):
check_is_fitted(ard, msg=msg)
msg = "Another message %(name)s, %(name)s"
match = "Another message SVR, SVR"
with pytest.raises(AttributeError, match=match):
check_is_fitted(svr, msg=msg)
ard.fit(*make_blobs())
svr.fit(*make_blobs())
assert check_is_fitted(ard) is None
assert check_is_fitted(svr) is None
def test_check_is_fitted_attributes():
class MyEstimator:
def fit(self, X, y):
return self
msg = "not fitted"
est = MyEstimator()
with pytest.raises(NotFittedError, match=msg):
check_is_fitted(est, attributes=["a_", "b_"])
with pytest.raises(NotFittedError, match=msg):
check_is_fitted(est, attributes=["a_", "b_"], all_or_any=all)
with pytest.raises(NotFittedError, match=msg):
check_is_fitted(est, attributes=["a_", "b_"], all_or_any=any)
est.a_ = "a"
with pytest.raises(NotFittedError, match=msg):
check_is_fitted(est, attributes=["a_", "b_"])
with pytest.raises(NotFittedError, match=msg):
check_is_fitted(est, attributes=["a_", "b_"], all_or_any=all)
check_is_fitted(est, attributes=["a_", "b_"], all_or_any=any)
est.b_ = "b"
check_is_fitted(est, attributes=["a_", "b_"])
check_is_fitted(est, attributes=["a_", "b_"], all_or_any=all)
check_is_fitted(est, attributes=["a_", "b_"], all_or_any=any)
@pytest.mark.parametrize(
"wrap", [itemgetter(0), list, tuple], ids=["single", "list", "tuple"]
)
def test_check_is_fitted_with_attributes(wrap):
ard = ARDRegression()
with pytest.raises(NotFittedError, match="is not fitted yet"):
check_is_fitted(ard, wrap(["coef_"]))
ard.fit(*make_blobs())
# Does not raise
check_is_fitted(ard, wrap(["coef_"]))
# Raises when using attribute that is not defined
with pytest.raises(NotFittedError, match="is not fitted yet"):
check_is_fitted(ard, wrap(["coef_bad_"]))
def test_check_consistent_length():
check_consistent_length([1], [2], [3], [4], [5])
check_consistent_length([[1, 2], [[1, 2]]], [1, 2], ["a", "b"])
check_consistent_length([1], (2,), np.array([3]), sp.csr_matrix((1, 2)))
with pytest.raises(ValueError, match="inconsistent numbers of samples"):
check_consistent_length([1, 2], [1])
with pytest.raises(TypeError, match=r"got <\w+ 'int'>"):
check_consistent_length([1, 2], 1)
with pytest.raises(TypeError, match=r"got <\w+ 'object'>"):
check_consistent_length([1, 2], object())
with pytest.raises(TypeError):
check_consistent_length([1, 2], np.array(1))
# Despite ensembles having __len__ they must raise TypeError
with pytest.raises(TypeError, match="Expected sequence or array-like"):
check_consistent_length([1, 2], RandomForestRegressor())
# XXX: We should have a test with a string, but what is correct behaviour?
def test_check_dataframe_fit_attribute():
# check pandas dataframe with 'fit' column does not raise error
# https://github.com/scikit-learn/scikit-learn/issues/8415
try:
import pandas as pd
X = np.array([[1, 2, 3], [4, 5, 6], [7, 8, 9]])
X_df = pd.DataFrame(X, columns=["a", "b", "fit"])
check_consistent_length(X_df)
except ImportError:
raise SkipTest("Pandas not found")
def test_suppress_validation():
X = np.array([0, np.inf])
with pytest.raises(ValueError):
assert_all_finite(X)
sklearn.set_config(assume_finite=True)
assert_all_finite(X)
sklearn.set_config(assume_finite=False)
with pytest.raises(ValueError):
assert_all_finite(X)
def test_check_array_series():
# regression test that check_array works on pandas Series
pd = importorskip("pandas")
res = check_array(pd.Series([1, 2, 3]), ensure_2d=False)
assert_array_equal(res, np.array([1, 2, 3]))
# with categorical dtype (not a numpy dtype) (GH12699)
s = pd.Series(["a", "b", "c"]).astype("category")
res = check_array(s, dtype=None, ensure_2d=False)
assert_array_equal(res, np.array(["a", "b", "c"], dtype=object))
@pytest.mark.parametrize(
"dtype", ((np.float64, np.float32), np.float64, None, "numeric")
)
@pytest.mark.parametrize("bool_dtype", ("bool", "boolean"))
def test_check_dataframe_mixed_float_dtypes(dtype, bool_dtype):
# pandas dataframe will coerce a boolean into a object, this is a mismatch
# with np.result_type which will return a float
# check_array needs to explicitly check for bool dtype in a dataframe for
# this situation
# https://github.com/scikit-learn/scikit-learn/issues/15787
if bool_dtype == "boolean":
# boolean extension arrays was introduced in 1.0
pd = importorskip("pandas", minversion="1.0")
else:
pd = importorskip("pandas")
df = pd.DataFrame(
{
"int": [1, 2, 3],
"float": [0, 0.1, 2.1],
"bool": pd.Series([True, False, True], dtype=bool_dtype),
},
columns=["int", "float", "bool"],
)
array = check_array(df, dtype=dtype)
assert array.dtype == np.float64
expected_array = np.array(
[[1.0, 0.0, 1.0], [2.0, 0.1, 0.0], [3.0, 2.1, 1.0]], dtype=float
)
assert_allclose_dense_sparse(array, expected_array)
def test_check_dataframe_with_only_bool():
"""Check that dataframe with bool return a boolean arrays."""
pd = importorskip("pandas")
df = pd.DataFrame({"bool": [True, False, True]})
array = check_array(df, dtype=None)
assert array.dtype == np.bool_
assert_array_equal(array, [[True], [False], [True]])
# common dtype is int for bool + int
df = pd.DataFrame(
{"bool": [True, False, True], "int": [1, 2, 3]},
columns=["bool", "int"],
)
array = check_array(df, dtype="numeric")
assert array.dtype == np.int64
assert_array_equal(array, [[1, 1], [0, 2], [1, 3]])
def test_check_dataframe_with_only_boolean():
"""Check that dataframe with boolean return a float array with dtype=None"""
pd = importorskip("pandas", minversion="1.0")
df = pd.DataFrame({"bool": pd.Series([True, False, True], dtype="boolean")})
array = check_array(df, dtype=None)
assert array.dtype == np.float64
assert_array_equal(array, [[True], [False], [True]])
class DummyMemory:
def cache(self, func):
return func
class WrongDummyMemory:
pass
def test_check_memory():
memory = check_memory("cache_directory")
assert memory.location == "cache_directory"
memory = check_memory(None)
assert memory.location is None
dummy = DummyMemory()
memory = check_memory(dummy)
assert memory is dummy
msg = (
"'memory' should be None, a string or have the same interface as"
" joblib.Memory. Got memory='1' instead."