File: test_label.py

package info (click to toggle)
scikit-learn 0.20.2%2Bdfsg-6
  • links: PTS, VCS
  • area: main
  • in suites: buster
  • size: 51,036 kB
  • sloc: python: 108,171; ansic: 8,722; cpp: 5,651; makefile: 192; sh: 40
file content (589 lines) | stat: -rw-r--r-- 21,685 bytes parent folder | download
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
import numpy as np

import pytest

from scipy.sparse import issparse
from scipy.sparse import coo_matrix
from scipy.sparse import csc_matrix
from scipy.sparse import csr_matrix
from scipy.sparse import dok_matrix
from scipy.sparse import lil_matrix

from sklearn.utils.multiclass import type_of_target

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_raise_message
from sklearn.utils.testing import assert_warns_message
from sklearn.utils.testing import ignore_warnings

from sklearn.preprocessing.label import LabelBinarizer
from sklearn.preprocessing.label import MultiLabelBinarizer
from sklearn.preprocessing.label import LabelEncoder
from sklearn.preprocessing.label import label_binarize

from sklearn.preprocessing.label import _inverse_binarize_thresholding
from sklearn.preprocessing.label import _inverse_binarize_multiclass
from sklearn.preprocessing.label import _encode

from sklearn import datasets

iris = datasets.load_iris()


def toarray(a):
    if hasattr(a, "toarray"):
        a = a.toarray()
    return a


def test_label_binarizer():
    # one-class case defaults to negative label
    # For dense case:
    inp = ["pos", "pos", "pos", "pos"]
    lb = LabelBinarizer(sparse_output=False)
    expected = np.array([[0, 0, 0, 0]]).T
    got = lb.fit_transform(inp)
    assert_array_equal(lb.classes_, ["pos"])
    assert_array_equal(expected, got)
    assert_array_equal(lb.inverse_transform(got), inp)

    # For sparse case:
    lb = LabelBinarizer(sparse_output=True)
    got = lb.fit_transform(inp)
    assert issparse(got)
    assert_array_equal(lb.classes_, ["pos"])
    assert_array_equal(expected, got.toarray())
    assert_array_equal(lb.inverse_transform(got.toarray()), inp)

    lb = LabelBinarizer(sparse_output=False)
    # two-class case
    inp = ["neg", "pos", "pos", "neg"]
    expected = np.array([[0, 1, 1, 0]]).T
    got = lb.fit_transform(inp)
    assert_array_equal(lb.classes_, ["neg", "pos"])
    assert_array_equal(expected, got)

    to_invert = np.array([[1, 0],
                          [0, 1],
                          [0, 1],
                          [1, 0]])
    assert_array_equal(lb.inverse_transform(to_invert), inp)

    # multi-class case
    inp = ["spam", "ham", "eggs", "ham", "0"]
    expected = np.array([[0, 0, 0, 1],
                         [0, 0, 1, 0],
                         [0, 1, 0, 0],
                         [0, 0, 1, 0],
                         [1, 0, 0, 0]])
    got = lb.fit_transform(inp)
    assert_array_equal(lb.classes_, ['0', 'eggs', 'ham', 'spam'])
    assert_array_equal(expected, got)
    assert_array_equal(lb.inverse_transform(got), inp)


def test_label_binarizer_unseen_labels():
    lb = LabelBinarizer()

    expected = np.array([[1, 0, 0],
                         [0, 1, 0],
                         [0, 0, 1]])
    got = lb.fit_transform(['b', 'd', 'e'])
    assert_array_equal(expected, got)

    expected = np.array([[0, 0, 0],
                         [1, 0, 0],
                         [0, 0, 0],
                         [0, 1, 0],
                         [0, 0, 1],
                         [0, 0, 0]])
    got = lb.transform(['a', 'b', 'c', 'd', 'e', 'f'])
    assert_array_equal(expected, got)


def test_label_binarizer_set_label_encoding():
    lb = LabelBinarizer(neg_label=-2, pos_label=0)

    # two-class case with pos_label=0
    inp = np.array([0, 1, 1, 0])
    expected = np.array([[-2, 0, 0, -2]]).T
    got = lb.fit_transform(inp)
    assert_array_equal(expected, got)
    assert_array_equal(lb.inverse_transform(got), inp)

    lb = LabelBinarizer(neg_label=-2, pos_label=2)

    # multi-class case
    inp = np.array([3, 2, 1, 2, 0])
    expected = np.array([[-2, -2, -2, +2],
                         [-2, -2, +2, -2],
                         [-2, +2, -2, -2],
                         [-2, -2, +2, -2],
                         [+2, -2, -2, -2]])
    got = lb.fit_transform(inp)
    assert_array_equal(expected, got)
    assert_array_equal(lb.inverse_transform(got), inp)


@ignore_warnings
def test_label_binarizer_errors():
    # Check that invalid arguments yield ValueError
    one_class = np.array([0, 0, 0, 0])
    lb = LabelBinarizer().fit(one_class)

    multi_label = [(2, 3), (0,), (0, 2)]
    assert_raises(ValueError, lb.transform, multi_label)

    lb = LabelBinarizer()
    assert_raises(ValueError, lb.transform, [])
    assert_raises(ValueError, lb.inverse_transform, [])

    assert_raises(ValueError, LabelBinarizer, neg_label=2, pos_label=1)
    assert_raises(ValueError, LabelBinarizer, neg_label=2, pos_label=2)

    assert_raises(ValueError, LabelBinarizer, neg_label=1, pos_label=2,
                  sparse_output=True)

    # Fail on y_type
    assert_raises(ValueError, _inverse_binarize_thresholding,
                  y=csr_matrix([[1, 2], [2, 1]]), output_type="foo",
                  classes=[1, 2], threshold=0)

    # Sequence of seq type should raise ValueError
    y_seq_of_seqs = [[], [1, 2], [3], [0, 1, 3], [2]]
    assert_raises(ValueError, LabelBinarizer().fit_transform, y_seq_of_seqs)

    # Fail on the number of classes
    assert_raises(ValueError, _inverse_binarize_thresholding,
                  y=csr_matrix([[1, 2], [2, 1]]), output_type="foo",
                  classes=[1, 2, 3], threshold=0)

    # Fail on the dimension of 'binary'
    assert_raises(ValueError, _inverse_binarize_thresholding,
                  y=np.array([[1, 2, 3], [2, 1, 3]]), output_type="binary",
                  classes=[1, 2, 3], threshold=0)

    # Fail on multioutput data
    assert_raises(ValueError, LabelBinarizer().fit, np.array([[1, 3], [2, 1]]))
    assert_raises(ValueError, label_binarize, np.array([[1, 3], [2, 1]]),
                  [1, 2, 3])


@pytest.mark.parametrize(
        "values, classes, unknown",
        [(np.array([2, 1, 3, 1, 3], dtype='int64'),
          np.array([1, 2, 3], dtype='int64'), np.array([4], dtype='int64')),
         (np.array(['b', 'a', 'c', 'a', 'c'], dtype=object),
          np.array(['a', 'b', 'c'], dtype=object),
          np.array(['d'], dtype=object)),
         (np.array(['b', 'a', 'c', 'a', 'c']),
          np.array(['a', 'b', 'c']), np.array(['d']))],
        ids=['int64', 'object', 'str'])
def test_label_encoder(values, classes, unknown):
    # Test LabelEncoder's transform, fit_transform and
    # inverse_transform methods
    le = LabelEncoder()
    le.fit(values)
    assert_array_equal(le.classes_, classes)
    assert_array_equal(le.transform(values), [1, 0, 2, 0, 2])
    assert_array_equal(le.inverse_transform([1, 0, 2, 0, 2]), values)
    le = LabelEncoder()
    ret = le.fit_transform(values)
    assert_array_equal(ret, [1, 0, 2, 0, 2])

    with pytest.raises(ValueError, match="unseen labels"):
        le.transform(unknown)


def test_label_encoder_negative_ints():
    le = LabelEncoder()
    le.fit([1, 1, 4, 5, -1, 0])
    assert_array_equal(le.classes_, [-1, 0, 1, 4, 5])
    assert_array_equal(le.transform([0, 1, 4, 4, 5, -1, -1]),
                       [1, 2, 3, 3, 4, 0, 0])
    assert_array_equal(le.inverse_transform([1, 2, 3, 3, 4, 0, 0]),
                       [0, 1, 4, 4, 5, -1, -1])
    assert_raises(ValueError, le.transform, [0, 6])


@pytest.mark.parametrize("dtype", ['str', 'object'])
def test_label_encoder_str_bad_shape(dtype):
    le = LabelEncoder()
    le.fit(np.array(["apple", "orange"], dtype=dtype))
    msg = "bad input shape"
    assert_raise_message(ValueError, msg, le.transform, "apple")


def test_label_encoder_errors():
    # Check that invalid arguments yield ValueError
    le = LabelEncoder()
    assert_raises(ValueError, le.transform, [])
    assert_raises(ValueError, le.inverse_transform, [])

    # Fail on unseen labels
    le = LabelEncoder()
    le.fit([1, 2, 3, -1, 1])
    msg = "contains previously unseen labels"
    assert_raise_message(ValueError, msg, le.inverse_transform, [-2])
    assert_raise_message(ValueError, msg, le.inverse_transform, [-2, -3, -4])

    # Fail on inverse_transform("")
    msg = "bad input shape ()"
    assert_raise_message(ValueError, msg, le.inverse_transform, "")


@pytest.mark.parametrize(
        "values",
        [np.array([2, 1, 3, 1, 3], dtype='int64'),
         np.array(['b', 'a', 'c', 'a', 'c'], dtype=object),
         np.array(['b', 'a', 'c', 'a', 'c'])],
        ids=['int64', 'object', 'str'])
def test_label_encoder_empty_array(values):
    le = LabelEncoder()
    le.fit(values)
    # test empty transform
    transformed = le.transform([])
    assert_array_equal(np.array([]), transformed)
    # test empty inverse transform
    inverse_transformed = le.inverse_transform([])
    assert_array_equal(np.array([]), inverse_transformed)


def test_sparse_output_multilabel_binarizer():
    # test input as iterable of iterables
    inputs = [
        lambda: [(2, 3), (1,), (1, 2)],
        lambda: (set([2, 3]), set([1]), set([1, 2])),
        lambda: iter([iter((2, 3)), iter((1,)), set([1, 2])]),
    ]
    indicator_mat = np.array([[0, 1, 1],
                              [1, 0, 0],
                              [1, 1, 0]])

    inverse = inputs[0]()
    for sparse_output in [True, False]:
        for inp in inputs:
            # With fit_transform
            mlb = MultiLabelBinarizer(sparse_output=sparse_output)
            got = mlb.fit_transform(inp())
            assert_equal(issparse(got), sparse_output)
            if sparse_output:
                # verify CSR assumption that indices and indptr have same dtype
                assert_equal(got.indices.dtype, got.indptr.dtype)
                got = got.toarray()
            assert_array_equal(indicator_mat, got)
            assert_array_equal([1, 2, 3], mlb.classes_)
            assert_equal(mlb.inverse_transform(got), inverse)

            # With fit
            mlb = MultiLabelBinarizer(sparse_output=sparse_output)
            got = mlb.fit(inp()).transform(inp())
            assert_equal(issparse(got), sparse_output)
            if sparse_output:
                # verify CSR assumption that indices and indptr have same dtype
                assert_equal(got.indices.dtype, got.indptr.dtype)
                got = got.toarray()
            assert_array_equal(indicator_mat, got)
            assert_array_equal([1, 2, 3], mlb.classes_)
            assert_equal(mlb.inverse_transform(got), inverse)

    assert_raises(ValueError, mlb.inverse_transform,
                  csr_matrix(np.array([[0, 1, 1],
                                       [2, 0, 0],
                                       [1, 1, 0]])))


def test_multilabel_binarizer():
    # test input as iterable of iterables
    inputs = [
        lambda: [(2, 3), (1,), (1, 2)],
        lambda: (set([2, 3]), set([1]), set([1, 2])),
        lambda: iter([iter((2, 3)), iter((1,)), set([1, 2])]),
    ]
    indicator_mat = np.array([[0, 1, 1],
                              [1, 0, 0],
                              [1, 1, 0]])
    inverse = inputs[0]()
    for inp in inputs:
        # With fit_transform
        mlb = MultiLabelBinarizer()
        got = mlb.fit_transform(inp())
        assert_array_equal(indicator_mat, got)
        assert_array_equal([1, 2, 3], mlb.classes_)
        assert_equal(mlb.inverse_transform(got), inverse)

        # With fit
        mlb = MultiLabelBinarizer()
        got = mlb.fit(inp()).transform(inp())
        assert_array_equal(indicator_mat, got)
        assert_array_equal([1, 2, 3], mlb.classes_)
        assert_equal(mlb.inverse_transform(got), inverse)


def test_multilabel_binarizer_empty_sample():
    mlb = MultiLabelBinarizer()
    y = [[1, 2], [1], []]
    Y = np.array([[1, 1],
                  [1, 0],
                  [0, 0]])
    assert_array_equal(mlb.fit_transform(y), Y)


def test_multilabel_binarizer_unknown_class():
    mlb = MultiLabelBinarizer()
    y = [[1, 2]]
    Y = np.array([[1, 0], [0, 1]])
    w = 'unknown class(es) [0, 4] will be ignored'
    matrix = assert_warns_message(UserWarning, w,
                                  mlb.fit(y).transform, [[4, 1], [2, 0]])
    assert_array_equal(matrix, Y)

    Y = np.array([[1, 0, 0], [0, 1, 0]])
    mlb = MultiLabelBinarizer(classes=[1, 2, 3])
    matrix = assert_warns_message(UserWarning, w,
                                  mlb.fit(y).transform, [[4, 1], [2, 0]])
    assert_array_equal(matrix, Y)


def test_multilabel_binarizer_given_classes():
    inp = [(2, 3), (1,), (1, 2)]
    indicator_mat = np.array([[0, 1, 1],
                              [1, 0, 0],
                              [1, 0, 1]])
    # fit_transform()
    mlb = MultiLabelBinarizer(classes=[1, 3, 2])
    assert_array_equal(mlb.fit_transform(inp), indicator_mat)
    assert_array_equal(mlb.classes_, [1, 3, 2])

    # fit().transform()
    mlb = MultiLabelBinarizer(classes=[1, 3, 2])
    assert_array_equal(mlb.fit(inp).transform(inp), indicator_mat)
    assert_array_equal(mlb.classes_, [1, 3, 2])

    # ensure works with extra class
    mlb = MultiLabelBinarizer(classes=[4, 1, 3, 2])
    assert_array_equal(mlb.fit_transform(inp),
                       np.hstack(([[0], [0], [0]], indicator_mat)))
    assert_array_equal(mlb.classes_, [4, 1, 3, 2])

    # ensure fit is no-op as iterable is not consumed
    inp = iter(inp)
    mlb = MultiLabelBinarizer(classes=[1, 3, 2])
    assert_array_equal(mlb.fit(inp).transform(inp), indicator_mat)

    # ensure a ValueError is thrown if given duplicate classes
    err_msg = "The classes argument contains duplicate classes. Remove " \
              "these duplicates before passing them to MultiLabelBinarizer."
    mlb = MultiLabelBinarizer(classes=[1, 3, 2, 3])
    assert_raise_message(ValueError, err_msg, mlb.fit, inp)


def test_multilabel_binarizer_same_length_sequence():
    # Ensure sequences of the same length are not interpreted as a 2-d array
    inp = [[1], [0], [2]]
    indicator_mat = np.array([[0, 1, 0],
                              [1, 0, 0],
                              [0, 0, 1]])
    # fit_transform()
    mlb = MultiLabelBinarizer()
    assert_array_equal(mlb.fit_transform(inp), indicator_mat)
    assert_array_equal(mlb.inverse_transform(indicator_mat), inp)

    # fit().transform()
    mlb = MultiLabelBinarizer()
    assert_array_equal(mlb.fit(inp).transform(inp), indicator_mat)
    assert_array_equal(mlb.inverse_transform(indicator_mat), inp)


def test_multilabel_binarizer_non_integer_labels():
    tuple_classes = np.empty(3, dtype=object)
    tuple_classes[:] = [(1,), (2,), (3,)]
    inputs = [
        ([('2', '3'), ('1',), ('1', '2')], ['1', '2', '3']),
        ([('b', 'c'), ('a',), ('a', 'b')], ['a', 'b', 'c']),
        ([((2,), (3,)), ((1,),), ((1,), (2,))], tuple_classes),
    ]
    indicator_mat = np.array([[0, 1, 1],
                              [1, 0, 0],
                              [1, 1, 0]])
    for inp, classes in inputs:
        # fit_transform()
        mlb = MultiLabelBinarizer()
        assert_array_equal(mlb.fit_transform(inp), indicator_mat)
        assert_array_equal(mlb.classes_, classes)
        assert_array_equal(mlb.inverse_transform(indicator_mat), inp)

        # fit().transform()
        mlb = MultiLabelBinarizer()
        assert_array_equal(mlb.fit(inp).transform(inp), indicator_mat)
        assert_array_equal(mlb.classes_, classes)
        assert_array_equal(mlb.inverse_transform(indicator_mat), inp)

    mlb = MultiLabelBinarizer()
    assert_raises(TypeError, mlb.fit_transform, [({}), ({}, {'a': 'b'})])


def test_multilabel_binarizer_non_unique():
    inp = [(1, 1, 1, 0)]
    indicator_mat = np.array([[1, 1]])
    mlb = MultiLabelBinarizer()
    assert_array_equal(mlb.fit_transform(inp), indicator_mat)


def test_multilabel_binarizer_inverse_validation():
    inp = [(1, 1, 1, 0)]
    mlb = MultiLabelBinarizer()
    mlb.fit_transform(inp)
    # Not binary
    assert_raises(ValueError, mlb.inverse_transform, np.array([[1, 3]]))
    # The following binary cases are fine, however
    mlb.inverse_transform(np.array([[0, 0]]))
    mlb.inverse_transform(np.array([[1, 1]]))
    mlb.inverse_transform(np.array([[1, 0]]))

    # Wrong shape
    assert_raises(ValueError, mlb.inverse_transform, np.array([[1]]))
    assert_raises(ValueError, mlb.inverse_transform, np.array([[1, 1, 1]]))


def test_label_binarize_with_class_order():
    out = label_binarize([1, 6], classes=[1, 2, 4, 6])
    expected = np.array([[1, 0, 0, 0], [0, 0, 0, 1]])
    assert_array_equal(out, expected)

    # Modified class order
    out = label_binarize([1, 6], classes=[1, 6, 4, 2])
    expected = np.array([[1, 0, 0, 0], [0, 1, 0, 0]])
    assert_array_equal(out, expected)

    out = label_binarize([0, 1, 2, 3], classes=[3, 2, 0, 1])
    expected = np.array([[0, 0, 1, 0],
                         [0, 0, 0, 1],
                         [0, 1, 0, 0],
                         [1, 0, 0, 0]])
    assert_array_equal(out, expected)


def check_binarized_results(y, classes, pos_label, neg_label, expected):
    for sparse_output in [True, False]:
        if ((pos_label == 0 or neg_label != 0) and sparse_output):
            assert_raises(ValueError, label_binarize, y, classes,
                          neg_label=neg_label, pos_label=pos_label,
                          sparse_output=sparse_output)
            continue

        # check label_binarize
        binarized = label_binarize(y, classes, neg_label=neg_label,
                                   pos_label=pos_label,
                                   sparse_output=sparse_output)
        assert_array_equal(toarray(binarized), expected)
        assert_equal(issparse(binarized), sparse_output)

        # check inverse
        y_type = type_of_target(y)
        if y_type == "multiclass":
            inversed = _inverse_binarize_multiclass(binarized, classes=classes)

        else:
            inversed = _inverse_binarize_thresholding(binarized,
                                                      output_type=y_type,
                                                      classes=classes,
                                                      threshold=((neg_label +
                                                                 pos_label) /
                                                                 2.))

        assert_array_equal(toarray(inversed), toarray(y))

        # Check label binarizer
        lb = LabelBinarizer(neg_label=neg_label, pos_label=pos_label,
                            sparse_output=sparse_output)
        binarized = lb.fit_transform(y)
        assert_array_equal(toarray(binarized), expected)
        assert_equal(issparse(binarized), sparse_output)
        inverse_output = lb.inverse_transform(binarized)
        assert_array_equal(toarray(inverse_output), toarray(y))
        assert_equal(issparse(inverse_output), issparse(y))


def test_label_binarize_binary():
    y = [0, 1, 0]
    classes = [0, 1]
    pos_label = 2
    neg_label = -1
    expected = np.array([[2, -1], [-1, 2], [2, -1]])[:, 1].reshape((-1, 1))

    check_binarized_results(y, classes, pos_label, neg_label, expected)

    # Binary case where sparse_output = True will not result in a ValueError
    y = [0, 1, 0]
    classes = [0, 1]
    pos_label = 3
    neg_label = 0
    expected = np.array([[3, 0], [0, 3], [3, 0]])[:, 1].reshape((-1, 1))

    check_binarized_results(y, classes, pos_label, neg_label, expected)


def test_label_binarize_multiclass():
    y = [0, 1, 2]
    classes = [0, 1, 2]
    pos_label = 2
    neg_label = 0
    expected = 2 * np.eye(3)

    check_binarized_results(y, classes, pos_label, neg_label, expected)

    assert_raises(ValueError, label_binarize, y, classes, neg_label=-1,
                  pos_label=pos_label, sparse_output=True)


def test_label_binarize_multilabel():
    y_ind = np.array([[0, 1, 0], [1, 1, 1], [0, 0, 0]])
    classes = [0, 1, 2]
    pos_label = 2
    neg_label = 0
    expected = pos_label * y_ind
    y_sparse = [sparse_matrix(y_ind)
                for sparse_matrix in [coo_matrix, csc_matrix, csr_matrix,
                                      dok_matrix, lil_matrix]]

    for y in [y_ind] + y_sparse:
        check_binarized_results(y, classes, pos_label, neg_label,
                                expected)

    assert_raises(ValueError, label_binarize, y, classes, neg_label=-1,
                  pos_label=pos_label, sparse_output=True)


def test_invalid_input_label_binarize():
    assert_raises(ValueError, label_binarize, [0, 2], classes=[0, 2],
                  pos_label=0, neg_label=1)


def test_inverse_binarize_multiclass():
    got = _inverse_binarize_multiclass(csr_matrix([[0, 1, 0],
                                                   [-1, 0, -1],
                                                   [0, 0, 0]]),
                                       np.arange(3))
    assert_array_equal(got, np.array([1, 1, 0]))


@pytest.mark.parametrize(
        "values, expected",
        [(np.array([2, 1, 3, 1, 3], dtype='int64'),
          np.array([1, 2, 3], dtype='int64')),
         (np.array(['b', 'a', 'c', 'a', 'c'], dtype=object),
          np.array(['a', 'b', 'c'], dtype=object)),
         (np.array(['b', 'a', 'c', 'a', 'c']),
          np.array(['a', 'b', 'c']))],
        ids=['int64', 'object', 'str'])
def test_encode_util(values, expected):
    uniques = _encode(values)
    assert_array_equal(uniques, expected)
    uniques, encoded = _encode(values, encode=True)
    assert_array_equal(uniques, expected)
    assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))
    _, encoded = _encode(values, uniques, encode=True)
    assert_array_equal(encoded, np.array([1, 0, 2, 0, 2]))