/
__init__.py
1197 lines (994 loc) · 36.6 KB
/
__init__.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
"""
The :mod:`sklearn.utils` module includes various utilities.
"""
import math
import numbers
import platform
import struct
import timeit
import warnings
from collections.abc import Sequence
from contextlib import contextmanager, suppress
from itertools import compress, islice
import numpy as np
from scipy.sparse import issparse
from .. import get_config
from ..exceptions import DataConversionWarning
from . import _joblib, metadata_routing
from ._bunch import Bunch
from ._estimator_html_repr import estimator_html_repr
from ._param_validation import Interval, validate_params
from .class_weight import compute_class_weight, compute_sample_weight
from .deprecation import deprecated
from .discovery import all_estimators
from .fixes import parse_version, threadpool_info
from .murmurhash import murmurhash3_32
from .validation import (
_is_arraylike_not_scalar,
as_float_array,
assert_all_finite,
check_array,
check_consistent_length,
check_random_state,
check_scalar,
check_symmetric,
check_X_y,
column_or_1d,
indexable,
)
# Do not deprecate parallel_backend and register_parallel_backend as they are
# needed to tune `scikit-learn` behavior and have different effect if called
# from the vendored version or or the site-package version. The other are
# utilities that are independent of scikit-learn so they are not part of
# scikit-learn public API.
parallel_backend = _joblib.parallel_backend
register_parallel_backend = _joblib.register_parallel_backend
__all__ = [
"murmurhash3_32",
"as_float_array",
"assert_all_finite",
"check_array",
"check_random_state",
"compute_class_weight",
"compute_sample_weight",
"column_or_1d",
"check_consistent_length",
"check_X_y",
"check_scalar",
"indexable",
"check_symmetric",
"indices_to_mask",
"deprecated",
"parallel_backend",
"register_parallel_backend",
"resample",
"shuffle",
"check_matplotlib_support",
"all_estimators",
"DataConversionWarning",
"estimator_html_repr",
"Bunch",
"metadata_routing",
]
IS_PYPY = platform.python_implementation() == "PyPy"
_IS_32BIT = 8 * struct.calcsize("P") == 32
def _in_unstable_openblas_configuration():
"""Return True if in an unstable configuration for OpenBLAS"""
# Import libraries which might load OpenBLAS.
import numpy # noqa
import scipy # noqa
modules_info = threadpool_info()
open_blas_used = any(info["internal_api"] == "openblas" for info in modules_info)
if not open_blas_used:
return False
# OpenBLAS 0.3.16 fixed unstability for arm64, see:
# https://github.com/xianyi/OpenBLAS/blob/1b6db3dbba672b4f8af935bd43a1ff6cff4d20b7/Changelog.txt#L56-L58 # noqa
openblas_arm64_stable_version = parse_version("0.3.16")
for info in modules_info:
if info["internal_api"] != "openblas":
continue
openblas_version = info.get("version")
openblas_architecture = info.get("architecture")
if openblas_version is None or openblas_architecture is None:
# Cannot be sure that OpenBLAS is good enough. Assume unstable:
return True
if (
openblas_architecture == "neoversen1"
and parse_version(openblas_version) < openblas_arm64_stable_version
):
# See discussions in https://github.com/numpy/numpy/issues/19411
return True
return False
def safe_mask(X, mask):
"""Return a mask which is safe to use on X.
Parameters
----------
X : {array-like, sparse matrix}
Data on which to apply mask.
mask : ndarray
Mask to be used on X.
Returns
-------
mask : ndarray
Array that is safe to use on X.
"""
mask = np.asarray(mask)
if np.issubdtype(mask.dtype, np.signedinteger):
return mask
if hasattr(X, "toarray"):
ind = np.arange(mask.shape[0])
mask = ind[mask]
return mask
def axis0_safe_slice(X, mask, len_mask):
"""Return a mask which is safer to use on X than safe_mask.
This mask is safer than safe_mask since it returns an
empty array, when a sparse matrix is sliced with a boolean mask
with all False, instead of raising an unhelpful error in older
versions of SciPy.
See: https://github.com/scipy/scipy/issues/5361
Also note that we can avoid doing the dot product by checking if
the len_mask is not zero in _huber_loss_and_gradient but this
is not going to be the bottleneck, since the number of outliers
and non_outliers are typically non-zero and it makes the code
tougher to follow.
Parameters
----------
X : {array-like, sparse matrix}
Data on which to apply mask.
mask : ndarray
Mask to be used on X.
len_mask : int
The length of the mask.
Returns
-------
mask : ndarray
Array that is safe to use on X.
"""
if len_mask != 0:
return X[safe_mask(X, mask), :]
return np.zeros(shape=(0, X.shape[1]))
def _array_indexing(array, key, key_dtype, axis):
"""Index an array or scipy.sparse consistently across NumPy version."""
if issparse(array) and key_dtype == "bool":
key = np.asarray(key)
if isinstance(key, tuple):
key = list(key)
return array[key] if axis == 0 else array[:, key]
def _pandas_indexing(X, key, key_dtype, axis):
"""Index a pandas dataframe or a series."""
if _is_arraylike_not_scalar(key):
key = np.asarray(key)
if key_dtype == "int" and not (isinstance(key, slice) or np.isscalar(key)):
# using take() instead of iloc[] ensures the return value is a "proper"
# copy that will not raise SettingWithCopyWarning
return X.take(key, axis=axis)
else:
# check whether we should index with loc or iloc
indexer = X.iloc if key_dtype == "int" else X.loc
return indexer[:, key] if axis else indexer[key]
def _list_indexing(X, key, key_dtype):
"""Index a Python list."""
if np.isscalar(key) or isinstance(key, slice):
# key is a slice or a scalar
return X[key]
if key_dtype == "bool":
# key is a boolean array-like
return list(compress(X, key))
# key is a integer array-like of key
return [X[idx] for idx in key]
def _determine_key_type(key, accept_slice=True):
"""Determine the data type of key.
Parameters
----------
key : scalar, slice or array-like
The key from which we want to infer the data type.
accept_slice : bool, default=True
Whether or not to raise an error if the key is a slice.
Returns
-------
dtype : {'int', 'str', 'bool', None}
Returns the data type of key.
"""
err_msg = (
"No valid specification of the columns. Only a scalar, list or "
"slice of all integers or all strings, or boolean mask is "
"allowed"
)
dtype_to_str = {int: "int", str: "str", bool: "bool", np.bool_: "bool"}
array_dtype_to_str = {
"i": "int",
"u": "int",
"b": "bool",
"O": "str",
"U": "str",
"S": "str",
}
if key is None:
return None
if isinstance(key, tuple(dtype_to_str.keys())):
try:
return dtype_to_str[type(key)]
except KeyError:
raise ValueError(err_msg)
if isinstance(key, slice):
if not accept_slice:
raise TypeError(
"Only array-like or scalar are supported. A Python slice was given."
)
if key.start is None and key.stop is None:
return None
key_start_type = _determine_key_type(key.start)
key_stop_type = _determine_key_type(key.stop)
if key_start_type is not None and key_stop_type is not None:
if key_start_type != key_stop_type:
raise ValueError(err_msg)
if key_start_type is not None:
return key_start_type
return key_stop_type
if isinstance(key, (list, tuple)):
unique_key = set(key)
key_type = {_determine_key_type(elt) for elt in unique_key}
if not key_type:
return None
if len(key_type) != 1:
raise ValueError(err_msg)
return key_type.pop()
if hasattr(key, "dtype"):
try:
return array_dtype_to_str[key.dtype.kind]
except KeyError:
raise ValueError(err_msg)
raise ValueError(err_msg)
def _safe_indexing(X, indices, *, axis=0):
"""Return rows, items or columns of X using indices.
.. warning::
This utility is documented, but **private**. This means that
backward compatibility might be broken without any deprecation
cycle.
Parameters
----------
X : array-like, sparse-matrix, list, pandas.DataFrame, pandas.Series
Data from which to sample rows, items or columns. `list` are only
supported when `axis=0`.
indices : bool, int, str, slice, array-like
- If `axis=0`, boolean and integer array-like, integer slice,
and scalar integer are supported.
- If `axis=1`:
- to select a single column, `indices` can be of `int` type for
all `X` types and `str` only for dataframe. The selected subset
will be 1D, unless `X` is a sparse matrix in which case it will
be 2D.
- to select multiples columns, `indices` can be one of the
following: `list`, `array`, `slice`. The type used in
these containers can be one of the following: `int`, 'bool' and
`str`. However, `str` is only supported when `X` is a dataframe.
The selected subset will be 2D.
axis : int, default=0
The axis along which `X` will be subsampled. `axis=0` will select
rows while `axis=1` will select columns.
Returns
-------
subset
Subset of X on axis 0 or 1.
Notes
-----
CSR, CSC, and LIL sparse matrices are supported. COO sparse matrices are
not supported.
"""
if indices is None:
return X
if axis not in (0, 1):
raise ValueError(
"'axis' should be either 0 (to index rows) or 1 (to index "
" column). Got {} instead.".format(axis)
)
indices_dtype = _determine_key_type(indices)
if axis == 0 and indices_dtype == "str":
raise ValueError("String indexing is not supported with 'axis=0'")
if axis == 1 and X.ndim != 2:
raise ValueError(
"'X' should be a 2D NumPy array, 2D sparse matrix or pandas "
"dataframe when indexing the columns (i.e. 'axis=1'). "
"Got {} instead with {} dimension(s).".format(type(X), X.ndim)
)
if axis == 1 and indices_dtype == "str" and not hasattr(X, "loc"):
raise ValueError(
"Specifying the columns using strings is only supported for "
"pandas DataFrames"
)
if hasattr(X, "iloc"):
return _pandas_indexing(X, indices, indices_dtype, axis=axis)
elif hasattr(X, "shape"):
return _array_indexing(X, indices, indices_dtype, axis=axis)
else:
return _list_indexing(X, indices, indices_dtype)
def _safe_assign(X, values, *, row_indexer=None, column_indexer=None):
"""Safe assignment to a numpy array, sparse matrix, or pandas dataframe.
Parameters
----------
X : {ndarray, sparse-matrix, dataframe}
Array to be modified. It is expected to be 2-dimensional.
values : ndarray
The values to be assigned to `X`.
row_indexer : array-like, dtype={int, bool}, default=None
A 1-dimensional array to select the rows of interest. If `None`, all
rows are selected.
column_indexer : array-like, dtype={int, bool}, default=None
A 1-dimensional array to select the columns of interest. If `None`, all
columns are selected.
"""
row_indexer = slice(None, None, None) if row_indexer is None else row_indexer
column_indexer = (
slice(None, None, None) if column_indexer is None else column_indexer
)
if hasattr(X, "iloc"): # pandas dataframe
with warnings.catch_warnings():
# pandas >= 1.5 raises a warning when using iloc to set values in a column
# that does not have the same type as the column being set. It happens
# for instance when setting a categorical column with a string.
# In the future the behavior won't change and the warning should disappear.
# TODO(1.3): check if the warning is still raised or remove the filter.
warnings.simplefilter("ignore", FutureWarning)
X.iloc[row_indexer, column_indexer] = values
else: # numpy array or sparse matrix
X[row_indexer, column_indexer] = values
def _get_column_indices(X, key):
"""Get feature column indices for input data X and key.
For accepted values of `key`, see the docstring of
:func:`_safe_indexing`.
"""
n_columns = X.shape[1]
key_dtype = _determine_key_type(key)
if isinstance(key, (list, tuple)) and not key:
# we get an empty list
return []
elif key_dtype in ("bool", "int"):
# Convert key into positive indexes
try:
idx = _safe_indexing(np.arange(n_columns), key)
except IndexError as e:
raise ValueError(
"all features must be in [0, {}] or [-{}, 0]".format(
n_columns - 1, n_columns
)
) from e
return np.atleast_1d(idx).tolist()
elif key_dtype == "str":
try:
all_columns = X.columns
except AttributeError:
raise ValueError(
"Specifying the columns using strings is only "
"supported for pandas DataFrames"
)
if isinstance(key, str):
columns = [key]
elif isinstance(key, slice):
start, stop = key.start, key.stop
if start is not None:
start = all_columns.get_loc(start)
if stop is not None:
# pandas indexing with strings is endpoint included
stop = all_columns.get_loc(stop) + 1
else:
stop = n_columns + 1
return list(islice(range(n_columns), start, stop))
else:
columns = list(key)
try:
column_indices = []
for col in columns:
col_idx = all_columns.get_loc(col)
if not isinstance(col_idx, numbers.Integral):
raise ValueError(
f"Selected columns, {columns}, are not unique in dataframe"
)
column_indices.append(col_idx)
except KeyError as e:
raise ValueError("A given column is not a column of the dataframe") from e
return column_indices
else:
raise ValueError(
"No valid specification of the columns. Only a "
"scalar, list or slice of all integers or all "
"strings, or boolean mask is allowed"
)
@validate_params(
{
"replace": ["boolean"],
"n_samples": [Interval(numbers.Integral, 1, None, closed="left"), None],
"random_state": ["random_state"],
"stratify": ["array-like", None],
},
prefer_skip_nested_validation=True,
)
def resample(*arrays, replace=True, n_samples=None, random_state=None, stratify=None):
"""Resample arrays or sparse matrices in a consistent way.
The default strategy implements one step of the bootstrapping
procedure.
Parameters
----------
*arrays : sequence of array-like of shape (n_samples,) or \
(n_samples, n_outputs)
Indexable data-structures can be arrays, lists, dataframes or scipy
sparse matrices with consistent first dimension.
replace : bool, default=True
Implements resampling with replacement. If False, this will implement
(sliced) random permutations.
n_samples : int, default=None
Number of samples to generate. If left to None this is
automatically set to the first dimension of the arrays.
If replace is False it should not be larger than the length of
arrays.
random_state : int, RandomState instance or None, default=None
Determines random number generation for shuffling
the data.
Pass an int for reproducible results across multiple function calls.
See :term:`Glossary <random_state>`.
stratify : array-like of shape (n_samples,) or (n_samples, n_outputs), \
default=None
If not None, data is split in a stratified fashion, using this as
the class labels.
Returns
-------
resampled_arrays : sequence of array-like of shape (n_samples,) or \
(n_samples, n_outputs)
Sequence of resampled copies of the collections. The original arrays
are not impacted.
See Also
--------
shuffle : Shuffle arrays or sparse matrices in a consistent way.
Examples
--------
It is possible to mix sparse and dense arrays in the same run::
>>> import numpy as np
>>> X = np.array([[1., 0.], [2., 1.], [0., 0.]])
>>> y = np.array([0, 1, 2])
>>> from scipy.sparse import coo_matrix
>>> X_sparse = coo_matrix(X)
>>> from sklearn.utils import resample
>>> X, X_sparse, y = resample(X, X_sparse, y, random_state=0)
>>> X
array([[1., 0.],
[2., 1.],
[1., 0.]])
>>> X_sparse
<3x2 sparse matrix of type '<... 'numpy.float64'>'
with 4 stored elements in Compressed Sparse Row format>
>>> X_sparse.toarray()
array([[1., 0.],
[2., 1.],
[1., 0.]])
>>> y
array([0, 1, 0])
>>> resample(y, n_samples=2, random_state=0)
array([0, 1])
Example using stratification::
>>> y = [0, 0, 1, 1, 1, 1, 1, 1, 1]
>>> resample(y, n_samples=5, replace=False, stratify=y,
... random_state=0)
[1, 1, 1, 0, 1]
"""
max_n_samples = n_samples
random_state = check_random_state(random_state)
if len(arrays) == 0:
return None
first = arrays[0]
n_samples = first.shape[0] if hasattr(first, "shape") else len(first)
if max_n_samples is None:
max_n_samples = n_samples
elif (max_n_samples > n_samples) and (not replace):
raise ValueError(
"Cannot sample %d out of arrays with dim %d when replace is False"
% (max_n_samples, n_samples)
)
check_consistent_length(*arrays)
if stratify is None:
if replace:
indices = random_state.randint(0, n_samples, size=(max_n_samples,))
else:
indices = np.arange(n_samples)
random_state.shuffle(indices)
indices = indices[:max_n_samples]
else:
# Code adapted from StratifiedShuffleSplit()
y = check_array(stratify, ensure_2d=False, dtype=None)
if y.ndim == 2:
# for multi-label y, map each distinct row to a string repr
# using join because str(row) uses an ellipsis if len(row) > 1000
y = np.array([" ".join(row.astype("str")) for row in y])
classes, y_indices = np.unique(y, return_inverse=True)
n_classes = classes.shape[0]
class_counts = np.bincount(y_indices)
# Find the sorted list of instances for each class:
# (np.unique above performs a sort, so code is O(n logn) already)
class_indices = np.split(
np.argsort(y_indices, kind="mergesort"), np.cumsum(class_counts)[:-1]
)
n_i = _approximate_mode(class_counts, max_n_samples, random_state)
indices = []
for i in range(n_classes):
indices_i = random_state.choice(class_indices[i], n_i[i], replace=replace)
indices.extend(indices_i)
indices = random_state.permutation(indices)
# convert sparse matrices to CSR for row-based indexing
arrays = [a.tocsr() if issparse(a) else a for a in arrays]
resampled_arrays = [_safe_indexing(a, indices) for a in arrays]
if len(resampled_arrays) == 1:
# syntactic sugar for the unit argument case
return resampled_arrays[0]
else:
return resampled_arrays
def shuffle(*arrays, random_state=None, n_samples=None):
"""Shuffle arrays or sparse matrices in a consistent way.
This is a convenience alias to ``resample(*arrays, replace=False)`` to do
random permutations of the collections.
Parameters
----------
*arrays : sequence of indexable data-structures
Indexable data-structures can be arrays, lists, dataframes or scipy
sparse matrices with consistent first dimension.
random_state : int, RandomState instance or None, default=None
Determines random number generation for shuffling
the data.
Pass an int for reproducible results across multiple function calls.
See :term:`Glossary <random_state>`.
n_samples : int, default=None
Number of samples to generate. If left to None this is
automatically set to the first dimension of the arrays. It should
not be larger than the length of arrays.
Returns
-------
shuffled_arrays : sequence of indexable data-structures
Sequence of shuffled copies of the collections. The original arrays
are not impacted.
See Also
--------
resample : Resample arrays or sparse matrices in a consistent way.
Examples
--------
It is possible to mix sparse and dense arrays in the same run::
>>> import numpy as np
>>> X = np.array([[1., 0.], [2., 1.], [0., 0.]])
>>> y = np.array([0, 1, 2])
>>> from scipy.sparse import coo_matrix
>>> X_sparse = coo_matrix(X)
>>> from sklearn.utils import shuffle
>>> X, X_sparse, y = shuffle(X, X_sparse, y, random_state=0)
>>> X
array([[0., 0.],
[2., 1.],
[1., 0.]])
>>> X_sparse
<3x2 sparse matrix of type '<... 'numpy.float64'>'
with 3 stored elements in Compressed Sparse Row format>
>>> X_sparse.toarray()
array([[0., 0.],
[2., 1.],
[1., 0.]])
>>> y
array([2, 1, 0])
>>> shuffle(y, n_samples=2, random_state=0)
array([0, 1])
"""
return resample(
*arrays, replace=False, n_samples=n_samples, random_state=random_state
)
def safe_sqr(X, *, copy=True):
"""Element wise squaring of array-likes and sparse matrices.
Parameters
----------
X : {array-like, ndarray, sparse matrix}
copy : bool, default=True
Whether to create a copy of X and operate on it or to perform
inplace computation (default behaviour).
Returns
-------
X ** 2 : element wise square
Return the element-wise square of the input.
"""
X = check_array(X, accept_sparse=["csr", "csc", "coo"], ensure_2d=False)
if issparse(X):
if copy:
X = X.copy()
X.data **= 2
else:
if copy:
X = X**2
else:
X **= 2
return X
def _chunk_generator(gen, chunksize):
"""Chunk generator, ``gen`` into lists of length ``chunksize``. The last
chunk may have a length less than ``chunksize``."""
while True:
chunk = list(islice(gen, chunksize))
if chunk:
yield chunk
else:
return
@validate_params(
{
"n": [Interval(numbers.Integral, 1, None, closed="left")],
"batch_size": [Interval(numbers.Integral, 1, None, closed="left")],
"min_batch_size": [Interval(numbers.Integral, 0, None, closed="left")],
},
prefer_skip_nested_validation=True,
)
def gen_batches(n, batch_size, *, min_batch_size=0):
"""Generator to create slices containing `batch_size` elements from 0 to `n`.
The last slice may contain less than `batch_size` elements, when
`batch_size` does not divide `n`.
Parameters
----------
n : int
Size of the sequence.
batch_size : int
Number of elements in each batch.
min_batch_size : int, default=0
Minimum number of elements in each batch.
Yields
------
slice of `batch_size` elements
See Also
--------
gen_even_slices: Generator to create n_packs slices going up to n.
Examples
--------
>>> from sklearn.utils import gen_batches
>>> list(gen_batches(7, 3))
[slice(0, 3, None), slice(3, 6, None), slice(6, 7, None)]
>>> list(gen_batches(6, 3))
[slice(0, 3, None), slice(3, 6, None)]
>>> list(gen_batches(2, 3))
[slice(0, 2, None)]
>>> list(gen_batches(7, 3, min_batch_size=0))
[slice(0, 3, None), slice(3, 6, None), slice(6, 7, None)]
>>> list(gen_batches(7, 3, min_batch_size=2))
[slice(0, 3, None), slice(3, 7, None)]
"""
start = 0
for _ in range(int(n // batch_size)):
end = start + batch_size
if end + min_batch_size > n:
continue
yield slice(start, end)
start = end
if start < n:
yield slice(start, n)
def gen_even_slices(n, n_packs, *, n_samples=None):
"""Generator to create `n_packs` evenly spaced slices going up to `n`.
If `n_packs` does not divide `n`, except for the first `n % n_packs`
slices, remaining slices may contain fewer elements.
Parameters
----------
n : int
Size of the sequence.
n_packs : int
Number of slices to generate.
n_samples : int, default=None
Number of samples. Pass `n_samples` when the slices are to be used for
sparse matrix indexing; slicing off-the-end raises an exception, while
it works for NumPy arrays.
Yields
------
`slice` representing a set of indices from 0 to n.
See Also
--------
gen_batches: Generator to create slices containing batch_size elements
from 0 to n.
Examples
--------
>>> from sklearn.utils import gen_even_slices
>>> list(gen_even_slices(10, 1))
[slice(0, 10, None)]
>>> list(gen_even_slices(10, 10))
[slice(0, 1, None), slice(1, 2, None), ..., slice(9, 10, None)]
>>> list(gen_even_slices(10, 5))
[slice(0, 2, None), slice(2, 4, None), ..., slice(8, 10, None)]
>>> list(gen_even_slices(10, 3))
[slice(0, 4, None), slice(4, 7, None), slice(7, 10, None)]
"""
start = 0
if n_packs < 1:
raise ValueError("gen_even_slices got n_packs=%s, must be >=1" % n_packs)
for pack_num in range(n_packs):
this_n = n // n_packs
if pack_num < n % n_packs:
this_n += 1
if this_n > 0:
end = start + this_n
if n_samples is not None:
end = min(n_samples, end)
yield slice(start, end, None)
start = end
def tosequence(x):
"""Cast iterable x to a Sequence, avoiding a copy if possible.
Parameters
----------
x : iterable
The iterable to be converted.
Returns
-------
x : Sequence
If `x` is a NumPy array, it returns it as a `ndarray`. If `x`
is a `Sequence`, `x` is returned as-is. If `x` is from any other
type, `x` is returned casted as a list.
"""
if isinstance(x, np.ndarray):
return np.asarray(x)
elif isinstance(x, Sequence):
return x
else:
return list(x)
def _to_object_array(sequence):
"""Convert sequence to a 1-D NumPy array of object dtype.
numpy.array constructor has a similar use but it's output
is ambiguous. It can be 1-D NumPy array of object dtype if
the input is a ragged array, but if the input is a list of
equal length arrays, then the output is a 2D numpy.array.
_to_object_array solves this ambiguity by guarantying that
the output is a 1-D NumPy array of objects for any input.
Parameters
----------
sequence : array-like of shape (n_elements,)
The sequence to be converted.
Returns
-------
out : ndarray of shape (n_elements,), dtype=object
The converted sequence into a 1-D NumPy array of object dtype.
Examples
--------
>>> import numpy as np
>>> from sklearn.utils import _to_object_array
>>> _to_object_array([np.array([0]), np.array([1])])
array([array([0]), array([1])], dtype=object)
>>> _to_object_array([np.array([0]), np.array([1, 2])])
array([array([0]), array([1, 2])], dtype=object)
>>> _to_object_array([np.array([0]), np.array([1, 2])])
array([array([0]), array([1, 2])], dtype=object)
"""
out = np.empty(len(sequence), dtype=object)
out[:] = sequence
return out
def indices_to_mask(indices, mask_length):
"""Convert list of indices to boolean mask.
Parameters
----------
indices : list-like
List of integers treated as indices.
mask_length : int
Length of boolean mask to be generated.
This parameter must be greater than max(indices).
Returns
-------
mask : 1d boolean nd-array
Boolean array that is True where indices are present, else False.
Examples
--------
>>> from sklearn.utils import indices_to_mask
>>> indices = [1, 2 , 3, 4]
>>> indices_to_mask(indices, 5)
array([False, True, True, True, True])
"""
if mask_length <= np.max(indices):
raise ValueError("mask_length must be greater than max(indices)")
mask = np.zeros(mask_length, dtype=bool)
mask[indices] = True
return mask
def _message_with_time(source, message, time):
"""Create one line message for logging purposes.
Parameters
----------
source : str
String indicating the source or the reference of the message.
message : str
Short message.
time : int
Time in seconds.
"""
start_message = "[%s] " % source
# adapted from joblib.logger.short_format_time without the Windows -.1s
# adjustment
if time > 60:
time_str = "%4.1fmin" % (time / 60)
else:
time_str = " %5.1fs" % time
end_message = " %s, total=%s" % (message, time_str)
dots_len = 70 - len(start_message) - len(end_message)
return "%s%s%s" % (start_message, dots_len * ".", end_message)
@contextmanager
def _print_elapsed_time(source, message=None):
"""Log elapsed time to stdout when the context is exited.
Parameters
----------
source : str
String indicating the source or the reference of the message.
message : str, default=None
Short message. If None, nothing will be printed.
Returns
-------
context_manager
Prints elapsed time upon exit if verbose.
"""
if message is None:
yield
else:
start = timeit.default_timer()
yield
print(_message_with_time(source, message, timeit.default_timer() - start))
def get_chunk_n_rows(row_bytes, *, max_n_rows=None, working_memory=None):
"""Calculate how many rows can be processed within `working_memory`.
Parameters
----------
row_bytes : int
The expected number of bytes of memory that will be consumed
during the processing of each row.
max_n_rows : int, default=None
The maximum return value.
working_memory : int or float, default=None
The number of rows to fit inside this number of MiB will be
returned. When None (default), the value of