-
-
Notifications
You must be signed in to change notification settings - Fork 26.9k
Expand file tree
/
Copy path_data.py
More file actions
3757 lines (3090 loc) · 127 KB
/
_data.py
File metadata and controls
3757 lines (3090 loc) · 127 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
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
# Authors: The scikit-learn developers
# SPDX-License-Identifier: BSD-3-Clause
import warnings
from numbers import Integral, Real
import numpy as np
from scipy import sparse, stats
from scipy.special import boxcox, inv_boxcox
from sklearn.base import (
BaseEstimator,
ClassNamePrefixFeaturesOutMixin,
OneToOneFeatureMixin,
TransformerMixin,
_fit_context,
)
from sklearn.preprocessing._encoders import OneHotEncoder
from sklearn.utils import _array_api, check_array, metadata_routing, resample
from sklearn.utils._array_api import (
_find_matching_floating_dtype,
_max_precision_float_dtype,
_modify_in_place_if_numpy,
device,
get_namespace,
get_namespace_and_device,
size,
supported_float_dtypes,
)
from sklearn.utils._param_validation import (
Interval,
Options,
StrOptions,
validate_params,
)
from sklearn.utils.extmath import _incremental_mean_and_var, row_norms
from sklearn.utils.sparsefuncs import (
incr_mean_variance_axis,
inplace_column_scale,
mean_variance_axis,
min_max_axis,
)
from sklearn.utils.sparsefuncs_fast import (
inplace_csr_row_normalize_l1,
inplace_csr_row_normalize_l2,
)
from sklearn.utils.validation import (
FLOAT_DTYPES,
_check_sample_weight,
check_is_fitted,
check_random_state,
validate_data,
)
BOUNDS_THRESHOLD = 1e-7
__all__ = [
"Binarizer",
"KernelCenterer",
"MaxAbsScaler",
"MinMaxScaler",
"Normalizer",
"OneHotEncoder",
"PowerTransformer",
"QuantileTransformer",
"RobustScaler",
"StandardScaler",
"add_dummy_feature",
"binarize",
"maxabs_scale",
"minmax_scale",
"normalize",
"power_transform",
"quantile_transform",
"robust_scale",
"scale",
]
def _is_constant_feature(var, mean, n_samples):
"""Detect if a feature is indistinguishable from a constant feature.
The detection is based on its computed variance and on the theoretical
error bounds of the '2 pass algorithm' for variance computation.
See "Algorithms for computing the sample variance: analysis and
recommendations", by Chan, Golub, and LeVeque.
"""
# In scikit-learn, variance is always computed using float64 accumulators.
xp, _, device_ = get_namespace_and_device(var, mean)
max_float_dtype = _max_precision_float_dtype(xp=xp, device=device_)
eps = xp.finfo(max_float_dtype).eps
upper_bound = n_samples * eps * var + (n_samples * mean * eps) ** 2
return var <= upper_bound
def _handle_zeros_in_scale(scale, copy=True, constant_mask=None):
"""Set scales of near constant features to 1.
The goal is to avoid division by very small or zero values.
Near constant features are detected automatically by identifying
scales close to machine precision unless they are precomputed by
the caller and passed with the `constant_mask` kwarg.
Typically for standard scaling, the scales are the standard
deviation while near constant features are better detected on the
computed variances which are closer to machine precision by
construction.
"""
# if we are fitting on 1D arrays, scale might be a scalar
if np.isscalar(scale):
if scale == 0.0:
scale = 1.0
return scale
# scale is an array
else:
xp, _ = get_namespace(scale)
if constant_mask is None:
# Detect near constant values to avoid dividing by a very small
# value that could lead to surprising results and numerical
# stability issues.
constant_mask = scale < 10 * xp.finfo(scale.dtype).eps
if copy:
# New array to avoid side-effects
scale = xp.asarray(scale, copy=True)
scale[constant_mask] = 1.0
return scale
@validate_params(
{
"X": ["array-like", "sparse matrix"],
"axis": [Options(Integral, {0, 1})],
"with_mean": ["boolean"],
"with_std": ["boolean"],
"copy": ["boolean"],
},
prefer_skip_nested_validation=True,
)
def scale(X, *, axis=0, with_mean=True, with_std=True, copy=True):
"""Standardize a dataset along any axis.
Center to the mean and component wise scale to unit variance.
Read more in the :ref:`User Guide <preprocessing_scaler>`.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The data to center and scale.
axis : {0, 1}, default=0
Axis used to compute the means and standard deviations along. If 0,
independently standardize each feature, otherwise (if 1) standardize
each sample.
with_mean : bool, default=True
If True, center the data before scaling.
with_std : bool, default=True
If True, scale the data to unit variance (or equivalently,
unit standard deviation).
copy : bool, default=True
If False, try to avoid a copy and scale in place.
This is not guaranteed to always work in place; e.g. if the data is
a numpy array with an int dtype, a copy will be returned even with
copy=False.
Returns
-------
X_tr : {ndarray, sparse matrix} of shape (n_samples, n_features)
The transformed data.
See Also
--------
StandardScaler : Performs scaling to unit variance using the Transformer
API (e.g. as part of a preprocessing
:class:`~sklearn.pipeline.Pipeline`).
Notes
-----
This implementation will refuse to center scipy.sparse matrices
since it would make them non-sparse and would potentially crash the
program with memory exhaustion problems.
Instead the caller is expected to either set explicitly
`with_mean=False` (in that case, only variance scaling will be
performed on the features of the CSC matrix) or to call `X.toarray()`
if he/she expects the materialized dense array to fit in memory.
To avoid memory copy the caller should pass a CSC matrix.
NaNs are treated as missing values: disregarded to compute the statistics,
and maintained during the data transformation.
We use a biased estimator for the standard deviation, equivalent to
`numpy.std(x, ddof=0)`. Note that the choice of `ddof` is unlikely to
affect model performance.
For a comparison of the different scalers, transformers, and normalizers,
see: :ref:`sphx_glr_auto_examples_preprocessing_plot_all_scaling.py`.
.. warning:: Risk of data leak
Do not use :func:`~sklearn.preprocessing.scale` unless you know
what you are doing. A common mistake is to apply it to the entire data
*before* splitting into training and test sets. This will bias the
model evaluation because information would have leaked from the test
set to the training set.
In general, we recommend using
:class:`~sklearn.preprocessing.StandardScaler` within a
:ref:`Pipeline <pipeline>` in order to prevent most risks of data
leaking: `pipe = make_pipeline(StandardScaler(), LogisticRegression())`.
Examples
--------
>>> from sklearn.preprocessing import scale
>>> X = [[-2, 1, 2], [-1, 0, 1]]
>>> scale(X, axis=0) # scaling each column independently
array([[-1., 1., 1.],
[ 1., -1., -1.]])
>>> scale(X, axis=1) # scaling each row independently
array([[-1.37, 0.39, 0.98],
[-1.22, 0. , 1.22]])
"""
X = check_array(
X,
accept_sparse="csc",
copy=copy,
ensure_2d=False,
estimator="the scale function",
dtype=FLOAT_DTYPES,
ensure_all_finite="allow-nan",
input_name="X",
)
if sparse.issparse(X):
if with_mean:
raise ValueError(
"Cannot center sparse matrices: pass `with_mean=False` instead"
" See docstring for motivation and alternatives."
)
if axis != 0:
raise ValueError(
"Can only scale sparse matrix on axis=0, got axis=%d" % axis
)
if with_std:
_, var = mean_variance_axis(X, axis=0)
var = _handle_zeros_in_scale(var, copy=False)
inplace_column_scale(X, 1 / np.sqrt(var))
else:
X = np.asarray(X)
if with_mean:
mean_ = np.nanmean(X, axis)
if with_std:
scale_ = np.nanstd(X, axis)
# Xr is a view on the original array that enables easy use of
# broadcasting on the axis in which we are interested in
Xr = np.rollaxis(X, axis)
if with_mean:
Xr -= mean_
mean_1 = np.nanmean(Xr, axis=0)
# Verify that mean_1 is 'close to zero'. If X contains very
# large values, mean_1 can also be very large, due to a lack of
# precision of mean_. In this case, a pre-scaling of the
# concerned feature is efficient, for instance by its mean or
# maximum.
if not np.allclose(mean_1, 0):
warnings.warn(
"Numerical issues were encountered "
"when centering the data "
"and might not be solved. Dataset may "
"contain too large values. You may need "
"to prescale your features."
)
Xr -= mean_1
if with_std:
scale_ = _handle_zeros_in_scale(scale_, copy=False)
Xr /= scale_
if with_mean:
mean_2 = np.nanmean(Xr, axis=0)
# If mean_2 is not 'close to zero', it comes from the fact that
# scale_ is very small so that mean_2 = mean_1/scale_ > 0, even
# if mean_1 was close to zero. The problem is thus essentially
# due to the lack of precision of mean_. A solution is then to
# subtract the mean again:
if not np.allclose(mean_2, 0):
warnings.warn(
"Numerical issues were encountered "
"when scaling the data "
"and might not be solved. The standard "
"deviation of the data is probably "
"very close to 0. "
)
Xr -= mean_2
return X
class MinMaxScaler(OneToOneFeatureMixin, TransformerMixin, BaseEstimator):
"""Transform features by scaling each feature to a given range.
This estimator scales and translates each feature individually such
that it is in the given range on the training set, e.g. between
zero and one.
The transformation is given by::
X_std = (X - X.min(axis=0)) / (X.max(axis=0) - X.min(axis=0))
X_scaled = X_std * (max - min) + min
where min, max = feature_range.
This transformation is often used as an alternative to zero mean,
unit variance scaling.
`MinMaxScaler` doesn't reduce the effect of outliers, but it linearly
scales them down into a fixed range, where the largest occurring data point
corresponds to the maximum value and the smallest one corresponds to the
minimum value. For an example visualization, refer to :ref:`Compare
MinMaxScaler with other scalers <plot_all_scaling_minmax_scaler_section>`.
Read more in the :ref:`User Guide <preprocessing_scaler>`.
Parameters
----------
feature_range : tuple (min, max), default=(0, 1)
Desired range of transformed data.
copy : bool, default=True
Set to False to perform inplace row normalization and avoid a
copy (if the input is already a numpy array).
clip : bool, default=False
Set to True to clip transformed values of held-out data to
provided `feature_range`.
Since this parameter will clip values, `inverse_transform` may not
be able to restore the original data.
.. note::
Setting `clip=True` does not prevent feature drift (a distribution
shift between training and test data). The transformed values are clipped
to the `feature_range`, which helps avoid unintended behavior in models
sensitive to out-of-range inputs (e.g. linear models). Use with care,
as clipping can distort the distribution of test data.
.. versionadded:: 0.24
Attributes
----------
min_ : ndarray of shape (n_features,)
Per feature adjustment for minimum. Equivalent to
``min - X.min(axis=0) * self.scale_``
scale_ : ndarray of shape (n_features,)
Per feature relative scaling of the data. Equivalent to
``(max - min) / (X.max(axis=0) - X.min(axis=0))``
.. versionadded:: 0.17
*scale_* attribute.
data_min_ : ndarray of shape (n_features,)
Per feature minimum seen in the data
.. versionadded:: 0.17
*data_min_*
data_max_ : ndarray of shape (n_features,)
Per feature maximum seen in the data
.. versionadded:: 0.17
*data_max_*
data_range_ : ndarray of shape (n_features,)
Per feature range ``(data_max_ - data_min_)`` seen in the data
.. versionadded:: 0.17
*data_range_*
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
n_samples_seen_ : int
The number of samples processed by the estimator.
It will be reset on new calls to fit, but increments across
``partial_fit`` calls.
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
See Also
--------
minmax_scale : Equivalent function without the estimator API.
Notes
-----
NaNs are treated as missing values: disregarded in fit, and maintained in
transform.
Examples
--------
>>> from sklearn.preprocessing import MinMaxScaler
>>> data = [[-1, 2], [-0.5, 6], [0, 10], [1, 18]]
>>> scaler = MinMaxScaler()
>>> print(scaler.fit(data))
MinMaxScaler()
>>> print(scaler.data_max_)
[ 1. 18.]
>>> print(scaler.transform(data))
[[0. 0. ]
[0.25 0.25]
[0.5 0.5 ]
[1. 1. ]]
>>> print(scaler.transform([[2, 2]]))
[[1.5 0. ]]
"""
_parameter_constraints: dict = {
"feature_range": [tuple],
"copy": ["boolean"],
"clip": ["boolean"],
}
def __init__(self, feature_range=(0, 1), *, copy=True, clip=False):
self.feature_range = feature_range
self.copy = copy
self.clip = clip
def _reset(self):
"""Reset internal data-dependent state of the scaler, if necessary.
__init__ parameters are not touched.
"""
# Checking one attribute is enough, because they are all set together
# in partial_fit
if hasattr(self, "scale_"):
del self.scale_
del self.min_
del self.n_samples_seen_
del self.data_min_
del self.data_max_
del self.data_range_
def fit(self, X, y=None):
"""Compute the minimum and maximum to be used for later scaling.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The data used to compute the per-feature minimum and maximum
used for later scaling along the features axis.
y : None
Ignored.
Returns
-------
self : object
Fitted scaler.
"""
# Reset internal state before fitting
self._reset()
return self.partial_fit(X, y)
@_fit_context(prefer_skip_nested_validation=True)
def partial_fit(self, X, y=None):
"""Online computation of min and max on X for later scaling.
All of X is processed as a single batch. This is intended for cases
when :meth:`fit` is not feasible due to very large number of
`n_samples` or because X is read from a continuous stream.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The data used to compute the mean and standard deviation
used for later scaling along the features axis.
y : None
Ignored.
Returns
-------
self : object
Fitted scaler.
"""
feature_range = self.feature_range
if feature_range[0] >= feature_range[1]:
raise ValueError(
"Minimum of desired feature range must be smaller than maximum. Got %s."
% str(feature_range)
)
if sparse.issparse(X):
raise TypeError(
"MinMaxScaler does not support sparse input. "
"Consider using MaxAbsScaler instead."
)
xp, _ = get_namespace(X)
first_pass = not hasattr(self, "n_samples_seen_")
X = validate_data(
self,
X,
reset=first_pass,
dtype=_array_api.supported_float_dtypes(xp),
ensure_all_finite="allow-nan",
)
device_ = device(X)
feature_range = (
xp.asarray(feature_range[0], dtype=X.dtype, device=device_),
xp.asarray(feature_range[1], dtype=X.dtype, device=device_),
)
data_min = _array_api._nanmin(X, axis=0, xp=xp)
data_max = _array_api._nanmax(X, axis=0, xp=xp)
if first_pass:
self.n_samples_seen_ = X.shape[0]
else:
data_min = xp.minimum(self.data_min_, data_min)
data_max = xp.maximum(self.data_max_, data_max)
self.n_samples_seen_ += X.shape[0]
data_range = data_max - data_min
self.scale_ = (feature_range[1] - feature_range[0]) / _handle_zeros_in_scale(
data_range, copy=True
)
self.min_ = feature_range[0] - data_min * self.scale_
self.data_min_ = data_min
self.data_max_ = data_max
self.data_range_ = data_range
return self
def transform(self, X):
"""Scale features of X according to feature_range.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Input data that will be transformed.
Returns
-------
Xt : ndarray of shape (n_samples, n_features)
Transformed data.
"""
check_is_fitted(self)
xp, _ = get_namespace(X)
X = validate_data(
self,
X,
copy=self.copy,
dtype=_array_api.supported_float_dtypes(xp),
force_writeable=True,
ensure_all_finite="allow-nan",
reset=False,
)
X *= self.scale_
X += self.min_
if self.clip:
device_ = device(X)
X = _modify_in_place_if_numpy(
xp,
xp.clip,
X,
xp.asarray(self.feature_range[0], dtype=X.dtype, device=device_),
xp.asarray(self.feature_range[1], dtype=X.dtype, device=device_),
out=X,
)
return X
def inverse_transform(self, X):
"""Undo the scaling of X according to feature_range.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Input data that will be transformed. It cannot be sparse.
Returns
-------
X_original : ndarray of shape (n_samples, n_features)
Transformed data.
"""
check_is_fitted(self)
xp, _ = get_namespace(X)
X = check_array(
X,
copy=self.copy,
dtype=_array_api.supported_float_dtypes(xp),
force_writeable=True,
ensure_all_finite="allow-nan",
)
X -= self.min_
X /= self.scale_
return X
def __sklearn_tags__(self):
tags = super().__sklearn_tags__()
tags.input_tags.allow_nan = True
tags.array_api_support = True
return tags
@validate_params(
{
"X": ["array-like"],
"axis": [Options(Integral, {0, 1})],
},
prefer_skip_nested_validation=False,
)
def minmax_scale(X, feature_range=(0, 1), *, axis=0, copy=True):
"""Transform features by scaling each feature to a given range.
This estimator scales and translates each feature individually such
that it is in the given range on the training set, i.e. between
zero and one.
The transformation is given by (when ``axis=0``)::
X_std = (X - X.min(axis=0)) / (X.max(axis=0) - X.min(axis=0))
X_scaled = X_std * (max - min) + min
where min, max = feature_range.
The transformation is calculated as (when ``axis=0``)::
X_scaled = scale * X + min - X.min(axis=0) * scale
where scale = (max - min) / (X.max(axis=0) - X.min(axis=0))
This transformation is often used as an alternative to zero mean,
unit variance scaling.
Read more in the :ref:`User Guide <preprocessing_scaler>`.
.. versionadded:: 0.17
*minmax_scale* function interface
to :class:`~sklearn.preprocessing.MinMaxScaler`.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The data.
feature_range : tuple (min, max), default=(0, 1)
Desired range of transformed data.
axis : {0, 1}, default=0
Axis used to scale along. If 0, independently scale each feature,
otherwise (if 1) scale each sample.
copy : bool, default=True
If False, try to avoid a copy and scale in place.
This is not guaranteed to always work in place; e.g. if the data is
a numpy array with an int dtype, a copy will be returned even with
copy=False.
Returns
-------
X_tr : ndarray of shape (n_samples, n_features)
The transformed data.
.. warning:: Risk of data leak
Do not use :func:`~sklearn.preprocessing.minmax_scale` unless you know
what you are doing. A common mistake is to apply it to the entire data
*before* splitting into training and test sets. This will bias the
model evaluation because information would have leaked from the test
set to the training set.
In general, we recommend using
:class:`~sklearn.preprocessing.MinMaxScaler` within a
:ref:`Pipeline <pipeline>` in order to prevent most risks of data
leaking: `pipe = make_pipeline(MinMaxScaler(), LogisticRegression())`.
See Also
--------
MinMaxScaler : Performs scaling to a given range using the Transformer
API (e.g. as part of a preprocessing
:class:`~sklearn.pipeline.Pipeline`).
Notes
-----
For a comparison of the different scalers, transformers, and normalizers,
see: :ref:`sphx_glr_auto_examples_preprocessing_plot_all_scaling.py`.
Examples
--------
>>> from sklearn.preprocessing import minmax_scale
>>> X = [[-2, 1, 2], [-1, 0, 1]]
>>> minmax_scale(X, axis=0) # scale each column independently
array([[0., 1., 1.],
[1., 0., 0.]])
>>> minmax_scale(X, axis=1) # scale each row independently
array([[0. , 0.75, 1. ],
[0. , 0.5 , 1. ]])
"""
# Unlike the scaler object, this function allows 1d input.
# If copy is required, it will be done inside the scaler object.
X = check_array(
X,
copy=False,
ensure_2d=False,
dtype=FLOAT_DTYPES,
ensure_all_finite="allow-nan",
)
original_ndim = X.ndim
if original_ndim == 1:
X = X.reshape(X.shape[0], 1)
s = MinMaxScaler(feature_range=feature_range, copy=copy)
if axis == 0:
X = s.fit_transform(X)
else:
X = s.fit_transform(X.T).T
if original_ndim == 1:
X = X.ravel()
return X
class StandardScaler(OneToOneFeatureMixin, TransformerMixin, BaseEstimator):
"""Standardize features by removing the mean and scaling to unit variance.
The standard score of a sample `x` is calculated as:
.. code-block:: text
z = (x - u) / s
where `u` is the mean of the training samples or zero if `with_mean=False`,
and `s` is the standard deviation of the training samples or one if
`with_std=False`.
Centering and scaling happen independently on each feature by computing
the relevant statistics on the samples in the training set. Mean and
standard deviation are then stored to be used on later data using
:meth:`transform`.
Standardization of a dataset is a common requirement for many
machine learning estimators: they might behave badly if the
individual features do not more or less look like standard normally
distributed data (e.g. Gaussian with 0 mean and unit variance).
For instance many elements used in the objective function of
a learning algorithm (such as the RBF kernel of Support Vector
Machines or the L1 and L2 regularizers of linear models) assume that
all features are centered around 0 and have variance in the same
order. If a feature has a variance that is orders of magnitude larger
than others, it might dominate the objective function and make the
estimator unable to learn from other features correctly as expected.
`StandardScaler` is sensitive to outliers, and the features may scale
differently from each other in the presence of outliers. For an example
visualization, refer to :ref:`Compare StandardScaler with other scalers
<plot_all_scaling_standard_scaler_section>`.
This scaler can also be applied to sparse CSR or CSC matrices by passing
`with_mean=False` to avoid breaking the sparsity structure of the data.
Read more in the :ref:`User Guide <preprocessing_scaler>`.
Parameters
----------
copy : bool, default=True
If False, try to avoid a copy and do inplace scaling instead.
This is not guaranteed to always work inplace; e.g. if the data is
not a NumPy array or scipy.sparse CSR matrix, a copy may still be
returned.
with_mean : bool, default=True
If True, center the data before scaling.
This does not work (and will raise an exception) when attempted on
sparse matrices, because centering them entails building a dense
matrix which in common use cases is likely to be too large to fit in
memory.
with_std : bool, default=True
If True, scale the data to unit variance (or equivalently,
unit standard deviation).
Attributes
----------
scale_ : ndarray of shape (n_features,) or None
Per feature relative scaling of the data to achieve zero mean and unit
variance. Generally this is calculated using `np.sqrt(var_)`. If a
variance is zero, we can't achieve unit variance, and the data is left
as-is, giving a scaling factor of 1. `scale_` is equal to `None`
when `with_std=False`.
.. versionadded:: 0.17
*scale_*
mean_ : ndarray of shape (n_features,) or None
The mean value for each feature in the training set.
Equal to ``None`` when ``with_mean=False`` and ``with_std=False``.
var_ : ndarray of shape (n_features,) or None
The variance for each feature in the training set. Used to compute
`scale_`. Equal to ``None`` when ``with_mean=False`` and
``with_std=False``.
n_features_in_ : int
Number of features seen during :term:`fit`.
.. versionadded:: 0.24
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
n_samples_seen_ : int or ndarray of shape (n_features,)
The number of samples processed by the estimator for each feature.
If there are no missing samples, the ``n_samples_seen`` will be an
integer, otherwise it will be an array of dtype int. If
`sample_weights` are used it will be a float (if no missing data)
or an array of dtype float that sums the weights seen so far.
Will be reset on new calls to fit, but increments across
``partial_fit`` calls.
See Also
--------
scale : Equivalent function without the estimator API.
:class:`~sklearn.decomposition.PCA` : Further removes the linear
correlation across features with 'whiten=True'.
Notes
-----
NaNs are treated as missing values: disregarded in fit, and maintained in
transform.
We use a biased estimator for the standard deviation, equivalent to
`numpy.std(x, ddof=0)`. Note that the choice of `ddof` is unlikely to
affect model performance.
Examples
--------
>>> from sklearn.preprocessing import StandardScaler
>>> data = [[0, 0], [0, 0], [1, 1], [1, 1]]
>>> scaler = StandardScaler()
>>> print(scaler.fit(data))
StandardScaler()
>>> print(scaler.mean_)
[0.5 0.5]
>>> print(scaler.transform(data))
[[-1. -1.]
[-1. -1.]
[ 1. 1.]
[ 1. 1.]]
>>> print(scaler.transform([[2, 2]]))
[[3. 3.]]
"""
_parameter_constraints: dict = {
"copy": ["boolean"],
"with_mean": ["boolean"],
"with_std": ["boolean"],
}
def __init__(self, *, copy=True, with_mean=True, with_std=True):
self.with_mean = with_mean
self.with_std = with_std
self.copy = copy
def _reset(self):
"""Reset internal data-dependent state of the scaler, if necessary.
__init__ parameters are not touched.
"""
# Checking one attribute is enough, because they are all set together
# in partial_fit
if hasattr(self, "scale_"):
del self.scale_
del self.n_samples_seen_
del self.mean_
del self.var_
def fit(self, X, y=None, sample_weight=None):
"""Compute the mean and std to be used for later scaling.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The data used to compute the mean and standard deviation
used for later scaling along the features axis.
y : None
Ignored.
sample_weight : array-like of shape (n_samples,), default=None
Individual weights for each sample.
.. versionadded:: 0.24
parameter *sample_weight* support to StandardScaler.
Returns
-------
self : object
Fitted scaler.
"""
# Reset internal state before fitting
self._reset()
return self.partial_fit(X, y, sample_weight)
@_fit_context(prefer_skip_nested_validation=True)
def partial_fit(self, X, y=None, sample_weight=None):
"""Online computation of mean and std on X for later scaling.
All of X is processed as a single batch. This is intended for cases
when :meth:`fit` is not feasible due to very large number of
`n_samples` or because X is read from a continuous stream.
The algorithm for incremental mean and std is given in Equation 1.5a,b
in Chan, Tony F., Gene H. Golub, and Randall J. LeVeque. "Algorithms
for computing the sample variance: Analysis and recommendations."
The American Statistician 37.3 (1983): 242-247:
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The data used to compute the mean and standard deviation
used for later scaling along the features axis.
y : None
Ignored.
sample_weight : array-like of shape (n_samples,), default=None
Individual weights for each sample.
.. versionadded:: 0.24
parameter *sample_weight* support to StandardScaler.
Returns
-------
self : object
Fitted scaler.
"""
xp, _, X_device = get_namespace_and_device(X)
first_call = not hasattr(self, "n_samples_seen_")
X = validate_data(
self,
X,
accept_sparse=("csr", "csc"),
dtype=supported_float_dtypes(xp, X_device),
ensure_all_finite="allow-nan",
reset=first_call,
)
n_features = X.shape[1]
if sample_weight is not None:
sample_weight = _check_sample_weight(sample_weight, X, dtype=X.dtype)
# Even in the case of `with_mean=False`, we update the mean anyway
# This is needed for the incremental computation of the var
# See incr_mean_variance_axis and _incremental_mean_variance_axis
# if n_samples_seen_ is an integer (i.e. no missing values), we need to
# transform it to an array of shape (n_features,) required by
# incr_mean_variance_axis and _incremental_variance_axis
dtype = xp.int64 if sample_weight is None else X.dtype
if first_call:
self.n_samples_seen_ = xp.zeros(n_features, dtype=dtype, device=X_device)
elif size(self.n_samples_seen_) == 1:
self.n_samples_seen_ = xp.repeat(self.n_samples_seen_, X.shape[1])
self.n_samples_seen_ = xp.astype(self.n_samples_seen_, dtype, copy=False)
if sparse.issparse(X):
if self.with_mean:
raise ValueError(
"Cannot center sparse matrices: pass `with_mean=False` "
"instead. See docstring for motivation and alternatives."
)
sparse_constructor = (
sparse.csr_matrix if X.format == "csr" else sparse.csc_matrix
)
if self.with_std:
# First pass
if not hasattr(self, "scale_"):