/
_rfe.py
765 lines (618 loc) · 26.3 KB
/
_rfe.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
# Authors: Alexandre Gramfort <alexandre.gramfort@inria.fr>
# Vincent Michel <vincent.michel@inria.fr>
# Gilles Louppe <g.louppe@gmail.com>
#
# License: BSD 3 clause
"""Recursive feature elimination for feature ranking"""
import numpy as np
from numbers import Integral, Real
from joblib import effective_n_jobs
from ..utils.metaestimators import available_if
from ..utils.metaestimators import _safe_split
from ..utils._param_validation import HasMethods, Interval
from ..utils._tags import _safe_tags
from ..utils.validation import check_is_fitted
from ..utils.parallel import delayed, Parallel
from ..base import BaseEstimator
from ..base import MetaEstimatorMixin
from ..base import clone
from ..base import is_classifier
from ..model_selection import check_cv
from ..model_selection._validation import _score
from ..metrics import check_scoring
from ._base import SelectorMixin
from ._base import _get_feature_importances
def _rfe_single_fit(rfe, estimator, X, y, train, test, scorer):
"""
Return the score for a fit across one fold.
"""
X_train, y_train = _safe_split(estimator, X, y, train)
X_test, y_test = _safe_split(estimator, X, y, test, train)
return rfe._fit(
X_train,
y_train,
lambda estimator, features: _score(
estimator, X_test[:, features], y_test, scorer
),
).scores_
def _estimator_has(attr):
"""Check if we can delegate a method to the underlying estimator.
First, we check the first fitted estimator if available, otherwise we
check the unfitted estimator.
"""
return lambda self: (
hasattr(self.estimator_, attr)
if hasattr(self, "estimator_")
else hasattr(self.estimator, attr)
)
class RFE(SelectorMixin, MetaEstimatorMixin, BaseEstimator):
"""Feature ranking with recursive feature elimination.
Given an external estimator that assigns weights to features (e.g., the
coefficients of a linear model), the goal of recursive feature elimination
(RFE) is to select features by recursively considering smaller and smaller
sets of features. First, the estimator is trained on the initial set of
features and the importance of each feature is obtained either through
any specific attribute or callable.
Then, the least important features are pruned from current set of features.
That procedure is recursively repeated on the pruned set until the desired
number of features to select is eventually reached.
Read more in the :ref:`User Guide <rfe>`.
Parameters
----------
estimator : ``Estimator`` instance
A supervised learning estimator with a ``fit`` method that provides
information about feature importance
(e.g. `coef_`, `feature_importances_`).
n_features_to_select : int or float, default=None
The number of features to select. If `None`, half of the features are
selected. If integer, the parameter is the absolute number of features
to select. If float between 0 and 1, it is the fraction of features to
select.
.. versionchanged:: 0.24
Added float values for fractions.
step : int or float, default=1
If greater than or equal to 1, then ``step`` corresponds to the
(integer) number of features to remove at each iteration.
If within (0.0, 1.0), then ``step`` corresponds to the percentage
(rounded down) of features to remove at each iteration.
verbose : int, default=0
Controls verbosity of output.
importance_getter : str or callable, default='auto'
If 'auto', uses the feature importance either through a `coef_`
or `feature_importances_` attributes of estimator.
Also accepts a string that specifies an attribute name/path
for extracting feature importance (implemented with `attrgetter`).
For example, give `regressor_.coef_` in case of
:class:`~sklearn.compose.TransformedTargetRegressor` or
`named_steps.clf.feature_importances_` in case of
class:`~sklearn.pipeline.Pipeline` with its last step named `clf`.
If `callable`, overrides the default feature importance getter.
The callable is passed with the fitted estimator and it should
return importance for each feature.
.. versionadded:: 0.24
Attributes
----------
classes_ : ndarray of shape (n_classes,)
The classes labels. Only available when `estimator` is a classifier.
estimator_ : ``Estimator`` instance
The fitted estimator used to select features.
n_features_ : int
The number of selected features.
n_features_in_ : int
Number of features seen during :term:`fit`. Only defined if the
underlying estimator exposes such an attribute when 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
ranking_ : ndarray of shape (n_features,)
The feature ranking, such that ``ranking_[i]`` corresponds to the
ranking position of the i-th feature. Selected (i.e., estimated
best) features are assigned rank 1.
support_ : ndarray of shape (n_features,)
The mask of selected features.
See Also
--------
RFECV : Recursive feature elimination with built-in cross-validated
selection of the best number of features.
SelectFromModel : Feature selection based on thresholds of importance
weights.
SequentialFeatureSelector : Sequential cross-validation based feature
selection. Does not rely on importance weights.
Notes
-----
Allows NaN/Inf in the input if the underlying estimator does as well.
References
----------
.. [1] Guyon, I., Weston, J., Barnhill, S., & Vapnik, V., "Gene selection
for cancer classification using support vector machines",
Mach. Learn., 46(1-3), 389--422, 2002.
Examples
--------
The following example shows how to retrieve the 5 most informative
features in the Friedman #1 dataset.
>>> from sklearn.datasets import make_friedman1
>>> from sklearn.feature_selection import RFE
>>> from sklearn.svm import SVR
>>> X, y = make_friedman1(n_samples=50, n_features=10, random_state=0)
>>> estimator = SVR(kernel="linear")
>>> selector = RFE(estimator, n_features_to_select=5, step=1)
>>> selector = selector.fit(X, y)
>>> selector.support_
array([ True, True, True, True, True, False, False, False, False,
False])
>>> selector.ranking_
array([1, 1, 1, 1, 1, 6, 4, 3, 2, 5])
"""
_parameter_constraints: dict = {
"estimator": [HasMethods(["fit"])],
"n_features_to_select": [
None,
Interval(Real, 0, 1, closed="right"),
Interval(Integral, 0, None, closed="neither"),
],
"step": [
Interval(Integral, 0, None, closed="neither"),
Interval(Real, 0, 1, closed="neither"),
],
"verbose": ["verbose"],
"importance_getter": [str, callable],
}
def __init__(
self,
estimator,
*,
n_features_to_select=None,
step=1,
verbose=0,
importance_getter="auto",
):
self.estimator = estimator
self.n_features_to_select = n_features_to_select
self.step = step
self.importance_getter = importance_getter
self.verbose = verbose
@property
def _estimator_type(self):
return self.estimator._estimator_type
@property
def classes_(self):
"""Classes labels available when `estimator` is a classifier.
Returns
-------
ndarray of shape (n_classes,)
"""
return self.estimator_.classes_
def fit(self, X, y, **fit_params):
"""Fit the RFE model and then the underlying estimator on the selected features.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The training input samples.
y : array-like of shape (n_samples,)
The target values.
**fit_params : dict
Additional parameters passed to the `fit` method of the underlying
estimator.
Returns
-------
self : object
Fitted estimator.
"""
self._validate_params()
return self._fit(X, y, **fit_params)
def _fit(self, X, y, step_score=None, **fit_params):
# Parameter step_score controls the calculation of self.scores_
# step_score is not exposed to users
# and is used when implementing RFECV
# self.scores_ will not be calculated when calling _fit through fit
tags = self._get_tags()
X, y = self._validate_data(
X,
y,
accept_sparse="csc",
ensure_min_features=2,
force_all_finite=not tags.get("allow_nan", True),
multi_output=True,
)
# Initialization
n_features = X.shape[1]
if self.n_features_to_select is None:
n_features_to_select = n_features // 2
elif isinstance(self.n_features_to_select, Integral): # int
n_features_to_select = self.n_features_to_select
else: # float
n_features_to_select = int(n_features * self.n_features_to_select)
if 0.0 < self.step < 1.0:
step = int(max(1, self.step * n_features))
else:
step = int(self.step)
support_ = np.ones(n_features, dtype=bool)
ranking_ = np.ones(n_features, dtype=int)
if step_score:
self.scores_ = []
# Elimination
while np.sum(support_) > n_features_to_select:
# Remaining features
features = np.arange(n_features)[support_]
# Rank the remaining features
estimator = clone(self.estimator)
if self.verbose > 0:
print("Fitting estimator with %d features." % np.sum(support_))
estimator.fit(X[:, features], y, **fit_params)
# Get importance and rank them
importances = _get_feature_importances(
estimator,
self.importance_getter,
transform_func="square",
)
ranks = np.argsort(importances)
# for sparse case ranks is matrix
ranks = np.ravel(ranks)
# Eliminate the worse features
threshold = min(step, np.sum(support_) - n_features_to_select)
# Compute step score on the previous selection iteration
# because 'estimator' must use features
# that have not been eliminated yet
if step_score:
self.scores_.append(step_score(estimator, features))
support_[features[ranks][:threshold]] = False
ranking_[np.logical_not(support_)] += 1
# Set final attributes
features = np.arange(n_features)[support_]
self.estimator_ = clone(self.estimator)
self.estimator_.fit(X[:, features], y, **fit_params)
# Compute step score when only n_features_to_select features left
if step_score:
self.scores_.append(step_score(self.estimator_, features))
self.n_features_ = support_.sum()
self.support_ = support_
self.ranking_ = ranking_
return self
@available_if(_estimator_has("predict"))
def predict(self, X):
"""Reduce X to the selected features and predict using the estimator.
Parameters
----------
X : array of shape [n_samples, n_features]
The input samples.
Returns
-------
y : array of shape [n_samples]
The predicted target values.
"""
check_is_fitted(self)
return self.estimator_.predict(self.transform(X))
@available_if(_estimator_has("score"))
def score(self, X, y, **fit_params):
"""Reduce X to the selected features and return the score of the estimator.
Parameters
----------
X : array of shape [n_samples, n_features]
The input samples.
y : array of shape [n_samples]
The target values.
**fit_params : dict
Parameters to pass to the `score` method of the underlying
estimator.
.. versionadded:: 1.0
Returns
-------
score : float
Score of the underlying base estimator computed with the selected
features returned by `rfe.transform(X)` and `y`.
"""
check_is_fitted(self)
return self.estimator_.score(self.transform(X), y, **fit_params)
def _get_support_mask(self):
check_is_fitted(self)
return self.support_
@available_if(_estimator_has("decision_function"))
def decision_function(self, X):
"""Compute the decision function of ``X``.
Parameters
----------
X : {array-like or sparse matrix} of shape (n_samples, n_features)
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
Returns
-------
score : array, shape = [n_samples, n_classes] or [n_samples]
The decision function of the input samples. The order of the
classes corresponds to that in the attribute :term:`classes_`.
Regression and binary classification produce an array of shape
[n_samples].
"""
check_is_fitted(self)
return self.estimator_.decision_function(self.transform(X))
@available_if(_estimator_has("predict_proba"))
def predict_proba(self, X):
"""Predict class probabilities for X.
Parameters
----------
X : {array-like or sparse matrix} of shape (n_samples, n_features)
The input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
Returns
-------
p : array of shape (n_samples, n_classes)
The class probabilities of the input samples. The order of the
classes corresponds to that in the attribute :term:`classes_`.
"""
check_is_fitted(self)
return self.estimator_.predict_proba(self.transform(X))
@available_if(_estimator_has("predict_log_proba"))
def predict_log_proba(self, X):
"""Predict class log-probabilities for X.
Parameters
----------
X : array of shape [n_samples, n_features]
The input samples.
Returns
-------
p : array of shape (n_samples, n_classes)
The class log-probabilities of the input samples. The order of the
classes corresponds to that in the attribute :term:`classes_`.
"""
check_is_fitted(self)
return self.estimator_.predict_log_proba(self.transform(X))
def _more_tags(self):
return {
"poor_score": True,
"allow_nan": _safe_tags(self.estimator, key="allow_nan"),
"requires_y": True,
}
class RFECV(RFE):
"""Recursive feature elimination with cross-validation to select features.
See glossary entry for :term:`cross-validation estimator`.
Read more in the :ref:`User Guide <rfe>`.
Parameters
----------
estimator : ``Estimator`` instance
A supervised learning estimator with a ``fit`` method that provides
information about feature importance either through a ``coef_``
attribute or through a ``feature_importances_`` attribute.
step : int or float, default=1
If greater than or equal to 1, then ``step`` corresponds to the
(integer) number of features to remove at each iteration.
If within (0.0, 1.0), then ``step`` corresponds to the percentage
(rounded down) of features to remove at each iteration.
Note that the last iteration may remove fewer than ``step`` features in
order to reach ``min_features_to_select``.
min_features_to_select : int, default=1
The minimum number of features to be selected. This number of features
will always be scored, even if the difference between the original
feature count and ``min_features_to_select`` isn't divisible by
``step``.
.. versionadded:: 0.20
cv : int, cross-validation generator or an iterable, default=None
Determines the cross-validation splitting strategy.
Possible inputs for cv are:
- None, to use the default 5-fold cross-validation,
- integer, to specify the number of folds.
- :term:`CV splitter`,
- An iterable yielding (train, test) splits as arrays of indices.
For integer/None inputs, if ``y`` is binary or multiclass,
:class:`~sklearn.model_selection.StratifiedKFold` is used. If the
estimator is a classifier or if ``y`` is neither binary nor multiclass,
:class:`~sklearn.model_selection.KFold` is used.
Refer :ref:`User Guide <cross_validation>` for the various
cross-validation strategies that can be used here.
.. versionchanged:: 0.22
``cv`` default value of None changed from 3-fold to 5-fold.
scoring : str, callable or None, default=None
A string (see model evaluation documentation) or
a scorer callable object / function with signature
``scorer(estimator, X, y)``.
verbose : int, default=0
Controls verbosity of output.
n_jobs : int or None, default=None
Number of cores to run in parallel while fitting across folds.
``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
``-1`` means using all processors. See :term:`Glossary <n_jobs>`
for more details.
.. versionadded:: 0.18
importance_getter : str or callable, default='auto'
If 'auto', uses the feature importance either through a `coef_`
or `feature_importances_` attributes of estimator.
Also accepts a string that specifies an attribute name/path
for extracting feature importance.
For example, give `regressor_.coef_` in case of
:class:`~sklearn.compose.TransformedTargetRegressor` or
`named_steps.clf.feature_importances_` in case of
:class:`~sklearn.pipeline.Pipeline` with its last step named `clf`.
If `callable`, overrides the default feature importance getter.
The callable is passed with the fitted estimator and it should
return importance for each feature.
.. versionadded:: 0.24
Attributes
----------
classes_ : ndarray of shape (n_classes,)
The classes labels. Only available when `estimator` is a classifier.
estimator_ : ``Estimator`` instance
The fitted estimator used to select features.
cv_results_ : dict of ndarrays
A dict with keys:
split(k)_test_score : ndarray of shape (n_subsets_of_features,)
The cross-validation scores across (k)th fold.
mean_test_score : ndarray of shape (n_subsets_of_features,)
Mean of scores over the folds.
std_test_score : ndarray of shape (n_subsets_of_features,)
Standard deviation of scores over the folds.
.. versionadded:: 1.0
n_features_ : int
The number of selected features with cross-validation.
n_features_in_ : int
Number of features seen during :term:`fit`. Only defined if the
underlying estimator exposes such an attribute when 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
ranking_ : narray of shape (n_features,)
The feature ranking, such that `ranking_[i]`
corresponds to the ranking
position of the i-th feature.
Selected (i.e., estimated best)
features are assigned rank 1.
support_ : ndarray of shape (n_features,)
The mask of selected features.
See Also
--------
RFE : Recursive feature elimination.
Notes
-----
The size of all values in ``cv_results_`` is equal to
``ceil((n_features - min_features_to_select) / step) + 1``,
where step is the number of features removed at each iteration.
Allows NaN/Inf in the input if the underlying estimator does as well.
References
----------
.. [1] Guyon, I., Weston, J., Barnhill, S., & Vapnik, V., "Gene selection
for cancer classification using support vector machines",
Mach. Learn., 46(1-3), 389--422, 2002.
Examples
--------
The following example shows how to retrieve the a-priori not known 5
informative features in the Friedman #1 dataset.
>>> from sklearn.datasets import make_friedman1
>>> from sklearn.feature_selection import RFECV
>>> from sklearn.svm import SVR
>>> X, y = make_friedman1(n_samples=50, n_features=10, random_state=0)
>>> estimator = SVR(kernel="linear")
>>> selector = RFECV(estimator, step=1, cv=5)
>>> selector = selector.fit(X, y)
>>> selector.support_
array([ True, True, True, True, True, False, False, False, False,
False])
>>> selector.ranking_
array([1, 1, 1, 1, 1, 6, 4, 3, 2, 5])
"""
_parameter_constraints: dict = {
**RFE._parameter_constraints,
"min_features_to_select": [Interval(Integral, 0, None, closed="neither")],
"cv": ["cv_object"],
"scoring": [None, str, callable],
"n_jobs": [None, Integral],
}
_parameter_constraints.pop("n_features_to_select")
def __init__(
self,
estimator,
*,
step=1,
min_features_to_select=1,
cv=None,
scoring=None,
verbose=0,
n_jobs=None,
importance_getter="auto",
):
self.estimator = estimator
self.step = step
self.importance_getter = importance_getter
self.cv = cv
self.scoring = scoring
self.verbose = verbose
self.n_jobs = n_jobs
self.min_features_to_select = min_features_to_select
def fit(self, X, y, groups=None):
"""Fit the RFE model and automatically tune the number of selected features.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Training vector, where `n_samples` is the number of samples and
`n_features` is the total number of features.
y : array-like of shape (n_samples,)
Target values (integers for classification, real numbers for
regression).
groups : array-like of shape (n_samples,) or None, default=None
Group labels for the samples used while splitting the dataset into
train/test set. Only used in conjunction with a "Group" :term:`cv`
instance (e.g., :class:`~sklearn.model_selection.GroupKFold`).
.. versionadded:: 0.20
Returns
-------
self : object
Fitted estimator.
"""
self._validate_params()
tags = self._get_tags()
X, y = self._validate_data(
X,
y,
accept_sparse="csr",
ensure_min_features=2,
force_all_finite=not tags.get("allow_nan", True),
multi_output=True,
)
# Initialization
cv = check_cv(self.cv, y, classifier=is_classifier(self.estimator))
scorer = check_scoring(self.estimator, scoring=self.scoring)
n_features = X.shape[1]
if 0.0 < self.step < 1.0:
step = int(max(1, self.step * n_features))
else:
step = int(self.step)
# Build an RFE object, which will evaluate and score each possible
# feature count, down to self.min_features_to_select
rfe = RFE(
estimator=self.estimator,
n_features_to_select=self.min_features_to_select,
importance_getter=self.importance_getter,
step=self.step,
verbose=self.verbose,
)
# Determine the number of subsets of features by fitting across
# the train folds and choosing the "features_to_select" parameter
# that gives the least averaged error across all folds.
# Note that joblib raises a non-picklable error for bound methods
# even if n_jobs is set to 1 with the default multiprocessing
# backend.
# This branching is done so that to
# make sure that user code that sets n_jobs to 1
# and provides bound methods as scorers is not broken with the
# addition of n_jobs parameter in version 0.18.
if effective_n_jobs(self.n_jobs) == 1:
parallel, func = list, _rfe_single_fit
else:
parallel = Parallel(n_jobs=self.n_jobs)
func = delayed(_rfe_single_fit)
scores = parallel(
func(rfe, self.estimator, X, y, train, test, scorer)
for train, test in cv.split(X, y, groups)
)
scores = np.array(scores)
scores_sum = np.sum(scores, axis=0)
scores_sum_rev = scores_sum[::-1]
argmax_idx = len(scores_sum) - np.argmax(scores_sum_rev) - 1
n_features_to_select = max(
n_features - (argmax_idx * step), self.min_features_to_select
)
# Re-execute an elimination with best_k over the whole set
rfe = RFE(
estimator=self.estimator,
n_features_to_select=n_features_to_select,
step=self.step,
importance_getter=self.importance_getter,
verbose=self.verbose,
)
rfe.fit(X, y)
# Set final attributes
self.support_ = rfe.support_
self.n_features_ = rfe.n_features_
self.ranking_ = rfe.ranking_
self.estimator_ = clone(self.estimator)
self.estimator_.fit(self._transform(X), y)
# reverse to stay consistent with before
scores_rev = scores[:, ::-1]
self.cv_results_ = {}
self.cv_results_["mean_test_score"] = np.mean(scores_rev, axis=0)
self.cv_results_["std_test_score"] = np.std(scores_rev, axis=0)
for i in range(scores.shape[0]):
self.cv_results_[f"split{i}_test_score"] = scores_rev[i]
return self