-
-
Notifications
You must be signed in to change notification settings - Fork 25.4k
/
base.py
1477 lines (1217 loc) · 51.9 KB
/
base.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
"""Base classes for all estimators and various utility functions."""
# Author: Gael Varoquaux <gael.varoquaux@normalesup.org>
# License: BSD 3 clause
import copy
import functools
import inspect
import platform
import re
import warnings
from collections import defaultdict
import numpy as np
from . import __version__
from ._config import config_context, get_config
from .exceptions import InconsistentVersionWarning
from .utils._estimator_html_repr import _HTMLDocumentationLinkMixin, estimator_html_repr
from .utils._metadata_requests import _MetadataRequester, _routing_enabled
from .utils._param_validation import validate_parameter_constraints
from .utils._set_output import _SetOutputMixin
from .utils._tags import (
_DEFAULT_TAGS,
)
from .utils.fixes import _IS_32BIT
from .utils.validation import (
_check_feature_names_in,
_check_y,
_generate_get_feature_names_out,
_get_feature_names,
_is_fitted,
_num_features,
check_array,
check_is_fitted,
check_X_y,
)
def clone(estimator, *, safe=True):
"""Construct a new unfitted estimator with the same parameters.
Clone does a deep copy of the model in an estimator
without actually copying attached data. It returns a new estimator
with the same parameters that has not been fitted on any data.
.. versionchanged:: 1.3
Delegates to `estimator.__sklearn_clone__` if the method exists.
Parameters
----------
estimator : {list, tuple, set} of estimator instance or a single \
estimator instance
The estimator or group of estimators to be cloned.
safe : bool, default=True
If safe is False, clone will fall back to a deep copy on objects
that are not estimators. Ignored if `estimator.__sklearn_clone__`
exists.
Returns
-------
estimator : object
The deep copy of the input, an estimator if input is an estimator.
Notes
-----
If the estimator's `random_state` parameter is an integer (or if the
estimator doesn't have a `random_state` parameter), an *exact clone* is
returned: the clone and the original estimator will give the exact same
results. Otherwise, *statistical clone* is returned: the clone might
return different results from the original estimator. More details can be
found in :ref:`randomness`.
Examples
--------
>>> from sklearn.base import clone
>>> from sklearn.linear_model import LogisticRegression
>>> X = [[-1, 0], [0, 1], [0, -1], [1, 0]]
>>> y = [0, 0, 1, 1]
>>> classifier = LogisticRegression().fit(X, y)
>>> cloned_classifier = clone(classifier)
>>> hasattr(classifier, "classes_")
True
>>> hasattr(cloned_classifier, "classes_")
False
>>> classifier is cloned_classifier
False
"""
if hasattr(estimator, "__sklearn_clone__") and not inspect.isclass(estimator):
return estimator.__sklearn_clone__()
return _clone_parametrized(estimator, safe=safe)
def _clone_parametrized(estimator, *, safe=True):
"""Default implementation of clone. See :func:`sklearn.base.clone` for details."""
estimator_type = type(estimator)
if estimator_type is dict:
return {k: clone(v, safe=safe) for k, v in estimator.items()}
elif estimator_type in (list, tuple, set, frozenset):
return estimator_type([clone(e, safe=safe) for e in estimator])
elif not hasattr(estimator, "get_params") or isinstance(estimator, type):
if not safe:
return copy.deepcopy(estimator)
else:
if isinstance(estimator, type):
raise TypeError(
"Cannot clone object. "
+ "You should provide an instance of "
+ "scikit-learn estimator instead of a class."
)
else:
raise TypeError(
"Cannot clone object '%s' (type %s): "
"it does not seem to be a scikit-learn "
"estimator as it does not implement a "
"'get_params' method." % (repr(estimator), type(estimator))
)
klass = estimator.__class__
new_object_params = estimator.get_params(deep=False)
for name, param in new_object_params.items():
new_object_params[name] = clone(param, safe=False)
new_object = klass(**new_object_params)
try:
new_object._metadata_request = copy.deepcopy(estimator._metadata_request)
except AttributeError:
pass
params_set = new_object.get_params(deep=False)
# quick sanity check of the parameters of the clone
for name in new_object_params:
param1 = new_object_params[name]
param2 = params_set[name]
if param1 is not param2:
raise RuntimeError(
"Cannot clone object %s, as the constructor "
"either does not set or modifies parameter %s" % (estimator, name)
)
# _sklearn_output_config is used by `set_output` to configure the output
# container of an estimator.
if hasattr(estimator, "_sklearn_output_config"):
new_object._sklearn_output_config = copy.deepcopy(
estimator._sklearn_output_config
)
return new_object
class BaseEstimator(_HTMLDocumentationLinkMixin, _MetadataRequester):
"""Base class for all estimators in scikit-learn.
Inheriting from this class provides default implementations of:
- setting and getting parameters used by `GridSearchCV` and friends;
- textual and HTML representation displayed in terminals and IDEs;
- estimator serialization;
- parameters validation;
- data validation;
- feature names validation.
Read more in the :ref:`User Guide <rolling_your_own_estimator>`.
Notes
-----
All estimators should specify all the parameters that can be set
at the class level in their ``__init__`` as explicit keyword
arguments (no ``*args`` or ``**kwargs``).
Examples
--------
>>> import numpy as np
>>> from sklearn.base import BaseEstimator
>>> class MyEstimator(BaseEstimator):
... def __init__(self, *, param=1):
... self.param = param
... def fit(self, X, y=None):
... self.is_fitted_ = True
... return self
... def predict(self, X):
... return np.full(shape=X.shape[0], fill_value=self.param)
>>> estimator = MyEstimator(param=2)
>>> estimator.get_params()
{'param': 2}
>>> X = np.array([[1, 2], [2, 3], [3, 4]])
>>> y = np.array([1, 0, 1])
>>> estimator.fit(X, y).predict(X)
array([2, 2, 2])
>>> estimator.set_params(param=3).fit(X, y).predict(X)
array([3, 3, 3])
"""
@classmethod
def _get_param_names(cls):
"""Get parameter names for the estimator"""
# fetch the constructor or the original constructor before
# deprecation wrapping if any
init = getattr(cls.__init__, "deprecated_original", cls.__init__)
if init is object.__init__:
# No explicit constructor to introspect
return []
# introspect the constructor arguments to find the model parameters
# to represent
init_signature = inspect.signature(init)
# Consider the constructor parameters excluding 'self'
parameters = [
p
for p in init_signature.parameters.values()
if p.name != "self" and p.kind != p.VAR_KEYWORD
]
for p in parameters:
if p.kind == p.VAR_POSITIONAL:
raise RuntimeError(
"scikit-learn estimators should always "
"specify their parameters in the signature"
" of their __init__ (no varargs)."
" %s with constructor %s doesn't "
" follow this convention." % (cls, init_signature)
)
# Extract and sort argument names excluding 'self'
return sorted([p.name for p in parameters])
def get_params(self, deep=True):
"""
Get parameters for this estimator.
Parameters
----------
deep : bool, default=True
If True, will return the parameters for this estimator and
contained subobjects that are estimators.
Returns
-------
params : dict
Parameter names mapped to their values.
"""
out = dict()
for key in self._get_param_names():
value = getattr(self, key)
if deep and hasattr(value, "get_params") and not isinstance(value, type):
deep_items = value.get_params().items()
out.update((key + "__" + k, val) for k, val in deep_items)
out[key] = value
return out
def set_params(self, **params):
"""Set the parameters of this estimator.
The method works on simple estimators as well as on nested objects
(such as :class:`~sklearn.pipeline.Pipeline`). The latter have
parameters of the form ``<component>__<parameter>`` so that it's
possible to update each component of a nested object.
Parameters
----------
**params : dict
Estimator parameters.
Returns
-------
self : estimator instance
Estimator instance.
"""
if not params:
# Simple optimization to gain speed (inspect is slow)
return self
valid_params = self.get_params(deep=True)
nested_params = defaultdict(dict) # grouped by prefix
for key, value in params.items():
key, delim, sub_key = key.partition("__")
if key not in valid_params:
local_valid_params = self._get_param_names()
raise ValueError(
f"Invalid parameter {key!r} for estimator {self}. "
f"Valid parameters are: {local_valid_params!r}."
)
if delim:
nested_params[key][sub_key] = value
else:
setattr(self, key, value)
valid_params[key] = value
for key, sub_params in nested_params.items():
valid_params[key].set_params(**sub_params)
return self
def __sklearn_clone__(self):
return _clone_parametrized(self)
def __repr__(self, N_CHAR_MAX=700):
# N_CHAR_MAX is the (approximate) maximum number of non-blank
# characters to render. We pass it as an optional parameter to ease
# the tests.
from .utils._pprint import _EstimatorPrettyPrinter
N_MAX_ELEMENTS_TO_SHOW = 30 # number of elements to show in sequences
# use ellipsis for sequences with a lot of elements
pp = _EstimatorPrettyPrinter(
compact=True,
indent=1,
indent_at_name=True,
n_max_elements_to_show=N_MAX_ELEMENTS_TO_SHOW,
)
repr_ = pp.pformat(self)
# Use bruteforce ellipsis when there are a lot of non-blank characters
n_nonblank = len("".join(repr_.split()))
if n_nonblank > N_CHAR_MAX:
lim = N_CHAR_MAX // 2 # apprx number of chars to keep on both ends
regex = r"^(\s*\S){%d}" % lim
# The regex '^(\s*\S){%d}' % n
# matches from the start of the string until the nth non-blank
# character:
# - ^ matches the start of string
# - (pattern){n} matches n repetitions of pattern
# - \s*\S matches a non-blank char following zero or more blanks
left_lim = re.match(regex, repr_).end()
right_lim = re.match(regex, repr_[::-1]).end()
if "\n" in repr_[left_lim:-right_lim]:
# The left side and right side aren't on the same line.
# To avoid weird cuts, e.g.:
# categoric...ore',
# we need to start the right side with an appropriate newline
# character so that it renders properly as:
# categoric...
# handle_unknown='ignore',
# so we add [^\n]*\n which matches until the next \n
regex += r"[^\n]*\n"
right_lim = re.match(regex, repr_[::-1]).end()
ellipsis = "..."
if left_lim + len(ellipsis) < len(repr_) - right_lim:
# Only add ellipsis if it results in a shorter repr
repr_ = repr_[:left_lim] + "..." + repr_[-right_lim:]
return repr_
def __getstate__(self):
if getattr(self, "__slots__", None):
raise TypeError(
"You cannot use `__slots__` in objects inheriting from "
"`sklearn.base.BaseEstimator`."
)
try:
state = super().__getstate__()
if state is None:
# For Python 3.11+, empty instance (no `__slots__`,
# and `__dict__`) will return a state equal to `None`.
state = self.__dict__.copy()
except AttributeError:
# Python < 3.11
state = self.__dict__.copy()
if type(self).__module__.startswith("sklearn."):
return dict(state.items(), _sklearn_version=__version__)
else:
return state
def __setstate__(self, state):
if type(self).__module__.startswith("sklearn."):
pickle_version = state.pop("_sklearn_version", "pre-0.18")
if pickle_version != __version__:
warnings.warn(
InconsistentVersionWarning(
estimator_name=self.__class__.__name__,
current_sklearn_version=__version__,
original_sklearn_version=pickle_version,
),
)
try:
super().__setstate__(state)
except AttributeError:
self.__dict__.update(state)
def _more_tags(self):
return _DEFAULT_TAGS
def _get_tags(self):
collected_tags = {}
for base_class in reversed(inspect.getmro(self.__class__)):
if hasattr(base_class, "_more_tags"):
# need the if because mixins might not have _more_tags
# but might do redundant work in estimators
# (i.e. calling more tags on BaseEstimator multiple times)
more_tags = base_class._more_tags(self)
collected_tags.update(more_tags)
return collected_tags
def _check_n_features(self, X, reset):
"""Set the `n_features_in_` attribute, or check against it.
Parameters
----------
X : {ndarray, sparse matrix} of shape (n_samples, n_features)
The input samples.
reset : bool
If True, the `n_features_in_` attribute is set to `X.shape[1]`.
If False and the attribute exists, then check that it is equal to
`X.shape[1]`. If False and the attribute does *not* exist, then
the check is skipped.
.. note::
It is recommended to call reset=True in `fit` and in the first
call to `partial_fit`. All other methods that validate `X`
should set `reset=False`.
"""
try:
n_features = _num_features(X)
except TypeError as e:
if not reset and hasattr(self, "n_features_in_"):
raise ValueError(
"X does not contain any features, but "
f"{self.__class__.__name__} is expecting "
f"{self.n_features_in_} features"
) from e
# If the number of features is not defined and reset=True,
# then we skip this check
return
if reset:
self.n_features_in_ = n_features
return
if not hasattr(self, "n_features_in_"):
# Skip this check if the expected number of expected input features
# was not recorded by calling fit first. This is typically the case
# for stateless transformers.
return
if n_features != self.n_features_in_:
raise ValueError(
f"X has {n_features} features, but {self.__class__.__name__} "
f"is expecting {self.n_features_in_} features as input."
)
def _check_feature_names(self, X, *, reset):
"""Set or check the `feature_names_in_` attribute.
.. versionadded:: 1.0
Parameters
----------
X : {ndarray, dataframe} of shape (n_samples, n_features)
The input samples.
reset : bool
Whether to reset the `feature_names_in_` attribute.
If False, the input will be checked for consistency with
feature names of data provided when reset was last True.
.. note::
It is recommended to call `reset=True` in `fit` and in the first
call to `partial_fit`. All other methods that validate `X`
should set `reset=False`.
"""
if reset:
feature_names_in = _get_feature_names(X)
if feature_names_in is not None:
self.feature_names_in_ = feature_names_in
elif hasattr(self, "feature_names_in_"):
# Delete the attribute when the estimator is fitted on a new dataset
# that has no feature names.
delattr(self, "feature_names_in_")
return
fitted_feature_names = getattr(self, "feature_names_in_", None)
X_feature_names = _get_feature_names(X)
if fitted_feature_names is None and X_feature_names is None:
# no feature names seen in fit and in X
return
if X_feature_names is not None and fitted_feature_names is None:
warnings.warn(
f"X has feature names, but {self.__class__.__name__} was fitted without"
" feature names"
)
return
if X_feature_names is None and fitted_feature_names is not None:
warnings.warn(
"X does not have valid feature names, but"
f" {self.__class__.__name__} was fitted with feature names"
)
return
# validate the feature names against the `feature_names_in_` attribute
if len(fitted_feature_names) != len(X_feature_names) or np.any(
fitted_feature_names != X_feature_names
):
message = (
"The feature names should match those that were passed during fit.\n"
)
fitted_feature_names_set = set(fitted_feature_names)
X_feature_names_set = set(X_feature_names)
unexpected_names = sorted(X_feature_names_set - fitted_feature_names_set)
missing_names = sorted(fitted_feature_names_set - X_feature_names_set)
def add_names(names):
output = ""
max_n_names = 5
for i, name in enumerate(names):
if i >= max_n_names:
output += "- ...\n"
break
output += f"- {name}\n"
return output
if unexpected_names:
message += "Feature names unseen at fit time:\n"
message += add_names(unexpected_names)
if missing_names:
message += "Feature names seen at fit time, yet now missing:\n"
message += add_names(missing_names)
if not missing_names and not unexpected_names:
message += (
"Feature names must be in the same order as they were in fit.\n"
)
raise ValueError(message)
def _validate_data(
self,
X="no_validation",
y="no_validation",
reset=True,
validate_separately=False,
cast_to_ndarray=True,
**check_params,
):
"""Validate input data and set or check the `n_features_in_` attribute.
Parameters
----------
X : {array-like, sparse matrix, dataframe} of shape \
(n_samples, n_features), default='no validation'
The input samples.
If `'no_validation'`, no validation is performed on `X`. This is
useful for meta-estimator which can delegate input validation to
their underlying estimator(s). In that case `y` must be passed and
the only accepted `check_params` are `multi_output` and
`y_numeric`.
y : array-like of shape (n_samples,), default='no_validation'
The targets.
- If `None`, `check_array` is called on `X`. If the estimator's
requires_y tag is True, then an error will be raised.
- If `'no_validation'`, `check_array` is called on `X` and the
estimator's requires_y tag is ignored. This is a default
placeholder and is never meant to be explicitly set. In that case
`X` must be passed.
- Otherwise, only `y` with `_check_y` or both `X` and `y` are
checked with either `check_array` or `check_X_y` depending on
`validate_separately`.
reset : bool, default=True
Whether to reset the `n_features_in_` attribute.
If False, the input will be checked for consistency with data
provided when reset was last True.
.. note::
It is recommended to call reset=True in `fit` and in the first
call to `partial_fit`. All other methods that validate `X`
should set `reset=False`.
validate_separately : False or tuple of dicts, default=False
Only used if y is not None.
If False, call validate_X_y(). Else, it must be a tuple of kwargs
to be used for calling check_array() on X and y respectively.
`estimator=self` is automatically added to these dicts to generate
more informative error message in case of invalid input data.
cast_to_ndarray : bool, default=True
Cast `X` and `y` to ndarray with checks in `check_params`. If
`False`, `X` and `y` are unchanged and only `feature_names_in_` and
`n_features_in_` are checked.
**check_params : kwargs
Parameters passed to :func:`sklearn.utils.check_array` or
:func:`sklearn.utils.check_X_y`. Ignored if validate_separately
is not False.
`estimator=self` is automatically added to these params to generate
more informative error message in case of invalid input data.
Returns
-------
out : {ndarray, sparse matrix} or tuple of these
The validated input. A tuple is returned if both `X` and `y` are
validated.
"""
self._check_feature_names(X, reset=reset)
if y is None and self._get_tags()["requires_y"]:
raise ValueError(
f"This {self.__class__.__name__} estimator "
"requires y to be passed, but the target y is None."
)
no_val_X = isinstance(X, str) and X == "no_validation"
no_val_y = y is None or isinstance(y, str) and y == "no_validation"
if no_val_X and no_val_y:
raise ValueError("Validation should be done on X, y or both.")
default_check_params = {"estimator": self}
check_params = {**default_check_params, **check_params}
if not cast_to_ndarray:
if not no_val_X and no_val_y:
out = X
elif no_val_X and not no_val_y:
out = y
else:
out = X, y
elif not no_val_X and no_val_y:
out = check_array(X, input_name="X", **check_params)
elif no_val_X and not no_val_y:
out = _check_y(y, **check_params)
else:
if validate_separately:
# We need this because some estimators validate X and y
# separately, and in general, separately calling check_array()
# on X and y isn't equivalent to just calling check_X_y()
# :(
check_X_params, check_y_params = validate_separately
if "estimator" not in check_X_params:
check_X_params = {**default_check_params, **check_X_params}
X = check_array(X, input_name="X", **check_X_params)
if "estimator" not in check_y_params:
check_y_params = {**default_check_params, **check_y_params}
y = check_array(y, input_name="y", **check_y_params)
else:
X, y = check_X_y(X, y, **check_params)
out = X, y
if not no_val_X and check_params.get("ensure_2d", True):
self._check_n_features(X, reset=reset)
return out
def _validate_params(self):
"""Validate types and values of constructor parameters
The expected type and values must be defined in the `_parameter_constraints`
class attribute, which is a dictionary `param_name: list of constraints`. See
the docstring of `validate_parameter_constraints` for a description of the
accepted constraints.
"""
validate_parameter_constraints(
self._parameter_constraints,
self.get_params(deep=False),
caller_name=self.__class__.__name__,
)
@property
def _repr_html_(self):
"""HTML representation of estimator.
This is redundant with the logic of `_repr_mimebundle_`. The latter
should be favorted in the long term, `_repr_html_` is only
implemented for consumers who do not interpret `_repr_mimbundle_`.
"""
if get_config()["display"] != "diagram":
raise AttributeError(
"_repr_html_ is only defined when the "
"'display' configuration option is set to "
"'diagram'"
)
return self._repr_html_inner
def _repr_html_inner(self):
"""This function is returned by the @property `_repr_html_` to make
`hasattr(estimator, "_repr_html_") return `True` or `False` depending
on `get_config()["display"]`.
"""
return estimator_html_repr(self)
def _repr_mimebundle_(self, **kwargs):
"""Mime bundle used by jupyter kernels to display estimator"""
output = {"text/plain": repr(self)}
if get_config()["display"] == "diagram":
output["text/html"] = estimator_html_repr(self)
return output
class ClassifierMixin:
"""Mixin class for all classifiers in scikit-learn.
This mixin defines the following functionality:
- `_estimator_type` class attribute defaulting to `"classifier"`;
- `score` method that default to :func:`~sklearn.metrics.accuracy_score`.
- enforce that `fit` requires `y` to be passed through the `requires_y` tag.
Read more in the :ref:`User Guide <rolling_your_own_estimator>`.
Examples
--------
>>> import numpy as np
>>> from sklearn.base import BaseEstimator, ClassifierMixin
>>> # Mixin classes should always be on the left-hand side for a correct MRO
>>> class MyEstimator(ClassifierMixin, BaseEstimator):
... def __init__(self, *, param=1):
... self.param = param
... def fit(self, X, y=None):
... self.is_fitted_ = True
... return self
... def predict(self, X):
... return np.full(shape=X.shape[0], fill_value=self.param)
>>> estimator = MyEstimator(param=1)
>>> X = np.array([[1, 2], [2, 3], [3, 4]])
>>> y = np.array([1, 0, 1])
>>> estimator.fit(X, y).predict(X)
array([1, 1, 1])
>>> estimator.score(X, y)
0.66...
"""
_estimator_type = "classifier"
def score(self, X, y, sample_weight=None):
"""
Return the mean accuracy on the given test data and labels.
In multi-label classification, this is the subset accuracy
which is a harsh metric since you require for each sample that
each label set be correctly predicted.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Test samples.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
True labels for `X`.
sample_weight : array-like of shape (n_samples,), default=None
Sample weights.
Returns
-------
score : float
Mean accuracy of ``self.predict(X)`` w.r.t. `y`.
"""
from .metrics import accuracy_score
return accuracy_score(y, self.predict(X), sample_weight=sample_weight)
def _more_tags(self):
return {"requires_y": True}
class RegressorMixin:
"""Mixin class for all regression estimators in scikit-learn.
This mixin defines the following functionality:
- `_estimator_type` class attribute defaulting to `"regressor"`;
- `score` method that default to :func:`~sklearn.metrics.r2_score`.
- enforce that `fit` requires `y` to be passed through the `requires_y` tag.
Read more in the :ref:`User Guide <rolling_your_own_estimator>`.
Examples
--------
>>> import numpy as np
>>> from sklearn.base import BaseEstimator, RegressorMixin
>>> # Mixin classes should always be on the left-hand side for a correct MRO
>>> class MyEstimator(RegressorMixin, BaseEstimator):
... def __init__(self, *, param=1):
... self.param = param
... def fit(self, X, y=None):
... self.is_fitted_ = True
... return self
... def predict(self, X):
... return np.full(shape=X.shape[0], fill_value=self.param)
>>> estimator = MyEstimator(param=0)
>>> X = np.array([[1, 2], [2, 3], [3, 4]])
>>> y = np.array([-1, 0, 1])
>>> estimator.fit(X, y).predict(X)
array([0, 0, 0])
>>> estimator.score(X, y)
0.0
"""
_estimator_type = "regressor"
def score(self, X, y, sample_weight=None):
"""Return the coefficient of determination of the prediction.
The coefficient of determination :math:`R^2` is defined as
:math:`(1 - \\frac{u}{v})`, where :math:`u` is the residual
sum of squares ``((y_true - y_pred)** 2).sum()`` and :math:`v`
is the total sum of squares ``((y_true - y_true.mean()) ** 2).sum()``.
The best possible score is 1.0 and it can be negative (because the
model can be arbitrarily worse). A constant model that always predicts
the expected value of `y`, disregarding the input features, would get
a :math:`R^2` score of 0.0.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Test samples. For some estimators this may be a precomputed
kernel matrix or a list of generic objects instead with shape
``(n_samples, n_samples_fitted)``, where ``n_samples_fitted``
is the number of samples used in the fitting for the estimator.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
True values for `X`.
sample_weight : array-like of shape (n_samples,), default=None
Sample weights.
Returns
-------
score : float
:math:`R^2` of ``self.predict(X)`` w.r.t. `y`.
Notes
-----
The :math:`R^2` score used when calling ``score`` on a regressor uses
``multioutput='uniform_average'`` from version 0.23 to keep consistent
with default value of :func:`~sklearn.metrics.r2_score`.
This influences the ``score`` method of all the multioutput
regressors (except for
:class:`~sklearn.multioutput.MultiOutputRegressor`).
"""
from .metrics import r2_score
y_pred = self.predict(X)
return r2_score(y, y_pred, sample_weight=sample_weight)
def _more_tags(self):
return {"requires_y": True}
class ClusterMixin:
"""Mixin class for all cluster estimators in scikit-learn.
- `_estimator_type` class attribute defaulting to `"clusterer"`;
- `fit_predict` method returning the cluster labels associated to each sample.
Examples
--------
>>> import numpy as np
>>> from sklearn.base import BaseEstimator, ClusterMixin
>>> class MyClusterer(ClusterMixin, BaseEstimator):
... def fit(self, X, y=None):
... self.labels_ = np.ones(shape=(len(X),), dtype=np.int64)
... return self
>>> X = [[1, 2], [2, 3], [3, 4]]
>>> MyClusterer().fit_predict(X)
array([1, 1, 1])
"""
_estimator_type = "clusterer"
def fit_predict(self, X, y=None, **kwargs):
"""
Perform clustering on `X` and returns cluster labels.
Parameters
----------
X : array-like of shape (n_samples, n_features)
Input data.
y : Ignored
Not used, present for API consistency by convention.
**kwargs : dict
Arguments to be passed to ``fit``.
.. versionadded:: 1.4
Returns
-------
labels : ndarray of shape (n_samples,), dtype=np.int64
Cluster labels.
"""
# non-optimized default implementation; override when a better
# method is possible for a given clustering algorithm
self.fit(X, **kwargs)
return self.labels_
def _more_tags(self):
return {"preserves_dtype": []}
class BiclusterMixin:
"""Mixin class for all bicluster estimators in scikit-learn.
This mixin defines the following functionality:
- `biclusters_` property that returns the row and column indicators;
- `get_indices` method that returns the row and column indices of a bicluster;
- `get_shape` method that returns the shape of a bicluster;
- `get_submatrix` method that returns the submatrix corresponding to a bicluster.
Examples
--------
>>> import numpy as np
>>> from sklearn.base import BaseEstimator, BiclusterMixin
>>> class DummyBiClustering(BiclusterMixin, BaseEstimator):
... def fit(self, X, y=None):
... self.rows_ = np.ones(shape=(1, X.shape[0]), dtype=bool)
... self.columns_ = np.ones(shape=(1, X.shape[1]), dtype=bool)
... return self
>>> X = np.array([[1, 1], [2, 1], [1, 0],
... [4, 7], [3, 5], [3, 6]])
>>> bicluster = DummyBiClustering().fit(X)
>>> hasattr(bicluster, "biclusters_")
True
>>> bicluster.get_indices(0)
(array([0, 1, 2, 3, 4, 5]), array([0, 1]))
"""
@property
def biclusters_(self):
"""Convenient way to get row and column indicators together.
Returns the ``rows_`` and ``columns_`` members.
"""
return self.rows_, self.columns_
def get_indices(self, i):
"""Row and column indices of the `i`'th bicluster.
Only works if ``rows_`` and ``columns_`` attributes exist.
Parameters
----------
i : int
The index of the cluster.
Returns
-------
row_ind : ndarray, dtype=np.intp
Indices of rows in the dataset that belong to the bicluster.
col_ind : ndarray, dtype=np.intp
Indices of columns in the dataset that belong to the bicluster.
"""
rows = self.rows_[i]
columns = self.columns_[i]
return np.nonzero(rows)[0], np.nonzero(columns)[0]
def get_shape(self, i):
"""Shape of the `i`'th bicluster.
Parameters
----------
i : int
The index of the cluster.
Returns
-------
n_rows : int
Number of rows in the bicluster.
n_cols : int
Number of columns in the bicluster.
"""
indices = self.get_indices(i)
return tuple(len(i) for i in indices)
def get_submatrix(self, i, data):
"""Return the submatrix corresponding to bicluster `i`.
Parameters
----------
i : int
The index of the cluster.
data : array-like of shape (n_samples, n_features)
The data.
Returns
-------
submatrix : ndarray of shape (n_rows, n_cols)
The submatrix corresponding to bicluster `i`.
Notes
-----
Works with sparse matrices. Only works if ``rows_`` and