-
-
Notifications
You must be signed in to change notification settings - Fork 27k
Expand file tree
/
Copy path_forest.py
More file actions
3086 lines (2548 loc) · 117 KB
/
_forest.py
File metadata and controls
3086 lines (2548 loc) · 117 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
"""
Forest of trees-based ensemble methods.
Those methods include random forests and extremely randomized trees.
The module structure is the following:
- The ``BaseForest`` base class implements a common ``fit`` method for all
the estimators in the module. The ``fit`` method of the base ``Forest``
class calls the ``fit`` method of each sub-estimator on random samples
(with replacement, a.k.a. bootstrap) of the training set.
The init of the sub-estimator is further delegated to the
``BaseEnsemble`` constructor.
- The ``ForestClassifier`` and ``ForestRegressor`` base classes further
implement the prediction logic by computing an average of the predicted
outcomes of the sub-estimators.
- The ``RandomForestClassifier`` and ``RandomForestRegressor`` derived
classes provide the user with concrete implementations of
the forest ensemble method using classical, deterministic
``DecisionTreeClassifier`` and ``DecisionTreeRegressor`` as
sub-estimator implementations.
- The ``ExtraTreesClassifier`` and ``ExtraTreesRegressor`` derived
classes provide the user with concrete implementations of the
forest ensemble method using the extremely randomized trees
``ExtraTreeClassifier`` and ``ExtraTreeRegressor`` as
sub-estimator implementations.
Single and multi-output problems are both handled.
"""
# Authors: The scikit-learn developers
# SPDX-License-Identifier: BSD-3-Clause
import threading
from abc import ABCMeta, abstractmethod
from numbers import Integral
from warnings import warn
import numpy as np
from scipy.sparse import hstack as sparse_hstack
from scipy.sparse import issparse
from sklearn.base import (
ClassifierMixin,
MultiOutputMixin,
RegressorMixin,
TransformerMixin,
_fit_context,
is_classifier,
)
from sklearn.ensemble._base import BaseEnsemble, _partition_estimators
from sklearn.ensemble._bootstrap import _get_n_samples_bootstrap
from sklearn.exceptions import DataConversionWarning
from sklearn.metrics import accuracy_score, r2_score
from sklearn.preprocessing import OneHotEncoder
from sklearn.tree import (
BaseDecisionTree,
DecisionTreeClassifier,
DecisionTreeRegressor,
ExtraTreeClassifier,
ExtraTreeRegressor,
)
from sklearn.tree._tree import DOUBLE, DTYPE
from sklearn.utils import (
check_random_state,
compute_class_weight,
compute_sample_weight,
)
from sklearn.utils._param_validation import Interval, RealNotInt, StrOptions
from sklearn.utils._tags import get_tags
from sklearn.utils.multiclass import check_classification_targets, type_of_target
from sklearn.utils.parallel import Parallel, delayed
from sklearn.utils.validation import (
_check_feature_names_in,
_check_sample_weight,
_num_samples,
check_is_fitted,
validate_data,
)
__all__ = [
"ExtraTreesClassifier",
"ExtraTreesRegressor",
"RandomForestClassifier",
"RandomForestRegressor",
"RandomTreesEmbedding",
]
MAX_INT = np.iinfo(np.int32).max
def _generate_sample_indices(
random_state, n_samples, n_samples_bootstrap, sample_weight
):
"""
Private function used to _parallel_build_trees function."""
random_instance = check_random_state(random_state)
if sample_weight is None:
sample_indices = random_instance.randint(0, n_samples, n_samples_bootstrap)
else:
normalized_sample_weight = sample_weight / np.sum(sample_weight)
sample_indices = random_instance.choice(
n_samples,
n_samples_bootstrap,
replace=True,
p=normalized_sample_weight,
)
sample_indices = sample_indices.astype(np.int32)
return sample_indices
def _generate_unsampled_indices(
random_state, n_samples, n_samples_bootstrap, sample_weight
):
"""
Private function used to forest._set_oob_score function."""
sample_indices = _generate_sample_indices(
random_state, n_samples, n_samples_bootstrap, sample_weight
)
sample_counts = np.bincount(sample_indices, minlength=n_samples)
unsampled_mask = sample_counts == 0
indices_range = np.arange(n_samples)
unsampled_indices = indices_range[unsampled_mask]
return unsampled_indices
def _parallel_build_trees(
tree,
bootstrap,
X,
y,
sample_weight,
tree_idx,
n_trees,
verbose=0,
class_weight=None,
n_samples_bootstrap=None,
missing_values_in_feature_mask=None,
):
"""
Private function used to fit a single tree in parallel."""
if verbose > 1:
print("building tree %d of %d" % (tree_idx + 1, n_trees))
if bootstrap:
n_samples = X.shape[0]
indices = _generate_sample_indices(
tree.random_state, n_samples, n_samples_bootstrap, sample_weight
)
# Simulate row-wise sampling by passing counts as sample_weight in trees.
sample_weight_tree = np.bincount(indices, minlength=n_samples)
if class_weight == "balanced_subsample":
expanded_class_weight = compute_sample_weight(
"balanced", y, indices=indices
)
sample_weight_tree = sample_weight_tree * expanded_class_weight
tree._fit(
X,
y,
sample_weight=sample_weight_tree,
check_input=False,
missing_values_in_feature_mask=missing_values_in_feature_mask,
)
else:
tree._fit(
X,
y,
sample_weight=sample_weight,
check_input=False,
missing_values_in_feature_mask=missing_values_in_feature_mask,
)
return tree
class BaseForest(MultiOutputMixin, BaseEnsemble, metaclass=ABCMeta):
"""
Base class for forests of trees.
Warning: This class should not be used directly. Use derived classes
instead.
"""
_parameter_constraints: dict = {
"n_estimators": [Interval(Integral, 1, None, closed="left")],
"bootstrap": ["boolean"],
"oob_score": ["boolean", callable],
"n_jobs": [Integral, None],
"random_state": ["random_state"],
"verbose": ["verbose"],
"warm_start": ["boolean"],
"max_samples": [
None,
Interval(RealNotInt, 0.0, None, closed="neither"),
Interval(Integral, 1, None, closed="left"),
],
}
@abstractmethod
def __init__(
self,
estimator,
n_estimators=100,
*,
estimator_params=tuple(),
bootstrap=False,
oob_score=False,
n_jobs=None,
random_state=None,
verbose=0,
warm_start=False,
class_weight=None,
max_samples=None,
):
super().__init__(
estimator=estimator,
n_estimators=n_estimators,
estimator_params=estimator_params,
)
self.bootstrap = bootstrap
self.oob_score = oob_score
self.n_jobs = n_jobs
self.random_state = random_state
self.verbose = verbose
self.warm_start = warm_start
self.class_weight = class_weight
self.max_samples = max_samples
def apply(self, X):
"""
Apply trees in the forest to X, return leaf indices.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The input samples. Internally, its dtype will be converted to
``dtype=np.float32``. If a sparse matrix is provided, it will be
converted into a sparse ``csr_matrix``.
Returns
-------
X_leaves : ndarray of shape (n_samples, n_estimators)
For each datapoint x in X and for each tree in the forest,
return the index of the leaf x ends up in.
"""
X = self._validate_X_predict(X)
results = Parallel(
n_jobs=self.n_jobs,
verbose=self.verbose,
prefer="threads",
)(delayed(tree.apply)(X, check_input=False) for tree in self.estimators_)
return np.array(results).T
def decision_path(self, X):
"""
Return the decision path in the forest.
.. versionadded:: 0.18
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The input samples. Internally, its dtype will be converted to
``dtype=np.float32``. If a sparse matrix is provided, it will be
converted into a sparse ``csr_matrix``.
Returns
-------
indicator : sparse matrix of shape (n_samples, n_nodes)
Return a node indicator matrix where non zero elements indicates
that the samples goes through the nodes. The matrix is of CSR
format.
n_nodes_ptr : ndarray of shape (n_estimators + 1,)
The columns from indicator[n_nodes_ptr[i]:n_nodes_ptr[i+1]]
gives the indicator value for the i-th estimator.
"""
X = self._validate_X_predict(X)
indicators = Parallel(
n_jobs=self.n_jobs,
verbose=self.verbose,
prefer="threads",
)(
delayed(tree.decision_path)(X, check_input=False)
for tree in self.estimators_
)
n_nodes = [0]
n_nodes.extend([i.shape[1] for i in indicators])
n_nodes_ptr = np.array(n_nodes).cumsum()
return sparse_hstack(indicators).tocsr(), n_nodes_ptr
@_fit_context(prefer_skip_nested_validation=True)
def fit(self, X, y, sample_weight=None):
"""
Build a forest of trees from the training set (X, y).
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The training input samples. Internally, its dtype will be converted
to ``dtype=np.float32``. If a sparse matrix is provided, it will be
converted into a sparse ``csc_matrix``.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The target values (class labels in classification, real numbers in
regression).
sample_weight : array-like of shape (n_samples,), default=None
Sample weights. If None, then samples are equally weighted. Splits
that would create child nodes with net zero or negative weight are
ignored while searching for a split in each node. In the case of
classification, splits are also ignored if they would result in any
single class carrying a negative weight in either child node.
Returns
-------
self : object
Fitted estimator.
"""
# Validate or convert input data
if issparse(y):
raise ValueError("sparse multilabel-indicator for y is not supported.")
X, y = validate_data(
self,
X,
y,
multi_output=True,
accept_sparse="csc",
dtype=DTYPE,
ensure_all_finite=False,
)
# _compute_missing_values_in_feature_mask checks if X has missing values and
# will raise an error if the underlying tree base estimator can't handle missing
# values. Only the criterion is required to determine if the tree supports
# missing values.
estimator = type(self.estimator)(criterion=self.criterion)
missing_values_in_feature_mask = (
estimator._compute_missing_values_in_feature_mask(
X, estimator_name=self.__class__.__name__
)
)
if sample_weight is not None:
sample_weight = _check_sample_weight(sample_weight, X)
if issparse(X):
# Pre-sort indices to avoid that each individual tree of the
# ensemble sorts the indices.
X.sort_indices()
y = np.atleast_1d(y)
if y.ndim == 2 and y.shape[1] == 1:
warn(
(
"A column-vector y was passed when a 1d array was"
" expected. Please change the shape of y to "
"(n_samples,), for example using ravel()."
),
DataConversionWarning,
stacklevel=2,
)
if y.ndim == 1:
# reshape is necessary to preserve the data contiguity against vs
# [:, np.newaxis] that does not.
y = np.reshape(y, (-1, 1))
if self.criterion == "poisson":
if np.any(y < 0):
raise ValueError(
"Some value(s) of y are negative which is "
"not allowed for Poisson regression."
)
if np.sum(y) <= 0:
raise ValueError(
"Sum of y is not strictly positive which "
"is necessary for Poisson regression."
)
self._n_samples, self.n_outputs_ = y.shape
y, expanded_class_weight = self._validate_y_class_weight(y, sample_weight)
if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous:
y = np.ascontiguousarray(y, dtype=DOUBLE)
# Combined _sample_weight = sample_weight * expanded_class_weight
# (when provided) used in _parallel_build_trees to draw indices
# (bootstrap=True) or passed to the trees (bootstrap=False).
if sample_weight is None:
_sample_weight = expanded_class_weight
elif expanded_class_weight is None:
_sample_weight = sample_weight
else:
_sample_weight = sample_weight * expanded_class_weight
# Storing _sample_weight (needed by _get_estimators_indices).
self._sample_weight = _sample_weight
if not self.bootstrap and self.max_samples is not None:
raise ValueError(
"`max_sample` cannot be set if `bootstrap=False`. "
"Either switch to `bootstrap=True` or set "
"`max_sample=None`."
)
elif self.bootstrap:
n_samples_bootstrap = _get_n_samples_bootstrap(
X.shape[0], self.max_samples, _sample_weight
)
else:
n_samples_bootstrap = None
self._n_samples_bootstrap = n_samples_bootstrap
self._validate_estimator()
if not self.bootstrap and self.oob_score:
raise ValueError("Out of bag estimation only available if bootstrap=True")
random_state = check_random_state(self.random_state)
if not self.warm_start or not hasattr(self, "estimators_"):
# Free allocated memory, if any
self.estimators_ = []
n_more_estimators = self.n_estimators - len(self.estimators_)
if n_more_estimators < 0:
raise ValueError(
"n_estimators=%d must be larger or equal to "
"len(estimators_)=%d when warm_start==True"
% (self.n_estimators, len(self.estimators_))
)
elif n_more_estimators == 0:
warn(
"Warm-start fitting without increasing n_estimators does not "
"fit new trees."
)
else:
if self.warm_start and len(self.estimators_) > 0:
# We draw from the random state to get the random state we
# would have got if we hadn't used a warm_start.
random_state.randint(MAX_INT, size=len(self.estimators_))
trees = [
self._make_estimator(append=False, random_state=random_state)
for i in range(n_more_estimators)
]
# Parallel loop: we prefer the threading backend as the Cython code
# for fitting the trees is internally releasing the Python GIL
# making threading more efficient than multiprocessing in
# that case. However, for joblib 0.12+ we respect any
# parallel_backend contexts set at a higher level,
# since correctness does not rely on using threads.
trees = Parallel(
n_jobs=self.n_jobs,
verbose=self.verbose,
prefer="threads",
)(
delayed(_parallel_build_trees)(
t,
self.bootstrap,
X,
y,
_sample_weight,
i,
len(trees),
verbose=self.verbose,
class_weight=self.class_weight,
n_samples_bootstrap=n_samples_bootstrap,
missing_values_in_feature_mask=missing_values_in_feature_mask,
)
for i, t in enumerate(trees)
)
# Collect newly grown trees
self.estimators_.extend(trees)
if self.oob_score and (
n_more_estimators > 0 or not hasattr(self, "oob_score_")
):
y_type = type_of_target(y)
if y_type == "unknown" or (
is_classifier(self) and y_type == "multiclass-multioutput"
):
# FIXME: we could consider to support multiclass-multioutput if
# we introduce or reuse a constructor parameter (e.g.
# oob_score) allowing our user to pass a callable defining the
# scoring strategy on OOB sample.
raise ValueError(
"The type of target cannot be used to compute OOB "
f"estimates. Got {y_type} while only the following are "
"supported: continuous, continuous-multioutput, binary, "
"multiclass, multilabel-indicator."
)
if callable(self.oob_score):
self._set_oob_score_and_attributes(
X, y, scoring_function=self.oob_score
)
else:
self._set_oob_score_and_attributes(X, y)
# Decapsulate classes_ attributes
if hasattr(self, "classes_") and self.n_outputs_ == 1:
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
return self
@abstractmethod
def _set_oob_score_and_attributes(self, X, y, scoring_function=None):
"""Compute and set the OOB score and attributes.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The data matrix.
y : ndarray of shape (n_samples, n_outputs)
The target matrix.
scoring_function : callable, default=None
Scoring function for OOB score. Default depends on whether
this is a regression (R2 score) or classification problem
(accuracy score).
"""
def _compute_oob_predictions(self, X, y):
"""Compute and set the OOB score.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The data matrix.
y : ndarray of shape (n_samples, n_outputs)
The target matrix.
Returns
-------
oob_pred : ndarray of shape (n_samples, n_classes, n_outputs) or \
(n_samples, 1, n_outputs)
The OOB predictions.
"""
# Prediction requires X to be in CSR format
if issparse(X):
X = X.tocsr()
n_samples = y.shape[0]
n_outputs = self.n_outputs_
if is_classifier(self) and hasattr(self, "n_classes_"):
# n_classes_ is an ndarray at this stage
# all the supported type of target will have the same number of
# classes in all outputs
oob_pred_shape = (n_samples, self.n_classes_[0], n_outputs)
else:
# for regression, n_classes_ does not exist and we create an empty
# axis to be consistent with the classification case and make
# the array operations compatible with the 2 settings
oob_pred_shape = (n_samples, 1, n_outputs)
oob_pred = np.zeros(shape=oob_pred_shape, dtype=np.float64)
n_oob_pred = np.zeros((n_samples, n_outputs), dtype=np.int64)
for estimator in self.estimators_:
unsampled_indices = _generate_unsampled_indices(
estimator.random_state,
n_samples,
self._n_samples_bootstrap,
self._sample_weight,
)
y_pred = self._get_oob_predictions(estimator, X[unsampled_indices, :])
oob_pred[unsampled_indices, ...] += y_pred
n_oob_pred[unsampled_indices, :] += 1
for k in range(n_outputs):
if (n_oob_pred == 0).any():
warn(
(
"Some inputs do not have OOB scores. This probably means "
"too few trees were used to compute any reliable OOB "
"estimates."
),
UserWarning,
)
n_oob_pred[n_oob_pred == 0] = 1
oob_pred[..., k] /= n_oob_pred[..., [k]]
return oob_pred
def _validate_y_class_weight(self, y, sample_weight):
# Default implementation
return y, None
def _validate_X_predict(self, X):
"""
Validate X whenever one tries to predict, apply, predict_proba."""
check_is_fitted(self)
if self.estimators_[0]._support_missing_values(X):
ensure_all_finite = "allow-nan"
else:
ensure_all_finite = True
X = validate_data(
self,
X,
dtype=DTYPE,
accept_sparse="csr",
reset=False,
ensure_all_finite=ensure_all_finite,
)
if issparse(X) and (X.indices.dtype != np.intc or X.indptr.dtype != np.intc):
raise ValueError("No support for np.int64 index based sparse matrices")
return X
@property
def feature_importances_(self):
"""
The impurity-based feature importances.
The higher, the more important the feature.
The importance of a feature is computed as the (normalized)
total reduction of the criterion brought by that feature. It is also
known as the Gini importance.
Warning: impurity-based feature importances can be misleading for
high cardinality features (many unique values). See
:func:`sklearn.inspection.permutation_importance` as an alternative.
Returns
-------
feature_importances_ : ndarray of shape (n_features,)
The values of this array sum to 1, unless all trees are single node
trees consisting of only the root node, in which case it will be an
array of zeros.
"""
check_is_fitted(self)
all_importances = Parallel(n_jobs=self.n_jobs, prefer="threads")(
delayed(getattr)(tree, "feature_importances_")
for tree in self.estimators_
if tree.tree_.node_count > 1
)
if not all_importances:
return np.zeros(self.n_features_in_, dtype=np.float64)
all_importances = np.mean(all_importances, axis=0, dtype=np.float64)
return all_importances / np.sum(all_importances)
def _get_estimators_indices(self):
# Get drawn indices along both sample and feature axes
for tree in self.estimators_:
if not self.bootstrap:
yield np.arange(self._n_samples, dtype=np.int32)
else:
# tree.random_state is actually an immutable integer seed rather
# than a mutable RandomState instance, so it's safe to use it
# repeatedly when calling this property.
seed = tree.random_state
# Operations accessing random_state must be performed identically
# to those in `_parallel_build_trees()`
yield _generate_sample_indices(
seed,
self._n_samples,
self._n_samples_bootstrap,
self._sample_weight,
)
@property
def estimators_samples_(self):
"""The subset of drawn samples for each base estimator.
Returns a dynamically generated list of indices identifying
the samples used for fitting each member of the ensemble, i.e.,
the in-bag samples.
Note: the list is re-created at each call to the property in order
to reduce the object memory footprint by not storing the sampling
data. Thus fetching the property may be slower than expected.
"""
return [sample_indices for sample_indices in self._get_estimators_indices()]
def __sklearn_tags__(self):
tags = super().__sklearn_tags__()
# Only the criterion is required to determine if the tree supports
# missing values
estimator = type(self.estimator)(criterion=self.criterion)
tags.input_tags.allow_nan = get_tags(estimator).input_tags.allow_nan
return tags
def _accumulate_prediction(predict, X, out, lock):
"""
This is a utility function for joblib's Parallel.
It can't go locally in ForestClassifier or ForestRegressor, because joblib
complains that it cannot pickle it when placed there.
"""
prediction = predict(X, check_input=False)
with lock:
if len(out) == 1:
out[0] += prediction
else:
for i in range(len(out)):
out[i] += prediction[i]
class ForestClassifier(ClassifierMixin, BaseForest, metaclass=ABCMeta):
"""
Base class for forest of trees-based classifiers.
Warning: This class should not be used directly. Use derived classes
instead.
"""
@abstractmethod
def __init__(
self,
estimator,
n_estimators=100,
*,
estimator_params=tuple(),
bootstrap=False,
oob_score=False,
n_jobs=None,
random_state=None,
verbose=0,
warm_start=False,
class_weight=None,
max_samples=None,
):
super().__init__(
estimator=estimator,
n_estimators=n_estimators,
estimator_params=estimator_params,
bootstrap=bootstrap,
oob_score=oob_score,
n_jobs=n_jobs,
random_state=random_state,
verbose=verbose,
warm_start=warm_start,
class_weight=class_weight,
max_samples=max_samples,
)
@staticmethod
def _get_oob_predictions(tree, X):
"""Compute the OOB predictions for an individual tree.
Parameters
----------
tree : DecisionTreeClassifier object
A single decision tree classifier.
X : ndarray of shape (n_samples, n_features)
The OOB samples.
Returns
-------
y_pred : ndarray of shape (n_samples, n_classes, n_outputs)
The OOB associated predictions.
"""
y_pred = tree.predict_proba(X, check_input=False)
y_pred = np.asarray(y_pred)
if y_pred.ndim == 2:
# binary and multiclass
y_pred = y_pred[..., np.newaxis]
else:
# Roll the first `n_outputs` axis to the last axis. We will reshape
# from a shape of (n_outputs, n_samples, n_classes) to a shape of
# (n_samples, n_classes, n_outputs).
y_pred = np.rollaxis(y_pred, axis=0, start=3)
return y_pred
def _set_oob_score_and_attributes(self, X, y, scoring_function=None):
"""Compute and set the OOB score and attributes.
Parameters
----------
X : array-like of shape (n_samples, n_features)
The data matrix.
y : ndarray of shape (n_samples, n_outputs)
The target matrix.
scoring_function : callable, default=None
Scoring function for OOB score. Defaults to `accuracy_score`.
"""
self.oob_decision_function_ = super()._compute_oob_predictions(X, y)
if self.oob_decision_function_.shape[-1] == 1:
# drop the n_outputs axis if there is a single output
self.oob_decision_function_ = self.oob_decision_function_.squeeze(axis=-1)
if scoring_function is None:
scoring_function = accuracy_score
self.oob_score_ = scoring_function(
y, np.argmax(self.oob_decision_function_, axis=1)
)
def _validate_y_class_weight(self, y, sample_weight):
check_classification_targets(y)
y_original = np.copy(y)
self.classes_ = []
self.n_classes_ = []
y_store_unique_indices = np.zeros(y.shape, dtype=int)
for k in range(self.n_outputs_):
classes_k, y_store_unique_indices[:, k] = np.unique(
y[:, k], return_inverse=True
)
self.classes_.append(classes_k)
self.n_classes_.append(classes_k.shape[0])
y = y_store_unique_indices
if self.class_weight is None:
return y, None
# User defined class_weight (dict or list)
if isinstance(self.class_weight, (dict, list)):
expanded_class_weight = compute_sample_weight(self.class_weight, y_original)
return y, expanded_class_weight
# Checking class_weight options
valid_presets = ("balanced", "balanced_subsample")
if self.class_weight not in valid_presets:
raise ValueError(
"Valid presets for class_weight include "
'"balanced" and "balanced_subsample".'
'Given "%s".' % self.class_weight
)
if self.warm_start:
warn(
'class_weight presets "balanced" or '
'"balanced_subsample" are '
"not recommended for warm_start if the fitted data "
"differs from the full dataset. In order to use "
'"balanced" weights, use compute_class_weight '
'("balanced", classes, y). In place of y you can use '
"a large enough sample of the full training set "
"target to properly estimate the class frequency "
"distributions. Pass the resulting weights as the "
"class_weight parameter."
)
# "balanced_subsample" option with subsampling (bootstrap=True)
if self.class_weight == "balanced_subsample" and self.bootstrap:
# class_weight will be computed on the bootstrap sample
return y, None
# Computing class_weight (dict or list) for the "balanced" option.
# The "balanced_subsample" option without subsampling (bootstrap=False)
# is equivalent to the "balanced" option.
class_weight = []
for k in range(self.n_outputs_):
class_weight_k_vect = compute_class_weight(
"balanced",
classes=self.classes_[k],
y=y_original[:, k],
sample_weight=sample_weight,
)
class_weight_k = {
key: val for (key, val) in zip(self.classes_[k], class_weight_k_vect)
}
class_weight.append(class_weight_k)
if self.n_outputs_ == 1:
class_weight = class_weight[0]
expanded_class_weight = compute_sample_weight(class_weight, y_original)
return y, expanded_class_weight
def predict(self, X):
"""
Predict class for X.
The predicted class of an input sample is a vote by the trees in
the forest, weighted by their probability estimates. That is,
the predicted class is the one with highest mean probability
estimate across the trees.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The input samples. Internally, its dtype will be converted to
``dtype=np.float32``. If a sparse matrix is provided, it will be
converted into a sparse ``csr_matrix``.
Returns
-------
y : ndarray of shape (n_samples,) or (n_samples, n_outputs)
The predicted classes.
"""
proba = self.predict_proba(X)
if self.n_outputs_ == 1:
return self.classes_.take(np.argmax(proba, axis=1), axis=0)
else:
n_samples = proba[0].shape[0]
# all dtypes should be the same, so just take the first
class_type = self.classes_[0].dtype
predictions = np.empty((n_samples, self.n_outputs_), dtype=class_type)
for k in range(self.n_outputs_):
predictions[:, k] = self.classes_[k].take(
np.argmax(proba[k], axis=1), axis=0
)
return predictions
def predict_proba(self, X):
"""
Predict class probabilities for X.
The predicted class probabilities of an input sample are computed as
the mean predicted class probabilities of the trees in the forest.
The class probability of a single tree is the fraction of samples of
the same class in a leaf.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The input samples. Internally, its dtype will be converted to
``dtype=np.float32``. If a sparse matrix is provided, it will be
converted into a sparse ``csr_matrix``.
Returns
-------
p : ndarray of shape (n_samples, n_classes), or a list of such arrays
The class probabilities of the input samples. The order of the
classes corresponds to that in the attribute :term:`classes_`.
"""
check_is_fitted(self)
# Check data
X = self._validate_X_predict(X)
# Assign chunk of trees to jobs
n_jobs, _, _ = _partition_estimators(self.n_estimators, self.n_jobs)
# avoid storing the output of every estimator by summing them here
all_proba = [
np.zeros((X.shape[0], j), dtype=np.float64)
for j in np.atleast_1d(self.n_classes_)
]
lock = threading.Lock()
Parallel(n_jobs=n_jobs, verbose=self.verbose, require="sharedmem")(
delayed(_accumulate_prediction)(e.predict_proba, X, all_proba, lock)
for e in self.estimators_
)
for proba in all_proba:
proba /= len(self.estimators_)
if len(all_proba) == 1:
return all_proba[0]
else:
return all_proba
def predict_log_proba(self, X):
"""
Predict class log-probabilities for X.
The predicted class log-probabilities of an input sample is computed as
the log of the mean predicted class probabilities of the trees in the
forest.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The input samples. Internally, its dtype will be converted to
``dtype=np.float32``. If a sparse matrix is provided, it will be
converted into a sparse ``csr_matrix``.
Returns
-------
p : ndarray of shape (n_samples, n_classes), or a list of such arrays
The class probabilities of the input samples. The order of the
classes corresponds to that in the attribute :term:`classes_`.
"""
proba = self.predict_proba(X)
if self.n_outputs_ == 1:
return np.log(proba)
else:
for k in range(self.n_outputs_):
proba[k] = np.log(proba[k])
return proba