-
-
Notifications
You must be signed in to change notification settings - Fork 27k
Expand file tree
/
Copy path_classes.py
More file actions
1842 lines (1500 loc) · 69.6 KB
/
_classes.py
File metadata and controls
1842 lines (1500 loc) · 69.6 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
"""
This module gathers tree-based methods, including decision, regression and
randomized trees. Single and multi-output problems are both handled.
"""
# Authors: Gilles Louppe <g.louppe@gmail.com>
# Peter Prettenhofer <peter.prettenhofer@gmail.com>
# Brian Holt <bdholt1@gmail.com>
# Noel Dawe <noel@dawe.me>
# Satrajit Gosh <satrajit.ghosh@gmail.com>
# Joly Arnaud <arnaud.v.joly@gmail.com>
# Fares Hedayati <fares.hedayati@gmail.com>
# Nelson Liu <nelson@nelsonliu.me>
#
# License: BSD 3 clause
import copy
import numbers
import warnings
from abc import ABCMeta, abstractmethod
from math import ceil
from numbers import Integral, Real
import numpy as np
from scipy.sparse import issparse
from ..base import (
BaseEstimator,
ClassifierMixin,
MultiOutputMixin,
RegressorMixin,
_fit_context,
clone,
is_classifier,
)
from ..utils import Bunch, check_random_state, compute_sample_weight
from ..utils._param_validation import Hidden, Interval, RealNotInt, StrOptions
from ..utils.multiclass import check_classification_targets
from ..utils.validation import (
_assert_all_finite_element_wise,
_check_sample_weight,
assert_all_finite,
check_is_fitted,
)
from . import _criterion, _splitter, _tree
from ._criterion import Criterion
from ._splitter import Splitter
from ._tree import (
BestFirstTreeBuilder,
DepthFirstTreeBuilder,
Tree,
_build_pruned_tree_ccp,
ccp_pruning_path,
)
from ._utils import _any_isnan_axis0
__all__ = [
"DecisionTreeClassifier",
"DecisionTreeRegressor",
"ExtraTreeClassifier",
"ExtraTreeRegressor",
]
# =============================================================================
# Types and constants
# =============================================================================
DTYPE = _tree.DTYPE
DOUBLE = _tree.DOUBLE
CRITERIA_CLF = {
"gini": _criterion.Gini,
"log_loss": _criterion.Entropy,
"entropy": _criterion.Entropy,
}
CRITERIA_REG = {
"squared_error": _criterion.MSE,
"friedman_mse": _criterion.FriedmanMSE,
"absolute_error": _criterion.MAE,
"poisson": _criterion.Poisson,
}
DENSE_SPLITTERS = {"best": _splitter.BestSplitter, "random": _splitter.RandomSplitter}
SPARSE_SPLITTERS = {
"best": _splitter.BestSparseSplitter,
"random": _splitter.RandomSparseSplitter,
}
# =============================================================================
# Base decision tree
# =============================================================================
class BaseDecisionTree(MultiOutputMixin, BaseEstimator, metaclass=ABCMeta):
"""Base class for decision trees.
Warning: This class should not be used directly.
Use derived classes instead.
"""
_parameter_constraints: dict = {
"splitter": [StrOptions({"best", "random"})],
"max_depth": [Interval(Integral, 1, None, closed="left"), None],
"min_samples_split": [
Interval(Integral, 2, None, closed="left"),
Interval(RealNotInt, 0.0, 1.0, closed="right"),
],
"min_samples_leaf": [
Interval(Integral, 1, None, closed="left"),
Interval(RealNotInt, 0.0, 1.0, closed="neither"),
],
"min_weight_fraction_leaf": [Interval(Real, 0.0, 0.5, closed="both")],
"max_features": [
Interval(Integral, 1, None, closed="left"),
Interval(RealNotInt, 0.0, 1.0, closed="right"),
StrOptions({"sqrt", "log2"}),
None,
],
"random_state": ["random_state"],
"max_leaf_nodes": [Interval(Integral, 2, None, closed="left"), None],
"min_impurity_decrease": [Interval(Real, 0.0, None, closed="left")],
"ccp_alpha": [Interval(Real, 0.0, None, closed="left")],
}
@abstractmethod
def __init__(
self,
*,
criterion,
splitter,
max_depth,
min_samples_split,
min_samples_leaf,
min_weight_fraction_leaf,
max_features,
max_leaf_nodes,
random_state,
min_impurity_decrease,
class_weight=None,
ccp_alpha=0.0,
):
self.criterion = criterion
self.splitter = splitter
self.max_depth = max_depth
self.min_samples_split = min_samples_split
self.min_samples_leaf = min_samples_leaf
self.min_weight_fraction_leaf = min_weight_fraction_leaf
self.max_features = max_features
self.max_leaf_nodes = max_leaf_nodes
self.random_state = random_state
self.min_impurity_decrease = min_impurity_decrease
self.class_weight = class_weight
self.ccp_alpha = ccp_alpha
def get_depth(self):
"""Return the depth of the decision tree.
The depth of a tree is the maximum distance between the root
and any leaf.
Returns
-------
self.tree_.max_depth : int
The maximum depth of the tree.
"""
check_is_fitted(self)
return self.tree_.max_depth
def get_n_leaves(self):
"""Return the number of leaves of the decision tree.
Returns
-------
self.tree_.n_leaves : int
Number of leaves.
"""
check_is_fitted(self)
return self.tree_.n_leaves
def _support_missing_values(self, X):
return not issparse(X) and self._get_tags()["allow_nan"]
def _compute_missing_values_in_feature_mask(self, X):
"""Return boolean mask denoting if there are missing values for each feature.
This method also ensures that X is finite.
Parameter
---------
X : array-like of shape (n_samples, n_features), dtype=DOUBLE
Input data.
Returns
-------
missing_values_in_feature_mask : ndarray of shape (n_features,), or None
Missing value mask. If missing values are not supported or there
are no missing values, return None.
"""
common_kwargs = dict(estimator_name=self.__class__.__name__, input_name="X")
if not self._support_missing_values(X):
assert_all_finite(X, **common_kwargs)
return None
with np.errstate(over="ignore"):
overall_sum = np.sum(X)
if not np.isfinite(overall_sum):
# Raise a ValueError in case of the presence of an infinite element.
_assert_all_finite_element_wise(X, xp=np, allow_nan=True, **common_kwargs)
# If the sum is not nan, then there are no missing values
if not np.isnan(overall_sum):
return None
missing_values_in_feature_mask = _any_isnan_axis0(X)
return missing_values_in_feature_mask
def _fit(
self,
X,
y,
sample_weight=None,
check_input=True,
missing_values_in_feature_mask=None,
):
random_state = check_random_state(self.random_state)
if check_input:
# Need to validate separately here.
# We can't pass multi_output=True because that would allow y to be
# csr.
# _compute_missing_values_in_feature_mask will check for finite values and
# compute the missing mask if the tree supports missing values
check_X_params = dict(
dtype=DTYPE, accept_sparse="csc", force_all_finite=False
)
check_y_params = dict(ensure_2d=False, dtype=None)
X, y = self._validate_data(
X, y, validate_separately=(check_X_params, check_y_params)
)
missing_values_in_feature_mask = (
self._compute_missing_values_in_feature_mask(X)
)
if issparse(X):
X.sort_indices()
if X.indices.dtype != np.intc or X.indptr.dtype != np.intc:
raise ValueError(
"No support for np.int64 index based sparse matrices"
)
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 positive which is "
"necessary for Poisson regression."
)
# Determine output settings
n_samples, self.n_features_in_ = X.shape
is_classification = is_classifier(self)
y = np.atleast_1d(y)
expanded_class_weight = None
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))
self.n_outputs_ = y.shape[1]
if is_classification:
check_classification_targets(y)
y = np.copy(y)
self.classes_ = []
self.n_classes_ = []
if self.class_weight is not None:
y_original = np.copy(y)
y_encoded = np.zeros(y.shape, dtype=int)
for k in range(self.n_outputs_):
classes_k, y_encoded[:, k] = np.unique(y[:, k], return_inverse=True)
self.classes_.append(classes_k)
self.n_classes_.append(classes_k.shape[0])
y = y_encoded
if self.class_weight is not None:
expanded_class_weight = compute_sample_weight(
self.class_weight, y_original
)
self.n_classes_ = np.array(self.n_classes_, dtype=np.intp)
if getattr(y, "dtype", None) != DOUBLE or not y.flags.contiguous:
y = np.ascontiguousarray(y, dtype=DOUBLE)
max_depth = np.iinfo(np.int32).max if self.max_depth is None else self.max_depth
if isinstance(self.min_samples_leaf, numbers.Integral):
min_samples_leaf = self.min_samples_leaf
else: # float
min_samples_leaf = int(ceil(self.min_samples_leaf * n_samples))
if isinstance(self.min_samples_split, numbers.Integral):
min_samples_split = self.min_samples_split
else: # float
min_samples_split = int(ceil(self.min_samples_split * n_samples))
min_samples_split = max(2, min_samples_split)
min_samples_split = max(min_samples_split, 2 * min_samples_leaf)
if isinstance(self.max_features, str):
if self.max_features == "auto":
if is_classification:
max_features = max(1, int(np.sqrt(self.n_features_in_)))
warnings.warn(
(
"`max_features='auto'` has been deprecated in 1.1 "
"and will be removed in 1.3. To keep the past behaviour, "
"explicitly set `max_features='sqrt'`."
),
FutureWarning,
)
else:
max_features = self.n_features_in_
warnings.warn(
(
"`max_features='auto'` has been deprecated in 1.1 "
"and will be removed in 1.3. To keep the past behaviour, "
"explicitly set `max_features=1.0'`."
),
FutureWarning,
)
elif self.max_features == "sqrt":
max_features = max(1, int(np.sqrt(self.n_features_in_)))
elif self.max_features == "log2":
max_features = max(1, int(np.log2(self.n_features_in_)))
elif self.max_features is None:
max_features = self.n_features_in_
elif isinstance(self.max_features, numbers.Integral):
max_features = self.max_features
else: # float
if self.max_features > 0.0:
max_features = max(1, int(self.max_features * self.n_features_in_))
else:
max_features = 0
self.max_features_ = max_features
max_leaf_nodes = -1 if self.max_leaf_nodes is None else self.max_leaf_nodes
if len(y) != n_samples:
raise ValueError(
"Number of labels=%d does not match number of samples=%d"
% (len(y), n_samples)
)
if sample_weight is not None:
sample_weight = _check_sample_weight(sample_weight, X, DOUBLE)
if expanded_class_weight is not None:
if sample_weight is not None:
sample_weight = sample_weight * expanded_class_weight
else:
sample_weight = expanded_class_weight
# Set min_weight_leaf from min_weight_fraction_leaf
if sample_weight is None:
min_weight_leaf = self.min_weight_fraction_leaf * n_samples
else:
min_weight_leaf = self.min_weight_fraction_leaf * np.sum(sample_weight)
# Build tree
criterion = self.criterion
if not isinstance(criterion, Criterion):
if is_classification:
criterion = CRITERIA_CLF[self.criterion](
self.n_outputs_, self.n_classes_
)
else:
criterion = CRITERIA_REG[self.criterion](self.n_outputs_, n_samples)
else:
# Make a deepcopy in case the criterion has mutable attributes that
# might be shared and modified concurrently during parallel fitting
criterion = copy.deepcopy(criterion)
SPLITTERS = SPARSE_SPLITTERS if issparse(X) else DENSE_SPLITTERS
splitter = self.splitter
if not isinstance(self.splitter, Splitter):
splitter = SPLITTERS[self.splitter](
criterion,
self.max_features_,
min_samples_leaf,
min_weight_leaf,
random_state,
)
if is_classifier(self):
self.tree_ = Tree(self.n_features_in_, self.n_classes_, self.n_outputs_)
else:
self.tree_ = Tree(
self.n_features_in_,
# TODO: tree shouldn't need this in this case
np.array([1] * self.n_outputs_, dtype=np.intp),
self.n_outputs_,
)
# Use BestFirst if max_leaf_nodes given; use DepthFirst otherwise
if max_leaf_nodes < 0:
builder = DepthFirstTreeBuilder(
splitter,
min_samples_split,
min_samples_leaf,
min_weight_leaf,
max_depth,
self.min_impurity_decrease,
)
else:
builder = BestFirstTreeBuilder(
splitter,
min_samples_split,
min_samples_leaf,
min_weight_leaf,
max_depth,
max_leaf_nodes,
self.min_impurity_decrease,
)
builder.build(self.tree_, X, y, sample_weight, missing_values_in_feature_mask)
if self.n_outputs_ == 1 and is_classifier(self):
self.n_classes_ = self.n_classes_[0]
self.classes_ = self.classes_[0]
self._prune_tree()
return self
def _validate_X_predict(self, X, check_input):
"""Validate the training data on predict (probabilities)."""
if check_input:
if self._support_missing_values(X):
force_all_finite = "allow-nan"
else:
force_all_finite = True
X = self._validate_data(
X,
dtype=DTYPE,
accept_sparse="csr",
reset=False,
force_all_finite=force_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")
else:
# The number of features is checked regardless of `check_input`
self._check_n_features(X, reset=False)
return X
def predict(self, X, check_input=True):
"""Predict class or regression value for X.
For a classification model, the predicted class for each sample in X is
returned. For a regression model, the predicted value based on X is
returned.
Parameters
----------
X : {array-like, 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``.
check_input : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
Returns
-------
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The predicted classes, or the predict values.
"""
check_is_fitted(self)
X = self._validate_X_predict(X, check_input)
proba = self.tree_.predict(X)
n_samples = X.shape[0]
# Classification
if is_classifier(self):
if self.n_outputs_ == 1:
return self.classes_.take(np.argmax(proba, axis=1), axis=0)
else:
class_type = self.classes_[0].dtype
predictions = np.zeros((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
# Regression
else:
if self.n_outputs_ == 1:
return proba[:, 0]
else:
return proba[:, :, 0]
def apply(self, X, check_input=True):
"""Return the index of the leaf that each sample is predicted as.
.. versionadded:: 0.17
Parameters
----------
X : {array-like, 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``.
check_input : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
Returns
-------
X_leaves : array-like of shape (n_samples,)
For each datapoint x in X, return the index of the leaf x
ends up in. Leaves are numbered within
``[0; self.tree_.node_count)``, possibly with gaps in the
numbering.
"""
check_is_fitted(self)
X = self._validate_X_predict(X, check_input)
return self.tree_.apply(X)
def decision_path(self, X, check_input=True):
"""Return the decision path in the tree.
.. versionadded:: 0.18
Parameters
----------
X : {array-like, 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``.
check_input : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
Returns
-------
indicator : sparse matrix of shape (n_samples, n_nodes)
Return a node indicator CSR matrix where non zero elements
indicates that the samples goes through the nodes.
"""
X = self._validate_X_predict(X, check_input)
return self.tree_.decision_path(X)
def _prune_tree(self):
"""Prune tree using Minimal Cost-Complexity Pruning."""
check_is_fitted(self)
if self.ccp_alpha == 0.0:
return
# build pruned tree
if is_classifier(self):
n_classes = np.atleast_1d(self.n_classes_)
pruned_tree = Tree(self.n_features_in_, n_classes, self.n_outputs_)
else:
pruned_tree = Tree(
self.n_features_in_,
# TODO: the tree shouldn't need this param
np.array([1] * self.n_outputs_, dtype=np.intp),
self.n_outputs_,
)
_build_pruned_tree_ccp(pruned_tree, self.tree_, self.ccp_alpha)
self.tree_ = pruned_tree
def cost_complexity_pruning_path(self, X, y, sample_weight=None):
"""Compute the pruning path during Minimal Cost-Complexity Pruning.
See :ref:`minimal_cost_complexity_pruning` for details on the pruning
process.
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The target values (class labels) as integers or strings.
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. Splits are also
ignored if they would result in any single class carrying a
negative weight in either child node.
Returns
-------
ccp_path : :class:`~sklearn.utils.Bunch`
Dictionary-like object, with the following attributes.
ccp_alphas : ndarray
Effective alphas of subtree during pruning.
impurities : ndarray
Sum of the impurities of the subtree leaves for the
corresponding alpha value in ``ccp_alphas``.
"""
est = clone(self).set_params(ccp_alpha=0.0)
est.fit(X, y, sample_weight=sample_weight)
return Bunch(**ccp_pruning_path(est.tree_))
@property
def feature_importances_(self):
"""Return the feature importances.
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,)
Normalized total reduction of criteria by feature
(Gini importance).
"""
check_is_fitted(self)
return self.tree_.compute_feature_importances()
# =============================================================================
# Public estimators
# =============================================================================
class DecisionTreeClassifier(ClassifierMixin, BaseDecisionTree):
"""A decision tree classifier.
Read more in the :ref:`User Guide <tree>`.
Parameters
----------
criterion : {"gini", "entropy", "log_loss"}, default="gini"
The function to measure the quality of a split. Supported criteria are
"gini" for the Gini impurity and "log_loss" and "entropy" both for the
Shannon information gain, see :ref:`tree_mathematical_formulation`.
splitter : {"best", "random"}, default="best"
The strategy used to choose the split at each node. Supported
strategies are "best" to choose the best split and "random" to choose
the best random split.
max_depth : int, default=None
The maximum depth of the tree. If None, then nodes are expanded until
all leaves are pure or until all leaves contain less than
min_samples_split samples.
min_samples_split : int or float, default=2
The minimum number of samples required to split an internal node:
- If int, then consider `min_samples_split` as the minimum number.
- If float, then `min_samples_split` is a fraction and
`ceil(min_samples_split * n_samples)` are the minimum
number of samples for each split.
.. versionchanged:: 0.18
Added float values for fractions.
min_samples_leaf : int or float, default=1
The minimum number of samples required to be at a leaf node.
A split point at any depth will only be considered if it leaves at
least ``min_samples_leaf`` training samples in each of the left and
right branches. This may have the effect of smoothing the model,
especially in regression.
- If int, then consider `min_samples_leaf` as the minimum number.
- If float, then `min_samples_leaf` is a fraction and
`ceil(min_samples_leaf * n_samples)` are the minimum
number of samples for each node.
.. versionchanged:: 0.18
Added float values for fractions.
min_weight_fraction_leaf : float, default=0.0
The minimum weighted fraction of the sum total of weights (of all
the input samples) required to be at a leaf node. Samples have
equal weight when sample_weight is not provided.
max_features : int, float or {"auto", "sqrt", "log2"}, default=None
The number of features to consider when looking for the best split:
- If int, then consider `max_features` features at each split.
- If float, then `max_features` is a fraction and
`max(1, int(max_features * n_features_in_))` features are considered at
each split.
- If "sqrt", then `max_features=sqrt(n_features)`.
- If "log2", then `max_features=log2(n_features)`.
- If None, then `max_features=n_features`.
Note: the search for a split does not stop until at least one
valid partition of the node samples is found, even if it requires to
effectively inspect more than ``max_features`` features.
random_state : int, RandomState instance or None, default=None
Controls the randomness of the estimator. The features are always
randomly permuted at each split, even if ``splitter`` is set to
``"best"``. When ``max_features < n_features``, the algorithm will
select ``max_features`` at random at each split before finding the best
split among them. But the best found split may vary across different
runs, even if ``max_features=n_features``. That is the case, if the
improvement of the criterion is identical for several splits and one
split has to be selected at random. To obtain a deterministic behaviour
during fitting, ``random_state`` has to be fixed to an integer.
See :term:`Glossary <random_state>` for details.
max_leaf_nodes : int, default=None
Grow a tree with ``max_leaf_nodes`` in best-first fashion.
Best nodes are defined as relative reduction in impurity.
If None then unlimited number of leaf nodes.
min_impurity_decrease : float, default=0.0
A node will be split if this split induces a decrease of the impurity
greater than or equal to this value.
The weighted impurity decrease equation is the following::
N_t / N * (impurity - N_t_R / N_t * right_impurity
- N_t_L / N_t * left_impurity)
where ``N`` is the total number of samples, ``N_t`` is the number of
samples at the current node, ``N_t_L`` is the number of samples in the
left child, and ``N_t_R`` is the number of samples in the right child.
``N``, ``N_t``, ``N_t_R`` and ``N_t_L`` all refer to the weighted sum,
if ``sample_weight`` is passed.
.. versionadded:: 0.19
class_weight : dict, list of dict or "balanced", default=None
Weights associated with classes in the form ``{class_label: weight}``.
If None, all classes are supposed to have weight one. For
multi-output problems, a list of dicts can be provided in the same
order as the columns of y.
Note that for multioutput (including multilabel) weights should be
defined for each class of every column in its own dict. For example,
for four-class multilabel classification weights should be
[{0: 1, 1: 1}, {0: 1, 1: 5}, {0: 1, 1: 1}, {0: 1, 1: 1}] instead of
[{1:1}, {2:5}, {3:1}, {4:1}].
The "balanced" mode uses the values of y to automatically adjust
weights inversely proportional to class frequencies in the input data
as ``n_samples / (n_classes * np.bincount(y))``
For multi-output, the weights of each column of y will be multiplied.
Note that these weights will be multiplied with sample_weight (passed
through the fit method) if sample_weight is specified.
ccp_alpha : non-negative float, default=0.0
Complexity parameter used for Minimal Cost-Complexity Pruning. The
subtree with the largest cost complexity that is smaller than
``ccp_alpha`` will be chosen. By default, no pruning is performed. See
:ref:`minimal_cost_complexity_pruning` for details.
.. versionadded:: 0.22
Attributes
----------
classes_ : ndarray of shape (n_classes,) or list of ndarray
The classes labels (single output problem),
or a list of arrays of class labels (multi-output problem).
feature_importances_ : ndarray of shape (n_features,)
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 [4]_.
Warning: impurity-based feature importances can be misleading for
high cardinality features (many unique values). See
:func:`sklearn.inspection.permutation_importance` as an alternative.
max_features_ : int
The inferred value of max_features.
n_classes_ : int or list of int
The number of classes (for single output problems),
or a list containing the number of classes for each
output (for multi-output problems).
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_outputs_ : int
The number of outputs when ``fit`` is performed.
tree_ : Tree instance
The underlying Tree object. Please refer to
``help(sklearn.tree._tree.Tree)`` for attributes of Tree object and
:ref:`sphx_glr_auto_examples_tree_plot_unveil_tree_structure.py`
for basic usage of these attributes.
See Also
--------
DecisionTreeRegressor : A decision tree regressor.
Notes
-----
The default values for the parameters controlling the size of the trees
(e.g. ``max_depth``, ``min_samples_leaf``, etc.) lead to fully grown and
unpruned trees which can potentially be very large on some data sets. To
reduce memory consumption, the complexity and size of the trees should be
controlled by setting those parameter values.
The :meth:`predict` method operates using the :func:`numpy.argmax`
function on the outputs of :meth:`predict_proba`. This means that in
case the highest predicted probabilities are tied, the classifier will
predict the tied class with the lowest index in :term:`classes_`.
References
----------
.. [1] https://en.wikipedia.org/wiki/Decision_tree_learning
.. [2] L. Breiman, J. Friedman, R. Olshen, and C. Stone, "Classification
and Regression Trees", Wadsworth, Belmont, CA, 1984.
.. [3] T. Hastie, R. Tibshirani and J. Friedman. "Elements of Statistical
Learning", Springer, 2009.
.. [4] L. Breiman, and A. Cutler, "Random Forests",
https://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm
Examples
--------
>>> from sklearn.datasets import load_iris
>>> from sklearn.model_selection import cross_val_score
>>> from sklearn.tree import DecisionTreeClassifier
>>> clf = DecisionTreeClassifier(random_state=0)
>>> iris = load_iris()
>>> cross_val_score(clf, iris.data, iris.target, cv=10)
... # doctest: +SKIP
...
array([ 1. , 0.93..., 0.86..., 0.93..., 0.93...,
0.93..., 0.93..., 1. , 0.93..., 1. ])
"""
_parameter_constraints: dict = {
**BaseDecisionTree._parameter_constraints,
"criterion": [StrOptions({"gini", "entropy", "log_loss"}), Hidden(Criterion)],
"class_weight": [dict, list, StrOptions({"balanced"}), None],
}
def __init__(
self,
*,
criterion="gini",
splitter="best",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.0,
max_features=None,
random_state=None,
max_leaf_nodes=None,
min_impurity_decrease=0.0,
class_weight=None,
ccp_alpha=0.0,
):
super().__init__(
criterion=criterion,
splitter=splitter,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
class_weight=class_weight,
random_state=random_state,
min_impurity_decrease=min_impurity_decrease,
ccp_alpha=ccp_alpha,
)
@_fit_context(prefer_skip_nested_validation=True)
def fit(self, X, y, sample_weight=None, check_input=True):
"""Build a decision tree classifier from the training set (X, y).
Parameters
----------
X : {array-like, sparse matrix} of shape (n_samples, n_features)
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like of shape (n_samples,) or (n_samples, n_outputs)
The target values (class labels) as integers or strings.
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. Splits are also
ignored if they would result in any single class carrying a
negative weight in either child node.
check_input : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
Returns
-------
self : DecisionTreeClassifier
Fitted estimator.
"""
super()._fit(
X,
y,
sample_weight=sample_weight,
check_input=check_input,
)
return self
def predict_proba(self, X, check_input=True):
"""Predict class probabilities of the input samples X.
The predicted class probability 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, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csr_matrix``.
check_input : bool, default=True
Allow to bypass several input checking.
Don't use this parameter unless you know what you're doing.
Returns
-------
proba : ndarray of shape (n_samples, n_classes) or list of n_outputs \
such arrays if n_outputs > 1
The class probabilities of the input samples. The order of the
classes corresponds to that in the attribute :term:`classes_`.
"""
check_is_fitted(self)
X = self._validate_X_predict(X, check_input)
proba = self.tree_.predict(X)
if self.n_outputs_ == 1:
proba = proba[:, : self.n_classes_]
normalizer = proba.sum(axis=1)[:, np.newaxis]
normalizer[normalizer == 0.0] = 1.0
proba /= normalizer