forked from hermidalc/sklearn-extensions
-
Notifications
You must be signed in to change notification settings - Fork 0
/
pipeline.py
1191 lines (1007 loc) · 44.2 KB
/
pipeline.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
"""
The :mod:`sklearn.pipeline` module implements utilities to build a composite
estimator, as a chain of transforms and estimators.
"""
# Author: Edouard Duchesnay
# Gael Varoquaux
# Virgile Fritsch
# Alexandre Gramfort
# Lars Buitinck
# Leandro Hermida
# License: BSD
from collections import defaultdict
from itertools import islice
import numpy as np
import pandas as pd
from scipy import sparse
from sklearn.base import clone
from sklearn.compose import ColumnTransformer
from sklearn.pipeline import FeatureUnion, Pipeline
from sklearn.utils._joblib import Parallel, delayed
from sklearn.utils import Bunch, _print_elapsed_time
from sklearn.utils.metaestimators import if_delegate_has_method
from .base import ExtendedTransformerMixin
from .utils.metaestimators import check_routing
from .utils.validation import check_memory
__all__ = ['ExtendedPipeline', 'ExtendedFeatureUnion',
'transform_feature_meta', 'make_extended_pipeline',
'make_extended_union']
class ExtendedPipeline(Pipeline):
"""Pipeline of transforms with a final estimator.
Sequentially apply a list of transforms and a final estimator.
Intermediate steps of the pipeline must be 'transforms', that is, they
must implement fit and transform methods.
The final estimator only needs to implement fit.
The transformers in the pipeline can be cached using ``memory`` argument.
The purpose of the pipeline is to assemble several steps that can be
cross-validated together while setting different parameters.
For this, it enables setting parameters of the various steps using their
names and the parameter name separated by a '__', as in the example below.
A step's estimator may be replaced entirely by setting the parameter
with its name to another estimator, or a transformer removed by setting
it to 'passthrough' or ``None``.
Read more in the :ref:`User Guide <pipeline>`.
.. versionadded:: 0.5
Parameters
----------
steps : list
List of (name, transform) tuples (implementing fit/transform) that are
chained, in the order in which they are chained, with the last object
an estimator.
memory : None, str or object with the joblib.Memory interface, optional
Used to cache the fitted transformers of the pipeline. By default,
no caching is performed. If a string is given, it is the path to
the caching directory. Enabling caching triggers a clone of
the transformers before fitting. Therefore, the transformer
instance given to the pipeline cannot be inspected
directly. Use the attribute ``named_steps`` or ``steps`` to
inspect estimators within the pipeline. Caching the
transformers is advantageous when fitting is time consuming.
verbose : bool, default=False
If True, the time elapsed while fitting each step will be printed as it
is completed.
Attributes
----------
named_steps : bunch object, a dictionary with attribute access
Read-only attribute to access any step parameter by user given name.
Keys are step names and values are steps parameters.
See Also
--------
sklearn.pipeline.make_pipeline : Convenience function for simplified
pipeline construction.
Examples
--------
>>> from sklearn import svm
>>> from sklearn.datasets import make_classification
>>> from sklearn.feature_selection import SelectKBest
>>> from sklearn.feature_selection import f_regression
>>> from sklearn.pipeline import Pipeline
>>> # generate some data to play with
>>> X, y = make_classification(
... n_informative=5, n_redundant=0, random_state=42)
>>> # ANOVA SVM-C
>>> anova_filter = SelectKBest(f_regression, k=5)
>>> clf = svm.SVC(kernel='linear')
>>> anova_svm = Pipeline([('anova', anova_filter), ('svc', clf)])
>>> # You can set the parameters using the names issued
>>> # For instance, fit using a k of 10 in the SelectKBest
>>> # and a parameter 'C' of the svm
>>> anova_svm.set_params(anova__k=10, svc__C=.1).fit(X, y)
Pipeline(steps=[('anova', SelectKBest(...)), ('svc', SVC(...))])
>>> prediction = anova_svm.predict(X)
>>> anova_svm.score(X, y)
0.83
>>> # getting the selected features chosen by anova_filter
>>> anova_svm['anova'].get_support()
array([False, False, True, True, False, False, True, True, False,
True, False, True, True, False, True, False, True, True,
False, False])
>>> # Another way to get selected features chosen by anova_filter
>>> anova_svm.named_steps.anova.get_support()
array([False, False, True, True, False, False, True, True, False,
True, False, True, True, False, True, False, True, True,
False, False])
>>> # Indexing can also be used to extract a sub-pipeline.
>>> sub_pipeline = anova_svm[:1]
>>> sub_pipeline
Pipeline(steps=[('anova', SelectKBest(...))])
>>> coef = anova_svm[-1].coef_
>>> anova_svm['svc'] is anova_svm[-1]
True
>>> coef.shape
(1, 10)
>>> sub_pipeline.inverse_transform(coef).shape
(1, 20)
"""
# BaseEstimator interface
_required_parameters = ['steps']
def __init__(self, steps, memory=None, verbose=False, param_routing=None):
self.steps = steps
self.memory = memory
self.verbose = verbose
self.param_routing = param_routing
self._validate_steps()
self.router = check_routing(self.param_routing,
[[name, '*'] for name, _ in self.steps],
self._default_routing)
def get_params(self, deep=True):
"""Get parameters for this estimator.
Parameters
----------
deep : boolean, optional
If True, will return the parameters for this estimator and
contained subobjects that are estimators.
Returns
-------
params : mapping of string to any
Parameter names mapped to their values.
"""
return self._get_params('steps', deep=deep)
def set_params(self, **kwargs):
"""Set the parameters of this estimator.
Valid parameter keys can be listed with ``get_params()``.
Returns
-------
self
"""
self._set_params('steps', **kwargs)
if 'param_routing' in kwargs:
self.router = check_routing(
self.param_routing, [[name, '*'] for name, _ in self.steps],
self._default_routing)
return self
def _validate_steps(self):
names, estimators = zip(*self.steps)
# validate names
self._validate_names(names)
# validate estimators
transformers = estimators[:-1]
estimator = estimators[-1]
for t in transformers:
if t is None or t == 'passthrough':
continue
if (not (hasattr(t, "fit") or hasattr(t, "fit_transform")) or not
hasattr(t, "transform")):
raise TypeError("All intermediate steps should be "
"transformers and implement fit and transform "
"or be the string 'passthrough' "
"'%s' (type %s) doesn't" % (t, type(t)))
# We allow last estimator to be None as an identity transformation
if (estimator is not None and estimator != 'passthrough'
and not hasattr(estimator, "fit")):
raise TypeError(
"Last step of Pipeline should implement fit "
"or be the string 'passthrough'. "
"'%s' (type %s) doesn't" % (estimator, type(estimator)))
def _iter(self, with_final=True, filter_passthrough=True):
"""
Generate (idx, (name, trans)) tuples from self.steps
When filter_passthrough is True, 'passthrough' and None transformers
are filtered out.
"""
stop = len(self.steps)
if not with_final:
stop -= 1
for idx, (name, trans) in enumerate(islice(self.steps, 0, stop)):
if not filter_passthrough:
yield idx, name, trans
elif trans is not None and trans != 'passthrough':
yield idx, name, trans
def __len__(self):
"""
Returns the length of the Pipeline
"""
return len(self.steps)
def __getitem__(self, ind):
"""Returns a sub-pipeline or a single estimator in the pipeline
Indexing with an integer will return an estimator; using a slice
returns another Pipeline instance which copies a slice of this
Pipeline. This copy is shallow: modifying (or fitting) estimators in
the sub-pipeline will affect the larger pipeline and vice-versa.
However, replacing a value in `step` will not affect a copy.
"""
if isinstance(ind, slice):
if ind.step not in (1, None):
raise ValueError('Pipeline slicing only supports a step of 1')
return self.__class__(self.steps[ind])
try:
name, est = self.steps[ind]
except TypeError:
# Not an int, try get step by name
return self.named_steps[ind]
return est
@property
def _estimator_type(self):
return self.steps[-1][1]._estimator_type
@property
def named_steps(self):
# Use Bunch object to improve autocomplete
return Bunch(**dict(self.steps))
@property
def _final_estimator(self):
estimator = self.steps[-1][1]
return 'passthrough' if estimator is None else estimator
def _log_message(self, step_idx):
if not self.verbose:
return None
name, step = self.steps[step_idx]
return '(step %d of %d) Processing %s' % (step_idx + 1,
len(self.steps),
name)
def _default_routing(self, params):
names = [name for name, _ in self.steps]
step_params = {name: {} for name in names}
remainder = set()
for k, v in params.items():
if v is not None:
# XXX: not sure if we need to remove Nones
name, prop = k.split('__', 1)
try:
step_params[name][prop] = v
except KeyError:
remainder.add(k)
return [step_params[name] for name in names], remainder
def _transform_pipeline(self, caller_name, X, params):
step_params, remainder = self.router(params)
if remainder:
raise TypeError('%s() got unexpected keyword arguments %r'
% (caller_name, sorted(remainder)))
feature_meta = params.get('feature_meta', None)
if caller_name == 'transform':
step_iter = self._iter()
elif caller_name == 'inverse_transform':
step_iter = reversed(list(self._iter()))
else:
step_iter = self._iter(with_final=False)
for step_idx, _, transformer in step_iter:
if (step_idx > 0 and feature_meta is not None
and 'feature_meta' in step_params[step_idx]):
step_params[step_idx]['feature_meta'] = feature_meta
X = transformer.transform(X, **step_params[step_idx])
if feature_meta is not None:
feature_meta = transform_feature_meta(transformer,
feature_meta)
if caller_name in ['transform', 'inverse_transform']:
return X
if 'feature_meta' in step_params[-1]:
step_params[-1]['feature_meta'] = feature_meta
return X, step_params[-1]
# Estimator interface
def _fit(self, X, y=None, **fit_params):
# shallow copy of steps - this should really be steps_
self.steps = list(self.steps)
self._validate_steps()
# Setup the memory
memory = check_memory(self.memory)
fit_transform_one_cached = memory.cache(_fit_transform_one)
step_fit_params, remainder = self.router(fit_params)
if remainder:
raise TypeError('Got unexpected keyword arguments %r'
% sorted(remainder))
feature_meta = fit_params.get('feature_meta', None)
for (step_idx,
name,
transformer) in self._iter(with_final=False,
filter_passthrough=False):
if (transformer is None or transformer == 'passthrough'):
with _print_elapsed_time('Pipeline',
self._log_message(step_idx)):
continue
if hasattr(memory, 'location'):
# joblib >= 0.12
if memory.location is None:
# we do not clone when caching is disabled to
# preserve backward compatibility
cloned_transformer = transformer
else:
cloned_transformer = clone(transformer)
elif hasattr(memory, 'cachedir'):
# joblib < 0.11
if memory.cachedir is None:
# we do not clone when caching is disabled to
# preserve backward compatibility
cloned_transformer = transformer
else:
cloned_transformer = clone(transformer)
else:
cloned_transformer = clone(transformer)
if step_idx > 0 and 'feature_meta' in step_fit_params[step_idx]:
step_fit_params[step_idx]['feature_meta'] = feature_meta
# Fit or load from cache the current transformer
X, fitted_transformer = fit_transform_one_cached(
cloned_transformer, X, y, None,
message_clsname='Pipeline',
message=self._log_message(step_idx),
**step_fit_params[step_idx])
if feature_meta is not None:
feature_meta = transform_feature_meta(fitted_transformer,
feature_meta)
if X.shape[1] != feature_meta.shape[0]:
raise ValueError(('X ({:d}) and feature_meta ({:d}) have '
'different feature dimensions').format(
X.shape[1], feature_meta.shape[0]))
# Replace the transformer of the step with the fitted
# transformer. This is necessary when loading the transformer
# from the cache.
self.steps[step_idx] = (name, fitted_transformer)
if self._final_estimator == 'passthrough':
return X, {}
if 'feature_meta' in step_fit_params[-1]:
step_fit_params[-1]['feature_meta'] = feature_meta
return X, step_fit_params[-1]
def fit(self, X, y=None, **fit_params):
"""Fit the model
Fit all the transforms one after the other and transform the
data, then fit the transformed data using the final estimator.
Parameters
----------
X : iterable
Training data. Must fulfill input requirements of first step of the
pipeline.
y : iterable, default=None
Training targets. Must fulfill label requirements for all steps of
the pipeline.
**fit_params : dict of string -> object
Parameters passed to the ``fit`` method of each step, where
each parameter name is prefixed such that parameter ``p`` for step
``s`` has key ``s__p``.
Returns
-------
self : Pipeline
This estimator
"""
Xt, fit_params = self._fit(X, y, **fit_params)
with _print_elapsed_time('Pipeline',
self._log_message(len(self.steps) - 1)):
if self._final_estimator != 'passthrough':
self._final_estimator.fit(Xt, y, **fit_params)
return self
def fit_transform(self, X, y=None, **fit_params):
"""Fit the model and transform with the final estimator
Fits all the transforms one after the other and transforms the
data, then uses fit_transform on transformed data with the final
estimator.
Parameters
----------
X : iterable
Training data. Must fulfill input requirements of first step of the
pipeline.
y : iterable, default=None
Training targets. Must fulfill label requirements for all steps of
the pipeline.
**fit_params : dict of string -> object
Parameters passed to the ``fit`` method of each step, where
each parameter name is prefixed such that parameter ``p`` for step
``s`` has key ``s__p``.
Returns
-------
Xt : array-like of shape (n_samples, n_transformed_features)
Transformed samples
"""
last_step = self._final_estimator
Xt, fit_params = self._fit(X, y, **fit_params)
with _print_elapsed_time('Pipeline',
self._log_message(len(self.steps) - 1)):
if last_step == 'passthrough':
return Xt
if hasattr(last_step, 'fit_transform'):
return last_step.fit_transform(Xt, y, **fit_params)
else:
return last_step.fit(Xt, y, **fit_params).transform(
Xt, **fit_params)
@if_delegate_has_method(delegate='_final_estimator')
def predict(self, X, **predict_params):
"""Apply transforms to the data, and predict with the final estimator
Parameters
----------
X : iterable
Data to predict on. Must fulfill input requirements of first step
of the pipeline.
**predict_params : dict of string -> object
Parameters to the ``predict`` called at the end of all
transformations in the pipeline. Note that while this may be
used to return uncertainties from some models with return_std
or return_cov, uncertainties that are generated by the
transformations in the pipeline are not propagated to the
final estimator.
Returns
-------
y_pred : array-like
"""
Xt, predict_params = self._transform_pipeline('predict',
X, predict_params)
return self.steps[-1][-1].predict(Xt, **predict_params)
@if_delegate_has_method(delegate='_final_estimator')
def fit_predict(self, X, y=None, **fit_params):
"""Applies fit_predict of last step in pipeline after transforms.
Applies fit_transforms of a pipeline to the data, followed by the
fit_predict method of the final estimator in the pipeline. Valid
only if the final estimator implements fit_predict.
Parameters
----------
X : iterable
Training data. Must fulfill input requirements of first step of
the pipeline.
y : iterable, default=None
Training targets. Must fulfill label requirements for all steps
of the pipeline.
**fit_params : dict of string -> object
Parameters passed to the ``fit`` method of each step, where
each parameter name is prefixed such that parameter ``p`` for step
``s`` has key ``s__p``.
Returns
-------
y_pred : array-like
"""
Xt, fit_params = self._fit(X, y, **fit_params)
with _print_elapsed_time('Pipeline',
self._log_message(len(self.steps) - 1)):
y_pred = self.steps[-1][-1].fit_predict(Xt, y, **fit_params)
return y_pred
@if_delegate_has_method(delegate='_final_estimator')
def predict_proba(self, X, **predict_params):
"""Apply transforms, and predict_proba of the final estimator
Parameters
----------
X : iterable
Data to predict on. Must fulfill input requirements of first step
of the pipeline.
Returns
-------
y_proba : array-like of shape (n_samples, n_classes)
"""
Xt, predict_params = self._transform_pipeline('predict_proba',
X, predict_params)
return self.steps[-1][-1].predict_proba(Xt)
@if_delegate_has_method(delegate='_final_estimator')
def decision_function(self, X, **predict_params):
"""Apply transforms, and decision_function of the final estimator
Parameters
----------
X : iterable
Data to predict on. Must fulfill input requirements of first step
of the pipeline.
Returns
-------
y_score : array-like of shape (n_samples, n_classes)
"""
Xt, predict_params = self._transform_pipeline('decision_function',
X, predict_params)
return self.steps[-1][-1].decision_function(Xt)
@if_delegate_has_method(delegate='_final_estimator')
def score_samples(self, X, **predict_params):
"""Apply transforms, and score_samples of the final estimator.
Parameters
----------
X : iterable
Data to predict on. Must fulfill input requirements of first step
of the pipeline.
Returns
-------
y_score : ndarray, shape (n_samples,)
"""
Xt, predict_params = self._transform_pipeline('score_samples',
X, predict_params)
return self.steps[-1][-1].score_samples(Xt)
@if_delegate_has_method(delegate='_final_estimator')
def predict_log_proba(self, X, **predict_params):
"""Apply transforms, and predict_log_proba of the final estimator
Parameters
----------
X : iterable
Data to predict on. Must fulfill input requirements of first step
of the pipeline.
Returns
-------
y_score : array-like of shape (n_samples, n_classes)
"""
Xt, predict_params = self._transform_pipeline('predict_log_proba',
X, predict_params)
return self.steps[-1][-1].predict_log_proba(Xt)
@property
def transform(self):
"""Apply transforms, and transform with the final estimator
This also works where final estimator is ``None``: all prior
transformations are applied.
Parameters
----------
X : iterable
Data to transform. Must fulfill input requirements of first step
of the pipeline.
Returns
-------
Xt : array-like of shape (n_samples, n_transformed_features)
"""
# _final_estimator is None or has transform, otherwise attribute error
# XXX: Handling the None case means we can't use if_delegate_has_method
if self._final_estimator != 'passthrough':
self._final_estimator.transform
return self._transform
def _transform(self, X, **transform_params):
Xt = self._transform_pipeline('transform', X, transform_params)
return Xt
@property
def inverse_transform(self):
"""Apply inverse transformations in reverse order
All estimators in the pipeline must support ``inverse_transform``.
Parameters
----------
Xt : array-like of shape (n_samples, n_transformed_features)
Data samples, where ``n_samples`` is the number of samples and
``n_features`` is the number of features. Must fulfill
input requirements of last step of pipeline's
``inverse_transform`` method.
Returns
-------
Xt : array-like of shape (n_samples, n_features)
"""
# raise AttributeError if necessary for hasattr behaviour
# XXX: Handling the None case means we can't use if_delegate_has_method
for _, _, transform in self._iter():
transform.inverse_transform
return self._inverse_transform
def _inverse_transform(self, X, **transform_params):
Xt = self._transform_pipeline('inverse_transform', X, transform_params)
return Xt
@if_delegate_has_method(delegate='_final_estimator')
def score(self, X, y=None, sample_weight=None, **transform_params):
"""Apply transforms, and score with the final estimator
Parameters
----------
X : iterable
Data to predict on. Must fulfill input requirements of first step
of the pipeline.
y : iterable, default=None
Targets used for scoring. Must fulfill label requirements for all
steps of the pipeline.
sample_weight : array-like, default=None
If not None, this argument is passed as ``sample_weight`` keyword
argument to the ``score`` method of the final estimator.
Returns
-------
score : float
"""
Xt, _ = self._transform_pipeline('score', X, transform_params)
score_params = {}
if sample_weight is not None:
score_params['sample_weight'] = sample_weight
return self.steps[-1][-1].score(Xt, y, **score_params)
@property
def classes_(self):
return self.steps[-1][-1].classes_
@property
def _pairwise(self):
# check if first estimator expects pairwise input
return getattr(self.steps[0][1], '_pairwise', False)
def _name_estimators(estimators):
"""Generate names for estimators."""
names = [
estimator
if isinstance(estimator, str) else type(estimator).__name__.lower()
for estimator in estimators
]
namecount = defaultdict(int)
for est, name in zip(estimators, names):
namecount[name] += 1
for k, v in list(namecount.items()):
if v == 1:
del namecount[k]
for i in reversed(range(len(estimators))):
name = names[i]
if name in namecount:
names[i] += "-%d" % namecount[name]
namecount[name] -= 1
return list(zip(names, estimators))
def _transform_one(transformer, X, y, weight, message_clsname='',
message=None, **transform_params):
res = transformer.transform(X, **transform_params)
# if we have a weight for this transformer, multiply output
if weight is None:
return res
return res * weight
def _fit_transform_one(transformer,
X,
y,
weight,
message_clsname='',
message=None,
**fit_params):
"""
Fits ``transformer`` to ``X`` and ``y``. The transformed result is returned
with the fitted transformer. If ``weight`` is not ``None``, the result will
be multiplied by ``weight``.
"""
with _print_elapsed_time(message_clsname, message):
if hasattr(transformer, 'fit_transform'):
res = transformer.fit_transform(X, y, **fit_params)
else:
res = transformer.fit(X, y, **fit_params).transform(
X, **fit_params)
if weight is None:
return res, transformer
return res * weight, transformer
def _fit_one(transformer,
X,
y,
weight,
message_clsname='',
message=None,
**fit_params):
"""
Fits ``transformer`` to ``X`` and ``y``.
"""
with _print_elapsed_time(message_clsname, message):
return transformer.fit(X, y, **fit_params)
def transform_feature_meta(estimator, feature_meta):
if isinstance(estimator, ColumnTransformer):
transformed_feature_meta = None
for _, trf_transformer, trf_columns in estimator.transformers_:
if isinstance(trf_transformer, str) and trf_transformer == 'drop':
trf_feature_meta = feature_meta.iloc[
~feature_meta.index.isin(trf_columns)]
elif ((isinstance(trf_columns, slice)
and (isinstance(trf_columns.start, str)
or isinstance(trf_columns.stop, str)))
or isinstance(trf_columns[0], str)):
trf_feature_meta = feature_meta.loc[trf_columns]
else:
trf_feature_meta = feature_meta.iloc[trf_columns]
if isinstance(trf_transformer, Pipeline):
for transformer in trf_transformer:
trf_feature_meta = transform_feature_meta(transformer,
trf_feature_meta)
if transformed_feature_meta is None:
transformed_feature_meta = trf_feature_meta
else:
transformed_feature_meta = pd.concat(
[transformed_feature_meta, trf_feature_meta], axis=0)
elif hasattr(estimator, 'get_support'):
transformed_feature_meta = feature_meta.loc[estimator.get_support()]
elif hasattr(estimator, 'get_feature_names'):
transformed_feature_meta = None
feature_names = estimator.get_feature_names(
input_features=feature_meta.index.values).astype(str)
for feature_name in feature_meta.index:
f_feature_meta = pd.concat(
[feature_meta.loc[[feature_name]]] * np.sum(
np.char.startswith(feature_names,
'{}_'.format(feature_name))),
axis=0, ignore_index=True)
if transformed_feature_meta is None:
transformed_feature_meta = f_feature_meta
else:
transformed_feature_meta = pd.concat(
[transformed_feature_meta, f_feature_meta],
axis=0, ignore_index=True)
transformed_feature_meta = (transformed_feature_meta
.set_index(feature_names))
else:
transformed_feature_meta = feature_meta
return transformed_feature_meta
def make_extended_pipeline(*steps, **kwargs):
"""Construct an Pipeline from the given estimators.
This is a shorthand for the Pipeline constructor; it does not require, and
does not permit, naming the estimators. Instead, their names will be set
to the lowercase of their types automatically.
Parameters
----------
*steps : list of estimators.
memory : None, str or object with the joblib.Memory interface, optional
Used to cache the fitted transformers of the pipeline. By default,
no caching is performed. If a string is given, it is the path to
the caching directory. Enabling caching triggers a clone of
the transformers before fitting. Therefore, the transformer
instance given to the pipeline cannot be inspected
directly. Use the attribute ``named_steps`` or ``steps`` to
inspect estimators within the pipeline. Caching the
transformers is advantageous when fitting is time consuming.
verbose : boolean, default=False
If True, the time elapsed while fitting each step will be printed as it
is completed.
See Also
--------
sklearn.pipeline.Pipeline : Class for creating a pipeline of
transforms with a final estimator.
Examples
--------
>>> from sklearn.naive_bayes import GaussianNB
>>> from sklearn.preprocessing import StandardScaler
>>> make_pipeline(StandardScaler(), GaussianNB(priors=None))
Pipeline(steps=[('standardscaler', StandardScaler()),
('gaussiannb', GaussianNB())])
Returns
-------
p : Pipeline
"""
memory = kwargs.pop('memory', None)
verbose = kwargs.pop('verbose', False)
param_routing = kwargs.pop('param_routing', None)
if kwargs:
raise TypeError('Unknown keyword arguments: "{}"'
.format(list(kwargs.keys())[0]))
return ExtendedPipeline(_name_estimators(steps), memory=memory,
verbose=verbose, param_routing=param_routing)
class ExtendedFeatureUnion(ExtendedTransformerMixin, FeatureUnion):
"""Concatenates results of multiple transformer objects.
This estimator applies a list of transformer objects in parallel to the
input data, then concatenates the results. This is useful to combine
several feature extraction mechanisms into a single transformer.
Parameters of the transformers may be set using its name and the parameter
name separated by a '__'. A transformer may be replaced entirely by
setting the parameter with its name to another transformer,
or removed by setting to 'drop'.
Read more in the :ref:`User Guide <feature_union>`.
.. versionadded:: 0.13
Parameters
----------
transformer_list : list of (string, transformer) tuples
List of transformer objects to be applied to the data. The first
half of each tuple is the name of the transformer.
.. versionchanged:: 0.22
Deprecated `None` as a transformer in favor of 'drop'.
n_jobs : int or None, optional (default=None)
Number of jobs to run in parallel.
``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
``-1`` means using all processors. See :term:`Glossary <n_jobs>`
for more details.
transformer_weights : dict, optional
Multiplicative weights for features per transformer.
Keys are transformer names, values the weights.
verbose : boolean, optional(default=False)
If True, the time elapsed while fitting each transformer will be
printed as it is completed.
See Also
--------
sklearn.pipeline.make_union : Convenience function for simplified
feature union construction.
Examples
--------
>>> from sklearn.pipeline import FeatureUnion
>>> from sklearn.decomposition import PCA, TruncatedSVD
>>> union = FeatureUnion([("pca", PCA(n_components=1)),
... ("svd", TruncatedSVD(n_components=2))])
>>> X = [[0., 1., 3], [2., 2., 5]]
>>> union.fit_transform(X)
array([[ 1.5 , 3.0..., 0.8...],
[-1.5 , 5.7..., -0.4...]])
"""
_required_parameters = ["transformer_list"]
def __init__(self, transformer_list, n_jobs=None,
transformer_weights=None, verbose=False,
param_routing=None):
self.transformer_list = transformer_list
self.n_jobs = n_jobs
self.transformer_weights = transformer_weights
self.verbose = verbose
self.param_routing = param_routing
self._validate_transformers()
self.router = check_routing(
self.param_routing,
[[name, '*'] for name, _ in self.transformer_list],
self._default_routing)
def get_params(self, deep=True):
"""Get parameters for this estimator.
Parameters
----------
deep : boolean, optional
If True, will return the parameters for this estimator and
contained subobjects that are estimators.
Returns
-------
params : mapping of string to any
Parameter names mapped to their values.
"""
return self._get_params('transformer_list', deep=deep)
def set_params(self, **kwargs):
"""Set the parameters of this estimator.
Valid parameter keys can be listed with ``get_params()``.
Returns
-------
self
"""
self._set_params('transformer_list', **kwargs)
return self
def _validate_transformers(self):
names, transformers = zip(*self.transformer_list)
# validate names
self._validate_names(names)
# validate estimators
for t in transformers:
# TODO: Remove in 0.24 when None is removed
if t is None:
warnings.warn("Using None as a transformer is deprecated "
"in version 0.22 and will be removed in "
"version 0.24. Please use 'drop' instead.",
FutureWarning)
continue
if t == 'drop':
continue
if (not (hasattr(t, "fit") or hasattr(t, "fit_transform")) or not
hasattr(t, "transform")):
raise TypeError("All estimators should implement fit and "
"transform. '%s' (type %s) doesn't" %
(t, type(t)))
def _iter(self):
"""
Generate (name, trans, weight) tuples excluding None and
'drop' transformers.
"""
get_weight = (self.transformer_weights or {}).get
return ((name, trans, get_weight(name))
for name, trans in self.transformer_list
if trans is not None and trans != 'drop')
def _default_routing(self, params):
names = [name for name, _ in self.transformer_list]
transformer_params = {name: {} for name in names}
remainder = set()
for k, v in params.items():
if v is not None:
# XXX: not sure if we need to remove Nones
name, prop = k.split('__', 1)
try:
transformer_params[name][prop] = v
except KeyError:
remainder.add(k)
return [transformer_params[name] for name in names], remainder
def get_feature_names(self):
"""Get feature names from all transformers.