-
-
Notifications
You must be signed in to change notification settings - Fork 25.1k
/
_column_transformer.py
1653 lines (1414 loc) · 64.5 KB
/
_column_transformer.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.compose._column_transformer` module implements utilities
to work with heterogeneous data and to apply different transformers to
different columns.
"""
# Author: Andreas Mueller
# Joris Van den Bossche
# License: BSD
import warnings
from collections import Counter, UserList
from itertools import chain
from numbers import Integral, Real
import numpy as np
from scipy import sparse
from ..base import TransformerMixin, _fit_context, clone
from ..pipeline import _fit_transform_one, _name_estimators, _transform_one
from ..preprocessing import FunctionTransformer
from ..utils import Bunch
from ..utils._estimator_html_repr import _VisualBlock
from ..utils._indexing import _determine_key_type, _get_column_indices, _safe_indexing
from ..utils._metadata_requests import METHODS
from ..utils._param_validation import HasMethods, Hidden, Interval, StrOptions
from ..utils._set_output import (
_get_container_adapter,
_get_output_config,
_safe_set_output,
)
from ..utils.metadata_routing import (
MetadataRouter,
MethodMapping,
_raise_for_params,
_routing_enabled,
process_routing,
)
from ..utils.metaestimators import _BaseComposition
from ..utils.parallel import Parallel, delayed
from ..utils.validation import (
_check_feature_names_in,
_get_feature_names,
_is_pandas_df,
_num_samples,
check_array,
check_is_fitted,
)
__all__ = ["ColumnTransformer", "make_column_transformer", "make_column_selector"]
_ERR_MSG_1DCOLUMN = (
"1D data passed to a transformer that expects 2D data. "
"Try to specify the column selection as a list of one "
"item instead of a scalar."
)
class ColumnTransformer(TransformerMixin, _BaseComposition):
"""Applies transformers to columns of an array or pandas DataFrame.
This estimator allows different columns or column subsets of the input
to be transformed separately and the features generated by each transformer
will be concatenated to form a single feature space.
This is useful for heterogeneous or columnar data, to combine several
feature extraction mechanisms or transformations into a single transformer.
Read more in the :ref:`User Guide <column_transformer>`.
.. versionadded:: 0.20
Parameters
----------
transformers : list of tuples
List of (name, transformer, columns) tuples specifying the
transformer objects to be applied to subsets of the data.
name : str
Like in Pipeline and FeatureUnion, this allows the transformer and
its parameters to be set using ``set_params`` and searched in grid
search.
transformer : {'drop', 'passthrough'} or estimator
Estimator must support :term:`fit` and :term:`transform`.
Special-cased strings 'drop' and 'passthrough' are accepted as
well, to indicate to drop the columns or to pass them through
untransformed, respectively.
columns : str, array-like of str, int, array-like of int, \
array-like of bool, slice or callable
Indexes the data on its second axis. Integers are interpreted as
positional columns, while strings can reference DataFrame columns
by name. A scalar string or int should be used where
``transformer`` expects X to be a 1d array-like (vector),
otherwise a 2d array will be passed to the transformer.
A callable is passed the input data `X` and can return any of the
above. To select multiple columns by name or dtype, you can use
:obj:`make_column_selector`.
remainder : {'drop', 'passthrough'} or estimator, default='drop'
By default, only the specified columns in `transformers` are
transformed and combined in the output, and the non-specified
columns are dropped. (default of ``'drop'``).
By specifying ``remainder='passthrough'``, all remaining columns that
were not specified in `transformers`, but present in the data passed
to `fit` will be automatically passed through. This subset of columns
is concatenated with the output of the transformers. For dataframes,
extra columns not seen during `fit` will be excluded from the output
of `transform`.
By setting ``remainder`` to be an estimator, the remaining
non-specified columns will use the ``remainder`` estimator. The
estimator must support :term:`fit` and :term:`transform`.
Note that using this feature requires that the DataFrame columns
input at :term:`fit` and :term:`transform` have identical order.
sparse_threshold : float, default=0.3
If the output of the different transformers contains sparse matrices,
these will be stacked as a sparse matrix if the overall density is
lower than this value. Use ``sparse_threshold=0`` to always return
dense. When the transformed output consists of all dense data, the
stacked result will be dense, and this keyword will be ignored.
n_jobs : int, 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, default=None
Multiplicative weights for features per transformer. The output of the
transformer is multiplied by these weights. Keys are transformer names,
values the weights.
verbose : bool, default=False
If True, the time elapsed while fitting each transformer will be
printed as it is completed.
verbose_feature_names_out : bool, default=True
If True, :meth:`ColumnTransformer.get_feature_names_out` will prefix
all feature names with the name of the transformer that generated that
feature.
If False, :meth:`ColumnTransformer.get_feature_names_out` will not
prefix any feature names and will error if feature names are not
unique.
.. versionadded:: 1.0
force_int_remainder_cols : bool, default=True
Force the columns of the last entry of `transformers_`, which
corresponds to the "remainder" transformer, to always be stored as
indices (int) rather than column names (str). See description of the
`transformers_` attribute for details.
.. note::
If you do not access the list of columns for the remainder columns
in the `transformers_` fitted attribute, you do not need to set
this parameter.
.. versionadded:: 1.5
.. versionchanged:: 1.7
The default value for `force_int_remainder_cols` will change from
`True` to `False` in version 1.7.
Attributes
----------
transformers_ : list
The collection of fitted transformers as tuples of (name,
fitted_transformer, column). `fitted_transformer` can be an estimator,
or `'drop'`; `'passthrough'` is replaced with an equivalent
:class:`~sklearn.preprocessing.FunctionTransformer`. In case there were
no columns selected, this will be the unfitted transformer. If there
are remaining columns, the final element is a tuple of the form:
('remainder', transformer, remaining_columns) corresponding to the
``remainder`` parameter. If there are remaining columns, then
``len(transformers_)==len(transformers)+1``, otherwise
``len(transformers_)==len(transformers)``.
.. versionchanged:: 1.5
If there are remaining columns and `force_int_remainder_cols` is
True, the remaining columns are always represented by their
positional indices in the input `X` (as in older versions). If
`force_int_remainder_cols` is False, the format attempts to match
that of the other transformers: if all columns were provided as
column names (`str`), the remaining columns are stored as column
names; if all columns were provided as mask arrays (`bool`), so are
the remaining columns; in all other cases the remaining columns are
stored as indices (`int`).
named_transformers_ : :class:`~sklearn.utils.Bunch`
Read-only attribute to access any transformer by given name.
Keys are transformer names and values are the fitted transformer
objects.
sparse_output_ : bool
Boolean flag indicating whether the output of ``transform`` is a
sparse matrix or a dense numpy array, which depends on the output
of the individual transformers and the `sparse_threshold` keyword.
output_indices_ : dict
A dictionary from each transformer name to a slice, where the slice
corresponds to indices in the transformed output. This is useful to
inspect which transformer is responsible for which transformed
feature(s).
.. versionadded:: 1.0
n_features_in_ : int
Number of features seen during :term:`fit`. Only defined if the
underlying transformers expose such an attribute when fit.
.. versionadded:: 0.24
feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Defined only when `X`
has feature names that are all strings.
.. versionadded:: 1.0
See Also
--------
make_column_transformer : Convenience function for
combining the outputs of multiple transformer objects applied to
column subsets of the original feature space.
make_column_selector : Convenience function for selecting
columns based on datatype or the columns name with a regex pattern.
Notes
-----
The order of the columns in the transformed feature matrix follows the
order of how the columns are specified in the `transformers` list.
Columns of the original feature matrix that are not specified are
dropped from the resulting transformed feature matrix, unless specified
in the `passthrough` keyword. Those columns specified with `passthrough`
are added at the right to the output of the transformers.
Examples
--------
>>> import numpy as np
>>> from sklearn.compose import ColumnTransformer
>>> from sklearn.preprocessing import Normalizer
>>> ct = ColumnTransformer(
... [("norm1", Normalizer(norm='l1'), [0, 1]),
... ("norm2", Normalizer(norm='l1'), slice(2, 4))])
>>> X = np.array([[0., 1., 2., 2.],
... [1., 1., 0., 1.]])
>>> # Normalizer scales each row of X to unit norm. A separate scaling
>>> # is applied for the two first and two last elements of each
>>> # row independently.
>>> ct.fit_transform(X)
array([[0. , 1. , 0.5, 0.5],
[0.5, 0.5, 0. , 1. ]])
:class:`ColumnTransformer` can be configured with a transformer that requires
a 1d array by setting the column to a string:
>>> from sklearn.feature_extraction.text import CountVectorizer
>>> from sklearn.preprocessing import MinMaxScaler
>>> import pandas as pd # doctest: +SKIP
>>> X = pd.DataFrame({
... "documents": ["First item", "second one here", "Is this the last?"],
... "width": [3, 4, 5],
... }) # doctest: +SKIP
>>> # "documents" is a string which configures ColumnTransformer to
>>> # pass the documents column as a 1d array to the CountVectorizer
>>> ct = ColumnTransformer(
... [("text_preprocess", CountVectorizer(), "documents"),
... ("num_preprocess", MinMaxScaler(), ["width"])])
>>> X_trans = ct.fit_transform(X) # doctest: +SKIP
For a more detailed example of usage, see
:ref:`sphx_glr_auto_examples_compose_plot_column_transformer_mixed_types.py`.
"""
_required_parameters = ["transformers"]
_parameter_constraints: dict = {
"transformers": [list, Hidden(tuple)],
"remainder": [
StrOptions({"drop", "passthrough"}),
HasMethods(["fit", "transform"]),
HasMethods(["fit_transform", "transform"]),
],
"sparse_threshold": [Interval(Real, 0, 1, closed="both")],
"n_jobs": [Integral, None],
"transformer_weights": [dict, None],
"verbose": ["verbose"],
"verbose_feature_names_out": ["boolean"],
"force_int_remainder_cols": ["boolean"],
}
def __init__(
self,
transformers,
*,
remainder="drop",
sparse_threshold=0.3,
n_jobs=None,
transformer_weights=None,
verbose=False,
verbose_feature_names_out=True,
force_int_remainder_cols=True,
):
self.transformers = transformers
self.remainder = remainder
self.sparse_threshold = sparse_threshold
self.n_jobs = n_jobs
self.transformer_weights = transformer_weights
self.verbose = verbose
self.verbose_feature_names_out = verbose_feature_names_out
self.force_int_remainder_cols = force_int_remainder_cols
@property
def _transformers(self):
"""
Internal list of transformer only containing the name and
transformers, dropping the columns.
DO NOT USE: This is for the implementation of get_params via
BaseComposition._get_params which expects lists of tuples of len 2.
To iterate through the transformers, use ``self._iter`` instead.
"""
try:
return [(name, trans) for name, trans, _ in self.transformers]
except (TypeError, ValueError):
return self.transformers
@_transformers.setter
def _transformers(self, value):
"""DO NOT USE: This is for the implementation of set_params via
BaseComposition._get_params which gives lists of tuples of len 2.
"""
try:
self.transformers = [
(name, trans, col)
for ((name, trans), (_, _, col)) in zip(value, self.transformers)
]
except (TypeError, ValueError):
self.transformers = value
def set_output(self, *, transform=None):
"""Set the output container when `"transform"` and `"fit_transform"` are called.
Calling `set_output` will set the output of all estimators in `transformers`
and `transformers_`.
Parameters
----------
transform : {"default", "pandas", "polars"}, default=None
Configure output of `transform` and `fit_transform`.
- `"default"`: Default output format of a transformer
- `"pandas"`: DataFrame output
- `"polars"`: Polars output
- `None`: Transform configuration is unchanged
.. versionadded:: 1.4
`"polars"` option was added.
Returns
-------
self : estimator instance
Estimator instance.
"""
super().set_output(transform=transform)
transformers = (
trans
for _, trans, _ in chain(
self.transformers, getattr(self, "transformers_", [])
)
if trans not in {"passthrough", "drop"}
)
for trans in transformers:
_safe_set_output(trans, transform=transform)
if self.remainder not in {"passthrough", "drop"}:
_safe_set_output(self.remainder, transform=transform)
return self
def get_params(self, deep=True):
"""Get parameters for this estimator.
Returns the parameters given in the constructor as well as the
estimators contained within the `transformers` of the
`ColumnTransformer`.
Parameters
----------
deep : bool, default=True
If True, will return the parameters for this estimator and
contained subobjects that are estimators.
Returns
-------
params : dict
Parameter names mapped to their values.
"""
return self._get_params("_transformers", deep=deep)
def set_params(self, **kwargs):
"""Set the parameters of this estimator.
Valid parameter keys can be listed with ``get_params()``. Note that you
can directly set the parameters of the estimators contained in
`transformers` of `ColumnTransformer`.
Parameters
----------
**kwargs : dict
Estimator parameters.
Returns
-------
self : ColumnTransformer
This estimator.
"""
self._set_params("_transformers", **kwargs)
return self
def _iter(self, fitted, column_as_labels, skip_drop, skip_empty_columns):
"""
Generate (name, trans, columns, weight) tuples.
Parameters
----------
fitted : bool
If True, use the fitted transformers (``self.transformers_``) to
iterate through transformers, else use the transformers passed by
the user (``self.transformers``).
column_as_labels : bool
If True, columns are returned as string labels. If False, columns
are returned as they were given by the user. This can only be True
if the ``ColumnTransformer`` is already fitted.
skip_drop : bool
If True, 'drop' transformers are filtered out.
skip_empty_columns : bool
If True, transformers with empty selected columns are filtered out.
Yields
------
A generator of tuples containing:
- name : the name of the transformer
- transformer : the transformer object
- columns : the columns for that transformer
- weight : the weight of the transformer
"""
if fitted:
transformers = self.transformers_
else:
# interleave the validated column specifiers
transformers = [
(name, trans, column)
for (name, trans, _), column in zip(self.transformers, self._columns)
]
# add transformer tuple for remainder
if self._remainder[2]:
transformers = chain(transformers, [self._remainder])
# We want the warning about the future change of the remainder
# columns dtype to be shown only when a user accesses them
# directly, not when they are used by the ColumnTransformer itself.
# We disable warnings here; they are enabled when setting
# self.transformers_.
transformers = _with_dtype_warning_enabled_set_to(False, transformers)
get_weight = (self.transformer_weights or {}).get
for name, trans, columns in transformers:
if skip_drop and trans == "drop":
continue
if skip_empty_columns and _is_empty_column_selection(columns):
continue
if column_as_labels:
# Convert all columns to using their string labels
columns_is_scalar = np.isscalar(columns)
indices = self._transformer_to_input_indices[name]
columns = self.feature_names_in_[indices]
if columns_is_scalar:
# selection is done with one dimension
columns = columns[0]
yield (name, trans, columns, get_weight(name))
def _validate_transformers(self):
"""Validate names of transformers and the transformers themselves.
This checks whether given transformers have the required methods, i.e.
`fit` or `fit_transform` and `transform` implemented.
"""
if not self.transformers:
return
names, transformers, _ = zip(*self.transformers)
# validate names
self._validate_names(names)
# validate estimators
for t in transformers:
if t in ("drop", "passthrough"):
continue
if not (hasattr(t, "fit") or hasattr(t, "fit_transform")) or not hasattr(
t, "transform"
):
# Used to validate the transformers in the `transformers` list
raise TypeError(
"All estimators should implement fit and "
"transform, or can be 'drop' or 'passthrough' "
"specifiers. '%s' (type %s) doesn't." % (t, type(t))
)
def _validate_column_callables(self, X):
"""
Converts callable column specifications.
This stores a dictionary of the form `{step_name: column_indices}` and
calls the `columns` on `X` if `columns` is a callable for a given
transformer.
The results are then stored in `self._transformer_to_input_indices`.
"""
all_columns = []
transformer_to_input_indices = {}
for name, _, columns in self.transformers:
if callable(columns):
columns = columns(X)
all_columns.append(columns)
transformer_to_input_indices[name] = _get_column_indices(X, columns)
self._columns = all_columns
self._transformer_to_input_indices = transformer_to_input_indices
def _validate_remainder(self, X):
"""
Validates ``remainder`` and defines ``_remainder`` targeting
the remaining columns.
"""
cols = set(chain(*self._transformer_to_input_indices.values()))
remaining = sorted(set(range(self.n_features_in_)) - cols)
self._transformer_to_input_indices["remainder"] = remaining
remainder_cols = self._get_remainder_cols(remaining)
self._remainder = ("remainder", self.remainder, remainder_cols)
def _get_remainder_cols_dtype(self):
try:
all_dtypes = {_determine_key_type(c) for (*_, c) in self.transformers}
if len(all_dtypes) == 1:
return next(iter(all_dtypes))
except ValueError:
# _determine_key_type raises a ValueError if some transformer
# columns are Callables
return "int"
return "int"
def _get_remainder_cols(self, indices):
dtype = self._get_remainder_cols_dtype()
if self.force_int_remainder_cols and dtype != "int":
return _RemainderColsList(indices, future_dtype=dtype)
if dtype == "str":
return list(self.feature_names_in_[indices])
if dtype == "bool":
return [i in indices for i in range(self.n_features_in_)]
return indices
@property
def named_transformers_(self):
"""Access the fitted transformer by name.
Read-only attribute to access any transformer by given name.
Keys are transformer names and values are the fitted transformer
objects.
"""
# Use Bunch object to improve autocomplete
return Bunch(**{name: trans for name, trans, _ in self.transformers_})
def _get_feature_name_out_for_transformer(self, name, trans, feature_names_in):
"""Gets feature names of transformer.
Used in conjunction with self._iter(fitted=True) in get_feature_names_out.
"""
column_indices = self._transformer_to_input_indices[name]
names = feature_names_in[column_indices]
# An actual transformer
if not hasattr(trans, "get_feature_names_out"):
raise AttributeError(
f"Transformer {name} (type {type(trans).__name__}) does "
"not provide get_feature_names_out."
)
return trans.get_feature_names_out(names)
def get_feature_names_out(self, input_features=None):
"""Get output feature names for transformation.
Parameters
----------
input_features : array-like of str or None, default=None
Input features.
- If `input_features` is `None`, then `feature_names_in_` is
used as feature names in. If `feature_names_in_` is not defined,
then the following input feature names are generated:
`["x0", "x1", ..., "x(n_features_in_ - 1)"]`.
- If `input_features` is an array-like, then `input_features` must
match `feature_names_in_` if `feature_names_in_` is defined.
Returns
-------
feature_names_out : ndarray of str objects
Transformed feature names.
"""
check_is_fitted(self)
input_features = _check_feature_names_in(self, input_features)
# List of tuples (name, feature_names_out)
transformer_with_feature_names_out = []
for name, trans, *_ in self._iter(
fitted=True,
column_as_labels=False,
skip_empty_columns=True,
skip_drop=True,
):
feature_names_out = self._get_feature_name_out_for_transformer(
name, trans, input_features
)
if feature_names_out is None:
continue
transformer_with_feature_names_out.append((name, feature_names_out))
if not transformer_with_feature_names_out:
# No feature names
return np.array([], dtype=object)
return self._add_prefix_for_feature_names_out(
transformer_with_feature_names_out
)
def _add_prefix_for_feature_names_out(self, transformer_with_feature_names_out):
"""Add prefix for feature names out that includes the transformer names.
Parameters
----------
transformer_with_feature_names_out : list of tuples of (str, array-like of str)
The tuple consistent of the transformer's name and its feature names out.
Returns
-------
feature_names_out : ndarray of shape (n_features,), dtype=str
Transformed feature names.
"""
if self.verbose_feature_names_out:
# Prefix the feature names out with the transformers name
names = list(
chain.from_iterable(
(f"{name}__{i}" for i in feature_names_out)
for name, feature_names_out in transformer_with_feature_names_out
)
)
return np.asarray(names, dtype=object)
# verbose_feature_names_out is False
# Check that names are all unique without a prefix
feature_names_count = Counter(
chain.from_iterable(s for _, s in transformer_with_feature_names_out)
)
top_6_overlap = [
name for name, count in feature_names_count.most_common(6) if count > 1
]
top_6_overlap.sort()
if top_6_overlap:
if len(top_6_overlap) == 6:
# There are more than 5 overlapping names, we only show the 5
# of the feature names
names_repr = str(top_6_overlap[:5])[:-1] + ", ...]"
else:
names_repr = str(top_6_overlap)
raise ValueError(
f"Output feature names: {names_repr} are not unique. Please set "
"verbose_feature_names_out=True to add prefixes to feature names"
)
return np.concatenate(
[name for _, name in transformer_with_feature_names_out],
)
def _update_fitted_transformers(self, transformers):
"""Set self.transformers_ from given transformers.
Parameters
----------
transformers : list of estimators
The fitted estimators as the output of
`self._call_func_on_transformers(func=_fit_transform_one, ...)`.
That function doesn't include 'drop' or transformers for which no
column is selected. 'drop' is kept as is, and for the no-column
transformers the unfitted transformer is put in
`self.transformers_`.
"""
# transformers are fitted; excludes 'drop' cases
fitted_transformers = iter(transformers)
transformers_ = []
for name, old, column, _ in self._iter(
fitted=False,
column_as_labels=False,
skip_drop=False,
skip_empty_columns=False,
):
if old == "drop":
trans = "drop"
elif _is_empty_column_selection(column):
trans = old
else:
trans = next(fitted_transformers)
transformers_.append((name, trans, column))
# sanity check that transformers is exhausted
assert not list(fitted_transformers)
self.transformers_ = _with_dtype_warning_enabled_set_to(True, transformers_)
def _validate_output(self, result):
"""
Ensure that the output of each transformer is 2D. Otherwise
hstack can raise an error or produce incorrect results.
"""
names = [
name
for name, _, _, _ in self._iter(
fitted=True,
column_as_labels=False,
skip_drop=True,
skip_empty_columns=True,
)
]
for Xs, name in zip(result, names):
if not getattr(Xs, "ndim", 0) == 2 and not hasattr(Xs, "__dataframe__"):
raise ValueError(
"The output of the '{0}' transformer should be 2D (numpy array, "
"scipy sparse array, dataframe).".format(name)
)
if _get_output_config("transform", self)["dense"] == "pandas":
return
try:
import pandas as pd
except ImportError:
return
for Xs, name in zip(result, names):
if not _is_pandas_df(Xs):
continue
for col_name, dtype in Xs.dtypes.to_dict().items():
if getattr(dtype, "na_value", None) is not pd.NA:
continue
if pd.NA not in Xs[col_name].values:
continue
class_name = self.__class__.__name__
# TODO(1.6): replace warning with ValueError
warnings.warn(
(
f"The output of the '{name}' transformer for column"
f" '{col_name}' has dtype {dtype} and uses pandas.NA to"
" represent null values. Storing this output in a numpy array"
" can cause errors in downstream scikit-learn estimators, and"
" inefficiencies. Starting with scikit-learn version 1.6, this"
" will raise a ValueError. To avoid this problem you can (i)"
" store the output in a pandas DataFrame by using"
f" {class_name}.set_output(transform='pandas') or (ii) modify"
f" the input data or the '{name}' transformer to avoid the"
" presence of pandas.NA (for example by using"
" pandas.DataFrame.astype)."
),
FutureWarning,
)
def _record_output_indices(self, Xs):
"""
Record which transformer produced which column.
"""
idx = 0
self.output_indices_ = {}
for transformer_idx, (name, _, _, _) in enumerate(
self._iter(
fitted=True,
column_as_labels=False,
skip_drop=True,
skip_empty_columns=True,
)
):
n_columns = Xs[transformer_idx].shape[1]
self.output_indices_[name] = slice(idx, idx + n_columns)
idx += n_columns
# `_iter` only generates transformers that have a non empty
# selection. Here we set empty slices for transformers that
# generate no output, which are safe for indexing
all_names = [t[0] for t in self.transformers] + ["remainder"]
for name in all_names:
if name not in self.output_indices_:
self.output_indices_[name] = slice(0, 0)
def _log_message(self, name, idx, total):
if not self.verbose:
return None
return "(%d of %d) Processing %s" % (idx, total, name)
def _call_func_on_transformers(self, X, y, func, column_as_labels, routed_params):
"""
Private function to fit and/or transform on demand.
Parameters
----------
X : {array-like, dataframe} of shape (n_samples, n_features)
The data to be used in fit and/or transform.
y : array-like of shape (n_samples,)
Targets.
func : callable
Function to call, which can be _fit_transform_one or
_transform_one.
column_as_labels : bool
Used to iterate through transformers. If True, columns are returned
as strings. If False, columns are returned as they were given by
the user. Can be True only if the ``ColumnTransformer`` is already
fitted.
routed_params : dict
The routed parameters as the output from ``process_routing``.
Returns
-------
Return value (transformers and/or transformed X data) depends
on the passed function.
"""
if func is _fit_transform_one:
fitted = False
else: # func is _transform_one
fitted = True
transformers = list(
self._iter(
fitted=fitted,
column_as_labels=column_as_labels,
skip_drop=True,
skip_empty_columns=True,
)
)
try:
jobs = []
for idx, (name, trans, columns, weight) in enumerate(transformers, start=1):
if func is _fit_transform_one:
if trans == "passthrough":
output_config = _get_output_config("transform", self)
trans = FunctionTransformer(
accept_sparse=True,
check_inverse=False,
feature_names_out="one-to-one",
).set_output(transform=output_config["dense"])
extra_args = dict(
message_clsname="ColumnTransformer",
message=self._log_message(name, idx, len(transformers)),
)
else: # func is _transform_one
extra_args = {}
jobs.append(
delayed(func)(
transformer=clone(trans) if not fitted else trans,
X=_safe_indexing(X, columns, axis=1),
y=y,
weight=weight,
**extra_args,
params=routed_params[name],
)
)
return Parallel(n_jobs=self.n_jobs)(jobs)
except ValueError as e:
if "Expected 2D array, got 1D array instead" in str(e):
raise ValueError(_ERR_MSG_1DCOLUMN) from e
else:
raise
def fit(self, X, y=None, **params):
"""Fit all transformers using X.
Parameters
----------
X : {array-like, dataframe} of shape (n_samples, n_features)
Input data, of which specified subsets are used to fit the
transformers.
y : array-like of shape (n_samples,...), default=None
Targets for supervised learning.
**params : dict, default=None
Parameters to be passed to the underlying transformers' ``fit`` and
``transform`` methods.
You can only pass this if metadata routing is enabled, which you
can enable using ``sklearn.set_config(enable_metadata_routing=True)``.
.. versionadded:: 1.4
Returns
-------
self : ColumnTransformer
This estimator.
"""
_raise_for_params(params, self, "fit")
# we use fit_transform to make sure to set sparse_output_ (for which we
# need the transformed data) to have consistent output type in predict
self.fit_transform(X, y=y, **params)
return self
@_fit_context(
# estimators in ColumnTransformer.transformers are not validated yet
prefer_skip_nested_validation=False
)
def fit_transform(self, X, y=None, **params):
"""Fit all transformers, transform the data and concatenate results.
Parameters
----------
X : {array-like, dataframe} of shape (n_samples, n_features)
Input data, of which specified subsets are used to fit the
transformers.
y : array-like of shape (n_samples,), default=None
Targets for supervised learning.
**params : dict, default=None
Parameters to be passed to the underlying transformers' ``fit`` and
``transform`` methods.
You can only pass this if metadata routing is enabled, which you
can enable using ``sklearn.set_config(enable_metadata_routing=True)``.
.. versionadded:: 1.4
Returns
-------
X_t : {array-like, sparse matrix} of \
shape (n_samples, sum_n_components)
Horizontally stacked results of transformers. sum_n_components is the
sum of n_components (output dimension) over transformers. If
any result is a sparse matrix, everything will be converted to
sparse matrices.
"""
_raise_for_params(params, self, "fit_transform")
self._check_feature_names(X, reset=True)
X = _check_X(X)
# set n_features_in_ attribute
self._check_n_features(X, reset=True)
self._validate_transformers()
n_samples = _num_samples(X)
self._validate_column_callables(X)
self._validate_remainder(X)
if _routing_enabled():
routed_params = process_routing(self, "fit_transform", **params)
else:
routed_params = self._get_empty_routing()
result = self._call_func_on_transformers(
X,
y,
_fit_transform_one,
column_as_labels=False,
routed_params=routed_params,
)
if not result:
self._update_fitted_transformers([])
# All transformers are None
return np.zeros((n_samples, 0))
Xs, transformers = zip(*result)
# determine if concatenated output will be sparse or not
if any(sparse.issparse(X) for X in Xs):
nnz = sum(X.nnz if sparse.issparse(X) else X.size for X in Xs)
total = sum(
X.shape[0] * X.shape[1] if sparse.issparse(X) else X.size for X in Xs
)
density = nnz / total
self.sparse_output_ = density < self.sparse_threshold
else:
self.sparse_output_ = False