8000 FEA SLEP006: Metadata routing for `SelfTrainingClassifier` (#28494) · scikit-learn/scikit-learn@cef803a · GitHub
[go: up one dir, main page]

Skip to content

Commit cef803a

Browse files
authored
FEA SLEP006: Metadata routing for SelfTrainingClassifier (#28494)
1 parent 0dba98f commit cef803a

File tree

7 files changed

+382
-85
lines changed

7 files changed

+382
-85
lines changed

doc/metadata_routing.rst

+1-1
Original file line numberDiff line numberDiff line change
@@ -315,6 +315,7 @@ Meta-estimators and functions supporting metadata routing:
315315
- :class:`sklearn.multioutput.RegressorChain`
316316
- :class:`sklearn.pipeline.FeatureUnion`
317317
- :class:`sklearn.pipeline.Pipeline`
318+
- :class:`sklearn.semi_supervised.SelfTrainingClassifier`
318319

319320
Meta-estimators and tools not supporting metadata routing yet:
320321

@@ -324,4 +325,3 @@ Meta-estimators and tools not supporting metadata routing yet:
324325
- :class:`sklearn.feature_selection.RFECV`
325326
- :class:`sklearn.feature_selection.SequentialFeatureSelector`
326327
- :class:`sklearn.model_selection.permutation_test_score`
327-
- :class:`sklearn.semi_supervised.SelfTrainingClassifier`

doc/whats_new/v1.6.rst

+16-1
Original file line numberDiff line numberDiff line change
@@ -71,7 +71,7 @@ more details.
7171
:class:`ensemble.StackingRegressor` now support metadata routing and pass
7272
``**fit_params`` to the underlying estimators via their `fit` methods.
7373
:pr:`28701` by :user:`Stefanie Senger <StefanieSenger>`.
74-
74+
7575
- |Feature| :class:`compose.TransformedTargetRegressor` now supports metadata
7676
routing in its `fit` and `predict` methods and routes the corresponding
7777
params to the underlying regressor.
@@ -81,6 +81,14 @@ more details.
8181
the `fit` method of its estimator and for its underlying CV splitter and scorer.
8282
:pr:`29329` by :user:`Stefanie Senger <StefanieSenger>`.
8383

84+
- |Feature| :class:`semi_supervised.SelfTrainingClassifier`
85+
now supports metadata routing. The fit method now accepts ``**fit_params``
86+
which are passed to the underlying estimators via their `fit` methods.
87+
In addition, the `predict`, `predict_proba`, `predict_log_proba`, `score`
88+
and `decision_function` methods also accept ``**params`` which are
89+
passed to the underlying estimators via their respective methods.
90+
:pr:`28494` by :user:`Adam Li <adam2392>`.
91+
8492
Dropping official support for PyPy
8593
----------------------------------
8694

@@ -189,6 +197,13 @@ Changelog
189197
when duplicate values in the training data lead to inaccurate outlier detection.
190198
:pr:`28773` by :user:`Henrique Caroço <HenriqueProj>`.
191199

200+
:mod:`sklearn.semi_supervised`
201+
..............................
202+
203+
- |API| :class:`semi_supervised.SelfTrainingClassifier`
204+
deprecated the `base_estimator` parameter in favor of `estimator`.
205+
:pr:`28494` by :user:`Adam Li <adam2392>`.
206+
192207
Thanks to everyone who has contributed to the maintenance and improvement of
193208
the project since version 1.5, including:
194209

0 commit comments

Comments
 (0)
0