Thanks to visit codestin.com
Credit goes to github.com

Skip to content

ENH Adds feature_names_in_ to pipeline and multiclass #20780

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 7 commits into from
Aug 25, 2021
Merged

ENH Adds feature_names_in_ to pipeline and multiclass #20780

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
6d4c2ec
ENH Adds feature_names_in to pipeline and multiclass
thomasjpfan Aug 20, 2021
ab1419d
REV Reduce diff
thomasjpfan Aug 20, 2021
e13adf0
DOC Fix sphinx error
thomasjpfan Aug 20, 2021
f45825c
CLN Removes delgation code
thomasjpfan Aug 20, 2021
48e3463
DOC Adds ALL to docstring
thomasjpfan Aug 20, 2021
ccd95f7
Merge branch 'main' into feature_names_in_more
ogrisel Aug 23, 2021
c7ccfc9
Avoid duplicate call to _check_partial_fit_first_call in partial_fit
ogrisel Aug 23, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 26 additions & 2 deletions sklearn/multiclass.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,6 +269,12 @@ class OneVsRestClassifier(

.. versionadded:: 0.24

feature_names_in_ : ndarray of shape (`n_features_in_`,)
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

n_features_in_ without ticks? See #20818 (comment).

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Without the ticks sphinx will give a warning: " WARNING: Unknown target name: "n_features_in"." because rst is considering it a Hyperlink Target

Names of features seen during :term:`fit`. Only defined if the
underlying estimator exposes such an attribute when fit.

.. versionadded:: 1.0

Examples
--------
>>> import numpy as np
Expand Down Expand Up @@ -342,6 +348,8 @@ def fit(self, X, y):

if hasattr(self.estimators_[0], "n_features_in_"):
self.n_features_in_ = self.estimators_[0].n_features_in_
if hasattr(self.estimators_[0], "feature_names_in_"):
self.feature_names_in_ = self.estimators_[0].feature_names_in_

return self

Expand Down Expand Up @@ -664,6 +672,12 @@ class OneVsOneClassifier(MetaEstimatorMixin, ClassifierMixin, BaseEstimator):

.. 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

Examples
--------
>>> from sklearn.datasets import load_iris
Expand Down Expand Up @@ -762,7 +776,8 @@ def partial_fit(self, X, y, classes=None):
-------
self
"""
if _check_partial_fit_first_call(self, classes):
first_call = _check_partial_fit_first_call(self, classes)
if first_call:
self.estimators_ = [
clone(self.estimator)
for _ in range(self.n_classes_ * (self.n_classes_ - 1) // 2)
Expand All @@ -780,7 +795,7 @@ def partial_fit(self, X, y, classes=None):
y,
accept_sparse=["csr", "csc"],
force_all_finite=False,
reset=_check_partial_fit_first_call(self, classes),
reset=first_call,
)
check_classification_targets(y)
combinations = itertools.combinations(range(self.n_classes_), 2)
Expand Down Expand Up @@ -842,6 +857,7 @@ def decision_function(self, X):
scikit-learn conventions for binary classification.
"""
check_is_fitted(self)
self._check_feature_names(X, reset=False)

indices = self.pairwise_indices_
if indices is None:
Expand Down Expand Up @@ -936,6 +952,12 @@ class OutputCodeClassifier(MetaEstimatorMixin, ClassifierMixin, BaseEstimator):

.. versionadded:: 0.24

feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Only defined if the
underlying estimator exposes such an attribute when fit.

.. versionadded:: 1.0

Examples
--------
>>> from sklearn.multiclass import OutputCodeClassifier
Expand Down Expand Up @@ -1032,6 +1054,8 @@ def fit(self, X, y):

if hasattr(self.estimators_[0], "n_features_in_"):
self.n_features_in_ = self.estimators_[0].n_features_in_
if hasattr(self.estimators_[0], "feature_names_in_"):
self.feature_names_in_ = self.estimators_[0].feature_names_in_

return self

Expand Down
11 changes: 11 additions & 0 deletions sklearn/pipeline.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,6 +109,12 @@ class Pipeline(_BaseComposition):

.. versionadded:: 0.24

feature_names_in_ : ndarray of shape (`n_features_in_`,)
Names of features seen during :term:`fit`. Only defined if the
underlying estimator exposes such an attribute when fit.

.. versionadded:: 1.0

See Also
--------
make_pipeline : Convenience function for simplified pipeline construction.
Expand Down Expand Up @@ -672,6 +678,11 @@ def n_features_in_(self):
# delegate to first step (which will call _check_is_fitted)
return self.steps[0][1].n_features_in_

@property
def feature_names_in_(self):
# delegate to first step (which will call _check_is_fitted)
return self.steps[0][1].feature_names_in_

def __sklearn_is_fitted__(self):
"""Indicate whether pipeline has been fit."""
try:
Expand Down
10 changes: 6 additions & 4 deletions sklearn/tests/test_common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,7 +12,7 @@
import re
import pkgutil
from inspect import isgenerator, signature
from itertools import product
from itertools import product, chain
from functools import partial

import pytest
Expand Down Expand Up @@ -329,16 +329,18 @@ def test_check_n_features_in_after_fitting(estimator):
"feature_extraction",
"kernel_approximation",
"model_selection",
"multiclass",
"multioutput",
"pipeline",
"semi_supervised",
}

_estimators_to_test = list(
chain(_tested_estimators(), [make_pipeline(LogisticRegression(C=1))])
)


column_name_estimators = [
est
for est in _tested_estimators()
for est in _estimators_to_test
if est.__module__.split(".")[1] not in COLUMN_NAME_MODULES_TO_IGNORE
]

Expand Down