Implementation:Scikit learn Scikit learn SelectorMixin

Knowledge Sources	Scikit_learn Scikit-learn Docs
Domains	Machine Learning, Feature Selection
Last Updated	2026-02-08 15:00 GMT

Overview

Concrete tool for providing a generic feature selection mixin with transform and inverse_transform functionality, provided by scikit-learn.

Description

The SelectorMixin class is a transformer mixin that performs feature selection given a support mask. It provides get_support, transform, inverse_transform, and get_feature_names_out methods. Subclasses must implement _get_support_mask to define which features to select.

Usage

Use this mixin as a base class when implementing custom feature selectors. It provides the standard scikit-learn transformer interface for feature selection, handling both dense and sparse input data.

Code Reference

Source Location

• Repository: scikit-learn
• File: sklearn/feature_selection/_base.py

Signature

class SelectorMixin(TransformerMixin, metaclass=ABCMeta):
    def get_support(self, indices=False):
    def transform(self, X):
    def inverse_transform(self, X):
    def get_feature_names_out(self, input_features=None):
    @abstractmethod
    def _get_support_mask(self):

Import

from sklearn.feature_selection import SelectorMixin

I/O Contract

Inputs

Name	Type	Required	Description
X	array-like of shape (n_samples, n_features)	Yes	Input data to transform or inverse-transform
indices	bool	No	If True, get_support returns integer indices instead of boolean mask (default False)

Outputs

Name	Type	Description
support	ndarray	Boolean mask or integer indices of selected features
X_transformed	ndarray of shape (n_samples, n_selected_features)	Reduced feature matrix
X_original	ndarray of shape (n_samples, n_features)	Feature matrix with zeros for non-selected features

Usage Examples

Basic Usage

import numpy as np
from sklearn.datasets import load_iris
from sklearn.base import BaseEstimator
from sklearn.feature_selection import SelectorMixin

class FeatureSelector(SelectorMixin, BaseEstimator):
    def fit(self, X, y=None):
        self.n_features_in_ = X.shape[1]
        return self
    def _get_support_mask(self):
        mask = np.zeros(self.n_features_in_, dtype=bool)
        mask[:2] = True  # select the first two features
        return mask

X, y = load_iris(return_X_y=True)
print(FeatureSelector().fit_transform(X, y).shape)  # (150, 2)

Related Pages

• Principle:Scikit_learn_Scikit_learn_Feature_Selection