StackingFeatureSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Ensemble

Stacking-based Feature Selection.

Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> โ†’ StackingFeatureSelector<T>

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Stacking combines multiple ways of measuring feature importance (like correlation, variance, and mutual information). A second layer then learns how to best combine these measures, giving you more reliable feature selection than any single method alone.

How It Works

Uses a stacking ensemble approach where multiple base feature scorers are combined using a meta-learner to produce final feature rankings.

Constructors

Constructor Summary
StackingFeatureSelector(int nFeaturesToSelect, int[] columnIndices)

Properties

Property Summary
Vector<T> StackedScores { get; }
bool SupportsInverseTransform { get; }
int NFeaturesToSelect { get; }
int[] SelectedIndices { get; }

Methods

Method Summary
Matrix<T> FitTransform(Matrix<T> data, Vector<T> target)
bool[] GetSupportMask()
string[] GetFeatureNamesOut(string[] inputFeatureNames)
void Fit(Matrix<T> data, Vector<T> target)