EmbeddedWrapperHybridSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Hybrid

Embedded-Wrapper Hybrid Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

This method first uses Lasso regression to automatically shrink unimportant features to zero, giving us a candidate set. Then it fine-tunes this selection by trying to add or remove features to improve model performance. This balances speed with accuracy.

How It Works

Combines embedded (L1 regularization) and wrapper methods: first uses Lasso to identify a candidate set, then refines selection using sequential feature addition/removal.

Constructors

Constructor Summary
EmbeddedWrapperHybridSelector(int nFeaturesToSelect, double lassoAlpha, int wrapperIterations, int[] columnIndices)

Properties

Property Summary
Vector<T> FeatureScores { 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)