HSICSelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Kernel

Hilbert-Schmidt Independence Criterion (HSIC) based Feature Selection.

Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → HSICSelector<T>

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

HSIC is a powerful way to measure if two variables are related, even in complex non-linear ways. By computing HSIC between each feature and the target, we find features that are truly informative, even when the relationship isn’t a straight line.

How It Works

Uses HSIC to measure the statistical dependency between features and target in a reproducing kernel Hilbert space, capturing non-linear dependencies.

Constructors

Constructor Summary
HSICSelector(int nFeaturesToSelect, double gammaX, double gammaY, int[] columnIndices)

Properties

Property Summary
Vector<T> HSICScores { get; }
bool SupportsInverseTransform { get; }
double GammaX { get; }
double GammaY { 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)