FisherReliefHybrid<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Hybrid

Fisher-Relief Hybrid feature selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Fisher Score looks at class averages while ReliefF looks at individual sample relationships. Combining them gives you features that work well from both viewpoints - good class separation AND good at distinguishing similar vs different samples.

How It Works

Combines Fisher Score (parametric, class separability) with ReliefF (instance-based, neighbor relationships) to leverage both perspectives.

Constructors

Constructor Summary
FisherReliefHybrid(int nFeaturesToSelect, double fisherWeight, int nNeighbors, int[] columnIndices)

Properties

Property Summary
Vector<T> FisherScores { get; }
Vector<T> HybridScores { get; }
Vector<T> ReliefScores { get; }
bool SupportsInverseTransform { get; }
double FisherWeight { 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)