DistanceCorrelationSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Statistical

Distance Correlation Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Distance correlation is like regular correlation but can detect any type of relationship, not just linear ones. Unlike regular correlation, a distance correlation of 0 truly means no relationship exists. It computes distances between all pairs of points and correlates those distances.

How It Works

Uses distance correlation to detect both linear and non-linear dependencies between features and the target. Distance correlation is zero if and only if the variables are independent.

Constructors

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

Properties

Property Summary
Vector<T> DistanceCorrelations { 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)