CorrelationClusterSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Redundancy

Correlation Cluster based Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Features that are highly correlated form natural groups. Instead of keeping all similar features, this selector picks one representative from each group, reducing redundancy while keeping diversity.

How It Works

Selects features by clustering correlated features together and selecting the best representative from each cluster.

Constructors

Constructor Summary
CorrelationClusterSelector(int nFeaturesToSelect, double correlationThreshold, int[] columnIndices)

Properties

Property Summary
Vector<T> ClusterRepresentativeScores { get; }
bool SupportsInverseTransform { get; }
double CorrelationThreshold { 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)