MICorrelationHybrid<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Hybrid

Mutual Information and Correlation Hybrid Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Some features have linear relationships (more X means more Y), while others have non-linear patterns (X affects Y in complex ways). This method uses correlation to find linear patterns and mutual information to find any pattern, then combines both scores.

How It Works

Combines mutual information (captures non-linear relationships) with Pearson correlation (captures linear relationships) to identify features that are important under both perspectives.

Constructors

Constructor Summary
MICorrelationHybrid(int nFeaturesToSelect, double miWeight, int nBins, int[] columnIndices)

Properties

Property Summary
Vector<T> CorrelationScores { get; }
Vector<T> HybridScores { get; }
Vector<T> MIScores { get; }
bool SupportsInverseTransform { get; }
double MIWeight { 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)