NormalizedCompressionSelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Compression

Normalized Compression Distance based Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

This measures how much “shared information” exists between a feature and the target. Features that compress well together with the target share more mutual information.

How It Works

Selects features based on their normalized compression distance to the target, approximating Kolmogorov complexity for feature relevance.

Constructors

Constructor Summary
NormalizedCompressionSelector(int nFeaturesToSelect, int nBins, int[] columnIndices)

Properties

Property Summary
Vector<T> NCDScores { 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)