DISR<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Filter.InformationTheory

Double Input Symmetric Relevance (DISR) for feature selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

DISR looks at how pairs of features together relate to the target, using a normalized measure that accounts for both directions of information flow. This helps find features that complement each other in predicting the target.

How It Works

DISR extends mutual information by considering symmetric relevance between pairs of features and the target. It uses the concept of joint symmetric uncertainty to measure feature relevance.

Constructors

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

Properties

Property Summary
Vector<T> DISRScores { get; }
Vector<T> RelevanceScores { get; }
bool SupportsInverseTransform { get; }
int NBins { 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)