MLMI<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.MultiLabel

Multi-Label Mutual Information (ML-MI) for multi-label feature selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Mutual information measures how much knowing one thing tells you about another. In multi-label problems, ML-MI measures how much each feature tells you about the entire combination of labels an instance might have.

How It Works

ML-MI extends mutual information to handle multi-label problems by computing the mutual information between each feature and the entire label set. It can consider label correlations and dependencies.

Constructors

Constructor Summary
MLMI(int nFeaturesToSelect, int nBins, bool considerLabelCorrelations, int[] columnIndices)

Properties

Property Summary
Vector<T> MutualInformation { get; }
bool ConsiderLabelCorrelations { get; }
bool SupportsInverseTransform { get; }
int NBins { get; }
int NFeaturesToSelect { get; }
int[] SelectedIndices { get; }

Methods

Method Summary
Matrix<T> FitTransform(Matrix<T> data, Matrix<T> labels)
Matrix<T> FitTransform(Matrix<T> data, Vector<T> target)
bool[] GetSupportMask()
string[] GetFeatureNamesOut(string[] inputFeatureNames)
void Fit(Matrix<T> data, Matrix<T> labels)
void Fit(Matrix<T> data, Vector<T> target)