MutualInfoClassification<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Filter.Classification

Mutual Information for classification-based feature selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Mutual information measures how much knowing a feature’s value helps predict the class. Unlike correlation, MI can detect any type of relationship, not just linear ones. A high MI score means the feature contains useful information for classification.

How It Works

Mutual Information Classification estimates the mutual information between each feature and the discrete class label. MI measures how much knowing the feature reduces uncertainty about the class.

Constructors

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

Properties

Property Summary
Vector<T> MIScores { 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)