JointMISelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Multivariate

Joint Mutual Information Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Regular mutual information looks at features one at a time. Joint MI considers how features work together. It picks features that provide unique information about the target, avoiding features that just repeat what others already tell you.

How It Works

Selects features by maximizing joint mutual information with the target while minimizing redundancy among selected features.

Constructors

Constructor Summary
JointMISelector(int nFeaturesToSelect, int nBins, double redundancyPenalty, int[] columnIndices)

Properties

Property Summary
Vector<T> JMIScores { 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)