MinimalRedundancy<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Unsupervised

Minimal Redundancy feature selection for unsupervised learning.

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

Implements: IFixedCountFeatureSelector<T>

For Beginners

If two features are almost identical (highly correlated), keeping both is wasteful. This method picks features that are as different from each other as possible, giving you maximum diversity.

How It Works

Minimal Redundancy selects a diverse set of features that are not highly correlated with each other. This ensures the selected features provide complementary rather than overlapping information.

Constructors

Constructor Summary
MinimalRedundancy(int nFeaturesToSelect, double correlationThreshold, int[] columnIndices)

Properties

Property Summary
Matrix<T> CorrelationMatrix { get; }
bool SupportsInverseTransform { get; }
double CorrelationThreshold { get; }
int NFeaturesToSelect { get; }
int[] SelectedIndices { get; }

Methods

Method Summary
bool[] GetSupportMask()
string[] GetFeatureNamesOut(string[] inputFeatureNames)