ModalitySelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Distribution

Modality based Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>

For Beginners

Modality refers to how many peaks a distribution has. Unimodal = 1 peak, bimodal = 2 peaks, multimodal = many peaks. Features with multiple modes often indicate natural groupings or distinct populations in the data.

How It Works

Selects features based on the estimated number of modes (peaks) in their distributions, using a histogram-based peak detection approach.

Constructors

Constructor Summary
ModalitySelector(int nFeaturesToSelect, int nBins, int targetModality, int[] columnIndices)

Properties

Property Summary
bool SupportsInverseTransform { get; }
int NBins { get; }
int NFeaturesToSelect { get; }
int TargetModality { get; }
int[] ModalityCounts { get; }
int[] SelectedIndices { get; }

Methods

Method Summary
Matrix<T> FitTransform(Matrix<T> data)
bool[] GetSupportMask()
string[] GetFeatureNamesOut(string[] inputFeatureNames)