StabilitySelection<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Hybrid

Stability Selection for robust feature selection with FDR control.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

By running selection on many random subsets of data, we find features that are “stably” selected regardless of which samples we use. These are more likely to be truly important.

How It Works

Runs a base feature selector on many bootstrap samples and selects features that are consistently chosen across subsamples. Provides error rate control.

Constructors

Constructor Summary
StabilitySelection(int nFeaturesToSelect, int nBootstraps, double sampleFraction, double threshold, Func<Matrix<T>, Vector<T>, int[]> baseSelector, int? randomState, int[] columnIndices)

Properties

Property Summary
Vector<T> SelectionProbabilities { get; }
bool SupportsInverseTransform { 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)