StabilitySelection<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Stability

Stability Selection for robust feature selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Different samples of your data might give different feature rankings. Stability selection checks which features are consistently chosen across many random samples. Features that are always selected are likely to be truly important, not just lucky in one particular sample.

How It Works

Stability selection runs feature selection on multiple random subsets of the data and keeps features that are consistently selected across runs. This reduces the variance of feature selection and produces more reliable results.

Constructors

Constructor Summary
StabilitySelection(int nFeaturesToSelect, int nIterations, double subsampleRatio, double selectionThreshold, int? randomState, int[] columnIndices)

Properties

Property Summary
Vector<T> SelectionFrequencies { get; }
bool SupportsInverseTransform { get; }
double SelectionThreshold { get; }
double SubsampleRatio { get; }
int NFeaturesToSelect { get; }
int NIterations { 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)