RandomizedLassoSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Stability

Randomized Lasso Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Regular Lasso can be unstable - small changes in data can lead to different features being selected. Randomized Lasso runs Lasso many times with random perturbations and selects features that are consistently chosen, giving more reliable results.

How It Works

Combines Lasso with random reweighting and subsampling to provide more stable feature selection that is less sensitive to the choice of regularization parameter.

Constructors

Constructor Summary
RandomizedLassoSelector(int nFeaturesToSelect, int nIterations, double alpha, double sampleFraction, double weaknessRange, 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)