FloatingBackwardSelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Sequential

Sequential Floating Backward Selection (SFBS).

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

This is the reverse of SFFS. It starts with all features and removes them one by one, but can also add features back if doing so improves the result. The “floating” helps avoid getting stuck with bad choices.

How It Works

Starts with all features and combines backward elimination with conditional forward steps to find better feature subsets.

Constructors

Constructor Summary
FloatingBackwardSelector(int nFeaturesToSelect, int maxBacktracks, int[] columnIndices)

Properties

Property Summary
Vector<T> FeatureImportances { 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)