TabuSearchSelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Optimization

Tabu Search based Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Tabu search keeps a “forbidden list” of recent moves. This forces the algorithm to explore new areas instead of cycling back to old solutions, helping find better feature combinations.

How It Works

Uses tabu search optimization with a memory structure that prevents revisiting recently explored solutions, helping escape local optima.

Constructors

Constructor Summary
TabuSearchSelector(int nFeaturesToSelect, int tabuTenure, int nIterations, int? randomState, int[] columnIndices)

Properties

Property Summary
Vector<T> FeatureImportances { get; }
bool SupportsInverseTransform { get; }
int NFeaturesToSelect { get; }
int TabuTenure { 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)