WhaleOptimizationFS<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Wrapper

Whale Optimization Algorithm for feature selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Whales hunt by creating bubble nets around fish. This algorithm mimics this with shrinking circles and spirals to converge on good feature combinations.

How It Works

Inspired by humpback whale bubble-net feeding. Uses shrinking encircling and spiral updating to hunt prey (optimal solution).

Constructors

Constructor Summary
WhaleOptimizationFS(int nFeaturesToSelect, int populationSize, int nIterations, Func<Matrix<T>, Vector<T>, bool[], double> fitnessFunc, int? randomState, int[] columnIndices)

Properties

Property Summary
bool SupportsInverseTransform { get; }
double BestFitness { get; }
double[] FeatureImportances { 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)