ParticleSwarmSelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Genetic

Particle Swarm Optimization based Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Imagine a swarm of birds searching for food. Each bird (particle) explores feature combinations, remembers its best finds, and learns from the swarm’s best discoveries. Over time, they converge on good feature subsets.

How It Works

Uses particle swarm optimization to find optimal feature subsets where particles represent feature combinations moving through the solution space.

Constructors

Constructor Summary
ParticleSwarmSelector(int nFeaturesToSelect, int swarmSize, int nIterations, double inertia, double cognitive, double social, int? randomState, int[] columnIndices)

Properties

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