NSGAIISelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.MultiObjective

NSGA-II Multi-objective Feature Selection.

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

Implements: ISupervisedFeatureSelector<T>

For Beginners

Sometimes we want both good accuracy AND few features. NSGA-II finds multiple solutions that trade off between these goals. Some solutions have high accuracy but many features; others have fewer features but slightly lower accuracy. You can then choose the best trade-off.

How It Works

Uses the Non-dominated Sorting Genetic Algorithm II (NSGA-II) to optimize multiple objectives simultaneously: maximizing prediction accuracy while minimizing the number of selected features.

Constructors

Constructor Summary
NSGAIISelector(int maxFeatures, int populationSize, int nGenerations, double crossoverRate, double mutationRate, int[] columnIndices)

Properties

Property Summary
Vector<T> FeatureImportances { get; }
bool SupportsInverseTransform { get; }
int MaxFeatures { get; }
int PopulationSize { 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)