Boruta<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Bioinformatics

Boruta feature selection algorithm.

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

Implements: ISupervisedFeatureSelector<T>

For Beginners

Boruta asks: “Is this feature better than random noise?” It shuffles your features to create meaningless versions (shadows), then compares real features against these shadows. Features that consistently beat their shadows are truly informative.

How It Works

Boruta creates “shadow features” (shuffled copies of real features) and compares feature importance against these shadows. Features consistently outperforming the best shadow are confirmed as important.

Constructors

Constructor Summary
Boruta(int maxIterations, double pValue, Func<Matrix<T>, Vector<T>, Vector<T>> importanceFunction, int? randomState, int[] columnIndices)

Properties

Property Summary
BorutaDecision<T>[] Decisions { get; }
Vector<T> Importances { get; }
bool SupportsInverseTransform { get; }
int MaxIterations { 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)