HuberRobustSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Robustness

Huber Robust Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

The Huber loss combines squared error for small residuals with absolute error for large ones. This makes the regression less sensitive to outliers while still being efficient for normal data.

How It Works

Selects features based on their coefficients in a Huber regression, which downweights the influence of outliers using the Huber loss function.

Constructors

Constructor Summary
HuberRobustSelector(int nFeaturesToSelect, double delta, int maxIterations, double learningRate, int[] columnIndices)

Properties

Property Summary
Vector<T> HuberCoefficients { get; }
bool SupportsInverseTransform { get; }
double Delta { 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)