KDEBasedSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Density

Kernel Density Estimation (KDE) based Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

KDE estimates the probability distribution of your data smoothly. This selector finds features where different classes have clearly different distributions, making it easier to tell classes apart.

How It Works

Uses kernel density estimation to select features that maximize the separation of class-conditional density estimates.

Constructors

Constructor Summary
KDEBasedSelector(int nFeaturesToSelect, double bandwidth, int[] columnIndices)

Properties

Property Summary
Vector<T> KDESeparationScores { get; }
bool SupportsInverseTransform { get; }
double Bandwidth { 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)