FilterWrapperHybridSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Hybrid

Filter-Wrapper Hybrid Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

This method gets the best of both worlds. First, it quickly eliminates obviously irrelevant features using simple statistics (filter). Then, it carefully evaluates the remaining features using model performance (wrapper). This is faster than pure wrapper methods but more accurate than pure filter methods.

How It Works

Combines filter and wrapper methods: first uses a fast filter to reduce the feature space, then applies a more accurate wrapper method on the reduced set.

Constructors

Constructor Summary
FilterWrapperHybridSelector(int nFeaturesToSelect, int filterRatio, int wrapperIterations, int[] columnIndices)

Properties

Property Summary
Vector<T> FeatureScores { get; }
bool SupportsInverseTransform { 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)