EnsembleFS<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Ensemble

Ensemble Feature Selection combining multiple methods.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Different feature selection methods have different biases and catch different patterns. By combining multiple methods (like asking multiple experts), we get a more reliable answer. Features that everyone agrees are important are more trustworthy than those only one method likes.

How It Works

Ensemble Feature Selection combines the results of multiple feature selection methods using voting or rank aggregation. Features consistently selected across multiple methods are more likely to be truly important.

Constructors

Constructor Summary
EnsembleFS(int nFeaturesToSelect, double threshold, AggregationMethod<T> aggregation, int[] columnIndices)

Properties

Property Summary
AggregationMethod<T> Aggregation { get; }
Vector<T> AggregatedScores { get; }
bool SupportsInverseTransform { get; }
double Threshold { 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)