BackwardElimination<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Wrapper

Backward Elimination (Sequential Backward Selection) for feature selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Backward Elimination is like downsizing a team. You start with everyone and repeatedly remove the person whose absence hurts performance least. Unlike Forward Selection, this can find features that are only valuable together, since they start included.

How It Works

Starts with all features and greedily removes one feature at a time whose removal causes the least degradation in performance until the desired number is reached.

Constructors

Constructor Summary
BackwardElimination(int nFeaturesToSelect, Func<Matrix<T>, Vector<T>, int[], T> scoringFunction, int[] columnIndices)

Properties

Property Summary
Vector<T> RemovalScores { 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)