AdaptiveFeatureSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Incremental

Adaptive Feature Selector that adjusts selection based on performance.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Think of this like a sports team manager who keeps track of how well each player performs. Players who consistently do well stay on the team, while underperformers get replaced. Over time, this builds an optimal team (set of features).

How It Works

This selector adapts its feature selection over time based on observed performance. Features that consistently perform well are retained, while poor performers are replaced with alternatives.

Constructors

Constructor Summary
AdaptiveFeatureSelector(int nFeaturesToSelect, double adaptationRate, int minSamplesForAdaptation, int[] columnIndices)

Properties

Property Summary
Vector<T> PerformanceScores { get; }
bool SupportsInverseTransform { get; }
double AdaptationRate { get; }
int NFeaturesToSelect { get; }
int SampleCount { 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)
void PartialFit(Matrix<T> data, Vector<T> target)
void Reset()