OnlineFeatureSelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Streaming

Online Feature Selection for Streaming Data.

Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → OnlineFeatureSelector<T>

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Traditional feature selection processes all data at once. Online selection updates incrementally as new samples arrive, which is useful when you can’t store all data in memory or when data comes in continuously.

How It Works

Performs incremental feature selection that can update as new data arrives, suitable for streaming or online learning scenarios.

Constructors

Constructor Summary
OnlineFeatureSelector(int nFeaturesToSelect, double learningRate, int[] columnIndices)

Properties

Property Summary
Vector<T> RunningScores { get; }
bool SupportsInverseTransform { get; }
double LearningRate { 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)
void PartialFit(Matrix<T> data, Vector<T> target)