SlidingWindowSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Streaming

Sliding Window Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Data patterns can change over time (concept drift). This method only looks at the most recent samples in a sliding window, so it adapts to changes. Features that were important last month might not be important now, and this method handles that.

How It Works

Maintains a sliding window of recent samples and performs feature selection based on the most recent data, adapting to concept drift.

Constructors

Constructor Summary
SlidingWindowSelector(int nFeaturesToSelect, int windowSize, int[] columnIndices)

Properties

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