LagFeatureSelector<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.TimeSeries

Lag-based Feature Selection for Time Series.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

In time series, past values often predict future values. This selector finds features whose past values (lags) are strongly correlated with the target, helping you identify which features are most useful for forecasting.

How It Works

Selects features based on their lagged correlations with the target, identifying features that have predictive power at different time lags.

Constructors

Constructor Summary
LagFeatureSelector(int nFeaturesToSelect, int maxLag, int[] columnIndices)

Properties

Property Summary
Vector<T> BestLagCorrelations { get; }
bool SupportsInverseTransform { get; }
int MaxLag { get; }
int NFeaturesToSelect { get; }
int[] BestLags { 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)