SampleEntropySelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Entropy

Sample Entropy (SampEn) based Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>

For Beginners

Sample entropy is like approximate entropy but doesn’t count self-matches, making it more reliable for shorter sequences. It measures unpredictability - low SampEn means regular, predictable patterns; high SampEn means complex, chaotic behavior.

How It Works

Selects features based on their sample entropy, an improved version of approximate entropy that is less biased for short time series.

Constructors

Constructor Summary
SampleEntropySelector(int nFeaturesToSelect, int embeddingDimension, double tolerance, int[] columnIndices)

Properties

Property Summary
Vector<T> SampEnValues { get; }
bool SupportsInverseTransform { get; }
double Tolerance { get; }
int EmbeddingDimension { get; }
int NFeaturesToSelect { get; }
int[] SelectedIndices { get; }

Methods

Method Summary
Matrix<T> FitTransform(Matrix<T> data)
bool[] GetSupportMask()
string[] GetFeatureNamesOut(string[] inputFeatureNames)