JaccardSimilaritySelector<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Similarity

Jaccard Similarity based Feature Selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Jaccard similarity measures overlap between sets. After converting features to binary (above/below threshold), it compares which points are “high” in both feature and target simultaneously.

How It Works

Selects features based on their Jaccard similarity with the target after binarization, measuring the intersection over union of positive values.

Constructors

Constructor Summary
JaccardSimilaritySelector(int nFeaturesToSelect, int[] columnIndices)

Properties

Property Summary
Vector<T> JaccardScores { get; }
bool SupportsInverseTransform { 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)