FisherScore<T>

Models & Types · AiDotNet.Preprocessing.FeatureSelection.Filter

Fisher Score for feature selection.

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

Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>

For Beginners

Imagine you’re sorting fruits by color. A good feature (like color) would make all apples similar to each other but different from oranges. Fisher Score measures exactly this: how much a feature groups similar items together while keeping different groups apart.

How It Works

Fisher Score measures the ratio of between-class variance to within-class variance. Features with high Fisher Scores have good class separability, meaning samples from different classes are far apart while samples from the same class are close together.

Constructors

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

Properties

Property Summary
Vector<T> FisherScores { 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)