SelectFwe<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Filter.Univariate

Selects features based on a family-wise error rate test.

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

Implements: ISupervisedFeatureSelector<T>

For Beginners

FWER is the strictest correction:

  • Controls the probability of ANY false positive
  • Uses Bonferroni: alpha/number_of_features
  • Very conservative: may miss true positives
  • Best when false positives are costly

How It Works

SelectFwe applies Bonferroni correction to control the probability of making even one false positive among all selected features.

This is the most conservative multiple testing correction, dividing the significance threshold by the number of tests.

Constructors

Constructor Summary
SelectFwe(double alpha, SelectKBestScoreFunc scoringFunction, int[] columnIndices) Creates a new instance of SelectFwe.

Properties

Property Summary
SelectKBestScoreFunc ScoringFunction { get; } Gets the scoring function used.
Vector<T> AdjustedPValues { get; } Gets the Bonferroni-adjusted p-values.
Vector<T> PValues { get; } Gets the original p-values for each feature.
Vector<T> Scores { get; } Gets the scores for each feature.
bool SupportsInverseTransform { get; } Gets whether this transformer supports inverse transformation.
double Alpha { get; } Gets the family-wise significance level (alpha).
int[] SelectedIndices { get; } Gets the indices of selected features.

Methods

Method Summary
Matrix<T> FitTransform(Matrix<T> data, Vector<T> target) Fits and transforms the data.
bool[] GetSupportMask() Gets the support mask indicating which features are selected.
string[] GetFeatureNamesOut(string[] inputFeatureNames) Gets the output feature names after transformation.
void Fit(Matrix<T> data, Vector<T> target) Fits the selector by computing Bonferroni-corrected p-values.