GenericUnivariateSelect<T>
Models & Types · AiDotNet.Preprocessing.FeatureSelection.Filter.Univariate
Generic univariate feature selector with configurable mode.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → GenericUnivariateSelect<T>
Implements: ISupervisedFeatureSelector<T>
For Beginners
This is a “swiss army knife” selector:
- k_best: Select exactly k features
- percentile: Select top X% of features
- fpr: Select based on false positive rate
- fdr: Select based on false discovery rate
- fwe: Select based on family-wise error rate
How It Works
GenericUnivariateSelect provides a unified interface to all univariate feature selection methods. You can choose between k_best, percentile, fpr, fdr, and fwe modes.
This is useful when you want to experiment with different selection strategies without changing your code structure.
Constructors
| Constructor | Summary |
|---|---|
GenericUnivariateSelect(UnivariateSelectMode mode, object param, SelectKBestScoreFunc scoringFunction, int[] columnIndices) |
Creates a new instance of GenericUnivariateSelect. |
Properties
| Property | Summary |
|---|---|
SelectKBestScoreFunc ScoringFunction { get; } |
Gets the scoring function used. |
UnivariateSelectMode Mode { get; } |
Gets the selection mode. |
Vector<T> PValues { get; } |
Gets the 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. |
int[] SelectedIndices { get; } |
Gets the indices of selected features. |
object Param { get; } |
Gets the mode parameter (k, percentile, or alpha depending on mode). |
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 scores and selecting features. |