FRegression<T>
Models & Types · AiDotNet.Preprocessing.FeatureSelection.Filter.Univariate
F-Regression for feature selection based on linear relationship with continuous target.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → FRegression<T>
Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>
For Beginners
For regression problems (predicting continuous values), we need to know which features have a linear relationship with what we’re predicting. F-regression fits a simple line between each feature and the target, then measures how well that line explains the variation in the target.
How It Works
Computes the F-statistic for a univariate linear regression between each feature and the continuous target. Features with higher F-statistics have stronger linear relationships with the target.
Constructors
| Constructor | Summary |
|---|---|
FRegression(int nFeaturesToSelect, double pValueThreshold, int[] columnIndices) |
Properties
| Property | Summary |
|---|---|
Vector<T> FStatistics { get; } |
|
Vector<T> PValues { get; } |
|
Vector<T> RSquaredValues { 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) |