CIFE<T>
Models & Types · AiDotNet.Preprocessing.FeatureSelection.Filter.InformationTheory
Conditional Infomax Feature Extraction (CIFE) for feature selection.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → CIFE<T>
Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>
For Beginners
CIFE evaluates how much new information a feature provides about the target, given what you already know from selected features. It’s like asking “what do you know that I don’t already know?” for each feature.
How It Works
CIFE is an information-theoretic method that maximizes the conditional mutual information while considering the interaction between features and the target.
Constructors
| Constructor | Summary |
|---|---|
CIFE(int nFeaturesToSelect, int nBins, double beta, int[] columnIndices) |
Properties
| Property | Summary |
|---|---|
Vector<T> CIFEScores { get; } |
|
bool SupportsInverseTransform { get; } |
|
double Beta { get; } |
|
int NBins { 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) |