FCBF<T>
Models & Types · AiDotNet.Preprocessing.FeatureSelection.Filter.Multivariate
Fast Correlation-Based Filter (FCBF) for feature selection.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → FCBF<T>
Implements: ISupervisedFeatureSelector<T>
For Beginners
FCBF finds features that are strongly related to the target and removes any feature that’s “dominated” by another (meaning the other feature is just as good at predicting the target AND is more correlated with this feature). This efficiently eliminates redundancy.
How It Works
FCBF uses symmetrical uncertainty to identify relevant features and remove redundant ones. It’s efficient for high-dimensional data with the concept of predominant features that are not dominated by any other feature.
Constructors
| Constructor | Summary |
|---|---|
FCBF(double threshold, int[] columnIndices) |
Properties
| Property | Summary |
|---|---|
Vector<T> SymmetricalUncertainties { get; } |
|
bool SupportsInverseTransform { 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) |