GiniImpuritySelection<T>
Models & Types · AiDotNet.Preprocessing.FeatureSelection.Filter
Gini Impurity-based Feature Selection.
Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> → GiniImpuritySelection<T>
Implements: IFixedCountFeatureSelector<T>, ISupervisedFeatureSelector<T>
For Beginners
Gini impurity measures how “mixed” a group is. If splitting data by a feature creates groups where samples are mostly the same class (pure groups), that feature is valuable. This method finds features that best separate different classes from each other.
How It Works
Measures how much each feature reduces impurity (Gini impurity) when used to split the data. Features that create purer groups after splitting are considered more important.
Constructors
| Constructor | Summary |
|---|---|
GiniImpuritySelection(int nFeaturesToSelect, int nThresholds, int[] columnIndices) |
Properties
| Property | Summary |
|---|---|
Vector<T> GiniReductionScores { 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) |