PCABasedSelection<T>

Models & Types ยท AiDotNet.Preprocessing.FeatureSelection.Dimensionality

PCA-Based Feature Selection using loadings analysis.

Inheritance: TransformerBase<T, Matrix<T>, Matrix<T>> โ†’ PCABasedSelection<T>

Implements: IFixedCountFeatureSelector<T>

For Beginners

PCA finds combinations of features that capture the most variation in your data. By looking at which original features contribute most to these combinations, we can identify which features are most informative overall.

How It Works

Uses Principal Component Analysis to identify which original features contribute most to the principal components. Features with high loadings on important components are selected.

Constructors

Constructor Summary
PCABasedSelection(int nFeaturesToSelect, int nComponents, int[] columnIndices)

Properties

Property Summary
Vector<T> FeatureImportances { get; }
bool SupportsInverseTransform { get; }
int NComponents { get; }
int NFeaturesToSelect { get; }
int[] SelectedIndices { get; }

Methods

Method Summary
bool[] GetSupportMask()
string[] GetFeatureNamesOut(string[] inputFeatureNames)