StratifiedShuffleSplitter<T>

Models & Types ยท AiDotNet.Preprocessing.DataPreparation.Splitting.CrossValidation

Stratified Monte Carlo cross-validation that preserves class distribution in random splits.

Inheritance: DataSplitterBase<T> โ†’ StratifiedShuffleSplitter<T>

For Beginners

This combines:

  • Shuffle-Split: Random train/test splits repeated multiple times
  • Stratification: Each split preserves the original class distribution

How It Works

When to Use:

  • Classification problems with imbalanced classes
  • When you want multiple random evaluations (like Monte Carlo CV)
  • But also need to ensure each split has proper class representation

Constructors

Constructor Summary
StratifiedShuffleSplitter(int nSplits, double testSize, int randomSeed) Creates a new Stratified Shuffle splitter.

Properties

Property Summary
bool RequiresLabels { get; }
int NumSplits { get; }
string Description { get; }

Methods

Method Summary
DataSplitResult<T> Split(Matrix<T> X, Vector<T> y)
IEnumerable<DataSplitResult<T>> GetSplits(Matrix<T> X, Vector<T> y)