Module Description

Splitters are destined to split the provided dataset varous ways to simplify cross-validation analysis, implement boosting of the estimates, or sample null-space via permutation testing.

Most of the splitters at the moment split 2-ways -- conventionally first part is used for training, and 2nd part for testing by CrossValidatedTransferError and SplitClassifier.

Brief Description of Available Splitters

• NoneSplitter - just return full dataset as the desired part (training/testing)
• OddEvenSplitter - 2 splits: (odd samples,even samples) and (even, odd)
• HalfSplitter - 2 splits: (first half, second half) and (second, first)
• NFoldSplitter - splits for N-Fold cross validation.

Module Organization

Package Tree for splitters