Class RandomizedCrossValidation
- java.lang.Object
-
- elki.evaluation.classification.holdout.AbstractHoldout
-
- elki.evaluation.classification.holdout.RandomizedHoldout
-
- elki.evaluation.classification.holdout.RandomizedCrossValidation
-
- All Implemented Interfaces:
Holdout
public class RandomizedCrossValidation extends RandomizedHoldout
RandomizedCrossValidation provides a set of partitions of a database to perform cross-validation. The test sets are not guaranteed to be disjoint.- Since:
- 0.7.0
- Author:
- Arthur Zimek
-
-
Nested Class Summary
Nested Classes Modifier and Type Class Description static class
RandomizedCrossValidation.Par
Parameterization class
-
Field Summary
Fields Modifier and Type Field Description protected int
fold
Holds the number of folds, current fold.protected int
nfold
Holds the number of folds, current fold.-
Fields inherited from class elki.evaluation.classification.holdout.RandomizedHoldout
random
-
Fields inherited from class elki.evaluation.classification.holdout.AbstractHoldout
bundle, labelcol, labels
-
-
Constructor Summary
Constructors Constructor Description RandomizedCrossValidation(RandomFactory random, int nfold)
Constructor for n-fold cross-validation.
-
Method Summary
All Methods Instance Methods Concrete Methods Modifier and Type Method Description void
initialize(MultipleObjectsBundle bundle)
Initialize the holdout procedure for a data set.TrainingAndTestSet
nextPartitioning()
Get the next partitioning of the given holdout.int
numberOfPartitions()
How many partitions to test.-
Methods inherited from class elki.evaluation.classification.holdout.AbstractHoldout
allClassLabels, allClassLabels, findClassLabelColumn, getLabels
-
-
-
-
Constructor Detail
-
RandomizedCrossValidation
public RandomizedCrossValidation(RandomFactory random, int nfold)
Constructor for n-fold cross-validation.- Parameters:
random
- Random seednfold
- Number of folds
-
-
Method Detail
-
initialize
public void initialize(MultipleObjectsBundle bundle)
Description copied from interface:Holdout
Initialize the holdout procedure for a data set.- Specified by:
initialize
in interfaceHoldout
- Overrides:
initialize
in classAbstractHoldout
- Parameters:
bundle
- Data set bundle
-
numberOfPartitions
public int numberOfPartitions()
Description copied from interface:Holdout
How many partitions to test.- Returns:
- Number of partitions.
-
nextPartitioning
public TrainingAndTestSet nextPartitioning()
Description copied from interface:Holdout
Get the next partitioning of the given holdout.- Returns:
- Next partitioning of the data set
-
-