org.neuroph.eval

Class CrossValidation

java.lang.Object

org.neuroph.eval.CrossValidation

public class CrossValidation
extends java.lang.Object

This class implements multithreaded cross validation procedure. Splits data set into k subsets (folds), trains the network with data from k-1 and tests with one subset Repeats the procedure k times each time using different subset for testing.

Constructor Summary

Constructors

Constructor and Description
CrossValidation(NeuralNetwork neuralNetwork, DataSet dataSet, int foldCount) Creates a new instance of crrossvalidation for specified neural network, data set and number of folds.

Method Summary

Modifier and Type	Method and Description
void	addEvaluator(Evaluator eval)
Evaluation	getEvaluation()
<T extends Evaluator> T	getEvaluator(java.lang.Class<T> type)
CrossValidationResult	getResult()
Sampling	getSampling()
void	run()
void	setSampling(Sampling sampling)

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Detail

CrossValidation

public CrossValidation(NeuralNetwork neuralNetwork,
                       DataSet dataSet,
                       int foldCount)

Creates a new instance of crrossvalidation for specified neural network, data set and number of folds.

Parameters:

neuralNetwork -

dataSet -

foldCount - number of folds to use

Method Detail

getSampling

public Sampling getSampling()

setSampling

public void setSampling(Sampling sampling)

getEvaluation

public Evaluation getEvaluation()

run

public void run()
         throws java.lang.InterruptedException,
                java.util.concurrent.ExecutionException

Throws:

java.lang.InterruptedException

java.util.concurrent.ExecutionException

addEvaluator

public void addEvaluator(Evaluator eval)

getEvaluator

public <T extends Evaluator> T getEvaluator(java.lang.Class<T> type)

getResult

public CrossValidationResult getResult()