meka.experiment.evaluators

Class RepeatedRuns

java.lang.Object

meka.events.LogObject

meka.experiment.evaluators.AbstractEvaluator

meka.experiment.evaluators.AbstractMetaEvaluator

meka.experiment.evaluators.RepeatedRuns

All Implemented Interfaces:

Serializable, ThreadLimiter, LogSupporter, Evaluator, weka.core.OptionHandler

public class RepeatedRuns
extends AbstractMetaEvaluator
implements ThreadLimiter

Repeatedly executes the base evaluator.

Version:

$Revision$

Author:

FracPete (fracpete at waikato dot ac dot nz)

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
static String	KEY_RUN the key for the run number.
protected int	m_ActualNumThreads the actual number of threads to use.
protected ExecutorService	m_Executor the executor service to use for parallel execution.
protected int	m_LowerRuns the lower number of runs (included).
protected int	m_NumThreads the number of threads to use for parallel execution.
protected int	m_UpperRuns the upper number of runs (included).

Fields inherited from class meka.experiment.evaluators.AbstractMetaEvaluator

m_Evaluator

Fields inherited from class meka.experiment.evaluators.AbstractEvaluator

m_Stopped

Fields inherited from class meka.events.LogObject

m_Debug, m_LogListeners

Constructor Summary

Constructors

Constructor and Description
RepeatedRuns()

Method Summary

Modifier and Type	Method and Description
List<EvaluationStatistics>	evaluate(MultiLabelClassifier classifier, weka.core.Instances dataset) Returns the evaluation statistics generated for the dataset.
protected List<EvaluationStatistics>	evaluateParallel(MultiLabelClassifier classifier, weka.core.Instances dataset) Executes the runs in sequential order.
protected List<EvaluationStatistics>	evaluateSequential(MultiLabelClassifier classifier, weka.core.Instances dataset) Executes the runs in sequential order.
protected Evaluator	getDefaultEvaluator() Returns the default evaluator to use.
protected int	getDefaultLowerRuns() Returns the default lower number of runs to perform.
protected int	getDefaultNumThreads() Returns the default number of threads to use.
protected int	getDefaultUpperRuns() Returns the default upper number of runs to perform.
int	getLowerRuns() Returns the lower number of runs to perform (included).
int	getNumThreads() Returns the number of threads to use.
String[]	getOptions() Returns the options.
int	getUpperRuns() Returns the upper number of runs to perform (included).
String	globalInfo() Description to be displayed in the GUI.
Enumeration<weka.core.Option>	listOptions() Returns an enumeration of all the available options..
String	lowerRunsTipText() Describes this property.
String	numThreadsTipText() Returns the tip text for this property.
void	setLowerRuns(int value) Sets the lower number of runs to perform (included).
void	setNumThreads(int value) Sets the number of threads to use.
void	setOptions(String[] options) Sets the options.
void	setUpperRuns(int value) Sets the upper number of runs to perform (included).
void	stop() Stops the evaluation, if possible.
String	upperRunsTipText() Describes this property.

Methods inherited from class meka.experiment.evaluators.AbstractMetaEvaluator

addLogListener, evaluatorTipText, getEvaluator, initialize, removeLogListener, setEvaluator

Methods inherited from class meka.events.LogObject

debug, getLogListeners, handleException, log

Methods inherited from class java.lang.Object

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

Methods inherited from interface meka.events.LogSupporter

log

Field Detail

KEY_RUN

public static final String KEY_RUN

the key for the run number.

See Also:

Constant Field Values

m_LowerRuns

protected int m_LowerRuns

the lower number of runs (included).

m_UpperRuns

protected int m_UpperRuns

the upper number of runs (included).

m_NumThreads

protected int m_NumThreads

the number of threads to use for parallel execution.

m_ActualNumThreads

protected int m_ActualNumThreads

the actual number of threads to use.

m_Executor

protected transient ExecutorService m_Executor

the executor service to use for parallel execution.

Constructor Detail

RepeatedRuns

public RepeatedRuns()

Method Detail

globalInfo

public String globalInfo()

Description to be displayed in the GUI.

Specified by:

globalInfo in class AbstractEvaluator

Returns:

the description

getDefaultEvaluator

protected Evaluator getDefaultEvaluator()

Returns the default evaluator to use.

Specified by:

getDefaultEvaluator in class AbstractMetaEvaluator

Returns:

the default

getDefaultLowerRuns

protected int getDefaultLowerRuns()

Returns the default lower number of runs to perform.

Returns:

the default

setLowerRuns

public void setLowerRuns(int value)

Sets the lower number of runs to perform (included).

Parameters:

value - the number of runs

getLowerRuns

public int getLowerRuns()

Returns the lower number of runs to perform (included).

Returns:

the number of runs

lowerRunsTipText

public String lowerRunsTipText()

Describes this property.

Returns:

the description

getDefaultUpperRuns

protected int getDefaultUpperRuns()

Returns the default upper number of runs to perform.

Returns:

the default

setUpperRuns

public void setUpperRuns(int value)

Sets the upper number of runs to perform (included).

Parameters:

value - the number of runs

getUpperRuns

public int getUpperRuns()

Returns the upper number of runs to perform (included).

Returns:

the number of runs

upperRunsTipText

public String upperRunsTipText()

Describes this property.

Returns:

the description

getDefaultNumThreads

protected int getDefaultNumThreads()

Returns the default number of threads to use.

Returns:

the number of threads: -1 = # of CPUs/cores; 0/1 = sequential execution

setNumThreads

public void setNumThreads(int value)

Sets the number of threads to use.

Specified by:

setNumThreads in interface ThreadLimiter

Parameters:

value - the number of threads: -1 = # of CPUs/cores; 0/1 = sequential execution

getNumThreads

public int getNumThreads()

Returns the number of threads to use.

Specified by:

getNumThreads in interface ThreadLimiter

Returns:

the number of threads: -1 = # of CPUs/cores; 0/1 = sequential execution

numThreadsTipText

public String numThreadsTipText()

Returns the tip text for this property.

Returns:

tip text for this property suitable for displaying in the GUI or for listing the options.

listOptions

public Enumeration<weka.core.Option> listOptions()

Returns an enumeration of all the available options..

Specified by:

listOptions in interface weka.core.OptionHandler

Overrides:

listOptions in class AbstractMetaEvaluator

Returns:

an enumeration of all available options.

setOptions

public void setOptions(String[] options)
                throws Exception

Sets the options.

Specified by:

setOptions in interface weka.core.OptionHandler

Overrides:

setOptions in class AbstractMetaEvaluator

Parameters:

options - the options to parse

Throws:

Exception - if parsing fails

getOptions

public String[] getOptions()

Returns the options.

Specified by:

getOptions in interface weka.core.OptionHandler

Overrides:

getOptions in class AbstractMetaEvaluator

Returns:

the current options

evaluateSequential

protected List<EvaluationStatistics> evaluateSequential(MultiLabelClassifier classifier,
                                                        weka.core.Instances dataset)

Executes the runs in sequential order.

Parameters:

classifier - the classifier to evaluate

dataset - the dataset to evaluate on

Returns:

the statistics

evaluateParallel

protected List<EvaluationStatistics> evaluateParallel(MultiLabelClassifier classifier,
                                                      weka.core.Instances dataset)

Executes the runs in sequential order.

Parameters:

classifier - the classifier to evaluate

dataset - the dataset to evaluate on

Returns:

the statistics

evaluate

public List<EvaluationStatistics> evaluate(MultiLabelClassifier classifier,
                                           weka.core.Instances dataset)

Returns the evaluation statistics generated for the dataset.

Specified by:

evaluate in interface Evaluator

Parameters:

classifier - the classifier to evaluate

dataset - the dataset to evaluate on

Returns:

the statistics

stop

public void stop()

Stops the evaluation, if possible.

Specified by:

stop in interface Evaluator

Overrides:

stop in class AbstractMetaEvaluator