Package weka.classifiers

Class MultiLevelSplitGenerator

java.lang.Object

adams.core.logging.LoggingObject

adams.core.logging.CustomLoggingLevelObject

adams.core.option.AbstractOptionHandler

weka.classifiers.AbstractSplitGenerator

weka.classifiers.MultiLevelSplitGenerator

All Implemented Interfaces:

Destroyable, GlobalInfoSupporter, LoggingLevelHandler, LoggingSupporter, OptionHandler, Randomizable, SizeOfHandler, Stoppable, StoppableWithFeedback, SplitGenerator<weka.core.Instances,WekaTrainTestSetContainer>, InstancesViewSupporter, Serializable, Iterator<WekaTrainTestSetContainer>, SplitGenerator

public class MultiLevelSplitGenerator
extends AbstractSplitGenerator
implements SplitGenerator, StoppableWithFeedback

Generates splits based on groups extracted via regular expressions. Each attribute index/regular expression/group represents a level. At each level, the data gets split into groups according to the level's regexp/group, making up train and test sets.

Author:

fracpete (fracpete at waikato dot ac dot nz)

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field	Description
protected List<WekaTrainTestSetContainer>	m_Containers	the list of generated containers.
protected BaseString[]	m_Groups	the groups to generate.
protected WekaAttributeIndex[]	m_Indices	the attribute indices.
protected BaseRegExp[]	m_RegExps	the regular expressions to apply to determine the grouping.
protected boolean	m_Silent	whether to suppress error output.
protected boolean	m_Stopped	whether the generation got stopped.

Fields inherited from class weka.classifiers.AbstractSplitGenerator

m_Data, m_Initialized, m_OriginalIndices, m_Seed, m_UseViews

Fields inherited from class adams.core.option.AbstractOptionHandler

m_OptionManager

Fields inherited from class adams.core.logging.LoggingObject

m_Logger, m_LoggingIsEnabled, m_LoggingLevel

Constructor Summary

Constructors

Constructor	Description
MultiLevelSplitGenerator()

Method Summary

Modifier and Type	Method	Description
protected boolean	canRandomize()	Returns whether randomization is enabled.
protected boolean	checkNext()	Returns true if the iteration has more elements.
protected WekaTrainTestSetContainer	createNext()	Creates the next result.
void	defineOptions()	Adds options to the internal list of options.
protected void	doInitializeIterator()	Initializes the iterator.
protected void	generateContainers()	Generates the containers.
protected List<weka.core.Instances>	generateGroups(weka.core.Instances data, int index, String regexp, String group)	Generates the groups from the data by applying the regexp/group.
protected List<com.github.fracpete.javautils.struct.Struct2<weka.core.Instances,weka.core.Instances>>	generateSplits(weka.core.Instances data, int index, String regexp, String group)	Generates the train/test splits.
BaseString[]	getGroups()	Returns the groups to generate.
WekaAttributeIndex[]	getIndices()	Returns the attribute indices.
BaseRegExp[]	getRegExps()	Returns the regular expressions to use for extracting the groups.
boolean	getSilent()	Returns whether to suppress error messages.
String	globalInfo()	Returns a string describing the object.
String	groupsTipText()	Returns the tip text for this property.
String	indicesTipText()	Returns the tip text for this property.
protected void	initialize()	Initializes the members.
boolean	isStopped()	Whether the execution has been stopped.
protected List<com.github.fracpete.javautils.struct.Struct2<weka.core.Instances,weka.core.Instances>>	match(List<com.github.fracpete.javautils.struct.Struct2<weka.core.Instances,weka.core.Instances>> trainSplits, List<com.github.fracpete.javautils.struct.Struct2<weka.core.Instances,weka.core.Instances>> testSplits, int index)	Combines train and test splits as long as there are matches.
String	regExpsTipText()	Returns the tip text for this property.
protected void	reset()	Resets the scheme.
void	setGroups(BaseString[] value)	Sets the groups to generate.
void	setIndices(WekaAttributeIndex[] value)	Sets the attribute indices.
void	setRegExps(BaseRegExp[] value)	Sets the regular expressions to use for extracting the groups.
void	setSilent(boolean value)	Sets whether to suppress error messages.
String	silentTipText()	Returns the tip text for this property.
void	stopExecution()	Stops the execution.
protected weka.core.Instances	subset(List<weka.core.Instances> groups, int index, boolean invert)	Generates the subset: either the specified index of the rest.
String	toString()	Returns a short description of the generator.

Methods inherited from class weka.classifiers.AbstractSplitGenerator

getData, getSeed, getUseViews, hasNext, initializeIterator, next, randomize, remove, seedTipText, setData, setSeed, setUseViews, useViewsTipText

Methods inherited from class adams.core.option.AbstractOptionHandler

cleanUpOptions, destroy, finishInit, getDefaultLoggingLevel, getOptionManager, loggingLevelTipText, newOptionManager, setLoggingLevel, toCommandLine

Methods inherited from class adams.core.logging.LoggingObject

configureLogger, getLogger, getLoggingLevel, initializeLogging, isLoggingEnabled, sizeOf

Methods inherited from class java.lang.Object

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

Methods inherited from interface adams.core.Destroyable

destroy

Methods inherited from interface adams.data.weka.InstancesViewSupporter

getUseViews, setUseViews

Methods inherited from interface java.util.Iterator

forEachRemaining

Methods inherited from interface adams.core.logging.LoggingLevelHandler

getLoggingLevel

Methods inherited from interface adams.core.option.OptionHandler

cleanUpOptions, getOptionManager, toCommandLine

Methods inherited from interface adams.core.Randomizable

getSeed, seedTipText, setSeed

Methods inherited from interface weka.classifiers.SplitGenerator

getData, hasNext, initializeIterator, next, remove, setData

Field Detail

m_Indices

protected WekaAttributeIndex[] m_Indices

the attribute indices.

m_RegExps

protected BaseRegExp[] m_RegExps

the regular expressions to apply to determine the grouping.

m_Groups

protected BaseString[] m_Groups

the groups to generate.

m_Silent

protected boolean m_Silent

whether to suppress error output.

m_Containers

protected List<WekaTrainTestSetContainer> m_Containers

the list of generated containers.

m_Stopped

protected boolean m_Stopped

whether the generation got stopped.

Constructor Detail

MultiLevelSplitGenerator

public MultiLevelSplitGenerator()

Method Detail

globalInfo

public String globalInfo()

Returns a string describing the object.

Specified by:

globalInfo in interface GlobalInfoSupporter

Specified by:

globalInfo in class AbstractOptionHandler

Returns:

a description suitable for displaying in the gui

defineOptions

public void defineOptions()

Adds options to the internal list of options.

Specified by:

defineOptions in interface OptionHandler

Overrides:

defineOptions in class AbstractSplitGenerator

initialize

protected void initialize()

Initializes the members.

Overrides:

initialize in class AbstractSplitGenerator

reset

protected void reset()

Resets the scheme.

Overrides:

reset in class AbstractSplitGenerator

setIndices

public void setIndices(WekaAttributeIndex[] value)

Sets the attribute indices.

Parameters:

value - the indices

getIndices

public WekaAttributeIndex[] getIndices()

Returns the attribute indices.

Returns:

the indices

indicesTipText

public String indicesTipText()

Returns the tip text for this property.

Returns:

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

setRegExps

public void setRegExps(BaseRegExp[] value)

Sets the regular expressions to use for extracting the groups.

Parameters:

value - the expressions

getRegExps

public BaseRegExp[] getRegExps()

Returns the regular expressions to use for extracting the groups.

Returns:

the expressions

regExpsTipText

public String regExpsTipText()

Returns the tip text for this property.

Returns:

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

setGroups

public void setGroups(BaseString[] value)

Sets the groups to generate.

Parameters:

value - the groups

getGroups

public BaseString[] getGroups()

Returns the groups to generate.

Returns:

the groups

groupsTipText

public String groupsTipText()

Returns the tip text for this property.

Returns:

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

setSilent

public void setSilent(boolean value)

Sets whether to suppress error messages.

Parameters:

value - true if to suppress

getSilent

public boolean getSilent()

Returns whether to suppress error messages.

Returns:

true if to suppress

silentTipText

public String silentTipText()

Returns the tip text for this property.

Returns:

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

canRandomize

protected boolean canRandomize()

Returns whether randomization is enabled.

Specified by:

canRandomize in class AbstractSplitGenerator

Returns:

true if to randomize

generateGroups

protected List<weka.core.Instances> generateGroups(weka.core.Instances data,
                                                   int index,
                                                   String regexp,
                                                   String group)

Generates the groups from the data by applying the regexp/group.

Parameters:

data - the data to split into groups

index - the attribute index

regexp - the regexp to apply to the values of the attribute

group - the group ID to generate

Returns:

the generated groups

subset

protected weka.core.Instances subset(List<weka.core.Instances> groups,
                                     int index,
                                     boolean invert)

Generates the subset: either the specified index of the rest.

Parameters:

groups - the groups to use

index - the current index

invert - whether to invert

Returns:

the generated instances

generateSplits

protected List<com.github.fracpete.javautils.struct.Struct2<weka.core.Instances,weka.core.Instances>> generateSplits(weka.core.Instances data,
                                                                                                                           int index,
                                                                                                                           String regexp,
                                                                                                                           String group)

Generates the train/test splits.

Parameters:

data - the data to generate the splits for

index - the attribute index

regexp - the regexp to apply to the values of the attribute

group - the group ID to generate

Returns:

the generated splits

match

protected List<com.github.fracpete.javautils.struct.Struct2<weka.core.Instances,weka.core.Instances>> match(List<com.github.fracpete.javautils.struct.Struct2<weka.core.Instances,weka.core.Instances>> trainSplits,
                                                                                                                  List<com.github.fracpete.javautils.struct.Struct2<weka.core.Instances,weka.core.Instances>> testSplits,
                                                                                                                  int index)

Combines train and test splits as long as there are matches. Others get dropped.

Parameters:

trainSplits - the training splits

testSplits - the test splits

Returns:

the combined splits

generateContainers

protected void generateContainers()

Generates the containers.

doInitializeIterator

protected void doInitializeIterator()

Initializes the iterator.

Specified by:

doInitializeIterator in class AbstractSplitGenerator

See Also:

AbstractSplitGenerator.canRandomize()

checkNext

protected boolean checkNext()

Returns true if the iteration has more elements. (In other words, returns true if next would return an element rather than throwing an exception.)

Specified by:

checkNext in class AbstractSplitGenerator

Returns:

true if the iterator has more elements.

createNext

protected WekaTrainTestSetContainer createNext()

Creates the next result.

Specified by:

createNext in class AbstractSplitGenerator

Returns:

the next result

stopExecution

public void stopExecution()

Stops the execution.

Specified by:

stopExecution in interface Stoppable

isStopped

public boolean isStopped()

Whether the execution has been stopped.

Specified by:

isStopped in interface StoppableWithFeedback

Returns:

true if stopped

toString

public String toString()

Returns a short description of the generator.

Specified by:

toString in interface SplitGenerator<weka.core.Instances,WekaTrainTestSetContainer>

Specified by:

toString in interface SplitGenerator

Overrides:

toString in class AbstractSplitGenerator

Returns:

a short description