weka.filters.supervised.instance

Class ClassBalancer

java.lang.Object

weka.filters.Filter

weka.filters.SimpleFilter

weka.filters.SimpleBatchFilter

weka.filters.supervised.instance.ClassBalancer

All Implemented Interfaces:

java.io.Serializable, CapabilitiesHandler, CapabilitiesIgnorer, CommandlineRunnable, OptionHandler, RevisionHandler, WeightedAttributesHandler, WeightedInstancesHandler, SupervisedFilter

public class ClassBalancer
extends SimpleBatchFilter
implements SupervisedFilter, WeightedInstancesHandler, WeightedAttributesHandler

Reweights the instances in the data so that each class has the same total weight. The total sum of weights accross all instances will be maintained. Only the weights in the first batch of data received by this filter are changed, so it can be used with the FilteredClassifier. If the class is numeric, it is discretized using equal-width discretization to establish pseudo classes for weighting.

Valid options are:

 -num-intervals <positive integer>
  The number of discretization intervals to use when the class is numeric (default of weka.attribute.unsupervised.Discretize).

 -output-debug-info
  If set, filter is run in debug mode and
  may output additional info to the console

 -do-not-check-capabilities
  If set, filter capabilities are not checked when input format is set
  (use with caution).

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected int	m_NumIntervals number of discretization intervals to use if the class is numeric

Fields inherited from class weka.filters.Filter

m_Debug, m_DoNotCheckCapabilities, m_FirstBatchDone, m_InputRelAtts, m_InputStringAtts, m_NewBatch, m_OutputRelAtts, m_OutputStringAtts

Constructor Summary

Constructors

Constructor and Description
ClassBalancer()

Method Summary

Modifier and Type	Method and Description
protected Instances	determineOutputFormat(Instances inputFormat) Determines the output format based on the input format and returns this.
Capabilities	getCapabilities() Returns the Capabilities of this filter.
int	getNumIntervals() Gets the number of discretization intervals to use when the class is numeric.
java.lang.String	getRevision() Returns the revision string.
java.lang.String	globalInfo() Returns a string describing this filter.
static void	main(java.lang.String[] args) runs the filter with the given arguments
protected Instances	process(Instances instances) Processes the given data.
void	setNumIntervals(int num) Sets the number of discretization intervals to use.

Methods inherited from class weka.filters.SimpleBatchFilter

allowAccessToFullInputFormat, batchFinished, hasImmediateOutputFormat, input

Methods inherited from class weka.filters.SimpleFilter

reset, setInputFormat

Methods inherited from class weka.filters.Filter

batchFilterFile, bufferInput, copyValues, copyValues, debugTipText, doNotCheckCapabilitiesTipText, filterFile, flushInput, getCapabilities, getCopyOfInputFormat, getDebug, getDoNotCheckCapabilities, getInputFormat, getOptions, getOutputFormat, initInputLocators, initOutputLocators, inputFormatPeek, isFirstBatchDone, isNewBatch, isOutputFormatDefined, listOptions, makeCopies, makeCopy, mayRemoveInstanceAfterFirstBatchDone, numPendingOutput, output, outputFormatPeek, outputPeek, postExecution, preExecution, push, push, resetQueue, run, runFilter, setDebug, setDoNotCheckCapabilities, setOptions, setOutputFormat, testInputFormat, toString, useFilter, wekaStaticWrapper

Methods inherited from class java.lang.Object

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

Field Detail

m_NumIntervals

protected int m_NumIntervals

number of discretization intervals to use if the class is numeric

Constructor Detail

ClassBalancer

public ClassBalancer()

Method Detail

getNumIntervals

@OptionMetadata(displayName="Number of discretization intervals",
                description="The number of discretization intervals to use when the class is numeric.",
                displayOrder=1,
                commandLineParamName="num-intervals",
                commandLineParamSynopsis="-num-intervals <int>",
                commandLineParamIsFlag=false)
public int getNumIntervals()

Gets the number of discretization intervals to use when the class is numeric.

Returns:

the number of discretization intervals

setNumIntervals

public void setNumIntervals(int num)

Sets the number of discretization intervals to use.

Parameters:

num - the number of discretization intervals to use.

globalInfo

public java.lang.String globalInfo()

Returns a string describing this filter.

Specified by:

globalInfo in class SimpleFilter

Returns:

a description of the filter suitable for displaying in the explorer/experimenter gui

determineOutputFormat

protected Instances determineOutputFormat(Instances inputFormat)

Determines the output format based on the input format and returns this.

Specified by:

determineOutputFormat in class SimpleFilter

Parameters:

inputFormat - the input format to base the output format on

Returns:

the output format

See Also:

SimpleFilter.hasImmediateOutputFormat(), Filter.batchFinished()

getCapabilities

public Capabilities getCapabilities()

Returns the Capabilities of this filter.

Specified by:

getCapabilities in interface CapabilitiesHandler

Overrides:

getCapabilities in class Filter

Returns:

the capabilities of this object

See Also:

Capabilities

process

protected Instances process(Instances instances)
                     throws java.lang.Exception

Processes the given data.

Specified by:

process in class SimpleFilter

Parameters:

instances - the data to process

Returns:

the modified data

Throws:

java.lang.Exception - in case the processing goes wrong

See Also:

Filter.batchFinished()

getRevision

public java.lang.String getRevision()

Returns the revision string.

Specified by:

getRevision in interface RevisionHandler

Overrides:

getRevision in class Filter

Returns:

the revision

main

public static void main(java.lang.String[] args)

runs the filter with the given arguments

Parameters:

args - the commandline arguments