weka.classifiers.meta

Class Stacking

java.lang.Object

weka.classifiers.AbstractClassifier

weka.classifiers.MultipleClassifiersCombiner

weka.classifiers.ParallelMultipleClassifiersCombiner

weka.classifiers.RandomizableParallelMultipleClassifiersCombiner

weka.classifiers.meta.Stacking

All Implemented Interfaces:

java.io.Serializable, java.lang.Cloneable, Classifier, BatchPredictor, CapabilitiesHandler, CapabilitiesIgnorer, CommandlineRunnable, OptionHandler, Randomizable, RevisionHandler, TechnicalInformationHandler

public class Stacking
extends RandomizableParallelMultipleClassifiersCombiner
implements TechnicalInformationHandler

Combines several classifiers using the stacking method. Can do classification or regression.

For more information, see

David H. Wolpert (1992). Stacked generalization. Neural Networks. 5:241-259.

BibTeX:

 @article{Wolpert1992,
    author = {David H. Wolpert},
    journal = {Neural Networks},
    pages = {241-259},
    publisher = {Pergamon Press},
    title = {Stacked generalization},
    volume = {5},
    year = {1992}
 }
 

Valid options are:

  -M <scheme specification>
  Full name of meta classifier, followed by options.
  (default: "weka.classifiers.rules.Zero")
 

  -X <number of folds>
  Sets the number of cross-validation folds.
 

  -S <num>
  Random number seed.
  (default 1)
 

  -B <classifier specification>
  Full class name of classifier to include, followed
  by scheme options. May be specified multiple times.
  (default: "weka.classifiers.rules.ZeroR")
 

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

See Also:

Serialized Form

Field Summary

Fields

Modifier and Type	Field and Description
protected Instances	m_BaseFormat Format for base data
protected Classifier	m_MetaClassifier The meta classifier
protected Instances	m_MetaFormat Format for meta data
protected int	m_NumFolds Set the number of folds for the cross-validation

Fields inherited from class weka.classifiers.RandomizableParallelMultipleClassifiersCombiner

m_Seed

Fields inherited from class weka.classifiers.ParallelMultipleClassifiersCombiner

m_completed, m_executorPool, m_failed, m_numExecutionSlots

Fields inherited from class weka.classifiers.MultipleClassifiersCombiner

m_Classifiers

Fields inherited from class weka.classifiers.AbstractClassifier

BATCH_SIZE_DEFAULT, m_BatchSize, m_Debug, m_DoNotCheckCapabilities, m_numDecimalPlaces, NUM_DECIMAL_PLACES_DEFAULT

Constructor Summary

Constructors

Constructor and Description
Stacking()

Method Summary

Modifier and Type	Method and Description
void	buildClassifier(Instances data) Buildclassifier selects a classifier from the set of classifiers by minimising error on the training data.
double[]	distributionForInstance(Instance instance) Returns class probabilities.
protected void	generateMetaLevel(Instances newData, java.util.Random random) Generates the meta data
Capabilities	getCapabilities() Returns combined capabilities of the base classifiers, i.e., the capabilities all of them have in common.
Classifier	getMetaClassifier() Gets the meta classifier.
int	getNumFolds() Gets the number of folds for the cross-validation.
java.lang.String[]	getOptions() Gets the current settings of the Classifier.
java.lang.String	getRevision() Returns the revision string.
TechnicalInformation	getTechnicalInformation() Returns an instance of a TechnicalInformation object, containing detailed information about the technical background of this class, e.g., paper reference or book this class is based on.
java.lang.String	globalInfo() Returns a string describing classifier
java.util.Enumeration<Option>	listOptions() Returns an enumeration describing the available options.
static void	main(java.lang.String[] argv) Main method for testing this class.
java.lang.String	metaClassifierTipText() Returns the tip text for this property
protected Instances	metaFormat(Instances instances) Makes the format for the level-1 data.
protected Instance	metaInstance(Instance instance) Makes a level-1 instance from the given instance.
protected java.lang.String	metaOption() String describing option for setting meta classifier
java.lang.String	numFoldsTipText() Returns the tip text for this property
void	postExecution() Perform any teardown stuff that might need to happen after execution.
void	preExecution() Perform any setup stuff that might need to happen before commandline execution.
protected void	processMetaOptions(java.lang.String[] options) Process options setting meta classifier.
void	setMetaClassifier(Classifier classifier) Adds meta classifier
void	setNumFolds(int numFolds) Sets the number of folds for the cross-validation.
void	setOptions(java.lang.String[] options) Parses a given list of options.
java.lang.String	toString() Output a representation of this classifier

Methods inherited from class weka.classifiers.RandomizableParallelMultipleClassifiersCombiner

getSeed, seedTipText, setSeed

Methods inherited from class weka.classifiers.ParallelMultipleClassifiersCombiner

buildClassifiers, completedClassifier, getNumExecutionSlots, numExecutionSlotsTipText, setNumExecutionSlots, startExecutorPool

Methods inherited from class weka.classifiers.MultipleClassifiersCombiner

classifiersTipText, getClassifier, getClassifiers, getClassifierSpec, setClassifiers

Methods inherited from class weka.classifiers.AbstractClassifier

batchSizeTipText, classifyInstance, debugTipText, distributionsForInstances, doNotCheckCapabilitiesTipText, forName, getBatchSize, getDebug, getDoNotCheckCapabilities, getNumDecimalPlaces, implementsMoreEfficientBatchPrediction, makeCopies, makeCopy, numDecimalPlacesTipText, run, runClassifier, setBatchSize, setDebug, setDoNotCheckCapabilities, setNumDecimalPlaces

Methods inherited from class java.lang.Object

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

Field Detail

m_MetaClassifier

protected Classifier m_MetaClassifier

The meta classifier

m_MetaFormat

protected Instances m_MetaFormat

Format for meta data

m_BaseFormat

protected Instances m_BaseFormat

Format for base data

m_NumFolds

protected int m_NumFolds

Set the number of folds for the cross-validation

Constructor Detail

Stacking

public Stacking()

Method Detail

globalInfo

public java.lang.String globalInfo()

Returns a string describing classifier

Returns:

a description suitable for displaying in the explorer/experimenter gui

getTechnicalInformation

public TechnicalInformation getTechnicalInformation()

Returns an instance of a TechnicalInformation object, containing detailed information about the technical background of this class, e.g., paper reference or book this class is based on.

Specified by:

getTechnicalInformation in interface TechnicalInformationHandler

Returns:

the technical information about this class

listOptions

public java.util.Enumeration<Option> listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface OptionHandler

Overrides:

listOptions in class RandomizableParallelMultipleClassifiersCombiner

Returns:

an enumeration of all the available options.

metaOption

protected java.lang.String metaOption()

String describing option for setting meta classifier

Returns:

the string describing the option

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Parses a given list of options.

Valid options are:

  -M <scheme specification>
  Full name of meta classifier, followed by options.
  (default: "weka.classifiers.rules.Zero")
 

  -X <number of folds>
  Sets the number of cross-validation folds.
 

  -S <num>
  Random number seed.
  (default 1)
 

  -B <classifier specification>
  Full class name of classifier to include, followed
  by scheme options. May be specified multiple times.
  (default: "weka.classifiers.rules.ZeroR")
 

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

Specified by:

setOptions in interface OptionHandler

Overrides:

setOptions in class RandomizableParallelMultipleClassifiersCombiner

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported

processMetaOptions

protected void processMetaOptions(java.lang.String[] options)
                           throws java.lang.Exception

Process options setting meta classifier.

Parameters:

options - the options to parse

Throws:

java.lang.Exception - if the parsing fails

getOptions

public java.lang.String[] getOptions()

Gets the current settings of the Classifier.

Specified by:

getOptions in interface OptionHandler

Overrides:

getOptions in class RandomizableParallelMultipleClassifiersCombiner

Returns:

an array of strings suitable for passing to setOptions

numFoldsTipText

public java.lang.String numFoldsTipText()

Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

getNumFolds

public int getNumFolds()

Gets the number of folds for the cross-validation.

Returns:

the number of folds for the cross-validation

setNumFolds

public void setNumFolds(int numFolds)
                 throws java.lang.Exception

Sets the number of folds for the cross-validation.

Parameters:

numFolds - the number of folds for the cross-validation

Throws:

java.lang.Exception - if parameter illegal

metaClassifierTipText

public java.lang.String metaClassifierTipText()

Returns the tip text for this property

Returns:

tip text for this property suitable for displaying in the explorer/experimenter gui

setMetaClassifier

public void setMetaClassifier(Classifier classifier)

Adds meta classifier

Parameters:

classifier - the classifier with all options set.

getMetaClassifier

public Classifier getMetaClassifier()

Gets the meta classifier.

Returns:

the meta classifier

getCapabilities

public Capabilities getCapabilities()

Returns combined capabilities of the base classifiers, i.e., the capabilities all of them have in common.

Specified by:

getCapabilities in interface Classifier

Specified by:

getCapabilities in interface CapabilitiesHandler

Overrides:

getCapabilities in class MultipleClassifiersCombiner

Returns:

the capabilities of the base classifiers

See Also:

Capabilities

buildClassifier

public void buildClassifier(Instances data)
                     throws java.lang.Exception

Buildclassifier selects a classifier from the set of classifiers by minimising error on the training data.

Specified by:

buildClassifier in interface Classifier

Overrides:

buildClassifier in class ParallelMultipleClassifiersCombiner

Parameters:

data - the training data to be used for generating the boosted classifier.

Throws:

java.lang.Exception - if the classifier could not be built successfully

generateMetaLevel

protected void generateMetaLevel(Instances newData,
                                 java.util.Random random)
                          throws java.lang.Exception

Generates the meta data

Parameters:

newData - the data to work on

random - the random number generator to use for cross-validation

Throws:

java.lang.Exception - if generation fails

distributionForInstance

public double[] distributionForInstance(Instance instance)
                                 throws java.lang.Exception

Returns class probabilities.

Specified by:

distributionForInstance in interface Classifier

Overrides:

distributionForInstance in class AbstractClassifier

Parameters:

instance - the instance to be classified

Returns:

the distribution

Throws:

java.lang.Exception - if instance could not be classified successfully

toString

public java.lang.String toString()

Output a representation of this classifier

Overrides:

toString in class java.lang.Object

Returns:

a string representation of the classifier

metaFormat

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

Makes the format for the level-1 data.

Parameters:

instances - the level-0 format

Returns:

the format for the meta data

Throws:

java.lang.Exception - if the format generation fails

metaInstance

protected Instance metaInstance(Instance instance)
                         throws java.lang.Exception

Makes a level-1 instance from the given instance.

Parameters:

instance - the instance to be transformed

Returns:

the level-1 instance

Throws:

java.lang.Exception - if the instance generation fails

preExecution

public void preExecution()
                  throws java.lang.Exception

Description copied from class: AbstractClassifier

Perform any setup stuff that might need to happen before commandline execution. Subclasses should override if they need to do something here

Specified by:

preExecution in interface CommandlineRunnable

Overrides:

preExecution in class MultipleClassifiersCombiner

Throws:

java.lang.Exception - if a problem occurs during setup

postExecution

public void postExecution()
                   throws java.lang.Exception

Description copied from class: AbstractClassifier

Perform any teardown stuff that might need to happen after execution. Subclasses should override if they need to do something here

Specified by:

postExecution in interface CommandlineRunnable

Overrides:

postExecution in class MultipleClassifiersCombiner

Throws:

java.lang.Exception - if a problem occurs during teardown

getRevision

public java.lang.String getRevision()

Returns the revision string.

Specified by:

getRevision in interface RevisionHandler

Overrides:

getRevision in class AbstractClassifier

Returns:

the revision

main

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

Main method for testing this class.

Parameters:

argv - should contain the following arguments: -t training file [-T test file] [-c class index]