mulan.classifier.transformation
Class EnsembleOfClassifierChains

java.lang.Object
  mulan.classifier.MultiLabelLearnerBase
      mulan.classifier.transformation.TransformationBasedMultiLabelLearner
          mulan.classifier.transformation.EnsembleOfClassifierChains

All Implemented Interfaces:

Serializable, MultiLabelLearner, TechnicalInformationHandler

public class EnsembleOfClassifierChains
extends TransformationBasedMultiLabelLearner

Class implementing the Ensemble of Classifier Chains(ECC) algorithm. For more information, see

Read, Jesse, Pfahringer, Bernhard, Holmes, Geoff, Frank, Eibe: Classifier Chains for Multi-label Classification. In: , 335--359, 2011.

BibTeX:

 @inproceedings{Read2011,
    author = {Read, Jesse and Pfahringer, Bernhard and Holmes, Geoff and Frank, Eibe},
    journal = {Machine Learning},
    number = {3},
    pages = {335--359},
    title = {Classifier Chains for Multi-label Classification},
    volume = {85},
    year = {2011}
 }
 

Version:

2012.02.27

Author:

Eleftherios Spyromitros-Xioufis ( espyromi@csd.auth.gr ), Konstantinos Sechidis (sechidis@csd.auth.gr), Grigorios Tsoumakas (greg@csd.auth.gr)

See Also:

Serialized Form

Field Summary

protected int	BagSizePercent The size of each bag sample, as a percentage of the training size.
protected ClassifierChain[]	ensemble An array of ClassifierChain models
protected int	numOfModels The number of classifier chain models
protected Random	rand Random number generator
protected double	samplingPercentage The size of each sample, as a percentage of the training size Used when useSamplingWithReplacement is false
protected boolean	useConfidences Whether the output is computed based on the average votes or on the average confidences
protected boolean	useSamplingWithReplacement Whether to use sampling with replacement to create the data of the models of the ensemble

Fields inherited from class mulan.classifier.transformation.TransformationBasedMultiLabelLearner

baseClassifier

Fields inherited from class mulan.classifier.MultiLabelLearnerBase

featureIndices, labelIndices, numLabels

Constructor Summary

EnsembleOfClassifierChains()
Default constructor

EnsembleOfClassifierChains(Classifier classifier, int aNumOfModels, boolean doUseConfidences, boolean doUseSamplingWithReplacement)
Creates a new object

Method Summary

protected void	buildInternal(MultiLabelInstances trainingSet) Learner specific implementation of building the model from MultiLabelInstances training data set.
int	getBagSizePercent() Returns the size of each bag sample, as a percentage of the training size
double	getSamplingPercentage() Returns the sampling percentage
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.
String	globalInfo() Returns a string describing classifier.
protected MultiLabelOutput	makePredictionInternal(Instance instance) Learner specific implementation for predicting on specified data based on trained model.
void	setBagSizePercent(int bagSizePercent) Sets the size of each bag sample, as a percentage of the training size
void	setSamplingPercentage(double samplingPercentage) Sets the sampling percentage

Methods inherited from class mulan.classifier.transformation.TransformationBasedMultiLabelLearner

getBaseClassifier

Methods inherited from class mulan.classifier.MultiLabelLearnerBase

build, debug, getDebug, isModelInitialized, isUpdatable, makeCopy, makePrediction, setDebug

Methods inherited from class java.lang.Object

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

Field Detail

numOfModels

protected int numOfModels

The number of classifier chain models

ensemble

protected ClassifierChain[] ensemble

An array of ClassifierChain models

rand

protected Random rand

Random number generator

useConfidences

protected boolean useConfidences

Whether the output is computed based on the average votes or on the average confidences

useSamplingWithReplacement

protected boolean useSamplingWithReplacement

Whether to use sampling with replacement to create the data of the models of the ensemble

BagSizePercent

protected int BagSizePercent

The size of each bag sample, as a percentage of the training size. Used when useSamplingWithReplacement is true

samplingPercentage

protected double samplingPercentage

The size of each sample, as a percentage of the training size Used when useSamplingWithReplacement is false

Constructor Detail

EnsembleOfClassifierChains

public EnsembleOfClassifierChains()

Default constructor

EnsembleOfClassifierChains

public EnsembleOfClassifierChains(Classifier classifier,
                                  int aNumOfModels,
                                  boolean doUseConfidences,
                                  boolean doUseSamplingWithReplacement)

Creates a new object

Parameters:

classifier - the base classifier for each ClassifierChain model

aNumOfModels - the number of models

doUseConfidences -

doUseSamplingWithReplacement -

Method Detail

getBagSizePercent

public int getBagSizePercent()

Returns the size of each bag sample, as a percentage of the training size

Returns:

the size of each bag sample, as a percentage of the training size

setBagSizePercent

public void setBagSizePercent(int bagSizePercent)

Sets the size of each bag sample, as a percentage of the training size

Parameters:

bagSizePercent - the size of each bag sample, as a percentage of the training size

getSamplingPercentage

public double getSamplingPercentage()

Returns the sampling percentage

Returns:

the sampling percentage

setSamplingPercentage

public void setSamplingPercentage(double samplingPercentage)

Sets the sampling percentage

Parameters:

samplingPercentage - the sampling percentage

globalInfo

public String globalInfo()

Returns a string describing classifier.

Overrides:

globalInfo in class TransformationBasedMultiLabelLearner

Returns:

a description suitable for displaying in the explorer/experimenter gui

getTechnicalInformation

public TechnicalInformation getTechnicalInformation()

Description copied from class: TransformationBasedMultiLabelLearner

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

Overrides:

getTechnicalInformation in class TransformationBasedMultiLabelLearner

Returns:

the technical information about this class

buildInternal

protected void buildInternal(MultiLabelInstances trainingSet)
                      throws Exception

Description copied from class: MultiLabelLearnerBase

Learner specific implementation of building the model from MultiLabelInstances training data set. This method is called from MultiLabelLearnerBase.build(MultiLabelInstances) method, where behavior common across all learners is applied.

Specified by:

buildInternal in class MultiLabelLearnerBase

Parameters:

trainingSet - the training data set

Throws:

Exception - if learner model was not created successfully

makePredictionInternal

protected MultiLabelOutput makePredictionInternal(Instance instance)
                                           throws Exception,
                                                  InvalidDataException

Description copied from class: MultiLabelLearnerBase

Learner specific implementation for predicting on specified data based on trained model. This method is called from MultiLabelLearnerBase.makePrediction(weka.core.Instance) which guards for model initialization and apply common handling/behavior.

Specified by:

makePredictionInternal in class MultiLabelLearnerBase

Parameters:

instance - the data instance to predict on

Returns:

the output of the learner for the given instance

Throws:

Exception - if an error occurs while making the prediction.

InvalidDataException - if specified instance data is invalid and can not be processed by the learner