de.jstacs.classifiers.differentiableSequenceScoreBased.msp

Class MSPClassifier

java.lang.Object

de.jstacs.classifiers.AbstractClassifier

de.jstacs.classifiers.AbstractScoreBasedClassifier

de.jstacs.classifiers.differentiableSequenceScoreBased.ScoreClassifier

de.jstacs.classifiers.differentiableSequenceScoreBased.gendismix.GenDisMixClassifier

de.jstacs.classifiers.differentiableSequenceScoreBased.msp.MSPClassifier

All Implemented Interfaces:

Storable, Cloneable

public class MSPClassifier
extends GenDisMixClassifier

This class implements a classifier that allows the training via MCL or MSP principle.

Author:

Jens Keilwagen, Jan Grau

Nested Class Summary

Nested classes/interfaces inherited from class de.jstacs.classifiers.AbstractScoreBasedClassifier

AbstractScoreBasedClassifier.DoubleTableResult

Field Summary

Fields inherited from class de.jstacs.classifiers.differentiableSequenceScoreBased.gendismix.GenDisMixClassifier

beta, function, prior

Fields inherited from class de.jstacs.classifiers.differentiableSequenceScoreBased.ScoreClassifier

hasBeenOptimized, NOT_TRAINED_VALUE, params, score, sostream, template

Constructor Summary

Constructors

Constructor and Description
MSPClassifier(GenDisMixClassifierParameterSet params, DifferentiableSequenceScore... score) This convenience constructor creates an MSPClassifier that used MCL principle for training.
MSPClassifier(GenDisMixClassifierParameterSet params, LogPrior prior, DifferentiableSequenceScore... score) The default constructor that creates a new MSPClassifier from a given parameter set, a prior and DifferentiableSequenceScores for the classes.
MSPClassifier(GenDisMixClassifierParameterSet params, LogPrior prior, double lastScore, DifferentiableSequenceScore... score) This constructor that creates a new MSPClassifier from a given parameter set, a prior and DifferentiableSequenceScores for the classes.
MSPClassifier(StringBuffer xml) This is the constructor for Storable.

Method Summary

Modifier and Type	Method and Description
String	getInstanceName() Returns a short description of the classifier.
protected String	getXMLTag() Returns the String that is used as tag for the XML representation of the classifier.

Methods inherited from class de.jstacs.classifiers.differentiableSequenceScoreBased.gendismix.GenDisMixClassifier

clone, create, extractFurtherClassifierInfosFromXML, getFunction, getFurtherClassifierInfos, getNumberOfThreads, setNumberOfThreads, setPrior, setWeights, toString

Methods inherited from class de.jstacs.classifiers.differentiableSequenceScoreBased.ScoreClassifier

createStructure, createStructure, doOptimization, getClassifierAnnotation, getCurrentParameterSet, getDifferentiableSequenceScore, getDifferentiableSequenceScores, getIterations, getLastScore, getNumericalCharacteristics, getScore, hasBeenOptimized, initUsingParameters, isInitialized, preoptimize, setOutputStream, train

Methods inherited from class de.jstacs.classifiers.AbstractScoreBasedClassifier

check, check, classify, classify, createDefaultClassWeights, getClassWeight, getClassWeights, getMultiClassScores, getNumberOfClasses, getPValue, getPValue, getResults, getScore, getScores, setClassWeights, setClassWeights, setThresholdClassWeights

Methods inherited from class de.jstacs.classifiers.AbstractClassifier

classify, evaluate, evaluate, getAlphabetContainer, getCharacteristics, getLength, toXML, train

Methods inherited from class java.lang.Object

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

Constructor Detail

MSPClassifier

public MSPClassifier(GenDisMixClassifierParameterSet params,
                     DifferentiableSequenceScore... score)
              throws CloneNotSupportedException

This convenience constructor creates an MSPClassifier that used MCL principle for training.

Parameters:

params - the parameter set for the classifier

score - the DifferentiableSequenceScores for the classes

Throws:

CloneNotSupportedException - if at least one DifferentiableSequenceScore could not be cloned

See Also:

DoesNothingLogPrior, MSPClassifier(GenDisMixClassifierParameterSet, LogPrior, DifferentiableSequenceScore...)

MSPClassifier

public MSPClassifier(GenDisMixClassifierParameterSet params,
                     LogPrior prior,
                     DifferentiableSequenceScore... score)
              throws CloneNotSupportedException

The default constructor that creates a new MSPClassifier from a given parameter set, a prior and DifferentiableSequenceScores for the classes.

Parameters:

params - the parameter set for the classifier

prior - the prior that shall be used; the learning principle depends on the prior: if the prior is null or DoesNothingLogPrior then MCL is used otherwise MSP

score - the DifferentiableSequenceScores for the classes

Throws:

CloneNotSupportedException - if at least one DifferentiableSequenceScore could not be cloned

See Also:

MSPClassifier(GenDisMixClassifierParameterSet, LogPrior, double, DifferentiableSequenceScore...), ScoreClassifier.NOT_TRAINED_VALUE, GenDisMixClassifier.setPrior(LogPrior)

MSPClassifier

public MSPClassifier(GenDisMixClassifierParameterSet params,
                     LogPrior prior,
                     double lastScore,
                     DifferentiableSequenceScore... score)
              throws CloneNotSupportedException

This constructor that creates a new MSPClassifier from a given parameter set, a prior and DifferentiableSequenceScores for the classes. Additionally, the value lastScore can be set to determine the return value of ScoreClassifier.getLastScore(). This might be useful if the parameters of the classifier are determined by an external procedure.

Parameters:

params - the parameter set for the classifier

prior - the prior that shall be used; the learning principle depends on the prior: if the prior is null or DoesNothingLogPrior then MCL is used otherwise MSP

lastScore - the score of the last optimization

score - the DifferentiableSequenceScores for the classes

Throws:

CloneNotSupportedException - if at least one DifferentiableSequenceScore could not be cloned

See Also:

GenDisMixClassifier.GenDisMixClassifier(GenDisMixClassifierParameterSet, LogPrior, LearningPrinciple, de.jstacs.sequenceScores.statisticalModels.differentiable.DifferentiableStatisticalModel...), LearningPrinciple.MSP, GenDisMixClassifier.setPrior(LogPrior)

MSPClassifier

public MSPClassifier(StringBuffer xml)
              throws NonParsableException

This is the constructor for Storable.

Parameters:

xml - the xml representation

Throws:

NonParsableException - if the representation could not be parsed.

Method Detail

getXMLTag

protected String getXMLTag()

Description copied from class: AbstractClassifier

Returns the String that is used as tag for the XML representation of the classifier. This method is used by the methods AbstractClassifier.fromXML(StringBuffer) and AbstractClassifier.toXML().

Overrides:

getXMLTag in class GenDisMixClassifier

Returns:

the String that is used as tag for the XML representation of the classifier

getInstanceName

public String getInstanceName()

Description copied from class: AbstractClassifier

Returns a short description of the classifier.

Overrides:

getInstanceName in class GenDisMixClassifier

Returns:

a short description of the classifier