de.jstacs.classifiers.differentiableSequenceScoreBased

Class ScoreClassifier

java.lang.Object

de.jstacs.classifiers.AbstractClassifier

de.jstacs.classifiers.AbstractScoreBasedClassifier

de.jstacs.classifiers.differentiableSequenceScoreBased.ScoreClassifier

All Implemented Interfaces:

Storable, Cloneable

Direct Known Subclasses:

GenDisMixClassifier

public abstract class ScoreClassifier
extends AbstractScoreBasedClassifier

This abstract class implements the main functionality of a DifferentiableSequenceScore based classifier.

Author:

Jens Keilwagen, Jan Grau

Nested Class Summary

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

AbstractScoreBasedClassifier.DoubleTableResult

Field Summary

Fields

Modifier and Type	Field and Description
protected boolean	hasBeenOptimized This boolean indicates whether the classifier has been optimized with the method AbstractClassifier.train(DataSet[]) or the weighted version.
static double	NOT_TRAINED_VALUE This value should be used in getLastScore() if the classifier is not trained.
protected ScoreClassifierParameterSet	params The parameter set for the classifier.
protected DifferentiableSequenceScore[]	score The internally used scoring functions.
protected SafeOutputStream	sostream This stream is used for comments, e.g.
protected History	template The default history

Constructor Summary

Constructors

Constructor and Description
ScoreClassifier(ScoreClassifierParameterSet params, double lastScore, DifferentiableSequenceScore... score) Creates a new ScoreClassifier from a given ScoreClassifierParameterSet and DifferentiableSequenceScores .
ScoreClassifier(StringBuffer xml) The standard constructor for the interface Storable.

Method Summary

Modifier and Type	Method and Description
ScoreClassifier	clone()
protected void	createStructure(DataSet[] data, double[][] weights) Creates the structure that will be used in the optimization.
protected void	createStructure(DataSet[] data, double[][] weights, boolean initRandomly) Creates the structure that will be used in the optimization.
protected double	doOptimization(DataSet[] reduced, double[][] newWeights) This method does the optimization of the train-method
protected void	extractFurtherClassifierInfosFromXML(StringBuffer xml) Extracts further information of a classifier from an XML representation.
CategoricalResult[]	getClassifierAnnotation() Returns an array of Results of dimension AbstractClassifier.getNumberOfClasses() that contains information about the classifier and for each class. res[0] = new CategoricalResult( "classifier", "the kind of classifier", getInstanceName() ); res[1] = new CategoricalResult( "class info 0", "some information about the class", "info0" ); res[2] = new CategoricalResult( "class info 1", "some information about the class", "info1" ); ...
ScoreClassifierParameterSet	getCurrentParameterSet() This method returns the current ParameterSet of the classifier.
DifferentiableSequenceScore	getDifferentiableSequenceScore(int i) Returns the internally used DifferentiableSequenceScore with index i.
DifferentiableSequenceScore[]	getDifferentiableSequenceScores() Returns all internally used DifferentiableSequenceScores in the internal order.
protected abstract DiffSSBasedOptimizableFunction	getFunction(DataSet[] data, double[][] weights) Returns the function that should be optimized.
protected StringBuffer	getFurtherClassifierInfos() This method returns further information of a classifier as a StringBuffer.
String	getInstanceName() Returns a short description of the classifier.
protected int	getIterations() Returns the number of independent re-starts in the training.
double	getLastScore() Returns the score that was computed in the last optimization of the parameters.
NumericalResultSet	getNumericalCharacteristics() Returns the subset of numerical values that are also returned by AbstractClassifier.getCharacteristics().
protected double	getScore(Sequence seq, int i, boolean check) This method returns the score for a given Sequence and a given class.
protected abstract String	getXMLTag() Returns the String that is used as tag for the XML representation of the classifier.
boolean	hasBeenOptimized() This method indicates if the classifier has been optimized by a train-method.
void	initUsingParameters(double[] parameters) Sets the parameters of this classifier and the contained scoring functions to the supplied parameters.
boolean	isInitialized() This method gives information about the state of the classifier.
protected OptimizableFunction.KindOfParameter	preoptimize(OptimizableFunction f) This method allows to pre-optimize the parameter before the real optimization.
void	setOutputStream(OutputStream o) Sets the OutputStream that is used e.g.
void	train(DataSet[] data, double[][] weights) This method trains a classifier over an array of weighted DataSet s.

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, toString, wait, wait, wait

Field Detail

score

protected DifferentiableSequenceScore[] score

The internally used scoring functions.

params

protected ScoreClassifierParameterSet params

The parameter set for the classifier.

hasBeenOptimized

protected boolean hasBeenOptimized

This boolean indicates whether the classifier has been optimized with the method AbstractClassifier.train(DataSet[]) or the weighted version.

sostream

protected SafeOutputStream sostream

This stream is used for comments, e.g. during the training, ... .

NOT_TRAINED_VALUE

public static final double NOT_TRAINED_VALUE

This value should be used in getLastScore() if the classifier is not trained.

See Also:

Constant Field Values

template

protected History template

The default history

Constructor Detail

ScoreClassifier

public ScoreClassifier(ScoreClassifierParameterSet params,
                       double lastScore,
                       DifferentiableSequenceScore... score)
                throws CloneNotSupportedException

Creates a new ScoreClassifier from a given ScoreClassifierParameterSet and DifferentiableSequenceScores .

Parameters:

params - the parameter set for the classifier

lastScore - the score of the last optimization, if no such value exists the programmer should use NOT_TRAINED_VALUE

score - the DifferentiableSequenceScores for the classes

Throws:

CloneNotSupportedException - if at least one DifferentiableSequenceScore could not be cloned

See Also:

AbstractScoreBasedClassifier.AbstractScoreBasedClassifier(AlphabetContainer, int, int)

ScoreClassifier

public ScoreClassifier(StringBuffer xml)
                throws NonParsableException

The standard constructor for the interface Storable. Creates a new ScoreClassifier out of its XML representation.

Parameters:

xml - the XML representation as StringBuffer

Throws:

NonParsableException - if the ScoreClassifier could not be reconstructed out of the XML representation (the StringBuffer could not be parsed)

See Also:

AbstractScoreBasedClassifier.AbstractScoreBasedClassifier(StringBuffer), Storable

Method Detail

clone

public ScoreClassifier clone()
                      throws CloneNotSupportedException

Overrides:

clone in class AbstractScoreBasedClassifier

Throws:

CloneNotSupportedException

getInstanceName

public String getInstanceName()

Description copied from class: AbstractClassifier

Returns a short description of the classifier.

Specified by:

getInstanceName in class AbstractClassifier

Returns:

a short description of the classifier

getClassifierAnnotation

public CategoricalResult[] getClassifierAnnotation()

Description copied from class: AbstractClassifier

Returns an array of Results of dimension AbstractClassifier.getNumberOfClasses() that contains information about the classifier and for each class.

res[0] = new CategoricalResult( "classifier", "the kind of classifier", getInstanceName() );
res[1] = new CategoricalResult( "class info 0", "some information about the class", "info0" );
res[2] = new CategoricalResult( "class info 1", "some information about the class", "info1" );
...

Specified by:

getClassifierAnnotation in class AbstractClassifier

Returns:

an array of Results that contains information about the classifier

getNumericalCharacteristics

public NumericalResultSet getNumericalCharacteristics()
                                               throws Exception

Description copied from class: AbstractClassifier

Returns the subset of numerical values that are also returned by AbstractClassifier.getCharacteristics().

Specified by:

getNumericalCharacteristics in class AbstractClassifier

Returns:

the numerical characteristics

Throws:

Exception - if some of the characteristics could not be defined

isInitialized

public boolean isInitialized()

Description copied from class: AbstractClassifier

This method gives information about the state of the classifier.

Specified by:

isInitialized in class AbstractClassifier

Returns:

true if the classifier is initialized and therefore able to classify sequences, otherwise false

hasBeenOptimized

public boolean hasBeenOptimized()

This method indicates if the classifier has been optimized by a train-method.

Returns:

true if the classifier has been optimized by a train-method, false otherwise

setOutputStream

public void setOutputStream(OutputStream o)

Sets the OutputStream that is used e.g. for writing information during training. It is possible to set o=null, then nothing will be written.

Parameters:

o - the OutputStream

train

public void train(DataSet[] data,
                  double[][] weights)
           throws Exception

Description copied from class: AbstractClassifier

This method trains a classifier over an array of weighted DataSet s. That is why the following has to be fulfilled:

• s.length == weights.length
• and for all i: weights[i] == null || s[i].getNumberOfElements() == weights[i].length.

This method should work non-incrementally as the method AbstractClassifier.train(DataSet...).

This method should check that the DataSets are defined over the underlying alphabet and length.

Specified by:

train in class AbstractClassifier

Parameters:

data - an array of DataSets

weights - the weights for the DataSets

Throws:

Exception - if the weights are incorrect or the training did not succeed

See Also:

AbstractClassifier.train(DataSet...)

getIterations

protected int getIterations()

Returns the number of independent re-starts in the training. The default implementation uses AbstractDifferentiableSequenceScore.getNumberOfStarts(DifferentiableSequenceScore[]) for the internal DifferentiableSequenceScores.

Returns:

the number of starts

See Also:

doOptimization(DataSet[], double[][]), AbstractClassifier.train(DataSet...), train(DataSet[], double[][])

doOptimization

protected double doOptimization(DataSet[] reduced,
                                double[][] newWeights)
                         throws Exception

This method does the optimization of the train-method

Parameters:

reduced - the data sets

newWeights - the weights

Returns:

the value of the optimization

Throws:

Exception - if something went wrong during the optimization

preoptimize

protected OptimizableFunction.KindOfParameter preoptimize(OptimizableFunction f)
                                                   throws Exception

This method allows to pre-optimize the parameter before the real optimization. It might be used useful, for instance, to find initial parameters on a part of the complete data.

Parameters:

f - the function to be optimized

Returns:

enumeration value that indicates how to retrieve the parameters from the function

Throws:

Exception - if the pre-optimization fails

createStructure

protected void createStructure(DataSet[] data,
                               double[][] weights,
                               boolean initRandomly)
                        throws Exception

Creates the structure that will be used in the optimization.

Parameters:

data - the data

weights - the weights of the data

initRandomly - initialize the functions randomly

Throws:

Exception - if something went wrong

initUsingParameters

public void initUsingParameters(double[] parameters)
                         throws Exception

Sets the parameters of this classifier and the contained scoring functions to the supplied parameters.

Parameters:

parameters - the new parameters

Throws:

Exception - if the parameters could not be set

createStructure

protected void createStructure(DataSet[] data,
                               double[][] weights)
                        throws Exception

Creates the structure that will be used in the optimization.

Parameters:

data - the data

weights - the weights of the data *

Throws:

Exception - if something went wrong

extractFurtherClassifierInfosFromXML

protected void extractFurtherClassifierInfosFromXML(StringBuffer xml)
                                             throws NonParsableException

Description copied from class: AbstractClassifier

Extracts further information of a classifier from an XML representation. This method is used by the method AbstractClassifier.fromXML(StringBuffer) and should not be made public.

Overrides:

extractFurtherClassifierInfosFromXML in class AbstractScoreBasedClassifier

Parameters:

xml - the XML representation as StringBuffer

Throws:

NonParsableException - if the information could not be parsed out of the XML representation (the StringBuffer could not be parsed)

See Also:

AbstractClassifier.fromXML(StringBuffer)

getFunction

protected abstract DiffSSBasedOptimizableFunction getFunction(DataSet[] data,
                                                              double[][] weights)
                                                       throws Exception

Returns the function that should be optimized.

Parameters:

data - the data sets

weights - the weights of the sequences of the data sets

Returns:

the function that should be optimized

Throws:

Exception - if something went wrong

getFurtherClassifierInfos

protected StringBuffer getFurtherClassifierInfos()

Description copied from class: AbstractClassifier

This method returns further information of a classifier as a StringBuffer. This method is used by the method AbstractClassifier.toXML() and should not be made public.

Overrides:

getFurtherClassifierInfos in class AbstractScoreBasedClassifier

Returns:

further information of a classifier as a StringBuffer

See Also:

AbstractClassifier.toXML()

getScore

protected double getScore(Sequence seq,
                          int i,
                          boolean check)
                   throws IllegalArgumentException,
                          NotTrainedException,
                          Exception

Description copied from class: AbstractScoreBasedClassifier

This method returns the score for a given Sequence and a given class.

Specified by:

getScore in class AbstractScoreBasedClassifier

Parameters:

seq - the Sequence

i - the index of the class

check - the switch to decide whether to check AlphabetContainer and the length of the Sequence or not

Returns:

the score for a given Sequence and a given class

Throws:

IllegalArgumentException - if something is wrong with the Sequence seq

NotTrainedException - if the classifier is not trained

Exception - if something went wrong

getLastScore

public double getLastScore()

Returns the score that was computed in the last optimization of the parameters.

Returns:

score from the last parameter optimization

getDifferentiableSequenceScore

public DifferentiableSequenceScore getDifferentiableSequenceScore(int i)
                                                           throws CloneNotSupportedException

Returns the internally used DifferentiableSequenceScore with index i.

Parameters:

i - the internal index of the DifferentiableSequenceScore

Returns:

the internally used DifferentiableSequenceScore with index i

Throws:

CloneNotSupportedException - if the DifferentiableSequenceScore could not be cloned

getDifferentiableSequenceScores

public DifferentiableSequenceScore[] getDifferentiableSequenceScores()
                                                              throws CloneNotSupportedException

Returns all internally used DifferentiableSequenceScores in the internal order.

Returns:

the internally used DifferentiableSequenceScores in the internal order

Throws:

CloneNotSupportedException - if a DifferentiableSequenceScore could not be cloned

getXMLTag

protected abstract 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().

Specified by:

getXMLTag in class AbstractClassifier

Returns:

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

getCurrentParameterSet

public ScoreClassifierParameterSet getCurrentParameterSet()
                                                   throws CloneNotSupportedException

This method returns the current ParameterSet of the classifier.

Returns:

the current ParameterSet of the classifier.

Throws:

CloneNotSupportedException - if the ParameterSet could not be cloned