de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.motif
Class SkewNormalLikeDurationDiffSM

java.lang.Object
  de.jstacs.sequenceScores.differentiable.AbstractDifferentiableSequenceScore
      de.jstacs.sequenceScores.statisticalModels.differentiable.AbstractDifferentiableStatisticalModel
          de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.motif.PositionDiffSM
              de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.motif.DurationDiffSM
                  de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.motif.SkewNormalLikeDurationDiffSM

All Implemented Interfaces:

DifferentiableSequenceScore, SequenceScore, DifferentiableStatisticalModel, StatisticalModel, Storable, Cloneable

public class SkewNormalLikeDurationDiffSM
extends DurationDiffSM

This class implements a skew normal like discrete truncated distribution.

Author:

Jens Keilwagen

Field Summary

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.motif.DurationDiffSM

delta, ess, max, min

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.motif.PositionDiffSM

internal

Fields inherited from class de.jstacs.sequenceScores.differentiable.AbstractDifferentiableSequenceScore

alphabets, length, r

Fields inherited from interface de.jstacs.sequenceScores.differentiable.DifferentiableSequenceScore

UNKNOWN

Constructor Summary

SkewNormalLikeDurationDiffSM(int min, int max, boolean trainMean, double hyperMeanMean, double hyperMeanSigma, boolean trainPrecision, double hyperPrec1, double hyperPrec2, boolean trainSkew, double hyperSkewMean, double hyperSkewStdev, int starts)
This is the constructor that allows the most flexible handling of the parameters.

SkewNormalLikeDurationDiffSM(int min, int max, double param0, double param1, double param2)
This is the main constructor if the parameters are fixed.

SkewNormalLikeDurationDiffSM(StringBuffer source)
This is the constructor for Storable.

Method Summary

void	addGradientOfLogPriorTerm(double[] grad, int start) This method computes the gradient of DifferentiableStatisticalModel.getLogPriorTerm() for each parameter of this model.
void	adjust(int[] length, double[] weight) This method adjust the parameter based on the given statistic.
SkewNormalLikeDurationDiffSM	clone() Creates a clone (deep copy) of the current DifferentiableSequenceScore instance.
protected void	fromXML(StringBuffer rep) This method is called in the constructor for the Storable interface to create a scoring function from a StringBuffer.
double[]	getCurrentParameterValues() Returns a double array of dimension DifferentiableSequenceScore.getNumberOfParameters() containing the current parameter values.
String	getInstanceName() Should return a short instance name such as iMM(0), BN(2), ...
double	getLogPriorTerm() This method computes a value that is proportional to DifferentiableStatisticalModel.getESS() * DifferentiableStatisticalModel.getLogNormalizationConstant() + Math.log( prior ) where prior is the prior for the parameters of this model.
double	getLogScore(int... values) This method enables the user to get the log-score without using a sequence object.
double	getLogScoreAndPartialDerivation(IntList indices, DoubleList partialDer, int... values) This method enables the user to get the log-score and the partial derivations without using a sequence object.
int	getNumberOfParameters() Returns the number of parameters in this DifferentiableSequenceScore.
int	getNumberOfRecommendedStarts() This method returns the number of recommended optimization starts.
protected String	getRNotation(String distributionName) This method returns the distribution in R notation.
void	initializeFunction(int index, boolean freeParams, DataSet[] data, double[][] weights) This method creates the underlying structure of the DifferentiableSequenceScore.
void	initializeFunctionRandomly(boolean freeParams) This method initializes the DifferentiableSequenceScore randomly.
void	initializeUniformly() This method set special parameters that lead to an uniform distribution.
boolean	isInitialized() This method can be used to determine whether the instance is initialized.
boolean	isNormalized() This method indicates whether the implemented score is already normalized to 1 or not.
void	modify(int delta) This method modifies the underlying AlphabetContainer.
void	setParameters(double[] params, int start) This method sets the internal parameters to the values of params between start and start + DifferentiableSequenceScore.getNumberOfParameters() - 1
void	setParameters(double par0, double par1, double par2) this method can be used to set the parameters even if the parameters are not allowed to be optimized.
StringBuffer	toXML() This method returns an XML representation as StringBuffer of an instance of the implementing class.

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.motif.DurationDiffSM

getESS, getLogNormalizationConstant, getLogPartialNormalizationConstant, getMax, getMin, getNumberOfPossibilities, getSizeOfEventSpaceForRandomVariablesOfParameter, isPossible, next, reset, toString

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.mixture.motif.PositionDiffSM

getInternalPosition, getLogScoreAndPartialDerivation, getLogScoreAndPartialDerivationForInternal, getLogScoreFor, getLogScoreForInternal, getValuesFromSequence

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.AbstractDifferentiableStatisticalModel

emitDataSet, getInitialClassParam, getLogProbFor, getLogProbFor, getLogProbFor, getLogScoreFor, getLogScoreFor, getMaximalMarkovOrder, isNormalized

Methods inherited from class de.jstacs.sequenceScores.differentiable.AbstractDifferentiableSequenceScore

getAlphabetContainer, getCharacteristics, getLength, getLogScoreAndPartialDerivation, getLogScoreAndPartialDerivation, getLogScoreFor, getLogScoreFor, getNumberOfStarts, getNumericalCharacteristics

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.jstacs.sequenceScores.differentiable.DifferentiableSequenceScore

getLogScoreAndPartialDerivation, getLogScoreAndPartialDerivation

Methods inherited from interface de.jstacs.sequenceScores.SequenceScore

getAlphabetContainer, getCharacteristics, getLength, getLogScoreFor, getLogScoreFor, getNumericalCharacteristics

Constructor Detail

SkewNormalLikeDurationDiffSM

public SkewNormalLikeDurationDiffSM(int min,
                                    int max,
                                    double param0,
                                    double param1,
                                    double param2)

This is the main constructor if the parameters are fixed.

Parameters:

min - the minimal value

max - the maximal value

param0 - the fixed parameter value for the first parameter (mean)

param1 - the fixed parameter value for the second parameter (precision)

param2 - the fixed parameter value for the third parameter (skew)

SkewNormalLikeDurationDiffSM

public SkewNormalLikeDurationDiffSM(int min,
                                    int max,
                                    boolean trainMean,
                                    double hyperMeanMean,
                                    double hyperMeanSigma,
                                    boolean trainPrecision,
                                    double hyperPrec1,
                                    double hyperPrec2,
                                    boolean trainSkew,
                                    double hyperSkewMean,
                                    double hyperSkewStdev,
                                    int starts)

This is the constructor that allows the most flexible handling of the parameters.

Parameters:

min - the minimal value

max - the maximal value

trainMean - a switch whether to optimize the first parameter

hyperMeanMean - the mean hyper parameter for the first parameter

hyperMeanSigma - the standard deviation hyper parameter for the first parameter

trainPrecision - a switch whether to optimize the second parameter

hyperPrec1 - the first hyper parameter for the precision (first parameter of the transformed gamma density); this is value is used to determine the ess: hyperPrec1 = 0.5*ess

hyperPrec2 - the second hyper parameter for the precision (second parameter of the transformed gamma density)

trainSkew - a switch whether to optimize the third parameter

hyperSkewMean - the mean hyper parameter for the third parameter

hyperSkewStdev - the standard deviation hyper parameter for the third parameter

starts - the number of recommended starts

SkewNormalLikeDurationDiffSM

public SkewNormalLikeDurationDiffSM(StringBuffer source)
                             throws NonParsableException

This is the constructor for Storable. Creates a new SkewNormalLikeDurationDiffSM out of a StringBuffer.

Parameters:

source - the XML representation as StringBuffer

Throws:

NonParsableException - if the XML representation could not be parsed

Method Detail

clone

public SkewNormalLikeDurationDiffSM clone()
                                   throws CloneNotSupportedException

Description copied from interface: DifferentiableSequenceScore

Creates a clone (deep copy) of the current DifferentiableSequenceScore instance.

Specified by:

clone in interface DifferentiableSequenceScore

Specified by:

clone in interface SequenceScore

Overrides:

clone in class PositionDiffSM

Returns:

the cloned instance of the current DifferentiableSequenceScore

Throws:

CloneNotSupportedException - if something went wrong while cloning the DifferentiableSequenceScore

initializeFunction

public void initializeFunction(int index,
                               boolean freeParams,
                               DataSet[] data,
                               double[][] weights)
                        throws Exception

Description copied from interface: DifferentiableSequenceScore

This method creates the underlying structure of the DifferentiableSequenceScore.

Parameters:

index - the index of the class the DifferentiableSequenceScore models

freeParams - indicates whether the (reduced) parameterization is used

data - the samples

weights - the weights of the sequences in the samples

Throws:

Exception - if something went wrong

adjust

public void adjust(int[] length,
                   double[] weight)

Description copied from class: DurationDiffSM

This method adjust the parameter based on the given statistic.

Specified by:

adjust in class DurationDiffSM

Parameters:

length - an array containing length values

weight - an array containing corresponding weight values

initializeFunctionRandomly

public void initializeFunctionRandomly(boolean freeParams)
                                throws Exception

Description copied from interface: DifferentiableSequenceScore

This method initializes the DifferentiableSequenceScore randomly. It has to create the underlying structure of the DifferentiableSequenceScore.

Parameters:

freeParams - indicates whether the (reduced) parameterization is used

Throws:

Exception - if something went wrong

fromXML

protected void fromXML(StringBuffer rep)
                throws NonParsableException

Description copied from class: AbstractDifferentiableSequenceScore

This method is called in the constructor for the Storable interface to create a scoring function from a StringBuffer.

Overrides:

fromXML in class DurationDiffSM

Parameters:

rep - the XML representation as StringBuffer

Throws:

NonParsableException - if the StringBuffer could not be parsed

See Also:

AbstractDifferentiableSequenceScore.AbstractDifferentiableSequenceScore(StringBuffer)

getInstanceName

public String getInstanceName()

Description copied from interface: SequenceScore

Should return a short instance name such as iMM(0), BN(2), ...

Returns:

a short instance name

getCurrentParameterValues

public double[] getCurrentParameterValues()
                                   throws Exception

Description copied from interface: DifferentiableSequenceScore

Returns a double array of dimension DifferentiableSequenceScore.getNumberOfParameters() containing the current parameter values. If one likes to use these parameters to start an optimization it is highly recommended to invoke DifferentiableSequenceScore.initializeFunction(int, boolean, DataSet[], double[][]) before. After an optimization this method can be used to get the current parameter values.

Returns:

the current parameter values

Throws:

Exception - if no parameters exist (yet)

getLogScore

public double getLogScore(int... values)

Description copied from class: PositionDiffSM

This method enables the user to get the log-score without using a sequence object.

Specified by:

getLogScore in class PositionDiffSM

Parameters:

values - the values

Returns:

the score

getLogScoreAndPartialDerivation

public double getLogScoreAndPartialDerivation(IntList indices,
                                              DoubleList partialDer,
                                              int... values)

Description copied from class: PositionDiffSM

This method enables the user to get the log-score and the partial derivations without using a sequence object.

Specified by:

getLogScoreAndPartialDerivation in class PositionDiffSM

Parameters:

indices - a list for the indices of the parameters

partialDer - a list of the partial derivations

values - the values

Returns:

the score

getNumberOfParameters

public int getNumberOfParameters()

Description copied from interface: DifferentiableSequenceScore

Returns the number of parameters in this DifferentiableSequenceScore. If the number of parameters is not known yet, the method returns DifferentiableSequenceScore.UNKNOWN.

Returns:

the number of parameters in this DifferentiableSequenceScore

See Also:

DifferentiableSequenceScore.UNKNOWN

setParameters

public void setParameters(double[] params,
                          int start)

Description copied from interface: DifferentiableSequenceScore

This method sets the internal parameters to the values of params between start and start + DifferentiableSequenceScore.getNumberOfParameters() - 1

Parameters:

params - the new parameters

start - the start index in params

setParameters

public void setParameters(double par0,
                          double par1,
                          double par2)

this method can be used to set the parameters even if the parameters are not allowed to be optimized.

Parameters:

par0 - the first parameter (for the mean or maximum)

par1 - the second parameter (for the precision)

par2 - the third parameter (for the skew)

toXML

public StringBuffer toXML()

Description copied from interface: Storable

This method returns an XML representation as StringBuffer of an instance of the implementing class.

Specified by:

toXML in interface Storable

Overrides:

toXML in class DurationDiffSM

Returns:

the XML representation

getRNotation

protected String getRNotation(String distributionName)

Description copied from class: DurationDiffSM

This method returns the distribution in R notation.

Specified by:

getRNotation in class DurationDiffSM

Parameters:

distributionName - the name of the distribution, e.g., "p"

Returns:

the distribution in R notation

See Also:

REnvironment

getLogPriorTerm

public double getLogPriorTerm()

Description copied from interface: DifferentiableStatisticalModel

This method computes a value that is proportional to

DifferentiableStatisticalModel.getESS() * DifferentiableStatisticalModel.getLogNormalizationConstant() + Math.log( prior )

where prior is the prior for the parameters of this model.

Returns:

a value that is proportional to DifferentiableStatisticalModel.getESS() * DifferentiableStatisticalModel.getLogNormalizationConstant() + Math.log( prior ).

See Also:

DifferentiableStatisticalModel.getESS(), DifferentiableStatisticalModel.getLogNormalizationConstant()

addGradientOfLogPriorTerm

public void addGradientOfLogPriorTerm(double[] grad,
                                      int start)
                               throws Exception

Description copied from interface: DifferentiableStatisticalModel

This method computes the gradient of DifferentiableStatisticalModel.getLogPriorTerm() for each parameter of this model. The results are added to the array grad beginning at index start.

Parameters:

grad - the array of gradients

start - the start index in the grad array, where the partial derivations for the parameters of this models shall be entered

Throws:

Exception - if something went wrong with the computing of the gradients

See Also:

DifferentiableStatisticalModel.getLogPriorTerm()

isInitialized

public boolean isInitialized()

Description copied from interface: SequenceScore

This method can be used to determine whether the instance is initialized. If the instance is initialized you should be able to invoke SequenceScore.getLogScoreFor(Sequence).

Returns:

true if the instance is initialized, false otherwise

isNormalized

public boolean isNormalized()

Description copied from interface: DifferentiableStatisticalModel

This method indicates whether the implemented score is already normalized to 1 or not. The standard implementation returns false.

Specified by:

isNormalized in interface DifferentiableStatisticalModel

Overrides:

isNormalized in class AbstractDifferentiableStatisticalModel

Returns:

true if the implemented score is already normalized to 1, false otherwise

initializeUniformly

public void initializeUniformly()

Description copied from class: DurationDiffSM

This method set special parameters that lead to an uniform distribution.

Specified by:

initializeUniformly in class DurationDiffSM

modify

public void modify(int delta)

Description copied from class: DurationDiffSM

This method modifies the underlying AlphabetContainer. This might be necessary if the motif length changed.

Overrides:

modify in class DurationDiffSM

Parameters:

delta - the change

See Also:

Mutable.modify(int, int), MutableMotifDiscoverer.modifyMotif(int, int, int)

getNumberOfRecommendedStarts

public int getNumberOfRecommendedStarts()

Description copied from interface: DifferentiableSequenceScore

This method returns the number of recommended optimization starts. The standard implementation returns 1.

Specified by:

getNumberOfRecommendedStarts in interface DifferentiableSequenceScore

Overrides:

getNumberOfRecommendedStarts in class AbstractDifferentiableSequenceScore

Returns:

the number of recommended optimization starts