de.jstacs.sequenceScores.statisticalModels.differentiable.directedGraphicalModels.structureLearning.measures
Class InhomogeneousMarkov

java.lang.Object
  de.jstacs.sequenceScores.statisticalModels.differentiable.directedGraphicalModels.structureLearning.measures.Measure
      de.jstacs.sequenceScores.statisticalModels.differentiable.directedGraphicalModels.structureLearning.measures.InhomogeneousMarkov

All Implemented Interfaces:

InstantiableFromParameterSet, Storable, Cloneable

public class InhomogeneousMarkov
extends Measure

Class for a network structure of a BayesianNetworkDiffSM that is an inhomogeneous Markov model. The order of the Markov model can be defined by the user. A Markov model of order 0 is also known as position weight matrix (PWM), a Markov model of order 1 is also known as weight array matrix (WAM) model.

Author:

Jan Grau

Nested Class Summary

static class

InhomogeneousMarkov.InhomogeneousMarkovParameterSet Class for an InstanceParameterSet that defines the parameters of an InhomogeneousMarkov structure Measure.

Nested classes/interfaces inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.directedGraphicalModels.structureLearning.measures.Measure

Measure.MeasureParameterSet

Field Summary

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.directedGraphicalModels.structureLearning.measures.Measure

parameters

Constructor Summary

InhomogeneousMarkov(InhomogeneousMarkov.InhomogeneousMarkovParameterSet parameters)
Creates a new InhomogeneousMarkov from the corresponding InstanceParameterSet parameters.

InhomogeneousMarkov(int order)
Creates the structure of an inhomogeneous Markov model of order order.

InhomogeneousMarkov(StringBuffer buf)
The standard constructor for the interface Storable.

Method Summary

InhomogeneousMarkov	clone()
String	getInstanceName() Returns the name of the Measure and possibly some additional information about the current instance.
int	getOrder() Returns the order of the Markov model as defined in the constructor
int[][]	getParents(DataSet fg, DataSet bg, double[] weightsFg, double[] weightsBg, int length) Returns the optimal parents for the given data and weights.
String	getXMLTag() Returns the XML-tag for storing this measure
boolean	isShiftable() Indicates if Measure supports shifts.

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.differentiable.directedGraphicalModels.structureLearning.measures.Measure

fillTensor, fillTensor, getCMI, getCMI, getCurrentParameterSet, getEAR, getEAR, getMI, getMI, getStatistics, getStatisticsOrderTwo, sum, toParents, toXML, union

Methods inherited from class java.lang.Object

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

Constructor Detail

InhomogeneousMarkov

public InhomogeneousMarkov(int order)
                    throws SimpleParameter.IllegalValueException,
                           CloneNotSupportedException

Creates the structure of an inhomogeneous Markov model of order order.

Parameters:

order - the order

Throws:

CloneNotSupportedException - if the parameters could not be cloned

SimpleParameter.IllegalValueException - if the order is not allowed

InhomogeneousMarkov

public InhomogeneousMarkov(InhomogeneousMarkov.InhomogeneousMarkovParameterSet parameters)
                    throws CloneNotSupportedException

Creates a new InhomogeneousMarkov from the corresponding InstanceParameterSet parameters.

Parameters:

parameters - the corresponding parameters

Throws:

CloneNotSupportedException - if the parameters could not be cloned

InhomogeneousMarkov

public InhomogeneousMarkov(StringBuffer buf)
                    throws NonParsableException

The standard constructor for the interface Storable. Recreates an InhomogeneousMarkov structure from its XML representation as returned by Measure.toXML().

Parameters:

buf - the XML representation as StringBuffer

Throws:

NonParsableException - if the XML code could not be parsed

Method Detail

getOrder

public int getOrder()

Returns the order of the Markov model as defined in the constructor

Returns:

the order

clone

public InhomogeneousMarkov clone()
                          throws CloneNotSupportedException

Overrides:

clone in class Measure

Throws:

CloneNotSupportedException

getInstanceName

public String getInstanceName()

Description copied from class: Measure

Returns the name of the Measure and possibly some additional information about the current instance.

Specified by:

getInstanceName in class Measure

Returns:

the name of the Measure

getParents

public int[][] getParents(DataSet fg,
                          DataSet bg,
                          double[] weightsFg,
                          double[] weightsBg,
                          int length)
                   throws Exception

Description copied from class: Measure

Returns the optimal parents for the given data and weights. The returned array of parents p at each position i is build as follows:

• p[i][p.length - 1] contains the index i itself
• p[i][p.length - 2] contains the "most important" parent
• ...
• p[i][0] contains the "least important" parent

Specified by:

getParents in class Measure

Parameters:

fg - the data of the current (foreground) class

bg - the data of the negative (background) class

weightsFg - the weights for the sequences of fg

weightsBg - the weights for the sequences of bg

length - the length of the model, must be equal to the length of the sequences

Returns:

the the array p with the optimal parents

Throws:

Exception - if the lengths do not match or other problems concerning the data occur

isShiftable

public boolean isShiftable()

Description copied from class: Measure

Indicates if Measure supports shifts.

Overrides:

isShiftable in class Measure

Returns:

if Measure supports shifts

getXMLTag

public String getXMLTag()

Description copied from class: Measure

Returns the XML-tag for storing this measure

Specified by:

getXMLTag in class Measure

Returns:

the tag