de.jstacs.sequenceScores.statisticalModels.trainable.discrete.inhomogeneous

Class BayesianNetworkTrainSM

java.lang.Object

de.jstacs.sequenceScores.statisticalModels.trainable.AbstractTrainableStatisticalModel

de.jstacs.sequenceScores.statisticalModels.trainable.discrete.DiscreteGraphicalTrainSM

de.jstacs.sequenceScores.statisticalModels.trainable.discrete.inhomogeneous.InhomogeneousDGTrainSM

de.jstacs.sequenceScores.statisticalModels.trainable.discrete.inhomogeneous.DAGTrainSM

de.jstacs.sequenceScores.statisticalModels.trainable.discrete.inhomogeneous.BayesianNetworkTrainSM

All Implemented Interfaces:

InstantiableFromParameterSet, SequenceScore, StatisticalModel, TrainableStatisticalModel, Storable, Cloneable

public class BayesianNetworkTrainSM
extends DAGTrainSM

The class implements a Bayesian network ( StructureLearner.ModelType.BN ) of fixed order. It allows the user to specify some kinds of specializations of BNs including inhomogeneous Markov models ( StructureLearner.ModelType.IMM ) and permuted Markov models ( StructureLearner.ModelType.PMM ).

Author:

Jens Keilwagen

See Also:

StructureLearner.ModelType

Field Summary

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.discrete.inhomogeneous.DAGTrainSM

constraints

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.discrete.inhomogeneous.InhomogeneousDGTrainSM

DEFAULT_STREAM, sostream

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.discrete.DiscreteGraphicalTrainSM

params, trained

Fields inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.AbstractTrainableStatisticalModel

alphabets, length

Constructor Summary

Constructors

Constructor and Description
BayesianNetworkTrainSM(BayesianNetworkTrainSMParameterSet params) Creates a new BayesianNetworkTrainSM from a given BayesianNetworkTrainSMParameterSet.
BayesianNetworkTrainSM(StringBuffer representation) The standard constructor for the interface Storable.

Method Summary

Modifier and Type	Method and Description
BayesianNetworkTrainSM	clone() Follows the conventions of Object's clone()-method.
protected int[]	count(int[][] structure, byte maxOrder) Counts the occurrence of the different indegrees and checks if the conventions are met.
String	getInstanceName() Should return a short instance name such as iMM(0), BN(2), ...
double	getLogPriorTerm() Returns a value that is proportional to the log of the prior.
byte	getMaximalMarkovOrder() This method returns the maximal used Markov order, if possible.
protected String	getXMLTag() Returns the XML tag that is used for this model in DiscreteGraphicalTrainSM.fromXML(StringBuffer) and DiscreteGraphicalTrainSM.toXML().
protected void	set(DGTrainSMParameterSet parameter, boolean trained) Sets the parameters as internal parameters and does some essential computations.
void	train(DataSet data, double[] weights) Trains the TrainableStatisticalModel object given the data as DataSet using the specified weights.

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.discrete.inhomogeneous.DAGTrainSM

checkAcyclic, createConstraints, drawParameters, emitDataSet, estimateParameters, getFurtherModelInfos, getLogProbFor, getNumericalCharacteristics, getStructure, setFurtherModelInfos, toString

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.discrete.inhomogeneous.InhomogeneousDGTrainSM

check, setOutputStream

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.discrete.DiscreteGraphicalTrainSM

fromXML, getCurrentParameterSet, getDescription, getESS, isInitialized, toXML

Methods inherited from class de.jstacs.sequenceScores.statisticalModels.trainable.AbstractTrainableStatisticalModel

getAlphabetContainer, getCharacteristics, getLength, getLogProbFor, getLogProbFor, getLogScoreFor, getLogScoreFor, getLogScoreFor, getLogScoreFor, getLogScoreFor, toString, train

Methods inherited from class java.lang.Object

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

Constructor Detail

BayesianNetworkTrainSM

public BayesianNetworkTrainSM(BayesianNetworkTrainSMParameterSet params)
                       throws CloneNotSupportedException,
                              IllegalArgumentException,
                              NonParsableException

Creates a new BayesianNetworkTrainSM from a given BayesianNetworkTrainSMParameterSet.

Parameters:

params - the given parameter set

Throws:

CloneNotSupportedException - if the parameter set could not be cloned

IllegalArgumentException - if the parameter set is not instantiated

NonParsableException - if the parameter set is not parsable

See Also:

DAGTrainSM.DAGTrainSM(de.jstacs.sequenceScores.statisticalModels.trainable.discrete.inhomogeneous.parameters.IDGTrainSMParameterSet)

BayesianNetworkTrainSM

public BayesianNetworkTrainSM(StringBuffer representation)
                       throws NonParsableException

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

Parameters:

representation - the XML representation as StringBuffer

Throws:

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

See Also:

Storable, DAGTrainSM.DAGTrainSM(StringBuffer)

Method Detail

clone

public BayesianNetworkTrainSM clone()
                             throws CloneNotSupportedException

Description copied from class: AbstractTrainableStatisticalModel

Follows the conventions of Object's clone()-method.

Specified by:

clone in interface SequenceScore

Specified by:

clone in interface TrainableStatisticalModel

Overrides:

clone in class DAGTrainSM

Returns:

an object, that is a copy of the current AbstractTrainableStatisticalModel (the member-AlphabetContainer isn't deeply cloned since it is assumed to be immutable). The type of the returned object is defined by the class X directly inherited from AbstractTrainableStatisticalModel. Hence X's clone()-method should work as:
1. Object o = (X)super.clone();
2. all additional member variables of o defined by X that are not of simple data-types like int, double, ... have to be deeply copied
3. return o

Throws:

CloneNotSupportedException - if something went wrong while cloning

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

getXMLTag

protected String getXMLTag()

Description copied from class: DiscreteGraphicalTrainSM

Returns the XML tag that is used for this model in DiscreteGraphicalTrainSM.fromXML(StringBuffer) and DiscreteGraphicalTrainSM.toXML().

Specified by:

getXMLTag in class DiscreteGraphicalTrainSM

Returns:

the XML tag that is used in DiscreteGraphicalTrainSM.fromXML(StringBuffer) and DiscreteGraphicalTrainSM.toXML()

See Also:

DiscreteGraphicalTrainSM.fromXML(StringBuffer), DiscreteGraphicalTrainSM.toXML()

train

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

Description copied from interface: TrainableStatisticalModel

Trains the TrainableStatisticalModel object given the data as DataSet using the specified weights. The weight at position i belongs to the element at position i. So the array weight should have the number of sequences in the data set as dimension. (Optionally it is possible to use weight == null if all weights have the value one.)
This method should work non-incrementally. That means the result of the following series: train(data1); train(data2) should be a fully trained model over data2 and not over data1+data2. All parameters of the model were given by the call of the constructor.

Parameters:

data - the given sequences as DataSet

weights - the weights of the elements, each weight should be non-negative

Throws:

Exception - if the training did not succeed (e.g. the dimension of weights and the number of sequences in the data set do not match)

See Also:

DataSet.getElementAt(int), DataSet.ElementEnumerator

getLogPriorTerm

public double getLogPriorTerm()
                       throws Exception

Description copied from interface: StatisticalModel

Returns a value that is proportional to the log of the prior. For maximum likelihood (ML) 0 should be returned.

Specified by:

getLogPriorTerm in interface StatisticalModel

Overrides:

getLogPriorTerm in class DAGTrainSM

Returns:

a value that is proportional to the log of the prior

Throws:

Exception - if something went wrong

getMaximalMarkovOrder

public byte getMaximalMarkovOrder()

Description copied from interface: StatisticalModel

This method returns the maximal used Markov order, if possible.

Specified by:

getMaximalMarkovOrder in interface StatisticalModel

Overrides:

getMaximalMarkovOrder in class AbstractTrainableStatisticalModel

Returns:

maximal used Markov order

count

protected int[] count(int[][] structure,
                      byte maxOrder)

Counts the occurrence of the different indegrees and checks if the conventions are met.

Parameters:

structure - the structure

maxOrder - the maximal order

Returns:

an int-array containing the occurrence of indegrees

set

protected void set(DGTrainSMParameterSet parameter,
                   boolean trained)
            throws CloneNotSupportedException,
                   NonParsableException

Description copied from class: DiscreteGraphicalTrainSM

Sets the parameters as internal parameters and does some essential computations. Used in fromParameterSet-methods.

Overrides:

set in class InhomogeneousDGTrainSM

Parameters:

parameter - the new ParameterSet

trained - indicates if the model is trained or not

Throws:

CloneNotSupportedException - if the parameter set could not be cloned

NonParsableException - if the parameters of the model could not be parsed