weka.classifiers.bayes.net.search.ci

Class CISearchAlgorithm

java.lang.Object

weka.classifiers.bayes.net.search.SearchAlgorithm

weka.classifiers.bayes.net.search.local.LocalScoreSearchAlgorithm

weka.classifiers.bayes.net.search.ci.CISearchAlgorithm

All Implemented Interfaces:

java.io.Serializable, OptionHandler, RevisionHandler

Direct Known Subclasses:

ICSSearchAlgorithm

public class CISearchAlgorithm
extends LocalScoreSearchAlgorithm

The CISearchAlgorithm class supports Bayes net structure search algorithms that are based on conditional independence test (as opposed to for example score based of cross validation based search algorithms).

Valid options are:

  -mbc
  Applies a Markov Blanket correction to the network structure,
  after a network structure is learned. This ensures that all
  nodes in the network are part of the Markov blanket of the
  classifier node.
 

  -S [BAYES|MDL|ENTROPY|AIC|CROSS_CLASSIC|CROSS_BAYES]
  Score type (BAYES, BDeu, MDL, ENTROPY and AIC)
 

See Also:

Serialized Form

Field Summary

Fields inherited from class weka.classifiers.bayes.net.search.local.LocalScoreSearchAlgorithm

TAGS_SCORE_TYPE

Fields inherited from class weka.classifiers.bayes.net.search.SearchAlgorithm

m_bInitAsNaiveBayes, m_bMarkovBlanketClassifier, m_nMaxNrOfParents, m_sInitalBIFFile

Constructor Summary

Constructors

Constructor and Description
CISearchAlgorithm()

Method Summary

Modifier and Type	Method and Description
java.lang.String	getRevision() Returns the revision string.
java.lang.String	globalInfo() Returns a string describing this object
protected boolean	isConditionalIndependent(int iAttributeX, int iAttributeY, int[] iAttributesZ, int nAttributesZ) IsConditionalIndependent tests whether two nodes X and Y are independent given a set of variables Z.

Methods inherited from class weka.classifiers.bayes.net.search.local.LocalScoreSearchAlgorithm

buildStructure, calcNodeScore, calcScoreOfCounts, calcScoreOfCounts2, calcScoreWithExtraParent, calcScoreWithMissingParent, getMarkovBlanketClassifier, getOptions, getScoreType, listOptions, logScore, markovBlanketClassifierTipText, scoreTypeTipText, setMarkovBlanketClassifier, setOptions, setScoreType

Methods inherited from class weka.classifiers.bayes.net.search.SearchAlgorithm

addArcMakesSense, doMarkovBlanketCorrection, initAsNaiveBayesTipText, isArc, maxNrOfParentsTipText, reverseArcMakesSense, search, toString

Methods inherited from class java.lang.Object

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

Constructor Detail

CISearchAlgorithm

public CISearchAlgorithm()

Method Detail

globalInfo

public java.lang.String globalInfo()

Returns a string describing this object

Overrides:

globalInfo in class LocalScoreSearchAlgorithm

Returns:

a description of the classifier suitable for displaying in the explorer/experimenter gui

isConditionalIndependent

protected boolean isConditionalIndependent(int iAttributeX,
                                           int iAttributeY,
                                           int[] iAttributesZ,
                                           int nAttributesZ)
                                    throws java.lang.InterruptedException

IsConditionalIndependent tests whether two nodes X and Y are independent given a set of variables Z. The test compares the score of the Bayes network with and without arrow Y->X where all nodes in Z are parents of X.

Parameters:

iAttributeX - - index of attribute representing variable X

iAttributeY - - index of attribute representing variable Y

iAttributesZ - - array of integers representing indices of attributes in set Z

nAttributesZ - - cardinality of Z

Returns:

true if X and Y conditionally independent given Z

Throws:

java.lang.InterruptedException

getRevision

public java.lang.String getRevision()

Returns the revision string.

Specified by:

getRevision in interface RevisionHandler

Overrides:

getRevision in class LocalScoreSearchAlgorithm

Returns:

the revision