weka.classifiers.bayes.net.search.local

Class HillClimber

java.lang.Object

weka.classifiers.bayes.net.search.SearchAlgorithm

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

weka.classifiers.bayes.net.search.local.HillClimber

All Implemented Interfaces:

java.io.Serializable, OptionHandler, RevisionHandler

Direct Known Subclasses:

LAGDHillClimber, RepeatedHillClimber, TabuSearch

public class HillClimber
extends LocalScoreSearchAlgorithm

This Bayes Network learning algorithm uses a hill climbing algorithm adding, deleting and reversing arcs. The search is not restricted by an order on the variables (unlike K2). The difference with B and B2 is that this hill climber also considers arrows part of the naive Bayes structure for deletion.

Valid options are:

 -P <nr of parents>
  Maximum number of parents

 -R
  Use arc reversal operation.
  (default false)

 -N
  Initial structure is empty (instead of Naive Bayes)

 -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)

Version:

$Revision: 1.9 $

Author:

Remco Bouckaert (rrb@xm.co.nz)

See Also:

Serialized Form

Field Summary

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

TAGS_SCORE_TYPE

Constructor Summary

Constructors

Constructor and Description
HillClimber()

Method Summary

Modifier and Type	Method and Description
boolean	getInitAsNaiveBayes() Gets whether to init as naive bayes
int	getMaxNrOfParents() Gets the max number of parents.
java.lang.String[]	getOptions() Gets the current settings of the search algorithm.
java.lang.String	getRevision() Returns the revision string.
boolean	getUseArcReversal() get use the arc reversal operation
java.lang.String	globalInfo() This will return a string describing the search algorithm.
java.util.Enumeration	listOptions() Returns an enumeration describing the available options.
void	setInitAsNaiveBayes(boolean bInitAsNaiveBayes) Sets whether to init as naive bayes
void	setMaxNrOfParents(int nMaxNrOfParents) Sets the max number of parents
void	setOptions(java.lang.String[] options) Parses a given list of options.
void	setUseArcReversal(boolean bUseArcReversal) set use the arc reversal operation
java.lang.String	useArcReversalTipText()

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

buildStructure, calcNodeScore, calcScoreWithExtraParent, calcScoreWithMissingParent, getMarkovBlanketClassifier, getScoreType, logScore, markovBlanketClassifierTipText, scoreTypeTipText, setMarkovBlanketClassifier, setScoreType

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

initAsNaiveBayesTipText, maxNrOfParentsTipText, toString

Methods inherited from class java.lang.Object

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

Constructor Detail

HillClimber

public HillClimber()

Method Detail

setMaxNrOfParents

public void setMaxNrOfParents(int nMaxNrOfParents)

Sets the max number of parents

Parameters:

nMaxNrOfParents - the max number of parents

getMaxNrOfParents

public int getMaxNrOfParents()

Gets the max number of parents.

Returns:

the max number of parents

listOptions

public java.util.Enumeration listOptions()

Returns an enumeration describing the available options.

Specified by:

listOptions in interface OptionHandler

Overrides:

listOptions in class LocalScoreSearchAlgorithm

Returns:

an enumeration of all the available options.

setOptions

public void setOptions(java.lang.String[] options)
                throws java.lang.Exception

Parses a given list of options.

Valid options are:

 -P <nr of parents>
  Maximum number of parents

 -R
  Use arc reversal operation.
  (default false)

 -N
  Initial structure is empty (instead of Naive Bayes)

 -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)

Specified by:

setOptions in interface OptionHandler

Overrides:

setOptions in class LocalScoreSearchAlgorithm

Parameters:

options - the list of options as an array of strings

Throws:

java.lang.Exception - if an option is not supported

getOptions

public java.lang.String[] getOptions()

Gets the current settings of the search algorithm.

Specified by:

getOptions in interface OptionHandler

Overrides:

getOptions in class LocalScoreSearchAlgorithm

Returns:

an array of strings suitable for passing to setOptions

setInitAsNaiveBayes

public void setInitAsNaiveBayes(boolean bInitAsNaiveBayes)

Sets whether to init as naive bayes

Parameters:

bInitAsNaiveBayes - whether to init as naive bayes

getInitAsNaiveBayes

public boolean getInitAsNaiveBayes()

Gets whether to init as naive bayes

Returns:

whether to init as naive bayes

getUseArcReversal

public boolean getUseArcReversal()

get use the arc reversal operation

Returns:

whether the arc reversal operation should be used

setUseArcReversal

public void setUseArcReversal(boolean bUseArcReversal)

set use the arc reversal operation

Parameters:

bUseArcReversal - whether the arc reversal operation should be used

globalInfo

public java.lang.String globalInfo()

This will return a string describing the search algorithm.

Overrides:

globalInfo in class LocalScoreSearchAlgorithm

Returns:

The string.

useArcReversalTipText

public java.lang.String useArcReversalTipText()

Returns:

a string to describe the Use Arc Reversal option.

getRevision

public java.lang.String getRevision()

Returns the revision string.

Specified by:

getRevision in interface RevisionHandler

Overrides:

getRevision in class LocalScoreSearchAlgorithm

Returns:

the revision