weka.classifiers.bayes.net

Class MarginCalculator

java.lang.Object

weka.classifiers.bayes.net.MarginCalculator

All Implemented Interfaces:

java.io.Serializable, RevisionHandler

public class MarginCalculator
extends java.lang.Object
implements java.io.Serializable, RevisionHandler

See Also:

Serialized Form

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
class	MarginCalculator.JunctionTreeNode
class	MarginCalculator.JunctionTreeSeparator

Field Summary

Fields

Modifier and Type	Field and Description
MarginCalculator.JunctionTreeNode	m_root

Constructor Summary

Constructors

Constructor and Description
MarginCalculator()

Method Summary

Modifier and Type	Method and Description
void	calcFullMargins(BayesNet bayesNet)
void	calcMargins(BayesNet bayesNet) Calc marginal distributions of nodes in Bayesian network Note that a connected network is assumed.
boolean[][]	fillIn(int[] order, boolean[][] bAdjacencyMatrix) Apply Tarjan and Yannakakis (1984) fill in algorithm for graph triangulation.
double[]	getMargin(int iNode)
int	getNode(java.lang.String sNodeName)
java.lang.String	getRevision() Returns the revision string.
static void	main(java.lang.String[] args)
boolean[][]	moralize(BayesNet bayesNet) moralize DAG and calculate adjacency matrix representation for a Bayes Network, effecively converting the directed acyclic graph to an undirected graph.
void	process(boolean[][] bAdjacencyMatrix, BayesNet bayesNet)
void	setEvidence(int nNode, int iValue)
java.lang.String	toString()
java.lang.String	toXMLBIF03()

Methods inherited from class java.lang.Object

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

Field Detail

m_root

public MarginCalculator.JunctionTreeNode m_root

Constructor Detail

MarginCalculator

public MarginCalculator()

Method Detail

getNode

public int getNode(java.lang.String sNodeName)

toXMLBIF03

public java.lang.String toXMLBIF03()

calcMargins

public void calcMargins(BayesNet bayesNet)
                 throws java.lang.Exception

Calc marginal distributions of nodes in Bayesian network Note that a connected network is assumed. Unconnected networks may give unexpected results.

Parameters:

bayesNet -

Throws:

java.lang.Exception

calcFullMargins

public void calcFullMargins(BayesNet bayesNet)
                     throws java.lang.Exception

Throws:

java.lang.Exception

process

public void process(boolean[][] bAdjacencyMatrix,
                    BayesNet bayesNet)
             throws java.lang.Exception

Throws:

java.lang.Exception

moralize

public boolean[][] moralize(BayesNet bayesNet)

moralize DAG and calculate adjacency matrix representation for a Bayes Network, effecively converting the directed acyclic graph to an undirected graph.

Parameters:

bayesNet - Bayes Network to process

Returns:

adjacencies in boolean matrix format

fillIn

public boolean[][] fillIn(int[] order,
                          boolean[][] bAdjacencyMatrix)

Apply Tarjan and Yannakakis (1984) fill in algorithm for graph triangulation. In reverse order, insert edges between any non-adjacent neighbors that are lower numbered in the ordering. Side effect: input matrix is used as output

Parameters:

order - node ordering

bAdjacencyMatrix - boolean matrix representing the graph

Returns:

boolean matrix representing the graph with fill ins

setEvidence

public void setEvidence(int nNode,
                        int iValue)
                 throws java.lang.Exception

Throws:

java.lang.Exception

toString

public java.lang.String toString()

Overrides:

toString in class java.lang.Object

getMargin

public double[] getMargin(int iNode)

getRevision

public java.lang.String getRevision()

Returns the revision string.

Specified by:

getRevision in interface RevisionHandler

Returns:

the revision

main

public static void main(java.lang.String[] args)