opendial.bn.nodes

Class ChanceNode

java.lang.Object

opendial.bn.nodes.BNode

opendial.bn.nodes.ChanceNode

All Implemented Interfaces:

java.lang.Comparable<BNode>

public class ChanceNode
extends BNode

Representation of a chance node (sometimes also called belief node), which is a random variable associated with a specific probability distribution.

Field Summary

Fields

Modifier and Type	Field and Description
protected java.util.Set<Value>	cachedValues
protected ProbDistribution	distrib

Fields inherited from class opendial.bn.nodes.BNode

inputNodes, nodeId, outputNodes

Constructor Summary

Constructors

Constructor and Description
ChanceNode(java.lang.String nodeId, ProbDistribution distrib) Creates a new chance node, with the given identifier and probability distribution
ChanceNode(java.lang.String nodeId, Value value) Creates a change node with a unique value (associated with a probability 1.0)

Method Summary

Modifier and Type	Method and Description
void	addInputNode(BNode inputNode) Adds a new (input) relation for the node
ChanceNode	copy() Returns a copy of the node.
ProbDistribution	getDistrib() Returns the probability distribution attached to the node
java.util.Map<Assignment,java.lang.Double>	getFactor() Returns the "factor matrix" mapping assignments of conditional variables + the node variable to a probability value.
int	getNbValues() Returns the number of values for the node
double	getProb(Assignment condition, Value nodeValue) Returns the probability associated with the conditional assignment and the node value, if one is defined.
double	getProb(Value nodeValue) Returns the probability associated with a specific value, according to the current distribution.
java.util.Set<Value>	getValues() Returns a discrete set of values for the node.
int	hashCode() Returns the hashcode for the node (based on the hashcode of the identifier and the distribution).
protected void	modifyVariableId(java.lang.String oldId, java.lang.String newId) Replaces the identifier for the input and output nodes with the new identifier
void	pruneValues(double threshold) Prune the values with a probability below a given threshold
Value	sample() Returns a sample value for the node, according to the probability distribution currently defined.
Value	sample(Assignment condition) Returns a sample value for the node, given a condition.
void	setDistrib(ProbDistribution distrib) Sets the probability distribution of the node, and erases the existing one.
void	setId(java.lang.String newId) Replaces the node identifier with a new one
java.lang.String	toString() Returns the string representation of the distribution.

Methods inherited from class opendial.bn.nodes.BNode

addInputNode_internal, addInputNodes, addOutputNode_internal, compareTo, equals, getAncestorIds, getAncestors, getAncestorsIds, getClique, getDescendantIds, getDescendants, getDescendantsIds, getId, getInputNodeIds, getInputNodes, getInputNodes, getOutputNodes, getOutputNodes, getOutputNodesIds, getPossibleConditions, hasAncestor, hasDescendant, hasDescendant, hasInputNode, hasOutputNode, hasOutputNode, removeAllRelations, removeInputNode_internal, removeInputNode, removeInputNodes, removeOutputNode, setNetwork

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Field Detail

distrib

protected ProbDistribution distrib

cachedValues

protected java.util.Set<Value> cachedValues

Constructor Detail

ChanceNode

public ChanceNode(java.lang.String nodeId,
                  ProbDistribution distrib)

Creates a new chance node, with the given identifier and probability distribution

Parameters:

nodeId - the unique node identifier

distrib - the probability distribution for the node

ChanceNode

public ChanceNode(java.lang.String nodeId,
                  Value value)

Creates a change node with a unique value (associated with a probability 1.0)

Parameters:

nodeId - the node identifier

value - the single value for the node

Method Detail

setDistrib

public void setDistrib(ProbDistribution distrib)

Sets the probability distribution of the node, and erases the existing one.

Parameters:

distrib - the distribution for the node

addInputNode

public void addInputNode(BNode inputNode)

Adds a new (input) relation for the node

Overrides:

addInputNode in class BNode

Parameters:

inputNode - the input node to connect

setId

public void setId(java.lang.String newId)

Replaces the node identifier with a new one

Overrides:

setId in class BNode

Parameters:

newId - the new identifier

pruneValues

public void pruneValues(double threshold)

Prune the values with a probability below a given threshold

Parameters:

threshold - the probability threshold

getProb

public double getProb(Value nodeValue)

Returns the probability associated with a specific value, according to the current distribution.

The method assumes that the node is conditionally independent of every other node. If it isn't, one should use the getProb(condition, nodeValue) method instead.

NB: the method should *not* be used to perform sophisticated inference, as it is not optimised and might lead to distorted results for very dependent networks

Parameters:

nodeValue - the value for the node

Returns:

its probability

getProb

public double getProb(Assignment condition,
                      Value nodeValue)

Returns the probability associated with the conditional assignment and the node value, if one is defined.

Parameters:

condition - the condition

nodeValue - the value

Returns:

the associated probability

sample

public Value sample()

Returns a sample value for the node, according to the probability distribution currently defined.

The method assumes that the node is conditionally independent of every other node. If it isn't, one should use the sample(condition) method instead.

Returns:

the sample value

sample

public Value sample(Assignment condition)

Returns a sample value for the node, given a condition. The sample is selected according to the probability distribution for the node.

Parameters:

condition - the value assignment on conditional nodes

Returns:

the sample value

getValues

public java.util.Set<Value> getValues()

Returns a discrete set of values for the node. If the variable for the node has a continuous range, this set if based on a discretisation procedure defined by the distribution.

Specified by:

getValues in class BNode

Returns:

the discrete set of values

getNbValues

public int getNbValues()

Returns the number of values for the node

Returns:

the number of values

getDistrib

public ProbDistribution getDistrib()

Returns the probability distribution attached to the node

Returns:

the distribution

getFactor

public java.util.Map<Assignment,java.lang.Double> getFactor()

Returns the "factor matrix" mapping assignments of conditional variables + the node variable to a probability value.

Specified by:

getFactor in class BNode

Returns:

the factor matrix.

copy

public ChanceNode copy()

Returns a copy of the node. Note that only the node content is copied, not its connection with other nodes.

Specified by:

copy in class BNode

Returns:

the copy

hashCode

public int hashCode()

Returns the hashcode for the node (based on the hashcode of the identifier and the distribution).

Overrides:

hashCode in class BNode

Returns:

the hashcode for the identifier

toString

public java.lang.String toString()

Returns the string representation of the distribution.

Overrides:

toString in class BNode

Returns:

the node identifier

modifyVariableId

protected void modifyVariableId(java.lang.String oldId,
                                java.lang.String newId)

Description copied from class: BNode

Replaces the identifier for the input and output nodes with the new identifier

Overrides:

modifyVariableId in class BNode

Parameters:

oldId - the old label for the node

newId - the new label for the node