Package edu.cmu.tetrad.bayes

Class UpdatedBayesIm

java.lang.Object

edu.cmu.tetrad.bayes.UpdatedBayesIm

All Implemented Interfaces:

BayesIm, Simulator, VariableSource, Im, TetradSerializable, Serializable

public final class UpdatedBayesIm
extends Object
implements BayesIm

Represents a Bayes IM in which all of the conditional probability tables have been updated to take into account evidence. Updated conditional probability values of variables with respect to comabinations of their parent values are calculated on the fly. Values that do not change due to being d-separated from a variable conditional on its parents are not calculated; rather, these are simply looked up in the underlying Bayes IM and returned.

Version:

$Id: $Id

Author:

josephramsey

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
UpdatedBayesIm(BayesIm bayesIm)	Constructs Bayes net in which CPT's updated for the given evidence are calculated on the fly.
UpdatedBayesIm(BayesIm bayesIm, Evidence evidence)	Constructs Bayes net in which CPT's updated for the given evidence are calculated on the fly.

Method Summary

Modifier and Type	Method	Description
void	clearRow(int nodeIndex, int rowIndex)	Assigns random probability values to the child values of this row that add to 1.
void	clearTable(int nodeIndex)	Randomizes every row in the table for the given node index.
boolean	equals(Object o)	Returns true iff this Bayes net is equal to the given Bayes net.
BayesPm	getBayesPm()	getBayesPm.
int	getCorrespondingNodeIndex(int nodeIndex, BayesIm otherBayesIm)	Returns the index of the given node in the given BayesIm.
Graph	getDag()	getDag.
Evidence	getEvidence()	Getter for the field evidence.
List<Node>	getMeasuredNodes()	getMeasuredNodes.
Node	getNode(int nodeIndex)	Returns the name of the given node.
Node	getNode(String name)	getNode.
int	getNodeIndex(Node node)	Returns the index of the given node.
int	getNumColumns(int nodeIndex)	Returns the number of columns.
int	getNumNodes()	getNumNodes.
int	getNumParents(int nodeIndex)	Returns the number of parents for the given node.
int	getNumRows(int nodeIndex)	Returns the number of rows.
int	getParent(int nodeIndex, int parentIndex)	Returns the ith parent of the givne node.
int	getParentDim(int nodeIndex, int parentIndex)	Returns the dimension of the given parent for the given node.
int[]	getParentDims(int nodeIndex)	Returns the dimensions of the pararents of the given node.
int[]	getParents(int nodeIndex)	Returns the parents of the given node.
int	getParentValue(int nodeIndex, int rowIndex, int colIndex)	Returns the given parent value.
int[]	getParentValues(int nodeIndex, int rowIndex)	Returns the parents values of the given node.
double	getProbability(int nodeIndex, int rowIndex, int colIndex)	Returns the probability for the given cell in the given CPT.
int	getRowIndex(int nodeIndex, int[] values)	getRowIndex.
List<String>	getVariableNames()	getVariableNames.
List<Node>	getVariables()	getVariables.
boolean	isIncomplete(int nodeIndex)	Returns true iff the given node has a Double.NaN value in it.
boolean	isIncomplete(int nodeIndex, int rowIndex)	Returns true iff the given row in the given node has a Double.NaN value in it.
void	normalizeAll()	normalizeAll.
void	normalizeNode(int nodeIndex)	Normalizes all rows in the table associated with a given node.
void	normalizeRow(int nodeIndex, int rowIndex)	Normalizes the given row.
void	randomizeIncompleteRows(int nodeIndex)	Randomizes any row in the table for the given node index that has a Double.NaN value in it.
void	randomizeRow(int nodeIndex, int rowIndex)	Assigns random probability values to the child values of this row that add to 1.
void	randomizeTable(int nodeIndex)	Randomizes every row in the table for the given node index.
static UpdatedBayesIm	serializableInstance()	Generates a simple exemplar of this class to test serialization.
void	setProbability(int nodeIndex, double[][] probMatrix)	setProbability.
void	setProbability(int nodeIndex, int rowIndex, int colIndex, double value)	Sets the probability for the given node at a given row and column in the table for that node.
DataSet	simulateData(int sampleSize, boolean latentDataSaved)	Simulates a data set with the specified number of rows.
DataSet	simulateData(DataSet dataSet, boolean latentDataSaved)	Simulates data based on the provided data set and saves the latent data if specified.
String	toString()	Prints out the probability table for each variable.

Methods inherited from class java.lang.Object

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

Methods inherited from interface edu.cmu.tetrad.bayes.BayesIm

getCptMapType

Constructor Details

UpdatedBayesIm

public UpdatedBayesIm(BayesIm bayesIm)

Constructs Bayes net in which CPT's updated for the given evidence are calculated on the fly.

Parameters:

bayesIm - a BayesIm object

UpdatedBayesIm

public UpdatedBayesIm(BayesIm bayesIm,
 Evidence evidence)

Constructs Bayes net in which CPT's updated for the given evidence are calculated on the fly.

Parameters:

bayesIm - a BayesIm object

evidence - a Evidence object

Method Details

serializableInstance

public static UpdatedBayesIm serializableInstance()

Generates a simple exemplar of this class to test serialization.

Returns:

a UpdatedBayesIm object

getBayesPm

public BayesPm getBayesPm()

getBayesPm.

Specified by:

getBayesPm in interface BayesIm

Returns:

a BayesPm object

getDag

public Graph getDag()

getDag.

Specified by:

getDag in interface BayesIm

Returns:

a Graph object

getNumNodes

public int getNumNodes()

getNumNodes.

Specified by:

getNumNodes in interface BayesIm

Returns:

a int

getNode

public Node getNode(int nodeIndex)

Returns the name of the given node.

Specified by:

getNode in interface BayesIm

Parameters:

nodeIndex - the index of the node.

Returns:

the node corresponding to the given node index.

getNode

public Node getNode(String name)

getNode.

Specified by:

getNode in interface BayesIm

Parameters:

name - a String object

Returns:

a Node object

getNodeIndex

public int getNodeIndex(Node node)

Returns the index of the given node.

Specified by:

getNodeIndex in interface BayesIm

Parameters:

node - the given node.

Returns:

the index for that node, or -1 if the node is not in the BayesIm.

getNumColumns

public int getNumColumns(int nodeIndex)

Returns the number of columns.

Specified by:

getNumColumns in interface BayesIm

Parameters:

nodeIndex - the index of the node.

Returns:

the number of columns in the table of the given node N with index 'nodeIndex'--that is, the number of possible values that N can take on. That is, if P(N=v0 | P1=v1, P2=v2, ... Pn=vn) is a conditional probability stored in 'probs', then the maximum number of rows in the table for N is #vals(N).

See Also:

• BayesIm.getNumRows(int)

getNumRows

public int getNumRows(int nodeIndex)

Returns the number of rows.

Specified by:

getNumRows in interface BayesIm

Parameters:

nodeIndex - the index of the node.

Returns:

the number of rows in the table of the given node, which would be the total number of possible combinations of parent values for a given node. That is, if P(N=v0 | P1=v1, P2=v2, ... Pn=vn) is a conditional probability stored in 'probs', then the maximum number of rows in the table for N is #vals(P1) x #vals(P2) x ... x #vals(Pn).

See Also:

• BayesIm.getRowIndex(int, int[])
• BayesIm.getNumColumns(int)

getNumParents

public int getNumParents(int nodeIndex)

Returns the number of parents for the given node.

Specified by:

getNumParents in interface BayesIm

Parameters:

nodeIndex - the given node.

Returns:

the number of parents of the given node.

getParent

public int getParent(int nodeIndex,
 int parentIndex)

Returns the ith parent of the givne node.

Specified by:

getParent in interface BayesIm

Parameters:

nodeIndex - the index of the node.

parentIndex - the index of the parent.

Returns:

the given parent of the given node.

getParentDim

public int getParentDim(int nodeIndex,
 int parentIndex)

Returns the dimension of the given parent for the given node.

Specified by:

getParentDim in interface BayesIm

Parameters:

nodeIndex - the index of the node.

parentIndex - the index of the parent.

Returns:

the dimension of the given parent for the given node.

getParentDims

public int[] getParentDims(int nodeIndex)

Returns the dimensions of the pararents of the given node.

Specified by:

getParentDims in interface BayesIm

Parameters:

nodeIndex - the index of the node.

Returns:

(a defensive copy of) the array representing the dimensionality of each parent of a node, that is, the number of values which that node can take on. The order of entries in this array is the same as the order of entries of nodes returned by getParents() for that node.

See Also:

• BayesIm.getParents(int)

getParents

public int[] getParents(int nodeIndex)

Returns the parents of the given node.

Specified by:

getParents in interface BayesIm

Parameters:

nodeIndex - the index of the node.

Returns:

(a defensive copy of) the array containing all of the parents of a given node in the order in which they are stored internally.

See Also:

• BayesIm.getParentDims(int)

getParentValues

public int[] getParentValues(int nodeIndex,
 int rowIndex)

Returns the parents values of the given node.

Specified by:

getParentValues in interface BayesIm

Parameters:

nodeIndex - the index of the node.

rowIndex - the index of the row in question.

Returns:

an array containing the combination of parent values for a given node and given row in the probability table for that node. To get the combination of parent values from the row number, the row number is represented using a variable-base place value system, where the bases for each place value are the dimensions of the parents in the order in which they are given by getParentDims(). For instance, if the row number (base 10) is 103 and the parent dimension array is [3 5 7], we calculate the first value as 103 / 7 = 14 with a remainder of 5. We then divide 14 / 5 = 2 with a remainder of 4. We then divide 2 / 3 = 0 with a remainder of 2. The variable place value representation is [2 4 5], which is the combination of parent values. This is the inverse function of getRowIndex().

See Also:

• BayesIm.getNodeIndex(edu.cmu.tetrad.graph.Node)
• BayesIm.getRowIndex(int, int[])

getParentValue

public int getParentValue(int nodeIndex,
 int rowIndex,
 int colIndex)

Returns the given parent value.

Specified by:

getParentValue in interface BayesIm

Parameters:

nodeIndex - the index of the node.

rowIndex - the index of the row in question.

colIndex - the index of the column in question.

Returns:

the value in the probability table for the given node, at the given row and column.

getProbability

public double getProbability(int nodeIndex,
 int rowIndex,
 int colIndex)

Returns the probability for the given cell in the given CPT.

Calculates the probability for the given node, at the given row and column of the conditional probability table (CPT), updated for the evidence provided in the constuctor.

Specified by:

getProbability in interface BayesIm

Parameters:

nodeIndex - the index of the node in question.

rowIndex - the row in the table for this for node which represents the combination of parent values in question.

colIndex - the column in the table for this node which represents the value of the node in question.

Returns:

the probability for the given node at the given row and column in the table for that node. To get the node index, use getNodeIndex(). To get the row index, use getRowIndex(). To get the column index, use getCategoryIndex() from the underlying BayesPm(). The value returned will represent a conditional probability of the form P(N=v0 | P1=v1, P2=v2, ... , Pn=vn), where N is the node referenced by nodeIndex, v0 is the value referenced by colIndex, and the combination of parent values indicated is the combination indicated by rowIndex.

See Also:

• BayesIm.getNodeIndex(edu.cmu.tetrad.graph.Node)
• BayesIm.getRowIndex(int, int[])

getRowIndex

public int getRowIndex(int nodeIndex,
 int[] values)

getRowIndex.

Specified by:

getRowIndex in interface BayesIm

Parameters:

nodeIndex - a int

values - an array of objects

Returns:

a int

See Also:

• BayesIm.getParentValues(int, int)

normalizeAll

public void normalizeAll()

normalizeAll.

Specified by:

normalizeAll in interface BayesIm

normalizeNode

public void normalizeNode(int nodeIndex)

Normalizes all rows in the table associated with a given node.

Specified by:

normalizeNode in interface BayesIm

Parameters:

nodeIndex - the index of the node in question.

normalizeRow

public void normalizeRow(int nodeIndex,
 int rowIndex)

Normalizes the given row.

Specified by:

normalizeRow in interface BayesIm

Parameters:

nodeIndex - the index of the node in question.

rowIndex - the index of the row in question.

setProbability

public void setProbability(int nodeIndex,
 double[][] probMatrix)

setProbability.

Specified by:

setProbability in interface BayesIm

Parameters:

nodeIndex - a int

probMatrix - an array of objects

setProbability

public void setProbability(int nodeIndex,
 int rowIndex,
 int colIndex,
 double value)

Sets the probability for the given node at a given row and column in the table for that node. To get the node index, use getNodeIndex(). To get the row index, use getRowIndex(). To get the column index, use getCategoryIndex() from the underlying BayesPm(). The value returned will represent a conditional probability of the form P(N=v0 | P1=v1, P2=v2, ... , Pn=vn), where N is the node referenced by nodeIndex, v0 is the value referenced by colIndex, and the combination of parent values indicated is the combination indicated by rowIndex.

Specified by:

setProbability in interface BayesIm

Parameters:

nodeIndex - the index of the node in question.

rowIndex - the row in the table for this for node which represents the combination of parent values in question.

colIndex - the column in the table for this node which represents the value of the node in question.

value - the desired probability to be set.

See Also:

• BayesIm.getProbability(int, int, int)

getCorrespondingNodeIndex

public int getCorrespondingNodeIndex(int nodeIndex,
 BayesIm otherBayesIm)

Returns the index of the given node in the given BayesIm.

Specified by:

getCorrespondingNodeIndex in interface BayesIm

Parameters:

nodeIndex - the index of the node in this BayesIm.

otherBayesIm - the BayesIm in which the node is to be found.

Returns:

the index of the node with the given name in the specified BayesIm.

clearRow

public void clearRow(int nodeIndex,
 int rowIndex)

Assigns random probability values to the child values of this row that add to 1.

Specified by:

clearRow in interface BayesIm

Parameters:

nodeIndex - the node for the table that this row belongs to.

rowIndex - the index of the row.

randomizeRow

public void randomizeRow(int nodeIndex,
 int rowIndex)

Assigns random probability values to the child values of this row that add to 1.

Specified by:

randomizeRow in interface BayesIm

Parameters:

nodeIndex - the node for the table that this row belongs to.

rowIndex - the index of the row.

randomizeIncompleteRows

public void randomizeIncompleteRows(int nodeIndex)

Randomizes any row in the table for the given node index that has a Double.NaN value in it.

Specified by:

randomizeIncompleteRows in interface BayesIm

Parameters:

nodeIndex - the node for the table whose incomplete rows are to be randomized.

randomizeTable

public void randomizeTable(int nodeIndex)

Randomizes every row in the table for the given node index.

Specified by:

randomizeTable in interface BayesIm

Parameters:

nodeIndex - the node for the table to be randomized.

clearTable

public void clearTable(int nodeIndex)

Randomizes every row in the table for the given node index.

Specified by:

clearTable in interface BayesIm

Parameters:

nodeIndex - the node for the table to be randomized.

isIncomplete

public boolean isIncomplete(int nodeIndex,
 int rowIndex)

Returns true iff the given row in the given node has a Double.NaN value in it.

Specified by:

isIncomplete in interface BayesIm

Parameters:

nodeIndex - the node for the table whose incomplete rows are to be checked.

rowIndex - the index of the row in question.

Returns:

true iff one of the values in the given row is Double.NaN.

isIncomplete

public boolean isIncomplete(int nodeIndex)

Returns true iff the given node has a Double.NaN value in it.

Specified by:

isIncomplete in interface BayesIm

Parameters:

nodeIndex - the node for the table whose incomplete rows are to be checked.

Returns:

true iff any value in the table for the given node is Double.NaN.

simulateData

public DataSet simulateData(int sampleSize,
 boolean latentDataSaved)

Simulates a data set with the specified number of rows.

Specified by:

simulateData in interface BayesIm

Specified by:

simulateData in interface Simulator

Parameters:

sampleSize - the number of rows to simulate.

latentDataSaved - if true, latent variables are saved in the data set.

Returns:

the simulated data set.

simulateData

public DataSet simulateData(DataSet dataSet,
 boolean latentDataSaved)

Simulates data based on the provided data set and saves the latent data if specified.

Specified by:

simulateData in interface BayesIm

Parameters:

dataSet - the data set to simulate data for

latentDataSaved - a boolean value indicating whether the latent data should be saved or not

Returns:

the simulated data set

getVariables

public List<Node> getVariables()

getVariables.

Specified by:

getVariables in interface BayesIm

Specified by:

getVariables in interface VariableSource

Returns:

a List object

getVariableNames

public List<String> getVariableNames()

getVariableNames.

Specified by:

getVariableNames in interface BayesIm

Specified by:

getVariableNames in interface VariableSource

Returns:

a List object

getMeasuredNodes

public List<Node> getMeasuredNodes()

getMeasuredNodes.

Specified by:

getMeasuredNodes in interface BayesIm

Returns:

a List object

equals

public boolean equals(Object o)

Returns true iff this Bayes net is equal to the given Bayes net. The sense of equality may vary depending on the type of Bayes net.

Specified by:

equals in interface BayesIm

Overrides:

equals in class Object

Parameters:

o - the Bayes net to be compared to this Bayes net.

Returns:

true iff this bayes net is equal to the given Bayes net. The sense of equality may vary depending on the type of Bayes net.

toString

public String toString()

Prints out the probability table for each variable.

Specified by:

toString in interface BayesIm

Overrides:

toString in class Object

Returns:

a String object

getEvidence

public Evidence getEvidence()

Getter for the field evidence.

Returns:

a Evidence object