Package de.uka.ipd.sdq.dsexplore.bayesnets.utility

Class BayesInference

java.lang.Object

de.uka.ipd.sdq.dsexplore.bayesnets.utility.BayesInference

public class BayesInference
extends Object

This class is used for all inference purposes. Currently, only P(Sample|Bayes Network) is supported. Other inference capabilities will be (hopefully) added later.

Constructor Summary

Constructors

Constructor	Description
BayesInference(int[][] Graph, int[][] Data)	Constructor for the class.

Method Summary

Modifier and Type	Method	Description
double	getProbabilityOfSampleGivenBayesNetwork(int[] Sample)	Calculates the P(Sample|Bayes Network).
static void	main(String[] args)

Methods inherited from class java.lang.Object

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

Constructor Details

BayesInference

public BayesInference(int[][] Graph,
 int[][] Data)

Constructor for the class.

Parameters:

Graph - - An adjacency matrix representing the Bayesian Network

Data - - The Data you have as a matrix. Each row is one datapoint

Method Details

main

public static void main(String[] args)

getProbabilityOfSampleGivenBayesNetwork

public double getProbabilityOfSampleGivenBayesNetwork(int[] Sample)

Calculates the P(Sample|Bayes Network). It is assumed that the Graph has been chosen by the user. Normally, it is recommended that the Graph is learnt from the Data using other classes of this de.uka.ipd.sdq.dsexplore.bayesnets plugin. But one can specify any Graph and any Data that one likes.

Parameters:

Sample - - The sample as an int array. The length of the Sample has to be equal to the number of variables in the Bayesian Network (this is equal to this.Graph.length)

Returns:

The probability P(Sample|Bayesian Network) as a double