BBN

Description

The package bbn consists of core classes for representing the data structure of a Bayesian network. BBN.java and Node.java are used to represent a Bayesian network. NodeManager.java helps handle evidence for inference. Some useful utilities are also included in this package such as a data generator.

Examples

Example 1: Load the network from an xmlbif file and print out the information of each node. The following example shows how to load a Bayesian network from a file, and how to access its node information. To run this example, create the file BBNExample.java as follows and make sure the network file asia.xml is under the same directory.

==============================BBNExample.java=====================================
import bbn.*;
import java.util.Vector;

public class BBNExample {
    public static void main(String[] args){
    System.out.println("load the network from file ... ");
    BBN network = new BBN();
    network.loadFromXML("asia.xml");

    System.out.println("printing out information of each node... ");
    for (int i = 0; i < network.size(); i++){
        System.out.println("i="+i);
        network.getNodeAt(i).print();
        network.getNodeAt(i).printStateNames();
        if(network.getNodeAt(i).getParents().size()>0){ 
            for(int j=0;j "+network.getNodeAt(i).getParentName(j));
             } 
            System.out.println("probabilities in CPT -->"+network.getNodeAt(i).getProbabilities());
            System.out.println("--------");
         }
    }
}

=============================Result of BBNExample=======================================
D:\bnj>javac BBNExample.java

D:\bnj>java BBNExample
load the network from file ...
printing out information of each node...
i=0
For node VisitAsia:
  Visit
  No_Visit
probabilities in CPT --> [0.01, 0.99]
--------
i=1
For node Tuberculosis:
  Present
  Absent
parents --> VisitAsia
probabilities in CPT --> [0.05, 0.01, 0.95, 0.99]
--------
i=2
For node Smoking:
  Smoker
  NonSmoker
probabilities in CPT --> [0.5, 0.5]
--------
i=3
For node Cancer:
  Present
  Absent
parents --> Smoking
probabilities in CPT --> [0.1, 0.01, 0.9, 0.99]
--------
i=4
For node TbOrCa:
  True
  False
parents --> Tuberculosis
parents --> Cancer
probabilities in CPT --> [1.0, 1.0, 1.0, 0.0, 0.0, 0.0, 0.0, 1.0]
--------
i=5
For node XRay:
  Abnormal
  Normal
parents --> TbOrCa
probabilities in CPT --> [0.98, 0.05, 0.02, 0.95]
--------
i=6
For node Bronchitis:
  Present
  Absent
parents --> Smoking
probabilities in CPT --> [0.6, 0.3, 0.4, 0.7]
--------
i=7
For node Dyspnea:
  Present
  Absent
parents --> TbOrCa
parents --> Bronchitis
probabilities in CPT --> [0.9, 0.7, 0.8, 0.1, 0.1, 0.3, 0.2, 0.9]
--------

================================================================

Example 2: Simulate the network and generate a data file from the network. DataGenerator can be used to simulate the network and generate a data file from the network. The output data file can be used as the training dataset of any learning algorithm. The simulation process is done by forward sampling, i.e., first simulating root nodes, then simulating their children, and so on. DataGenerator2.java is an optimized version of DataGenerator.java. The output data file is stored in an xml file format. DataGenerator can also be used to generate an evidence file if the number of samples is set to zero. The following example shows how to simulate the network and generate a data file with 20 samples, named asia20.xml, from the network. You can view the resulting data file here.
```
============================= Example of using DataGenerator ========================================

D:\bnj>java bbn/DataGenerator2
 * * * DataGenerator2 * * *
Usage: java DataGenerator2 input.xml output.xml number_of_samples (0 will 
generate an evidence file)

D:\bnj>java bbn/DataGenerator2 asia.xml asia20.xml 20
 * * * DataGenerator * * *
Usage: java DataGenerator input.xml output.xml number_of_samples (0 will 
generate an evidence file)
Success!

D:\bnj>

============================= End of Example=====================================
```

Example 3: Use DataGenerator to generate evidence file. The following example shows how to generate an evidence file using DataGenerator. The evidence file is useful for inference. You can modify the evidence bits at the first line to set evidence nodes (0 means query, 1 means evidence). You can view another sample evidence file for the asia network here.

=============================Example of using DataGenerator========================================

D:\bnj>java bbn/DataGenerator2 asia.xml asia_evidence.xml 0
 * * * DataGenerator2 * * *
Usage: java DataGenerator2 input.xml output.xml number_of_samples (0 will 
generate an evidence file)
Success!

D:\bnj>

=============================Result evidence file : asia_evidence.xml===================

0 0 0 0 0 0 0 0
VisitAsia|Smoking|Tuberculosis|Cancer|TbOrCa|XRay|Bronchitis|Dyspnea
Visit NonSmoker Absent Present False Normal Present Present

=============================end of evidence file=======================================

KDD-Tools
Fri June 28 2002