Author Topic: How to pass .dat file using JAVA HUgin API for EM learning.  (Read 36430 times)

Offline Ajay Tiwari

  • Newbie
  • *
  • Posts: 9
    • View Profile
Can anybody please tell me how to pass a .dat file for EM learning using JAVA HUGIN API.

Offline Martin

  • HUGIN Expert
  • Hero Member
  • *****
  • Posts: 613
    • View Profile
Re: How to pass .dat file using JAVA HUgin API for EM learning.
« Reply #1 on: January 04, 2008, 13:30:29 »
Quote
Can anybody please tell me how to pass a .dat file for EM learning using JAVA HUGIN API.

This is the procedure for using EM-learning:
1. Create instance of Domain (either by Loading a NET-file or by manually construct the network from the code)

2. Load data (Domain.parseCases)

3. Compile domain (Domain.compile)

4. Run EM-algorithm (Domain.learnTables)

Here is example code for loading a random network with discrete chance nodes, parsing a random data file and running EM-algorithm for computing new maximal likelihoods for the CPTs. After learning, the new CPTs are printed.

Code: [Select]
import java.util.*;

import COM.hugin.HAPI.*;

class EMLearning {
    public static void main(String[] args) {
if (args.length < 2) {
    System.err.println("use arguments: <network.net> <data.dat>");
    return;
}
String netFile = args[0];
String dataFile = args[1];
try {
    //load domain
    Domain dom = new Domain(netFile, new DefaultClassParseListener());
   
    //compile using defaults
    dom.compile();

    NodeList nodes = dom.getNodes();
    ListIterator li = nodes.listIterator();
    while (li.hasNext()) {
Node n = (Node)li.next();
if (n instanceof DiscreteChanceNode) {
    //make sure that all discrete chance nodes have experience tables with entries set to 0
    //to compute maximal likelihood estimates of CPTs
    DiscreteChanceNode dcc = (DiscreteChanceNode)n;
    Table experience = dcc.getExperienceTable();
    int size = experience.getSize();
    for (int i = 0; i < size; i++) {
experience.setDataItem(i, 0.0);
    }
}
    }
   
    //load data file
    dom.parseCases(dataFile, new DefaultClassParseListener());

    /* use these for configuring when EM should terminate
    dom.setMaxNumberOfEMIterations(0);
    dom.setLogLikelihoodTolerance(0.0001);
    */
   
    dom.learnTables();

    //print CPTs after EM-learning
    System.out.println("New tables after EM-learning:");
    li = nodes.listIterator();
    while (li.hasNext()) {
Node n = (Node)li.next();
if (n instanceof DiscreteChanceNode) {
    DiscreteChanceNode dcc = (DiscreteChanceNode)n;
    Table CPT = dcc.getTable();
    printTable(CPT);
}
    }

} catch (ExceptionHugin eh) {
    System.err.println(eh);
}
    }

    //print tables for all discrete chance nodes
    public static void printTable (Table CPT) throws ExceptionHugin {
NodeList nodes = CPT.getNodes();
int[] configuration = new int[nodes.size()];
int tableSize = CPT.getSize();
for (int i = 0; i < tableSize; i++) {
    CPT.getConfiguration(configuration, i);
    for (int j = 0; j < nodes.size(); j++) {
Node n = (Node)nodes.get(j);
System.out.print(n.getName() + "=" + configuration[j] + " ");
    }
    System.out.println(":= " + CPT.getDataItem(i));
}
    }
}

Compile code with javac:
javac -classpath <path to hapiXX.jar> -d <dir to place compiled class files> <path to source files *.java>

And run with java:
java -classpath <path to hapiXX.jar>;<dir with compiled class files> -Djava.library.path=<path to dir with hapiXX.dll> EMLearning (arguments)

(where (arguments) are the netfile to load and the datafile to use for EM-learning, e.g. asia.dat datafile.dat)

For more specific details of the EM-learning functionally in Hugin check out the API-Manual section 11.6 Learning conditional probability tables.

For details on compiling with the Hugin Java API (and APIs for other languages) refer to the API-manual section 1.3 Using the HUGIN API on Windows platforms.
« Last Edit: January 04, 2008, 14:16:55 by Martin Karlsen »
Hugin Expert A/S

Offline kari

  • Newbie
  • *
  • Posts: 5
    • View Profile
Re: How to pass .dat file using JAVA HUgin API for EM learning.
« Reply #2 on: August 20, 2009, 15:04:48 »
Hi,
I tried to compile this with the instructions given but got three errors:

kari@kant:~$ javac -classpath /usr/local/hugin/lib64/hapi71-64.jar -d EMclassfiles EMlearning.java
EMlearning.java:29: possible loss of precision
found   : long
required: int
          int size = experience.getSize();
                                       ^
EMlearning.java:67: possible loss of precision
found   : long
required: int
   int tableSize = CPT.getSize();
                              ^
EMlearning.java:69: getConfiguration(long[],long) in COM.hugin.HAPI.Table cannot be applied to (int[],int)
       CPT.getConfiguration(configuration, i);
          ^
3 errors

Any suggestions how to get rid of them? I am running Hugin Developer 7.1

Offline Anders L Madsen

  • HUGIN Expert
  • Hero Member
  • *****
  • Posts: 2295
    • View Profile
Re: How to pass .dat file using JAVA HUgin API for EM learning.
« Reply #3 on: August 21, 2009, 04:16:53 »
Hi Kari,

You are trying to compile the example with the 64-bit version of the HUGIN Java API. To compile the example successfully you can either 1) use the 32-bit version of the HUGIN Java API or 2) change int to long in the following declarations
Code: [Select]
int size = experience.getSize();
Code: [Select]
int[] configuration = new int[nodes.size()];
Code: [Select]
int tableSize = CPT.getSize();
Code: [Select]
int i = 0;
HUGIN EXPERT A/S

Offline Lyceum

  • Newbie
  • *
  • Posts: 1
    • View Profile
Re: How to pass .dat file using JAVA HUgin API for EM learning.
« Reply #4 on: June 09, 2011, 05:00:45 »
Hi martin,

      do we parseCases before domain compile or after domain compile? based on your description parseCases should be called before compiling the domain, but the coding seem to be another way round.


     thanks :)

     In edit mode, there is a EM Learning Wizard button which allow me to select .dat file , set iteration and tolerance.
     In run mode, i will need to load the Data via "File->Load Case".

     so the domain.parseCases actually simulate the Load case in run mode? or the EM Learning in edit mode?

From
Thomas

Offline Martin

  • HUGIN Expert
  • Hero Member
  • *****
  • Posts: 613
    • View Profile
Re: How to pass .dat file using JAVA HUgin API for EM learning.
« Reply #5 on: June 09, 2011, 16:14:32 »
The order of Domain.parseCases and Domain.compile does not matter.

When a set of cases has been loaded with Domain.parseCases the entire set can be used for doing EM Domain.learnTables(), and/or a single case can be entered as evidence in a compiled domain using Domain.enterCase(casenum).
Hugin Expert A/S