jbnc.inducers
Class TANInducer

java.lang.Object
  jbnc.inducers.BayesianInducer
      jbnc.inducers.TANInducer

public class TANInducer

extends BayesianInducer

Constructs Tree Augmented naive-Bayes classifier (TAN).

Friedman N, Geiger D, Goldszmidt M. "Bayesian Network Classifiers". Machine Learning , vol.29, issue 2/3, November 1997, pp.131-163.

Since:

June 1, 1999

Author:

Jarek Sacha

Nested Class Summary

Nested classes inherited from class jbnc.inducers.BayesianInducer

BayesianInducer.NetLayout

Field Summary

Fields inherited from class jbnc.inducers.BayesianInducer

debugMode, DEFAULT_APLHA_IJK, layout, net, qualityMeasure

Constructor Summary

TANInducer()

Method Summary

static void	main(java.lang.String[] arg) Used for testing of the TAN algorithm.
void	train(FrequencyCalc fc, boolean usePriors, double alpha_ijk) Construct TAN network from the training data

Methods inherited from class jbnc.inducers.BayesianInducer

clean, getDebugMode, getNetwork, getQualityMeasure, reset, setDebugMode, setQualityMeasure, train, verifyDataset

Methods inherited from class java.lang.Object

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

Constructor Detail

TANInducer

public TANInducer()

Method Detail

main

public static void main(java.lang.String[] arg)

Used for testing of the TAN algorithm.

Parameters:

arg - The command line arguments

train

public void train(FrequencyCalc fc,
                  boolean usePriors,
                  double alpha_ijk)
           throws java.lang.Exception

Construct TAN network from the training data

Specified by:

train in class BayesianInducer

Parameters:

fc - Description of Parameter

usePriors - Description of Parameter

alpha_ijk - Description of Parameter

Throws:

java.lang.Exception - Description of Exception