relational.classifier
Class ProbRNClassifier

java.lang.Object
  extended byweka.classifiers.Classifier
      extended byrelational.classifier.ProbRNClassifier
All Implemented Interfaces:
java.lang.Cloneable, weka.core.OptionHandler, java.io.Serializable
Direct Known Subclasses:
ProbRNMultiHop

public class ProbRNClassifier
extends weka.classifiers.Classifier

Author:
Christine Preisach Class contains the classifier PRN* und PRN* Geometric Mean (binary calssification)
See Also:
Serialized Form

Field Summary
 java.util.HashMap labels
           
 double maxProb
           
 int numClasses
           
 double[] priors
           
 
Constructor Summary
ProbRNClassifier(java.util.HashMap labels)
           
 
Method Summary
 void buildClassifier(weka.core.Instances instances)
           
 int classifyInstance(weka.core.Instance instance, double[] estimation)
          Classifies an instance according to the class probability distribution
 double[] distributionForInstance(edu.uci.ics.jung.graph.impl.SparseGraph graph, weka.core.Instance inst, java.util.HashMap id2ClassProb, java.util.HashMap weights, java.lang.String type)
          Calculates the class membership probability using Probabilistic Relational Classifier
 double[] distributionForInstanceGeometricMean(edu.uci.ics.jung.graph.impl.SparseGraph graph, weka.core.Instance inst, java.util.HashMap id2ClassProb, java.util.HashMap weights, java.lang.String type)
          Calculates the class membership probability using PRNGeometricMean
 
Methods inherited from class weka.classifiers.Classifier
classifyInstance, debugTipText, distributionForInstance, forName, getDebug, getOptions, listOptions, makeCopies, makeCopy, setDebug, setOptions
 
Methods inherited from class java.lang.Object
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

labels

public java.util.HashMap labels

priors

public double[] priors

maxProb

public double maxProb

numClasses

public int numClasses
Constructor Detail

ProbRNClassifier

public ProbRNClassifier(java.util.HashMap labels)
Method Detail

buildClassifier

public void buildClassifier(weka.core.Instances instances)
                     throws java.lang.Exception
Throws:
java.lang.Exception

distributionForInstance

public double[] distributionForInstance(edu.uci.ics.jung.graph.impl.SparseGraph graph,
                                        weka.core.Instance inst,
                                        java.util.HashMap id2ClassProb,
                                        java.util.HashMap weights,
                                        java.lang.String type)
                                 throws java.lang.Exception
Calculates the class membership probability using Probabilistic Relational Classifier

Parameters:
graph - - graph (jung)
inst - - instance to be classified
id2ClassProb - - initialization of test instances
weights - - weights of the edges
Returns:
class probability distribution
Throws:
java.lang.Exception

distributionForInstanceGeometricMean

public double[] distributionForInstanceGeometricMean(edu.uci.ics.jung.graph.impl.SparseGraph graph,
                                                     weka.core.Instance inst,
                                                     java.util.HashMap id2ClassProb,
                                                     java.util.HashMap weights,
                                                     java.lang.String type)
                                              throws java.lang.Exception
Calculates the class membership probability using PRNGeometricMean

Parameters:
graph - - graph (jung)
inst - - instance to be classified
id2ClassProb - - initialization of test instances
weights - - weights of the edges
Returns:
class probability distribution
Throws:
java.lang.Exception

classifyInstance

public int classifyInstance(weka.core.Instance instance,
                            double[] estimation)
                     throws java.lang.Exception
Classifies an instance according to the class probability distribution

Parameters:
instance - - instance to be classified
estimation - - class probability distribution
Returns:
the estimated category
Throws:
java.lang.Exception