|
|||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Objectrelational.classifier.Iterative
Class contains Collective Inference methods
Field Summary | |
java.util.Hashtable |
classified
|
Constructor Summary | |
Iterative()
|
Method Summary | |
void |
relaxationLabeling(weka.classifiers.Classifier prncl,
weka.core.Instances test,
java.util.HashMap id2ClassProb,
edu.uci.ics.jung.graph.impl.SparseGraph graph,
int maxiterations,
java.util.HashMap weightsMap,
java.util.HashMap probabilities,
java.lang.String type)
Iterative method for Relational Neighbor Classifier, it uses a heterogenous, directed, weighted, bipartite graph Only the first classe of an instance is considered |
void |
relaxationLabeling(relational.classifier.ProbRN2Hop prncl,
weka.core.Instances test,
java.util.HashMap id2ClassProb,
edu.uci.ics.jung.graph.impl.SparseGraph graph,
int maxiterations,
int numNeighbors,
java.util.HashMap weightsMap,
java.util.HashMap probabilities,
java.lang.String type)
Iterative Method for PRN2Hop, uses a bipartite graph Only the first class of an instance is considered |
void |
relaxationLabeling(ProbRNMultiHop prncl,
weka.core.Instances test,
java.util.HashMap id2ClassProb,
edu.uci.ics.jung.graph.impl.SparseGraph graph,
int maxiterations,
double minWeight,
java.util.HashMap weightsMap,
java.util.HashMap normWeights,
java.util.HashMap probabilities,
java.lang.String type,
int numNeighbors,
int hops)
Iterative method for PRNMultiHop, uses a bipartite graph. |
void |
relaxationLabelingMultiLabel(ProbRNMultiHopMultiLabel prncl,
weka.core.Instances test,
java.util.HashMap id2ClassProb,
edu.uci.ics.jung.graph.impl.SparseGraph graph,
int label,
java.util.HashMap expert,
java.util.HashMap result,
double th,
double minWeight,
int maxIterations,
java.util.HashMap probabilities,
int numNeighbors,
java.util.HashMap weights,
java.util.HashMap normWeights,
java.lang.String type,
int hops)
Iterative method for PRNMultiHop All categories of an instance are considered (binary classification) |
void |
relaxationLabelingMultiLabel(relational.classifier.ProbRNMultiLabel2Hop prncl,
weka.core.Instances test,
java.util.HashMap id2ClassProb,
edu.uci.ics.jung.graph.impl.SparseGraph graph,
int label,
java.util.HashMap expert,
java.util.HashMap result,
double th,
int maxIterations,
java.util.HashMap probabilities,
int numNeighbors,
java.util.HashMap weights,
java.lang.String type)
Iterative method for PRN2Hop. |
void |
relaxationLabelingMultiLabel(ProbRNMultiLabel prncl,
weka.core.Instances test,
java.util.HashMap id2ClassProb,
edu.uci.ics.jung.graph.impl.SparseGraph graph,
int label,
java.util.HashMap expert,
java.util.HashMap result,
java.util.HashMap weights,
double th,
int maxIterations,
java.util.HashMap probabilities,
java.lang.String type)
Iterative method for Probabilistic Relational Neighbor Classifier. |
void |
RNstar(RelationalNeighborClassifier cl,
weka.core.Instances test,
edu.uci.ics.jung.graph.impl.SparseGraph graph,
java.util.HashMap id2Label,
java.util.HashMap weights,
java.util.HashMap probabilities,
java.lang.String type)
Iterative method for Relational Neighbor Classifier, it uses a homogenous, undirected, weighted graph Only the first class of an instance is considered |
void |
RNstarMultiLabel(RNCMultiLabel cl,
weka.core.Instances test,
java.util.HashMap id2Label,
edu.uci.ics.jung.graph.impl.SparseGraph graph,
int Class,
java.util.HashMap expert,
java.util.HashMap result,
java.util.HashMap weights,
double th,
java.util.HashMap probabilities,
java.lang.String type)
Iterative method for Relational Neighbor Classifier, it uses a heterogenous, directed, weighted, bipartite graph All the classes of an instance are considered |
Methods inherited from class java.lang.Object |
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
public java.util.Hashtable classified
Constructor Detail |
public Iterative()
Method Detail |
public void RNstar(RelationalNeighborClassifier cl, weka.core.Instances test, edu.uci.ics.jung.graph.impl.SparseGraph graph, java.util.HashMap id2Label, java.util.HashMap weights, java.util.HashMap probabilities, java.lang.String type) throws java.lang.Exception
cl
- - classifier in inner looptest
- - test insatancesgraph
- - graph (jung)id2Label
- - initialization of test instancesweights
- - the weights of the edges in the graphprobabilities
- - resulting probabilities for each class and test instancetype
- - indicates the type of problem (heterogenous or homogenous)
java.lang.Exception
public void RNstarMultiLabel(RNCMultiLabel cl, weka.core.Instances test, java.util.HashMap id2Label, edu.uci.ics.jung.graph.impl.SparseGraph graph, int Class, java.util.HashMap expert, java.util.HashMap result, java.util.HashMap weights, double th, java.util.HashMap probabilities, java.lang.String type) throws java.lang.Exception
cl
- - classifier in inner looptest
- - test insatancesgraph
- - graph (jung)Class
- - the category to be considered in binary classificationid2Label
- - initialization of test instancesweights
- - the weights of the edges in the graphth
- - thresholdprobabilities
- - resulting probabilities for each class and test instancetype
- - indicates the type of problem (heterogenous or homogenous)
java.lang.Exception
public void relaxationLabeling(weka.classifiers.Classifier prncl, weka.core.Instances test, java.util.HashMap id2ClassProb, edu.uci.ics.jung.graph.impl.SparseGraph graph, int maxiterations, java.util.HashMap weightsMap, java.util.HashMap probabilities, java.lang.String type) throws java.lang.Exception
prncl
- - classifier in inner looptest
- - test insatancesid2ClassProb
- - initialization of test instancesgraph
- - graph (jung)maxiterations
- - the maximal number of iterations to be performedweightsMap
- - the weights of the edges in the graphprobabilities
- - resulting probabilities for each class and test instancetype
- - indicates the type of problem (heterogenous or homogenous)
java.lang.Exception
public void relaxationLabeling(relational.classifier.ProbRN2Hop prncl, weka.core.Instances test, java.util.HashMap id2ClassProb, edu.uci.ics.jung.graph.impl.SparseGraph graph, int maxiterations, int numNeighbors, java.util.HashMap weightsMap, java.util.HashMap probabilities, java.lang.String type) throws java.lang.Exception
prncl
- - classifier in inner looptest
- - test insatancesid2ClassProb
- - initialization of test instancesgraph
- - graph (jung)maxiterations
- - the maximal number of iterations to be performednumNeighbors
- - determines the number of neighbors for which additional indirect neighbors will be considered using PRN2HopweightsMap
- - the weights of the edges in the graphprobabilities
- - resulting probabilities for each class and test instancetype
- - indicates the type of problem (heterogenous or homogenous)
java.lang.Exception
public void relaxationLabeling(ProbRNMultiHop prncl, weka.core.Instances test, java.util.HashMap id2ClassProb, edu.uci.ics.jung.graph.impl.SparseGraph graph, int maxiterations, double minWeight, java.util.HashMap weightsMap, java.util.HashMap normWeights, java.util.HashMap probabilities, java.lang.String type, int numNeighbors, int hops) throws java.lang.Exception
prncl
- - Classifier in the inner looptest
- - Testsetid2ClassProb
- - initialization of test instancesgraph
- - graph (jung)maxiterations
- - the maximal number of iterations to be performedminWeight
- - the minimal weight which an edge has to have in order to be considered in PRNMultiHopweightsMap
- - the weights of the edges in the graphnormWeights
- - normalized weightsprobabilities
- - resulting probabilities for each class and test instancetype
- - indicates the type of problem (heterogenous or homogenous)numNeighbors
- - determines the number of neighbors for which additional indirect neighbors will be considered using PRNMultiHophops
- - maximal number of hops to be performed
java.lang.Exception
public void relaxationLabelingMultiLabel(relational.classifier.ProbRNMultiLabel2Hop prncl, weka.core.Instances test, java.util.HashMap id2ClassProb, edu.uci.ics.jung.graph.impl.SparseGraph graph, int label, java.util.HashMap expert, java.util.HashMap result, double th, int maxIterations, java.util.HashMap probabilities, int numNeighbors, java.util.HashMap weights, java.lang.String type) throws java.lang.Exception
prncl
- test
- id2ClassProb
- graph
- label
- expert
- result
- th
- maxIterations
- probabilities
- numNeighbors
- weights
-
java.lang.Exception
public void relaxationLabelingMultiLabel(ProbRNMultiHopMultiLabel prncl, weka.core.Instances test, java.util.HashMap id2ClassProb, edu.uci.ics.jung.graph.impl.SparseGraph graph, int label, java.util.HashMap expert, java.util.HashMap result, double th, double minWeight, int maxIterations, java.util.HashMap probabilities, int numNeighbors, java.util.HashMap weights, java.util.HashMap normWeights, java.lang.String type, int hops) throws java.lang.Exception
prncl
- - Classifier in the inner looptest
- - Testsetid2ClassProb
- - initialization of test instancesgraph
- - graph (jung)label
- - category to be consideredexpert
- - expert judgement (concerning the categories)result
- - results (categories)th
- - ThresholdmaxIterations
- - the maximal number of iterations to be performedprobabilities
- - resulting probabilities for each class and test instancenumNeighbors
- - determines the number of neighbors for which additional indirect neighbors will be considered using PRNMultiHopweights
- - the weights of the edges in the graphnormWeights
- - normalized weightstype
- - indicates the type of problem (heterogenous or homogenous)hops
- - maximal number of hops to be performed
java.lang.Exception
public void relaxationLabelingMultiLabel(ProbRNMultiLabel prncl, weka.core.Instances test, java.util.HashMap id2ClassProb, edu.uci.ics.jung.graph.impl.SparseGraph graph, int label, java.util.HashMap expert, java.util.HashMap result, java.util.HashMap weights, double th, int maxIterations, java.util.HashMap probabilities, java.lang.String type) throws java.lang.Exception
prncl
- - Classifier in the inner looptest
- - Testsetid2ClassProb
- - initialization of test instancesgraph
- - graph (jung)label
- - HashMap, containing the categoriesexpert
- - expert judgement (concerning the categories)result
- - results (categories)weights
- - the weights of the edges in the graphth
- - ThresholdmaxIterations
- - the maximal number of iterations to be performedprobabilities
- -resulting probabilities for each class and test instancetype
- -
java.lang.Exception
|
|||||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |