dragon.ir.clustering

Class BisectKMean

java.lang.Object

dragon.ir.clustering.AbstractClustering

dragon.ir.clustering.BisectKMean

All Implemented Interfaces:

Clustering

public class BisectKMean
extends AbstractClustering

BisectKMean clustering

Copyright: Copyright (c) 2005

Company: IST, Drexel University

Version:

1.0

Author:

Davis Zhou

Field Summary

Fields

Modifier and Type	Field and Description
protected DocClusterSet	clusterSet
protected ClusterModel	distMetric
protected int	maxIteration
protected boolean	refine

Fields inherited from class dragon.ir.clustering.AbstractClustering

clusterNum, featureFilter, indexReader, randomSeed, showProgress

Constructor Summary

Constructors

Constructor and Description
BisectKMean(IndexReader indexReader, ClusterModel distMetric, int clusterNum)
BisectKMean(IndexReader indexReader, ClusterModel distMetric, int clusterNum, boolean initAllObjs)

Method Summary

Modifier and Type	Method and Description
boolean	cluster(IRDoc[] arrDoc) Cluster given testing documents to the given number of clusters
DocClusterSet	getClusterSet() One should call the cluster method before calling this method.
int	getMaxIteration()
boolean	getUseAllObjectForInitialization()
void	setMaxIteration(int iteration)
void	setRefine(boolean refine)
void	setUseAllObjectForInitialization(boolean option) If this option is true, the algorithm randomly assign all objects to the given number of clusters during initialization.

Methods inherited from class dragon.ir.clustering.AbstractClustering

cluster, getCluster, getClusterNum, getFeatureFilter, getIndexReader, getRandomSeed, setFeatureFilter, setRandomSeed, setShowProgress

Methods inherited from class java.lang.Object

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

Field Detail

distMetric

protected ClusterModel distMetric

refine

protected boolean refine

maxIteration

protected int maxIteration

clusterSet

protected DocClusterSet clusterSet

Constructor Detail

BisectKMean

public BisectKMean(IndexReader indexReader,
                   ClusterModel distMetric,
                   int clusterNum)

BisectKMean

public BisectKMean(IndexReader indexReader,
                   ClusterModel distMetric,
                   int clusterNum,
                   boolean initAllObjs)

Method Detail

setUseAllObjectForInitialization

public void setUseAllObjectForInitialization(boolean option)

If this option is true, the algorithm randomly assign all objects to the given number of clusters during initialization. Otherwise, it picks only one object for each cluster during initialization.

Parameters:

option - whether use all objects for initialization

getUseAllObjectForInitialization

public boolean getUseAllObjectForInitialization()

cluster

public boolean cluster(IRDoc[] arrDoc)

Description copied from interface: Clustering

Cluster given testing documents to the given number of clusters

Parameters:

arrDoc - the document set for clustering

Returns:

true if clustering successfully

setRefine

public void setRefine(boolean refine)

getMaxIteration

public int getMaxIteration()

setMaxIteration

public void setMaxIteration(int iteration)

getClusterSet

public DocClusterSet getClusterSet()

Description copied from interface: Clustering

One should call the cluster method before calling this method.

Specified by:

getClusterSet in interface Clustering

Overrides:

getClusterSet in class AbstractClustering

Returns:

all clusters