baseCode.algorithm.learning.unsupervised.cluster
Class HierarchicalClusterer

java.lang.Object
  baseCode.algorithm.Algorithm
      baseCode.algorithm.learning.unsupervised.cluster.ClusteringAlgorithm
          baseCode.algorithm.learning.unsupervised.cluster.HierarchicalClusterer

public class HierarchicalClusterer

extends ClusteringAlgorithm

Start with all items in separate clusters. Compute the distances between all clusters Find the clusters with the highest similarity. Combine them into one cluster Iterate until there is only one cluster. Output: for each cluster, print the clusters it contains.

Copyright (c) 2004 Columbia University

Version:

$Id: HierarchicalClusterer.java,v 1.6 2004/08/14 15:19:05 pavlidis Exp $

Author:

pavlidis

Field Summary

Fields inherited from class baseCode.algorithm.Algorithm

log

Constructor Summary

HierarchicalClusterer(cern.colt.list.ObjectArrayList c)

Method Summary

java.lang.Object[]	getResults()
void	run() Perform a hierarchical clustering on the objects.

Methods inherited from class java.lang.Object

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

Constructor Detail

HierarchicalClusterer

public HierarchicalClusterer(cern.colt.list.ObjectArrayList c)

Parameters:

c - Objects to be clustered. These must be Distanceable

Method Detail

run

public void run()

Perform a hierarchical clustering on the objects. Initialize: compute the distances between all objects. Find the closest pair to initialize the clustering.

See Also:

baseCode.algorithm.learning.unsupervised.cluster.Algorithm#Run()

getResults

public java.lang.Object[] getResults()

Returns: