de.lmu.ifi.dbs.elki.algorithm.clustering.correlation
Class ERiC<V extends NumberVector<V,?>>

java.lang.Object
  de.lmu.ifi.dbs.elki.logging.AbstractLoggable
      de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm<V,Clustering<CorrelationModel<V>>>
          de.lmu.ifi.dbs.elki.algorithm.clustering.correlation.ERiC<V>

Type Parameters:

V - the type of NumberVector handled by this Algorithm

All Implemented Interfaces:

Algorithm<V,Clustering<CorrelationModel<V>>>, ClusteringAlgorithm<Clustering<CorrelationModel<V>>,V>, Parameterizable

@Title(value="ERiC: Exploring Relationships among Correlation Clusters")
@Description(value="Performs the DBSCAN algorithm on the data using a special distance function taking into account correlations among attributes and builds a hierarchy that allows multiple inheritance from the correlation clustering result.")
@Reference(authors="E. Achtert, C. B\u00f6hm, H.-P. Kriegel, P. Kr\u00f6ger, and A. Zimek",
           title="On Exploring Complex Relationships of Correlation Clusters",
           booktitle="Proc. 19th International Conference on Scientific and Statistical Database Management (SSDBM 2007), Banff, Canada, 2007",
           url="http://dx.doi.org/10.1109/SSDBM.2007.21")
public class ERiC<V extends NumberVector<V,?>>
extends AbstractAlgorithm<V,Clustering<CorrelationModel<V>>>
implements ClusteringAlgorithm<Clustering<CorrelationModel<V>>,V>

Performs correlation clustering on the data partitioned according to local correlation dimensionality and builds a hierarchy of correlation clusters that allows multiple inheritance from the clustering result.

Reference: E. Achtert, C. Böhm, H.-P. Kriegel, P. Kröger, and A. Zimek: On Exploring Complex Relationships of Correlation Clusters.
In Proc. 19th International Conference on Scientific and Statistical Database Management (SSDBM 2007), Banff, Canada, 2007.

Author:

Elke Achtert

Field Summary

private COPAC<V>

copacAlgorithm The COPAC clustering algorithm.

Fields inherited from class de.lmu.ifi.dbs.elki.logging.AbstractLoggable

debug, logger

Constructor Summary

ERiC(Parameterization config)
Performs the COPAC algorithm on the data and builds a hierarchy of correlation clusters that allows multiple inheritance from the clustering result.

Method Summary

private void	buildHierarchy(SortedMap<Integer,List<Cluster<CorrelationModel<V>>>> clusterMap)
private SortedMap<Integer,List<Cluster<CorrelationModel<V>>>>	extractCorrelationClusters(Clustering<Model> copacResult, Database<V> database, int dimensionality) Extracts the correlation clusters and noise from the copac result and returns a mapping of correlation dimension to maps of clusters within this correlation dimension.
private boolean	isParent(ERiCDistanceFunction<V,?> distanceFunction, Cluster<CorrelationModel<V>> parent, List<Cluster<CorrelationModel<V>>> children) Returns true, if the specified parent cluster is a parent of one child of the children clusters.
private ListParameterization	pcaParameters(int correlationDimension) Returns the parameters for the PCA for the specified correlation dimension.
protected Clustering<CorrelationModel<V>>	runInTime(Database<V> database) Performs the ERiC algorithm on the given database.

Methods inherited from class de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm

isTime, isVerbose, run, setTime, setVerbose

Methods inherited from class de.lmu.ifi.dbs.elki.logging.AbstractLoggable

debugFine, debugFiner, debugFinest, exception, progress, verbose, warning

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.lmu.ifi.dbs.elki.algorithm.clustering.ClusteringAlgorithm

run

Methods inherited from interface de.lmu.ifi.dbs.elki.algorithm.Algorithm

setTime, setVerbose

Field Detail

copacAlgorithm

private COPAC<V extends NumberVector<V,?>> copacAlgorithm

The COPAC clustering algorithm.

Constructor Detail

ERiC

public ERiC(Parameterization config)

Performs the COPAC algorithm on the data and builds a hierarchy of correlation clusters that allows multiple inheritance from the clustering result. Constructor, adhering to Parameterizable

Parameters:

config - Parameterization

Method Detail

runInTime

protected Clustering<CorrelationModel<V>> runInTime(Database<V> database)
                                                                       throws IllegalStateException

Performs the ERiC algorithm on the given database.

Specified by:

runInTime in class AbstractAlgorithm<V extends NumberVector<V,?>,Clustering<CorrelationModel<V extends NumberVector<V,?>>>>

Parameters:

database - the database to run the algorithm on

Returns:

the Result computed by this algorithm

Throws:

IllegalStateException - if the algorithm has not been initialized properly (e.g. the setParameters(String[]) method has been failed to be called).

extractCorrelationClusters

private SortedMap<Integer,List<Cluster<CorrelationModel<V>>>> extractCorrelationClusters(Clustering<Model> copacResult,
                                                                                         Database<V> database,
                                                                                         int dimensionality)

Extracts the correlation clusters and noise from the copac result and returns a mapping of correlation dimension to maps of clusters within this correlation dimension. Each cluster is defined by the basis vectors defining the subspace in which the cluster appears.

Parameters:

copacResult -

database - the database containing the objects

dimensionality - the dimensionality of the feature space

Returns:

a mapping of correlation dimension to maps of clusters

pcaParameters

private ListParameterization pcaParameters(int correlationDimension)

Returns the parameters for the PCA for the specified correlation dimension.

Parameters:

correlationDimension - the correlation dimension

Returns:

the parameters for the PCA for the specified correlation dimension

buildHierarchy

private void buildHierarchy(SortedMap<Integer,List<Cluster<CorrelationModel<V>>>> clusterMap)
                     throws IllegalStateException

Throws:

IllegalStateException

isParent

private boolean isParent(ERiCDistanceFunction<V,?> distanceFunction,
                         Cluster<CorrelationModel<V>> parent,
                         List<Cluster<CorrelationModel<V>>> children)

Returns true, if the specified parent cluster is a parent of one child of the children clusters.

Parameters:

distanceFunction - the distance function for distance computation between the clusters

parent - the parent to be tested

children - the list of children to be tested

Returns:

true, if the specified parent cluster is a parent of one child of the children clusters, false otherwise