de.lmu.ifi.dbs.elki.algorithm.result.clustering
Interface ClusteringResult<O extends DatabaseObject>

Type Parameters:

O - the type of DatabaseObjects handled by this Result

All Superinterfaces:

Result<O>

All Known Implementing Classes:

Clusters, ClustersPlusNoise, ClustersPlusNoisePlusCorrelationAnalysis, EMClusters, PartitionClusteringResults

public interface ClusteringResult<O extends DatabaseObject>
extends Result<O>

A Result that provides a set of disjunct clusters and a mapping from classlabels (supposedly assigned by the algorithm) to databases.

Author:

Arthur Zimek

Field Summary

Fields inherited from interface de.lmu.ifi.dbs.elki.algorithm.result.Result

SEPARATOR

Method Summary

<L extends ClassLabel<L>> void	appendModel(L clusterID, Result<O> model) Appends a model the designated cluster.
<L extends ClassLabel<L>> Database<O>	associate(Class<L> classLabel) Returns a new Database containing only non-noise Objects with a clusterID associated as AssociationID#CLASS.
<L extends ClassLabel<L>> Map<L,Database<O>>	clustering(Class<L> classLabel) Returns a Map of ClassLabel to Database, comprising a separate database for each cluster.
Cluster<O>[]	getClusters() Returns the clusters as array of arrays of object ids.
Database<O>	noise() Returns a database containing only noise objects.

Methods inherited from interface de.lmu.ifi.dbs.elki.algorithm.result.Result

output, output

Method Detail

getClusters

Cluster<O>[] getClusters()

Returns the clusters as array of arrays of object ids. The array must not contain noise objects.

Returns:

the clusters as defined in this result

clustering

<L extends ClassLabel<L>> Map<L,Database<O>> clustering(Class<L> classLabel)

Returns a Map of ClassLabel to Database, comprising a separate database for each cluster. Note that if the clustering result contains noise, the noise-objects are not comprised in this map.

Parameters:

classLabel - the class to be used as ClassLabel

Returns:

Map of ClassLabel to Database, comprising a separate database for each cluster without noise.

associate

<L extends ClassLabel<L>> Database<O> associate(Class<L> classLabel)

Returns a new Database containing only non-noise Objects with a clusterID associated as AssociationID#CLASS.

Parameters:

classLabel - the class to be used as ClassLabel

Returns:

a new Database of only non-noise objects

appendModel

<L extends ClassLabel<L>> void appendModel(L clusterID,
                                           Result<O> model)

Appends a model the designated cluster.

Parameters:

clusterID - ClassLabel assigned to the cluster a model should be appended to

model - the model describing the designated cluster

noise

Database<O> noise()

Returns a database containing only noise objects.

Returns:

a database containing only noise objects