de.lmu.ifi.dbs.elki.algorithm.clustering.hierarchical.extraction

Class ExtractFlatClusteringFromHierarchy

java.lang.Object

de.lmu.ifi.dbs.elki.algorithm.clustering.hierarchical.extraction.ExtractFlatClusteringFromHierarchy

All Implemented Interfaces:

Algorithm, ClusteringAlgorithm<Clustering<DendrogramModel>>

public class ExtractFlatClusteringFromHierarchy
extends Object
implements ClusteringAlgorithm<Clustering<DendrogramModel>>

Extract a flat clustering from a full hierarchy, represented in pointer form. FIXME: re-check tie handling! TODO: add an hierarchy simplification step.

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	ExtractFlatClusteringFromHierarchy.Parameterizer Parameterization class.
static class	ExtractFlatClusteringFromHierarchy.ThresholdMode Threshold mode.

Field Summary

Fields

Modifier and Type	Field and Description
private HierarchicalClusteringAlgorithm	algorithm Clustering algorithm to run to obtain the hierarchy.
private boolean	hierarchical Include empty clusters in the hierarchy produced.
private static Logging	LOG Class logger.
private int	minclusters Minimum number of clusters to extract
private boolean	nosingletons Merge singleton clusters into the parent cluster.
private double	threshold Threshold for extracting clusters.

Constructor Summary

Constructors

Constructor and Description
ExtractFlatClusteringFromHierarchy(HierarchicalClusteringAlgorithm algorithm, double threshold, boolean hierarchical, boolean nosingletons) Constructor.
ExtractFlatClusteringFromHierarchy(HierarchicalClusteringAlgorithm algorithm, int minclusters, boolean hierarchical, boolean nosingletons) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
Clustering<DendrogramModel>	extractClusters(DBIDs ids, DBIDDataStore pi, DoubleDataStore lambda) Extract all clusters from the pi-lambda-representation.
private int	findSplit(ArrayDBIDs order, DBIDArrayIter it, DoubleDataStore lambda) Find the splitting point in the ordered DBIDs list.
TypeInformation[]	getInputTypeRestriction() Get the input type restriction used for negotiating the data query.
private Cluster<DendrogramModel>	makeCluster(DBIDRef lead, double depth, DBIDs members) Make the cluster for the given object
Clustering<DendrogramModel>	run(Database database) Runs the algorithm.

Methods inherited from class java.lang.Object

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

Field Detail

LOG

private static final Logging LOG

Class logger.

minclusters

private final int minclusters

Minimum number of clusters to extract

threshold

private final double threshold

Threshold for extracting clusters.

hierarchical

private final boolean hierarchical

Include empty clusters in the hierarchy produced.

nosingletons

private final boolean nosingletons

Merge singleton clusters into the parent cluster.

algorithm

private final HierarchicalClusteringAlgorithm algorithm

Clustering algorithm to run to obtain the hierarchy.

Constructor Detail

ExtractFlatClusteringFromHierarchy

public ExtractFlatClusteringFromHierarchy(HierarchicalClusteringAlgorithm algorithm,
                                  int minclusters,
                                  boolean hierarchical,
                                  boolean nosingletons)

Constructor.

Parameters:

algorithm - Algorithm to run

minclusters - Minimum number of clusters

hierarchical - Produce a hierarchical output

nosingletons - Merge singletons into parent

ExtractFlatClusteringFromHierarchy

public ExtractFlatClusteringFromHierarchy(HierarchicalClusteringAlgorithm algorithm,
                                  double threshold,
                                  boolean hierarchical,
                                  boolean nosingletons)

Constructor.

Parameters:

algorithm - Algorithm to run

threshold - Distance threshold

hierarchical - Produce a hierarchical output

nosingletons - Merge singletons into parent

Method Detail

run

public Clustering<DendrogramModel> run(Database database)

Description copied from interface: Algorithm

Runs the algorithm.

Specified by:

run in interface Algorithm

Specified by:

run in interface ClusteringAlgorithm<Clustering<DendrogramModel>>

Parameters:

database - the database to run the algorithm on

Returns:

the Result computed by this algorithm

extractClusters

public Clustering<DendrogramModel> extractClusters(DBIDs ids,
                                          DBIDDataStore pi,
                                          DoubleDataStore lambda)

Extract all clusters from the pi-lambda-representation.

Parameters:

ids - Object ids to process

pi - Pi store

lambda - Lambda store

Returns:

Hierarchical clustering

findSplit

private int findSplit(ArrayDBIDs order,
            DBIDArrayIter it,
            DoubleDataStore lambda)

Find the splitting point in the ordered DBIDs list.

Parameters:

order - Ordered list

it - Iterator on this list (reused)

lambda - Join distances.

Returns:

Splitting point

makeCluster

private Cluster<DendrogramModel> makeCluster(DBIDRef lead,
                                   double depth,
                                   DBIDs members)

Make the cluster for the given object

Parameters:

lead - Leading object

depth - Linkage depth

members - Member objects

Returns:

Cluster

getInputTypeRestriction

public TypeInformation[] getInputTypeRestriction()

Description copied from interface: Algorithm

Get the input type restriction used for negotiating the data query.

Specified by:

getInputTypeRestriction in interface Algorithm

Returns:

Type restriction