de.lmu.ifi.dbs.elki.algorithm.clustering.optics

Class GeneralizedOPTICS<O,E extends ClusterOrderEntry<E>>

java.lang.Object

de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm<ClusterOrderResult<E>>

de.lmu.ifi.dbs.elki.algorithm.clustering.optics.GeneralizedOPTICS<O,E>

Type Parameters:

O - the type of DatabaseObjects handled by the algorithm

E - the type of entries in the cluster order

All Implemented Interfaces:

Algorithm, OPTICSTypeAlgorithm<E>

Direct Known Subclasses:

DiSH.DiSHOPTICS, HiCO, HiSC

public abstract class GeneralizedOPTICS<O,E extends ClusterOrderEntry<E>>
extends AbstractAlgorithm<ClusterOrderResult<E>>
implements OPTICSTypeAlgorithm<E>

A trivial generalization of OPTICS that is not restricted to numerical distances, and serves as a base for several other algorithms (HiCO, HiSC).

Author:

Erich Schubert

Field Summary

Fields

Modifier and Type	Field and Description
private int	minpts Density threshold in number of points.
static OptionID	MINPTS_ID Parameter to specify the threshold for minimum number of points in the epsilon-neighborhood of a point, must be an integer greater than 0.
private ModifiableDBIDs	processedIDs Holds a set of processed ids.

Constructor Summary

Constructors

Constructor and Description
GeneralizedOPTICS(int minpts) Constructor.

Method Summary

Modifier and Type	Method and Description
protected void	expandClusterOrder(ClusterOrderResult<E> clusterOrder, Relation<O> relation, DBID objectID, FiniteProgress progress) OPTICS-function expandClusterOrder.
int	getMinPts() Get the minpts value used.
protected abstract Collection<E>	getNeighborsForDBID(Relation<O> relation, DBID id) Compute the neighbors for the given DBID.
protected abstract E	makeSeedEntry(Relation<O> relation, DBID objectID) Create the initial element to seed the algorithm.
ClusterOrderResult<E>	run(Relation<O> relation) Run OPTICS on the database.

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

getInputTypeRestriction, getLogger, makeParameterDistanceFunction, run

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.optics.OPTICSTypeAlgorithm

getEntryType, run

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

getInputTypeRestriction

Field Detail

MINPTS_ID

public static final OptionID MINPTS_ID

Parameter to specify the threshold for minimum number of points in the epsilon-neighborhood of a point, must be an integer greater than 0.

minpts

private int minpts

Density threshold in number of points.

processedIDs

private ModifiableDBIDs processedIDs

Holds a set of processed ids.

Constructor Detail

GeneralizedOPTICS

public GeneralizedOPTICS(int minpts)

Constructor.

Parameters:

minpts - Minpts value

Method Detail

run

public ClusterOrderResult<E> run(Relation<O> relation)

Run OPTICS on the database.

Parameters:

relation - Relation

Returns:

Result

expandClusterOrder

protected void expandClusterOrder(ClusterOrderResult<E> clusterOrder,
                                  Relation<O> relation,
                                  DBID objectID,
                                  FiniteProgress progress)

OPTICS-function expandClusterOrder.

Parameters:

clusterOrder - Cluster order result to expand

relation - the data relation to run on

objectID - the currently processed object

progress - the progress object to actualize the current progress if the algorithm

makeSeedEntry

protected abstract E makeSeedEntry(Relation<O> relation,
                                   DBID objectID)

Create the initial element to seed the algorithm.

Parameters:

relation - Data relation

objectID - Object ID

Returns:

Seed element.

getNeighborsForDBID

protected abstract Collection<E> getNeighborsForDBID(Relation<O> relation,
                                                     DBID id)

Compute the neighbors for the given DBID.

Parameters:

relation - Data relation

id - Current object ID

Returns:

Neighbors

getMinPts

public int getMinPts()

Description copied from interface: OPTICSTypeAlgorithm

Get the minpts value used. Needed for OPTICS Xi etc.

Specified by:

getMinPts in interface OPTICSTypeAlgorithm<E extends ClusterOrderEntry<E>>

Returns:

minpts value