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

Class AbstractProjectedDBSCAN<R extends Clustering<Model>,V extends NumberVector<?>>

java.lang.Object

de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm<R>

de.lmu.ifi.dbs.elki.algorithm.clustering.AbstractProjectedDBSCAN<R,V>

Type Parameters:

V - the type of NumberVector handled by this Algorithm

All Implemented Interfaces:

Algorithm, ClusteringAlgorithm<R>, Parameterizable

Direct Known Subclasses:

FourC, PreDeCon

public abstract class AbstractProjectedDBSCAN<R extends Clustering<Model>,V extends NumberVector<?>>
extends AbstractAlgorithm<R>
implements ClusteringAlgorithm<R>

Provides an abstract algorithm requiring a VarianceAnalysisPreprocessor.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	AbstractProjectedDBSCAN.Parameterizer<V extends NumberVector<?>,D extends Distance<D>> Parameterization class.

Field Summary

Fields

Modifier and Type	Field and Description
private LocallyWeightedDistanceFunction<V>	distanceFunction Holds the instance of the distance function specified by INNER_DISTANCE_FUNCTION_ID.
protected DoubleDistance	epsilon Holds the value of EPSILON_ID.
static OptionID	EPSILON_ID Parameter to specify the maximum radius of the neighborhood to be considered, must be suitable to LocallyWeightedDistanceFunction.
static OptionID	INNER_DISTANCE_FUNCTION_ID Parameter distance function
private int	lambda Holds the value of LAMBDA_ID.
static OptionID	LAMBDA_ID Parameter to specify the intrinsic dimensionality of the clusters to find, must be an integer greater than 0.
protected int	minpts Holds the value of MINPTS_ID.
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	noise Holds a set of noise.
static OptionID	OUTER_DISTANCE_FUNCTION_ID Parameter to specify the distance function to determine the distance between database objects, must extend LocallyWeightedDistanceFunction .
private ModifiableDBIDs	processedIDs Holds a set of processed ids.
private List<ModifiableDBIDs>	resultList Holds a list of clusters found.

Constructor Summary

Constructors

Constructor and Description
AbstractProjectedDBSCAN(DoubleDistance epsilon, int minpts, LocallyWeightedDistanceFunction<V> distanceFunction, int lambda) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
protected void	expandCluster(LocallyWeightedDistanceFunction.Instance<V> distFunc, RangeQuery<V,DoubleDistance> rangeQuery, DBID startObjectID, FiniteProgress objprog, IndefiniteProgress clusprog) ExpandCluster function of DBSCAN.
TypeInformation[]	getInputTypeRestriction() Get the input type restriction used for negotiating the data query.
abstract String	getLongResultName() Return the long result name.
abstract String	getShortResultName() Return the short result name.
Clustering<Model>	run(Database database, Relation<V> relation) Run the algorithm

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

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.ClusteringAlgorithm

run

Field Detail

OUTER_DISTANCE_FUNCTION_ID

public static final OptionID OUTER_DISTANCE_FUNCTION_ID

Parameter to specify the distance function to determine the distance between database objects, must extend LocallyWeightedDistanceFunction .

Key: -projdbscan.distancefunction

Default value: LocallyWeightedDistanceFunction

INNER_DISTANCE_FUNCTION_ID

public static final OptionID INNER_DISTANCE_FUNCTION_ID

Parameter distance function

EPSILON_ID

public static final OptionID EPSILON_ID

Parameter to specify the maximum radius of the neighborhood to be considered, must be suitable to LocallyWeightedDistanceFunction.

Key: -projdbscan.epsilon

LAMBDA_ID

public static final OptionID LAMBDA_ID

Parameter to specify the intrinsic dimensionality of the clusters to find, must be an integer greater than 0.

Key: -projdbscan.lambda

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.

Key: -projdbscan.minpts

distanceFunction

private LocallyWeightedDistanceFunction<V extends NumberVector<?>> distanceFunction

Holds the instance of the distance function specified by INNER_DISTANCE_FUNCTION_ID.

epsilon

protected DoubleDistance epsilon

Holds the value of EPSILON_ID.

lambda

private int lambda

Holds the value of LAMBDA_ID.

minpts

protected int minpts

Holds the value of MINPTS_ID.

resultList

private List<ModifiableDBIDs> resultList

Holds a list of clusters found.

noise

private ModifiableDBIDs noise

Holds a set of noise.

processedIDs

private ModifiableDBIDs processedIDs

Holds a set of processed ids.

Constructor Detail

AbstractProjectedDBSCAN

public AbstractProjectedDBSCAN(DoubleDistance epsilon,
                       int minpts,
                       LocallyWeightedDistanceFunction<V> distanceFunction,
                       int lambda)

Constructor.

Parameters:

epsilon - Epsilon

minpts - MinPts parameter

distanceFunction - Outer distance function

lambda - Lambda value

Method Detail

run

public Clustering<Model> run(Database database,
                    Relation<V> relation)

Run the algorithm

Parameters:

database - Database to process

relation - Relation to process

Returns:

Clustering result

getLongResultName

public abstract String getLongResultName()

Return the long result name.

Returns:

Long name for result

getShortResultName

public abstract String getShortResultName()

Return the short result name.

Returns:

Short name for result

expandCluster

protected void expandCluster(LocallyWeightedDistanceFunction.Instance<V> distFunc,
                 RangeQuery<V,DoubleDistance> rangeQuery,
                 DBID startObjectID,
                 FiniteProgress objprog,
                 IndefiniteProgress clusprog)

ExpandCluster function of DBSCAN.

Parameters:

distFunc - Distance query to use

rangeQuery - Range query

startObjectID - the object id of the database object to start the expansion with

objprog - the progress object for logging the current status

getInputTypeRestriction

public TypeInformation[] getInputTypeRestriction()

Description copied from class: AbstractAlgorithm

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

Specified by:

getInputTypeRestriction in interface Algorithm

Specified by:

getInputTypeRestriction in class AbstractAlgorithm<R extends Clustering<Model>>

Returns:

Type restriction