de.lmu.ifi.dbs.elki.algorithm.clustering
Class AbstractProjectedClustering<R extends Clustering<Model>,V extends NumberVector<V,?>>

java.lang.Object
  de.lmu.ifi.dbs.elki.algorithm.AbstractAlgorithm<R>
      de.lmu.ifi.dbs.elki.algorithm.clustering.AbstractProjectedClustering<R,V>

Type Parameters:

R - the result we return

V - the type of FeatureVector handled by this Algorithm

All Implemented Interfaces:

Algorithm, ClusteringAlgorithm<R>, InspectionUtilFrequentlyScanned, Parameterizable

Direct Known Subclasses:

ORCLUS, PROCLUS

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

Abstract superclass for projected clustering algorithms, like PROCLUS and ORCLUS.

Nested Class Summary

static class

AbstractProjectedClustering.Parameterizer Parameterization class.

Field Summary

private DistanceFunction<? super V,DoubleDistance>	distanceFunction The euclidean distance function.
protected int	k Holds the value of K_ID.
protected int	k_i Holds the value of K_I_ID.
static OptionID	K_I_ID Parameter to specify the multiplier for the initial number of seeds, must be an integer greater than 0.
static OptionID	K_ID Parameter to specify the number of clusters to find, must be an integer greater than 0.
protected int	l Holds the value of L_ID.
static OptionID	L_ID Parameter to specify the dimensionality of the clusters to find, must be an integer greater than 0.

Constructor Summary

AbstractProjectedClustering(int k, int k_i, int l)
Internal constructor.

Method Summary

protected DistanceFunction<? super V,DoubleDistance>	getDistanceFunction() Returns the distance function.
protected DistanceQuery<V,DoubleDistance>	getDistanceQuery(Database database) Returns the distance function.

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.ClusteringAlgorithm

run

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

getInputTypeRestriction

Field Detail

K_ID

public static final OptionID K_ID

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

Key: -projectedclustering.k

K_I_ID

public static final OptionID K_I_ID

Parameter to specify the multiplier for the initial number of seeds, must be an integer greater than 0.

Default value: 30

Key: -projectedclustering.k_i

L_ID

public static final OptionID L_ID

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

Key: -projectedclustering.l

k

protected int k

Holds the value of K_ID.

k_i

protected int k_i

Holds the value of K_I_ID.

l

protected int l

Holds the value of L_ID.

distanceFunction

private DistanceFunction<? super V extends NumberVector<V,?>,DoubleDistance> distanceFunction

The euclidean distance function.

Constructor Detail

AbstractProjectedClustering

public AbstractProjectedClustering(int k,
                                   int k_i,
                                   int l)

Internal constructor.

Parameters:

k - K parameter

k_i - K_i parameter

l - L parameter

Method Detail

getDistanceFunction

protected DistanceFunction<? super V,DoubleDistance> getDistanceFunction()

Returns the distance function.

Returns:

the distance function

getDistanceQuery

protected DistanceQuery<V,DoubleDistance> getDistanceQuery(Database database)

Returns the distance function.

Returns:

the distance function