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

Class FDBSCANNeighborPredicate.Instance

java.lang.Object

de.lmu.ifi.dbs.elki.algorithm.clustering.uncertain.FDBSCANNeighborPredicate.Instance

All Implemented Interfaces:

NeighborPredicate.Instance<DBIDs>

Enclosing class:

FDBSCANNeighborPredicate

public static class FDBSCANNeighborPredicate.Instance
extends java.lang.Object
implements NeighborPredicate.Instance<DBIDs>

Instance of the neighbor predicate.

Author:

Alexander Koos, Erich Schubert

Field Summary

Fields

Modifier and Type	Field and Description
private double	epsilon The epsilon distance a neighbor may have at most.
private double	epsilonsq The epsilon distance a neighbor may have at most.
private java.util.Random	rand The random generator to draw the samples with.
private Relation<? extends UncertainObject>	relation The relation holding the uncertain objects.
private int	sampleSize The size of samplesets that should be drawn for neighborcheck.
private double	threshold The relative amount of epsilon-close pairings determined by the neighborcheck.

Constructor Summary

Constructors

Constructor and Description
Instance(double epsilon, int sampleSize, double threshold, Relation<? extends UncertainObject> relation, RandomFactory rand) Constructor.

Method Summary

Modifier and Type	Method and Description
private boolean	checkSamples(UncertainObject o1, UncertainObject o2)
DBIDs	getIDs() Get the IDs the predicate is defined for.
DBIDs	getNeighbors(DBIDRef reference) Get the neighbors of a reference object for DBSCAN.
DBIDIter	iterDBIDs(DBIDs neighbors) Add the neighbors to a DBID set

Methods inherited from class java.lang.Object

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

Field Detail

epsilon

private double epsilon

The epsilon distance a neighbor may have at most.

epsilonsq

private double epsilonsq

The epsilon distance a neighbor may have at most.

sampleSize

private int sampleSize

The size of samplesets that should be drawn for neighborcheck.

threshold

private double threshold

The relative amount of epsilon-close pairings determined by the neighborcheck.

relation

private Relation<? extends UncertainObject> relation

The relation holding the uncertain objects.

rand

private java.util.Random rand

The random generator to draw the samples with.

Constructor Detail

Instance

public Instance(double epsilon,
                int sampleSize,
                double threshold,
                Relation<? extends UncertainObject> relation,
                RandomFactory rand)

Constructor.

Parameters:

epsilon - Maximum distance

sampleSize - Sampling size

threshold - Threshold on how many samples are within the radius

relation - Data relation

rand - Random generator for sampling

Method Detail

getNeighbors

public DBIDs getNeighbors(DBIDRef reference)

Description copied from interface: NeighborPredicate.Instance

Get the neighbors of a reference object for DBSCAN.

Specified by:

getNeighbors in interface NeighborPredicate.Instance<DBIDs>

Parameters:

reference - Reference object

Returns:

Neighborhood

checkSamples

private boolean checkSamples(UncertainObject o1,
                             UncertainObject o2)

getIDs

public DBIDs getIDs()

Description copied from interface: NeighborPredicate.Instance

Get the IDs the predicate is defined for.

Specified by:

getIDs in interface NeighborPredicate.Instance<DBIDs>

Returns:

Database ids

iterDBIDs

public DBIDIter iterDBIDs(DBIDs neighbors)

Description copied from interface: NeighborPredicate.Instance

Add the neighbors to a DBID set

Specified by:

iterDBIDs in interface NeighborPredicate.Instance<DBIDs>

Parameters:

neighbors - Neighbors to iterate over

Returns:

iterator