de.lmu.ifi.dbs.elki.distance.distancefunction.correlation
Class ERiCDistanceFunction

java.lang.Object
  de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractDatabaseDistanceFunction<O,D>
      de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractIndexBasedDistanceFunction<NumberVector<?,?>,FilteredLocalPCAIndex<NumberVector<?,?>>,BitDistance>
          de.lmu.ifi.dbs.elki.distance.distancefunction.correlation.ERiCDistanceFunction

All Implemented Interfaces:

DistanceFunction<NumberVector<?,?>,BitDistance>, FilteredLocalPCABasedDistanceFunction<NumberVector<?,?>,FilteredLocalPCAIndex<NumberVector<?,?>>,BitDistance>, IndexBasedDistanceFunction<NumberVector<?,?>,BitDistance>, InspectionUtilFrequentlyScanned, Parameterizable

public class ERiCDistanceFunction
extends AbstractIndexBasedDistanceFunction<NumberVector<?,?>,FilteredLocalPCAIndex<NumberVector<?,?>>,BitDistance>
implements FilteredLocalPCABasedDistanceFunction<NumberVector<?,?>,FilteredLocalPCAIndex<NumberVector<?,?>>,BitDistance>

Provides a distance function for building the hierarchy in the ERiC algorithm.

Nested Class Summary

static class	ERiCDistanceFunction.Instance<V extends NumberVector<?,?>> The actual instance bound to a particular database.
static class	ERiCDistanceFunction.Parameterizer Parameterization class.

Field Summary

private double	delta Holds the value of DELTA_ID.
static OptionID	DELTA_ID Parameter to specify the threshold for approximate linear dependency: the strong eigenvectors of q are approximately linear dependent from the strong eigenvectors p if the following condition holds for all strong eigenvectors q_i of q (lambda_q < lambda_p): q_i' * M^check_p * q_i <= delta^2, must be a double equal to or greater than 0.
(package private) static Logging	logger Logger for debug.
private double	tau Holds the value of TAU_ID.
static OptionID	TAU_ID Parameter to specify the threshold for the maximum distance between two approximately linear dependent subspaces of two objects p and q (lambda_q < lambda_p) before considering them as parallel, must be a double equal to or greater than 0.

Fields inherited from class de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractIndexBasedDistanceFunction

indexFactory

Fields inherited from interface de.lmu.ifi.dbs.elki.distance.distancefunction.IndexBasedDistanceFunction

INDEX_ID

Constructor Summary

ERiCDistanceFunction(IndexFactory<NumberVector<?,?>,FilteredLocalPCAIndex<NumberVector<?,?>>> indexFactory, double delta, double tau)
Constructor.

Method Summary

private boolean	approximatelyLinearDependent(PCAFilteredResult pca1, PCAFilteredResult pca2) Returns true, if the strong eigenvectors of the two specified pcas span up the same space.
BitDistance	distance(NumberVector<?,?> v1, NumberVector<?,?> v2, PCAFilteredResult pca1, PCAFilteredResult pca2) Computes the distance between two given DatabaseObjects according to this distance function.
boolean	equals(Object obj)
BitDistance	getDistanceFactory() Method to get the distance functions factory.
<T extends NumberVector<?,?>> ERiCDistanceFunction.Instance<T>	instantiate(Relation<T> database) Instantiate with a database to get the actual distance query.

Methods inherited from class de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractIndexBasedDistanceFunction

getInputTypeRestriction, isMetric, isSymmetric

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.lmu.ifi.dbs.elki.distance.distancefunction.DistanceFunction

getInputTypeRestriction, isMetric, isSymmetric

Field Detail

logger

static Logging logger

Logger for debug.

DELTA_ID

public static final OptionID DELTA_ID

Parameter to specify the threshold for approximate linear dependency: the strong eigenvectors of q are approximately linear dependent from the strong eigenvectors p if the following condition holds for all strong eigenvectors q_i of q (lambda_q < lambda_p): q_i' * M^check_p * q_i <= delta^2, must be a double equal to or greater than 0.

Default value: 0.1

Key: -ericdf.delta

TAU_ID

public static final OptionID TAU_ID

Parameter to specify the threshold for the maximum distance between two approximately linear dependent subspaces of two objects p and q (lambda_q < lambda_p) before considering them as parallel, must be a double equal to or greater than 0.

Default value: 0.1

Key: -ericdf.tau

delta

private double delta

Holds the value of DELTA_ID.

tau

private double tau

Holds the value of TAU_ID.

Constructor Detail

ERiCDistanceFunction

public ERiCDistanceFunction(IndexFactory<NumberVector<?,?>,FilteredLocalPCAIndex<NumberVector<?,?>>> indexFactory,
                            double delta,
                            double tau)

Constructor.

Parameters:

indexFactory - Index factory.

delta - Delta parameter

tau - Tau parameter

Method Detail

getDistanceFactory

public BitDistance getDistanceFactory()

Description copied from interface: DistanceFunction

Method to get the distance functions factory.

Specified by:

getDistanceFactory in interface DistanceFunction<NumberVector<?,?>,BitDistance>

Specified by:

getDistanceFactory in class AbstractDatabaseDistanceFunction<NumberVector<?,?>,BitDistance>

Returns:

Factory for distance objects

instantiate

public <T extends NumberVector<?,?>> ERiCDistanceFunction.Instance<T> instantiate(Relation<T> database)

Description copied from interface: FilteredLocalPCABasedDistanceFunction

Instantiate with a database to get the actual distance query.

Specified by:

instantiate in interface DistanceFunction<NumberVector<?,?>,BitDistance>

Specified by:

instantiate in interface FilteredLocalPCABasedDistanceFunction<NumberVector<?,?>,FilteredLocalPCAIndex<NumberVector<?,?>>,BitDistance>

Parameters:

database - The representation to use

Returns:

Actual distance query.

approximatelyLinearDependent

private boolean approximatelyLinearDependent(PCAFilteredResult pca1,
                                             PCAFilteredResult pca2)

Returns true, if the strong eigenvectors of the two specified pcas span up the same space. Note, that the first pca must have equal ore more strong eigenvectors than the second pca.

Parameters:

pca1 - first PCA

pca2 - second PCA

Returns:

true, if the strong eigenvectors of the two specified pcas span up the same space

distance

public BitDistance distance(NumberVector<?,?> v1,
                            NumberVector<?,?> v2,
                            PCAFilteredResult pca1,
                            PCAFilteredResult pca2)

Computes the distance between two given DatabaseObjects according to this distance function. Note, that the first pca must have equal or more strong eigenvectors than the second pca.

Parameters:

v1 - first DatabaseObject

v2 - second DatabaseObject

pca1 - first PCA

pca2 - second PCA

Returns:

the distance between two given DatabaseObjects according to this distance function

equals

public boolean equals(Object obj)

Overrides:

equals in class Object