de.lmu.ifi.dbs.elki.distance.distancefunction.correlation
Class PCABasedCorrelationDistanceFunction.Instance<V extends NumberVector<?,?>>

java.lang.Object
  de.lmu.ifi.dbs.elki.database.query.AbstractDataBasedQuery<O>
      de.lmu.ifi.dbs.elki.database.query.distance.AbstractDistanceQuery<O,D>
          de.lmu.ifi.dbs.elki.database.query.distance.AbstractDatabaseDistanceQuery<O,D>
              de.lmu.ifi.dbs.elki.distance.distancefunction.AbstractIndexBasedDistanceFunction.Instance<V,FilteredLocalPCAIndex<V>,PCACorrelationDistance,PCABasedCorrelationDistanceFunction>
                  de.lmu.ifi.dbs.elki.distance.distancefunction.correlation.PCABasedCorrelationDistanceFunction.Instance<V>

All Implemented Interfaces:

DatabaseQuery, DistanceQuery<V,PCACorrelationDistance>, FilteredLocalPCABasedDistanceFunction.Instance<V,FilteredLocalPCAIndex<V>,PCACorrelationDistance>, IndexBasedDistanceFunction.Instance<V,FilteredLocalPCAIndex<V>,PCACorrelationDistance>

Enclosing class:

PCABasedCorrelationDistanceFunction

public static class PCABasedCorrelationDistanceFunction.Instance<V extends NumberVector<?,?>>
extends AbstractIndexBasedDistanceFunction.Instance<V,FilteredLocalPCAIndex<V>,PCACorrelationDistance,PCABasedCorrelationDistanceFunction>
implements FilteredLocalPCABasedDistanceFunction.Instance<V,FilteredLocalPCAIndex<V>,PCACorrelationDistance>

The actual instance bound to a particular database.

Field Summary

(package private) double

delta Delta value

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

index, parent

Fields inherited from class de.lmu.ifi.dbs.elki.database.query.AbstractDataBasedQuery

relation

Fields inherited from interface de.lmu.ifi.dbs.elki.database.query.DatabaseQuery

HINT_BULK, HINT_EXACT, HINT_HEAVY_USE, HINT_NO_CACHE, HINT_OPTIMIZED_ONLY, HINT_SINGLE

Constructor Summary

PCABasedCorrelationDistanceFunction.Instance(Relation<V> database, FilteredLocalPCAIndex<V> index, double delta, PCABasedCorrelationDistanceFunction distanceFunction)
Constructor.

Method Summary

private void	adjust(Matrix v, Matrix e_czech, Matrix vector, int corrDim) Inserts the specified vector into the given orthonormal matrix v at column corrDim.
int	correlationDistance(PCAFilteredResult pca1, PCAFilteredResult pca2, int dimensionality) Computes the correlation distance between the two subspaces defined by the specified PCAs.
PCACorrelationDistance	distance(DBID id1, DBID id2) Returns the distance between the two objects specified by their object ids.
private double	euclideanDistance(V dv1, V dv2) Computes the Euclidean distance between the given two vectors.

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

getDistanceFunction, getIndex

Methods inherited from class de.lmu.ifi.dbs.elki.database.query.distance.AbstractDatabaseDistanceQuery

distance, distance, distance

Methods inherited from class de.lmu.ifi.dbs.elki.database.query.distance.AbstractDistanceQuery

getDistanceFactory, infiniteDistance, nullDistance, undefinedDistance

Methods inherited from class de.lmu.ifi.dbs.elki.database.query.AbstractDataBasedQuery

getRelation

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.distance.distancefunction.IndexBasedDistanceFunction.Instance

getIndex

Methods inherited from interface de.lmu.ifi.dbs.elki.database.query.distance.DistanceQuery

distance, distance, distance, getDistanceFactory, getDistanceFunction, getRelation, infiniteDistance, nullDistance, undefinedDistance

Field Detail

delta

final double delta

Delta value

Constructor Detail

PCABasedCorrelationDistanceFunction.Instance

public PCABasedCorrelationDistanceFunction.Instance(Relation<V> database,
                                                    FilteredLocalPCAIndex<V> index,
                                                    double delta,
                                                    PCABasedCorrelationDistanceFunction distanceFunction)

Constructor.

Parameters:

database - Database

index - Index to use

delta - Delta

distanceFunction - Distance function

Method Detail

distance

public PCACorrelationDistance distance(DBID id1,
                                       DBID id2)

Description copied from class: AbstractDistanceQuery

Returns the distance between the two objects specified by their object ids.

Specified by:

distance in interface DistanceQuery<V extends NumberVector<?,?>,PCACorrelationDistance>

Specified by:

distance in class AbstractDistanceQuery<V extends NumberVector<?,?>,PCACorrelationDistance>

Parameters:

id1 - first object id

id2 - second object id

Returns:

the distance between the two objects specified by their object ids

correlationDistance

public int correlationDistance(PCAFilteredResult pca1,
                               PCAFilteredResult pca2,
                               int dimensionality)

Computes the correlation distance between the two subspaces defined by the specified PCAs.

Parameters:

pca1 - first PCA

pca2 - second PCA

dimensionality - the dimensionality of the data space

Returns:

the correlation distance between the two subspaces defined by the specified PCAs

adjust

private void adjust(Matrix v,
                    Matrix e_czech,
                    Matrix vector,
                    int corrDim)

Inserts the specified vector into the given orthonormal matrix v at column corrDim. After insertion the matrix v is orthonormalized and column corrDim of matrix e_czech is set to the corrDim-th unit vector.

Parameters:

v - the orthonormal matrix of the eigenvectors

e_czech - the selection matrix of the strong eigenvectors

vector - the vector to be inserted

corrDim - the column at which the vector should be inserted

euclideanDistance

private double euclideanDistance(V dv1,
                                 V dv2)

Computes the Euclidean distance between the given two vectors.

Parameters:

dv1 - first FeatureVector

dv2 - second FeatureVector

Returns:

the Euclidean distance between the given two vectors