de.lmu.ifi.dbs.elki.distance
Class PreferenceVectorBasedCorrelationDistance

java.lang.Object
  de.lmu.ifi.dbs.elki.distance.AbstractDistance<D>
      de.lmu.ifi.dbs.elki.distance.CorrelationDistance<PreferenceVectorBasedCorrelationDistance>
          de.lmu.ifi.dbs.elki.distance.PreferenceVectorBasedCorrelationDistance

All Implemented Interfaces:

Distance<PreferenceVectorBasedCorrelationDistance>, Externalizable, Serializable, Comparable<PreferenceVectorBasedCorrelationDistance>

public class PreferenceVectorBasedCorrelationDistance
extends CorrelationDistance<PreferenceVectorBasedCorrelationDistance>

A PreferenceVectorBasedCorrelationDistance holds additionally to the CorrelationDistance the common preference vector of the two objects defining the distance.

Author:

Elke Achtert

See Also:

Serialized Form

Field Summary

private BitSet	commonPreferenceVector The common preference vector of the two objects defining this distance.
private int	dimensionality The dimensionality of the feature space (needed for serialization).
private static long	serialVersionUID

Fields inherited from class de.lmu.ifi.dbs.elki.distance.CorrelationDistance

CORRELATION_DISTANCE_PATTERN, correlationValue, euclideanValue, SEPARATOR

Fields inherited from class de.lmu.ifi.dbs.elki.distance.AbstractDistance

DOUBLE_PATTERN, INFINITY_PATTERN, INTEGER_PATTERN

Constructor Summary

PreferenceVectorBasedCorrelationDistance()
Empty constructor for serialization purposes.

PreferenceVectorBasedCorrelationDistance(int dimensionality, int correlationValue, double euclideanValue, BitSet commonPreferenceVector)
Constructs a new CorrelationDistance object.

Method Summary

int	compareTo(PreferenceVectorBasedCorrelationDistance distance) Checks if the dimensionality values of this distance and the specified distance are equal.
int	externalizableSize() Returns the number of Bytes this distance uses if it is written to an external file.
BitSet	getCommonPreferenceVector() Returns the common preference vector of the two objects defining this distance.
Pattern	getPattern() Get the pattern accepted by this distance
PreferenceVectorBasedCorrelationDistance	infiniteDistance() Provides an infinite distance.
PreferenceVectorBasedCorrelationDistance	minus(PreferenceVectorBasedCorrelationDistance distance) Returns a new Distance by subtracting the given distance from this distance.
PreferenceVectorBasedCorrelationDistance	nullDistance() Provides a null distance.
PreferenceVectorBasedCorrelationDistance	parseString(String pattern) Provides a measurement suitable to this measurement function based on the given pattern.
PreferenceVectorBasedCorrelationDistance	plus(PreferenceVectorBasedCorrelationDistance distance) Returns a new distance as sum of this distance and the given distance.
void	readExternal(ObjectInput in) Calls CorrelationDistance.readExternal(java.io.ObjectInput) and reads additionally the dimensionality and each Byte of the common preference vector from the specified stream..
String	toString() Returns a string representation of this PreferenceVectorBasedCorrelationDistance.
PreferenceVectorBasedCorrelationDistance	undefinedDistance() Provides an undefined distance.
void	writeExternal(ObjectOutput out) Calls CorrelationDistance.writeExternal(java.io.ObjectOutput) and writes additionally the dimensionality and each Byte of the common preference vector to the specified stream.

Methods inherited from class de.lmu.ifi.dbs.elki.distance.CorrelationDistance

equals, getCorrelationValue, getEuclideanValue, hashCode

Methods inherited from class de.lmu.ifi.dbs.elki.distance.AbstractDistance

isInfiniteDistance, isNullDistance, isUndefinedDistance, requiredInputPattern, testInputPattern

Methods inherited from class java.lang.Object

clone, finalize, getClass, notify, notifyAll, wait, wait, wait

Field Detail

serialVersionUID

private static final long serialVersionUID

See Also:

Constant Field Values

dimensionality

private int dimensionality

The dimensionality of the feature space (needed for serialization).

commonPreferenceVector

private BitSet commonPreferenceVector

The common preference vector of the two objects defining this distance.

Constructor Detail

PreferenceVectorBasedCorrelationDistance

public PreferenceVectorBasedCorrelationDistance()

Empty constructor for serialization purposes.

PreferenceVectorBasedCorrelationDistance

public PreferenceVectorBasedCorrelationDistance(int dimensionality,
                                                int correlationValue,
                                                double euclideanValue,
                                                BitSet commonPreferenceVector)

Constructs a new CorrelationDistance object.

Parameters:

dimensionality - the dimensionality of the feature space (needed for serialization)

correlationValue - the correlation dimension to be represented by the CorrelationDistance

euclideanValue - the euclidean distance to be represented by the CorrelationDistance

commonPreferenceVector - the common preference vector of the two objects defining this distance

Method Detail

getCommonPreferenceVector

public BitSet getCommonPreferenceVector()

Returns the common preference vector of the two objects defining this distance.

Returns:

the common preference vector

toString

public String toString()

Returns a string representation of this PreferenceVectorBasedCorrelationDistance.

Specified by:

toString in interface Distance<PreferenceVectorBasedCorrelationDistance>

Overrides:

toString in class CorrelationDistance<PreferenceVectorBasedCorrelationDistance>

Returns:

the correlation value, the euclidean value and the common preference vector separated by blanks

plus

public PreferenceVectorBasedCorrelationDistance plus(PreferenceVectorBasedCorrelationDistance distance)

Description copied from interface: Distance

Returns a new distance as sum of this distance and the given distance.

Parameters:

distance - the distance to be added to this distance

Returns:

a new distance as sum of this distance and the given distance

Throws:

IllegalArgumentException - if the dimensionality values and common preference vectors of this distance and the specified distance are not equal

minus

public PreferenceVectorBasedCorrelationDistance minus(PreferenceVectorBasedCorrelationDistance distance)

Description copied from interface: Distance

Returns a new Distance by subtracting the given distance from this distance.

Parameters:

distance - the distance to be subtracted from this distance

Returns:

a new Distance by subtracting the given distance from this distance

Throws:

IllegalArgumentException - if the dimensionality values and common preference vectors of this distance and the specified distance are not equal

compareTo

public int compareTo(PreferenceVectorBasedCorrelationDistance distance)

Checks if the dimensionality values of this distance and the specified distance are equal. If the check fails an IllegalArgumentException is thrown, otherwise CorrelationDistance#compareTo(distance) is returned.

Specified by:

compareTo in interface Comparable<PreferenceVectorBasedCorrelationDistance>

Overrides:

compareTo in class CorrelationDistance<PreferenceVectorBasedCorrelationDistance>

Returns:

the value of CorrelationDistance#compareTo(distance)

Throws:

IllegalArgumentException - if the dimensionality values of this distance and the specified distance are not equal

writeExternal

public void writeExternal(ObjectOutput out)
                   throws IOException

Calls CorrelationDistance.writeExternal(java.io.ObjectOutput) and writes additionally the dimensionality and each Byte of the common preference vector to the specified stream.

Specified by:

writeExternal in interface Externalizable

Overrides:

writeExternal in class CorrelationDistance<PreferenceVectorBasedCorrelationDistance>

Throws:

IOException

readExternal

public void readExternal(ObjectInput in)
                  throws IOException

Calls CorrelationDistance.readExternal(java.io.ObjectInput) and reads additionally the dimensionality and each Byte of the common preference vector from the specified stream..

Specified by:

readExternal in interface Externalizable

Overrides:

readExternal in class CorrelationDistance<PreferenceVectorBasedCorrelationDistance>

Throws:

IOException

externalizableSize

public int externalizableSize()

Returns the number of Bytes this distance uses if it is written to an external file.

Specified by:

externalizableSize in interface Distance<PreferenceVectorBasedCorrelationDistance>

Overrides:

externalizableSize in class CorrelationDistance<PreferenceVectorBasedCorrelationDistance>

Returns:

16 + 4 * dimensionality (8 Byte for two integer, 8 Byte for a double value, and 4 * dimensionality for the bit set)

getPattern

public Pattern getPattern()

Description copied from class: AbstractDistance

Get the pattern accepted by this distance

Specified by:

getPattern in class AbstractDistance<PreferenceVectorBasedCorrelationDistance>

Returns:

Pattern

parseString

public PreferenceVectorBasedCorrelationDistance parseString(String pattern)
                                                     throws IllegalArgumentException

Description copied from interface: Distance

Provides a measurement suitable to this measurement function based on the given pattern.

Parameters:

pattern - a pattern defining a similarity suitable to this measurement function

Returns:

a measurement suitable to this measurement function based on the given pattern

Throws:

IllegalArgumentException - if the given pattern is not compatible with the requirements of this measurement function

infiniteDistance

public PreferenceVectorBasedCorrelationDistance infiniteDistance()

Description copied from interface: Distance

Provides an infinite distance.

Returns:

an infinite distance

nullDistance

public PreferenceVectorBasedCorrelationDistance nullDistance()

Description copied from interface: Distance

Provides a null distance.

Returns:

a null distance

undefinedDistance

public PreferenceVectorBasedCorrelationDistance undefinedDistance()

Description copied from interface: Distance

Provides an undefined distance.

Returns:

an undefined distance