de.lmu.ifi.dbs.elki.distance.similarityfunction

Class JaccardPrimitiveSimilarityFunction<O extends FeatureVector<?>>

java.lang.Object

de.lmu.ifi.dbs.elki.distance.similarityfunction.AbstractPrimitiveSimilarityFunction<O,DoubleDistance>

de.lmu.ifi.dbs.elki.distance.similarityfunction.JaccardPrimitiveSimilarityFunction<O>

Type Parameters:

O - Vector type

All Implemented Interfaces:

DistanceFunction<O,DoubleDistance>, PrimitiveDistanceFunction<O,DoubleDistance>, PrimitiveDoubleDistanceFunction<O>, NormalizedPrimitiveSimilarityFunction<O>, NormalizedSimilarityFunction<O>, PrimitiveDoubleSimilarityFunction<O>, PrimitiveSimilarityFunction<O,DoubleDistance>, SimilarityFunction<O,DoubleDistance>, Parameterizable

@Reference(authors="P. Jaccard",
           title="\u00c9tude comparative de la distribution florale dans une portion des Alpes et des Jura",
           booktitle="Bulletin del la Soci\u00e9t\u00e9 Vaudoise des Sciences Naturelles")
public class JaccardPrimitiveSimilarityFunction<O extends FeatureVector<?>>
extends AbstractPrimitiveSimilarityFunction<O,DoubleDistance>
implements NormalizedPrimitiveSimilarityFunction<O>, PrimitiveDoubleDistanceFunction<O>

A flexible extension of Jaccard similarity to non-binary vectors. Jaccard coefficient is commonly defined as |intersection|/|union|. We can extend this definition as follows: |non-zero and equal attributes|/|non-zero attributes|. For binary vectors, this will obviously be the same quantity. However, this version is more useful for categorical data. Reference:

P. Jaccard
Étude comparative de la distribution florale dans une portion des Alpes et des Jura
Bulletin del la Société Vaudoise des Sciences Naturelles

TODO: add optimized implementations for binary vectors.

Field Summary

Fields

Modifier and Type	Field and Description
private static Double	DOUBLE_NULL Constants for checking null.
private static Integer	INTEGER_NULL Constants for checking null.
private static String	STRING_NULL Empty string.

Constructor Summary

Constructors

Constructor and Description
JaccardPrimitiveSimilarityFunction() Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
DoubleDistance	distance(O o1, O o2) Computes the distance between two given DatabaseObjects according to this distance function.
double	doubleDistance(O o1, O o2) Computes the distance between two given Objects according to this distance function.
double	doubleSimilarity(O o1, O o2) Computes the similarity between two given Objects according to this similarity function.
static double	doubleSimilarityNumberVector(NumberVector<?> o1, NumberVector<?> o2) Compute Jaccard similarity for two number vectors.
DoubleDistance	getDistanceFactory() Get a distance factory.
SimpleTypeInformation<? super O>	getInputTypeRestriction() Get the input data type of the function.
<T extends O> DistanceSimilarityQuery<T,DoubleDistance>	instantiate(Relation<T> relation) Instantiate with a representation to get the actual similarity query.
boolean	isMetric() Is this distance function metric (in particular, does it satisfy the triangle equation?)
private static boolean	isNull(Object val) Test a value for null.
DoubleDistance	similarity(O o1, O o2) Computes the similarity between two given DatabaseObjects according to this similarity function.

Methods inherited from class de.lmu.ifi.dbs.elki.distance.similarityfunction.AbstractPrimitiveSimilarityFunction

isSymmetric

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.similarityfunction.SimilarityFunction

isSymmetric

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

isSymmetric

Field Detail

INTEGER_NULL

private static final Integer INTEGER_NULL

Constants for checking null.

DOUBLE_NULL

private static final Double DOUBLE_NULL

Constants for checking null.

STRING_NULL

private static final String STRING_NULL

Empty string.

See Also:

Constant Field Values

Constructor Detail

JaccardPrimitiveSimilarityFunction

public JaccardPrimitiveSimilarityFunction()

Constructor. No parameters.

Method Detail

doubleSimilarity

public double doubleSimilarity(O o1,
                      O o2)

Description copied from interface: PrimitiveDoubleSimilarityFunction

Computes the similarity between two given Objects according to this similarity function.

Specified by:

doubleSimilarity in interface PrimitiveDoubleSimilarityFunction<O extends FeatureVector<?>>

Parameters:

o1 - first Object

o2 - second Object

Returns:

the similarity between two given Objects according to this similarity function

doubleSimilarityNumberVector

public static double doubleSimilarityNumberVector(NumberVector<?> o1,
                                  NumberVector<?> o2)

Compute Jaccard similarity for two number vectors.

Parameters:

o1 - First vector

o2 - Second vector

Returns:

Jaccard similarity

similarity

public DoubleDistance similarity(O o1,
                        O o2)

Description copied from interface: PrimitiveSimilarityFunction

Computes the similarity between two given DatabaseObjects according to this similarity function.

Specified by:

similarity in interface PrimitiveSimilarityFunction<O extends FeatureVector<?>,DoubleDistance>

Specified by:

similarity in class AbstractPrimitiveSimilarityFunction<O extends FeatureVector<?>,DoubleDistance>

Parameters:

o1 - first DatabaseObject

o2 - second DatabaseObject

Returns:

the similarity between two given DatabaseObjects according to this similarity function

isNull

private static boolean isNull(Object val)

Test a value for null. TODO: delegate to FeatureVector instead?

Parameters:

val - Value

Returns:

true when null

distance

public DoubleDistance distance(O o1,
                      O o2)

Description copied from interface: PrimitiveDistanceFunction

Computes the distance between two given DatabaseObjects according to this distance function.

Specified by:

distance in interface PrimitiveDistanceFunction<O extends FeatureVector<?>,DoubleDistance>

Parameters:

o1 - first DatabaseObject

o2 - second DatabaseObject

Returns:

the distance between two given DatabaseObjects according to this distance function

doubleDistance

public double doubleDistance(O o1,
                    O o2)

Description copied from interface: PrimitiveDoubleDistanceFunction

Computes the distance between two given Objects according to this distance function.

Specified by:

doubleDistance in interface PrimitiveDoubleDistanceFunction<O extends FeatureVector<?>>

Parameters:

o1 - first Object

o2 - second Object

Returns:

the distance between two given Objects according to this distance function

isMetric

public boolean isMetric()

Description copied from interface: DistanceFunction

Is this distance function metric (in particular, does it satisfy the triangle equation?)

Specified by:

isMetric in interface DistanceFunction<O extends FeatureVector<?>,DoubleDistance>

Returns:

true when metric.

getDistanceFactory

public DoubleDistance getDistanceFactory()

Description copied from interface: SimilarityFunction

Get a distance factory.

Specified by:

getDistanceFactory in interface DistanceFunction<O extends FeatureVector<?>,DoubleDistance>

Specified by:

getDistanceFactory in interface SimilarityFunction<O extends FeatureVector<?>,DoubleDistance>

Returns:

distance factory

getInputTypeRestriction

public SimpleTypeInformation<? super O> getInputTypeRestriction()

Description copied from interface: SimilarityFunction

Get the input data type of the function.

Specified by:

getInputTypeRestriction in interface DistanceFunction<O extends FeatureVector<?>,DoubleDistance>

Specified by:

getInputTypeRestriction in interface PrimitiveDistanceFunction<O extends FeatureVector<?>,DoubleDistance>

Specified by:

getInputTypeRestriction in interface PrimitiveSimilarityFunction<O extends FeatureVector<?>,DoubleDistance>

Specified by:

getInputTypeRestriction in interface SimilarityFunction<O extends FeatureVector<?>,DoubleDistance>

Specified by:

getInputTypeRestriction in class AbstractPrimitiveSimilarityFunction<O extends FeatureVector<?>,DoubleDistance>

Returns:

Type restriction

instantiate

public <T extends O> DistanceSimilarityQuery<T,DoubleDistance> instantiate(Relation<T> relation)

Description copied from interface: SimilarityFunction

Instantiate with a representation to get the actual similarity query.

Specified by:

instantiate in interface DistanceFunction<O extends FeatureVector<?>,DoubleDistance>

Specified by:

instantiate in interface SimilarityFunction<O extends FeatureVector<?>,DoubleDistance>

Overrides:

instantiate in class AbstractPrimitiveSimilarityFunction<O extends FeatureVector<?>,DoubleDistance>

Parameters:

relation - Representation to use

Returns:

Actual distance query.