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

Interface SimilarityFunction<O>

Type Parameters:

O - object type

All Known Subinterfaces:

ClusteringDistanceSimilarityFunction, DBIDSimilarityFunction, IndexBasedSimilarityFunction<O>, NormalizedPrimitiveSimilarityFunction<O>, NormalizedSimilarityFunction<O>, PrimitiveSimilarityFunction<O>

All Known Implementing Classes:

AbstractDBIDSimilarityFunction, AbstractIndexBasedSimilarityFunction, AbstractVectorSimilarityFunction, ClusteringAdjustedRandIndexSimilarityFunction, ClusteringBCubedF1SimilarityFunction, ClusteringFowlkesMallowsSimilarityFunction, ClusteringRandIndexSimilarityFunction, ClusterIntersectionSimilarityFunction, ClusterJaccardSimilarityFunction, FractionalSharedNearestNeighborSimilarityFunction, HellingerDistanceFunction, InvertedDistanceSimilarityFunction, JaccardSimilarityDistanceFunction, Kulczynski1SimilarityFunction, Kulczynski2SimilarityFunction, LaplaceKernelFunction, LinearKernelFunction, PolynomialKernelFunction, RadialBasisFunctionKernelFunction, RationalQuadraticKernelFunction, SharedNearestNeighborSimilarityFunction, SigmoidKernelFunction

public interface SimilarityFunction<O>

Interface SimilarityFunction describes the requirements of any similarity function.

Since:

0.1

Author:

Erich Schubert

Method Summary

Modifier and Type	Method and Description
TypeInformation	getInputTypeRestriction() Get the input data type of the function.
<T extends O> SimilarityQuery<T>	instantiate(Relation<T> relation) Instantiate with a representation to get the actual similarity query.
default boolean	isSymmetric() Is this function symmetric?

Method Detail

isSymmetric

default boolean isSymmetric()

Is this function symmetric?

Returns:

true when symmetric

getInputTypeRestriction

TypeInformation getInputTypeRestriction()

Get the input data type of the function.

instantiate

<T extends O> SimilarityQuery<T> instantiate(Relation<T> relation)

Instantiate with a representation to get the actual similarity query.

Parameters:

relation - Representation to use

Returns:

Actual distance query.