es.uam.eps.ir.ranksys.nn.sim

Class SetCosineSimilarity

java.lang.Object

es.uam.eps.ir.ranksys.nn.sim.SetSimilarity

es.uam.eps.ir.ranksys.nn.sim.SetCosineSimilarity

All Implemented Interfaces:

Similarity

public class SetCosineSimilarity
extends SetSimilarity

Set cosine similarity. As in Aiolli's paper. Can be asymmetric if alpha != 0.5. sim(A, B) = |A n B| / (|A|^alpha |B|^(1 - alpha)) F. Aiolli. Efficient Top-N Recommendation for Very Large Scale Binary Rated Datasets. RecSys 2013.

Author:

Saúl Vargas (saul.vargas@uam.es)

Field Summary

Fields inherited from class es.uam.eps.ir.ranksys.nn.sim.SetSimilarity

data, dense

Constructor Summary

Constructors

Constructor and Description
SetCosineSimilarity(FastPreferenceData<?,?> data, double alpha, boolean dense) Constructor.

Method Summary

Modifier and Type	Method and Description
protected double	sim(int intersectionSize, int nA, int nB) Calculates the similarity value.

Methods inherited from class es.uam.eps.ir.ranksys.nn.sim.SetSimilarity

similarElems, similarity

Methods inherited from class java.lang.Object

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

Methods inherited from interface es.uam.eps.ir.ranksys.nn.sim.Similarity

similarity

Constructor Detail

SetCosineSimilarity

public SetCosineSimilarity(FastPreferenceData<?,?> data,
                           double alpha,
                           boolean dense)

Constructor.

Parameters:

data - preference data

alpha - asymmetry of the similarity, set to 0.5 for standard cosine

dense - true for array-based calculations, false to map-based

Method Detail

sim

protected double sim(int intersectionSize,
                     int nA,
                     int nB)

Description copied from class: SetSimilarity

Calculates the similarity value.

Specified by:

sim in class SetSimilarity

Parameters:

intersectionSize - size of the intersection of sets

nA - size of the first set

nB - size of the second set

Returns:

similarity value