net.librec.similarity

Class AbstractRecommenderSimilarity

java.lang.Object

net.librec.similarity.AbstractRecommenderSimilarity

All Implemented Interfaces:

RecommenderSimilarity

Direct Known Subclasses:

BinaryCosineSimilarity, CosineSimilarity, CPCSimilarity, DiceCoefficientSimilarity, ExJaccardSimilarity, JaccardSimilarity, KRCCSimilarity, MSDSimilarity, MSESimilarity, PCCSimilarity

public abstract class AbstractRecommenderSimilarity
extends java.lang.Object
implements RecommenderSimilarity

Calculate Recommender Similarity, such as cosine, Pearson, Jaccard similarity, etc.

Author:

zhanghaidong

Field Summary

Fields

Modifier and Type	Field and Description
protected Configuration	conf Configuration
protected SymmMatrix	similarityMatrix Similarity Matrix

Constructor Summary

Constructors

Constructor and Description
AbstractRecommenderSimilarity()

Method Summary

Methods

Modifier and Type	Method and Description
void	buildSimilarityMatrix(DataModel dataModel) Build social similarity matrix with trainMatrix in dataModel.
void	buildSocialSimilarityMatrix(DataModel dataModel) Build social similarity matrix with trainMatrix and socialMatrix in dataModel.
double	getCorrelation(SparseVector thisVector, SparseVector thatVector) Find the common rated items by this user and that user, or the common users have rated this item or that item.
protected abstract double	getSimilarity(java.util.List<? extends java.lang.Number> thisList, java.util.List<? extends java.lang.Number> thatList) Calculate the similarity between thisList and thatList.
SymmMatrix	getSimilarityMatrix() Return the similarity matrix.

Methods inherited from class java.lang.Object

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

Field Detail

conf

protected Configuration conf

Configuration

similarityMatrix

protected SymmMatrix similarityMatrix

Similarity Matrix

Constructor Detail

AbstractRecommenderSimilarity

public AbstractRecommenderSimilarity()

Method Detail

buildSimilarityMatrix

public void buildSimilarityMatrix(DataModel dataModel)

Build social similarity matrix with trainMatrix in dataModel.

Specified by:

buildSimilarityMatrix in interface RecommenderSimilarity

Parameters:

dataModel - the input data model

buildSocialSimilarityMatrix

public void buildSocialSimilarityMatrix(DataModel dataModel)

Build social similarity matrix with trainMatrix and socialMatrix in dataModel.

Parameters:

dataModel - the input data model

getCorrelation

public double getCorrelation(SparseVector thisVector,
                    SparseVector thatVector)

Find the common rated items by this user and that user, or the common users have rated this item or that item. And then return the similarity.

Parameters:

thisVector: - the rated items by this user, or users that have rated this item .

thatVector: - the rated items by that user, or users that have rated that item.

Returns:

similarity

getSimilarity

protected abstract double getSimilarity(java.util.List<? extends java.lang.Number> thisList,
                   java.util.List<? extends java.lang.Number> thatList)

Calculate the similarity between thisList and thatList.

Parameters:

thisList - this list

thatList - that list

Returns:

similarity

getSimilarityMatrix

public SymmMatrix getSimilarityMatrix()

Return the similarity matrix.

Specified by:

getSimilarityMatrix in interface RecommenderSimilarity

Returns:

the similarity matrix