net.librec.recommender

Class SocialRecommender

java.lang.Object

net.librec.recommender.AbstractRecommender

net.librec.recommender.MatrixFactorizationRecommender

net.librec.recommender.SocialRecommender

All Implemented Interfaces:

Recommender

Direct Known Subclasses:

RSTERecommender, SBPRRecommender, SocialMFRecommender, SoRecRecommender, SoRegRecommender, TrustMFRecommender, TrustSVDRecommender

public abstract class SocialRecommender
extends MatrixFactorizationRecommender

Social Recommender

Author:

Keqiang Wang

Field Summary

Fields

Modifier and Type	Field and Description
protected float	regSocial social regularization
protected SparseMatrix	socialMatrix socialMatrix: social rate matrix, indicating a user is connecting to a number of other users

Fields inherited from class net.librec.recommender.MatrixFactorizationRecommender

initMean, initStd, itemFactors, learnRate, maxLearnRate, numFactors, numIterations, regItem, regUser, userFactors

Fields inherited from class net.librec.recommender.AbstractRecommender

conf, context, decay, earlyStop, globalMean, isBoldDriver, isRanking, itemMappingData, lastLoss, LOG, loss, maxRate, minRate, numItems, numRates, numUsers, ratingScale, recommendedList, testMatrix, topN, trainMatrix, userMappingData, validMatrix, verbose

Constructor Summary

Constructors

Constructor and Description
SocialRecommender()

Method Summary

Methods

Modifier and Type	Method and Description
protected double	denormalize(double predictRating) denormalize a prediction to the region (minRate, maxRate)
protected double	normalize(double rating) normalize a rating to the region (0, 1)
protected double	predict(int userIdx, int itemIdx, boolean bounded) predict a specific rating for user userIdx on item itemIdx.
void	setup() setup init member method

Methods inherited from class net.librec.recommender.MatrixFactorizationRecommender

predict, updateLRate

Methods inherited from class net.librec.recommender.AbstractRecommender

cleanup, evaluate, evaluateMap, getContext, getDataModel, getRecommendedList, isConverged, loadModel, recommend, recommend, recommendRank, recommendRating, saveModel, setContext, trainModel

Methods inherited from class java.lang.Object

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

Field Detail

socialMatrix

protected SparseMatrix socialMatrix

socialMatrix: social rate matrix, indicating a user is connecting to a number of other users

regSocial

protected float regSocial

social regularization

Constructor Detail

SocialRecommender

public SocialRecommender()

Method Detail

setup

public void setup()
           throws LibrecException

Description copied from class: MatrixFactorizationRecommender

setup init member method

Overrides:

setup in class MatrixFactorizationRecommender

Throws:

LibrecException - if error occurs during setting up

predict

protected double predict(int userIdx,
             int itemIdx,
             boolean bounded)
                  throws LibrecException

Description copied from class: AbstractRecommender

predict a specific rating for user userIdx on item itemIdx. It is useful for evalution which requires predictions are bounded.

Overrides:

predict in class AbstractRecommender

Parameters:

userIdx - user index

itemIdx - item index

bounded - whether there is a bound

Returns:

predictive rating for user userIdx on item itemIdx with bound

Throws:

LibrecException - if error occurs during predicting

denormalize

protected double denormalize(double predictRating)

denormalize a prediction to the region (minRate, maxRate)

Parameters:

predictRating - a prediction to the region (minRate, maxRate)

Returns:

a denormalized prediction to the region (minRate, maxRate)

normalize

protected double normalize(double rating)

normalize a rating to the region (0, 1)

Parameters:

rating - a given rating

Returns:

a normalized rating