def readConfiguration(self):
super(IterativeRecommender, self).readConfiguration()
# set the reduced dimension
self.k = int(self.config['num.factors'])
# set maximum iteration
self.maxIter = int(self.config['num.max.iter'])
# set learning rate
learningRate = config.LineConfig(self.config['learnRate'])
self.lRate = float(learningRate['-init'])
self.maxLRate = float(learningRate['-max'])
# regularization parameter
regular = config.LineConfig(self.config['reg.lambda'])
self.regU,self.regI,self.regB= float(regular['-u']),float(regular['-i']),float(regular['-b'])
def readConfiguration(self):
super(APR, self).readConfiguration()
args = config.LineConfig(self.config['APR'])
self.eps = float(args['-eps'])
self.regAdv = float(args['-regA'])
self.advEpoch = int(args['-advEpoch'])
self.negativeCount = 3
def readConfiguration(self):
super(DeepRecommender, self).readConfiguration()
# set the reduced dimension
self.batch_size = int(self.config['batch_size'])
# regularization parameter
regular = config.LineConfig(self.config['reg.lambda'])
self.regU, self.regI, self.regB = float(regular['-u']), float(
regular['-i']), float(regular['-b'])
def buildModel(self):
# If necessary, you can fix the parameter in ./config/Trust.conf
self.trusterModel()
# train trusterModel and trusteeModel independently using the same
# parameter setting.
learningrate = config.LineConfig(self.config['learnRate'])
self.lRate = float(learningrate['-init'])
self.trusteeModel()
def readConfiguration(self):
super(CoFactor, self).readConfiguration()
extraSettings = config.LineConfig(self.config['CoFactor'])
self.negCount = int(extraSettings['-k']) #the number of negative samples
if self.negCount < 1:
self.negCount = 1
self.regR = float(extraSettings['-gamma'])
self.filter = int(extraSettings['-filter'])
def readConfiguration(self):
super(CUNE_BPR, self).readConfiguration()
options = config.LineConfig(self.config['CUNE-BPR'])
self.walkCount = int(options['-T'])
self.walkLength = int(options['-L'])
self.walkDim = int(options['-l'])
self.winSize = int(options['-w'])
self.topK = int(options['-k'])
self.s = float(options['-s'])
def readConfiguration(self):
super(ESRF, self).readConfiguration()
args = config.LineConfig(self.config['ESRF'])
self.K = int(
args['-K']) #controling the magnitude of adversarial learning
self.beta = float(args['-beta']) #the number of alternative neighbors
self.n_layers_D = int(
args['-n_layer']
) #the number of layers of the recommendation module (discriminator)
def readConfiguration(self):
super(BayesDetector, self).readConfiguration()
extraSettings = config.LineConfig(self.config['BayesDetector'])
self.k = int(extraSettings['-k'])
self.negCount = int(
extraSettings['-negCount']) # the number of negative samples
if self.negCount < 1:
self.negCount = 1
self.regR = float(extraSettings['-gamma'])
self.filter = int(extraSettings['-filter'])
self.delta = float(extraSettings['-delta'])
learningRate = config.LineConfig(self.config['learnRate'])
self.lRate = float(learningRate['-init'])
self.maxLRate = float(learningRate['-max'])
self.maxIter = int(self.config['num.max.iter'])
regular = config.LineConfig(self.config['reg.lambda'])
self.regU, self.regI = float(regular['-u']), float(regular['-i'])
def readConfiguration(self):
super(HME, self).readConfiguration()
options = config.LineConfig(self.config['HME'])
self.walkCount = int(options['-T'])
self.walkLength = int(options['-L'])
self.winSize = int(options['-w'])
self.alpha = float(options['-alpha'])
self.beta = float(options['-beta'])
self.epoch = int(options['-ep'])
def readConfiguration(self):
super(CUNE_MF, self).readConfiguration()
options = config.LineConfig(self.config['CUNE-MF'])
self.walkCount = int(options['-T'])
self.walkLength = int(options['-L'])
self.walkDim = int(options['-l'])
self.winSize = int(options['-w'])
self.topK = int(options['-k'])
self.epoch = int(options['-ep'])
self.alpha = float(options['-a'])
def readConfiguration(self):
super(IF_BPR, self).readConfiguration()
options = config.LineConfig(self.config['IF_BPR'])
self.walkLength = int(options['-L'])
self.walkDim = int(options['-l'])
self.winSize = int(options['-w'])
self.topK = int(options['-k'])
self.alpha = float(options['-a'])
self.epoch = int(options['-ep'])
self.neg = int(options['-neg'])
self.rate = float(options['-r'])
def readConfiguration(self):
super(SocialRecommender, self).readConfiguration()
alpha = config.LineConfig(self.config['RSTE'])
self.alpha = float(alpha['-alpha'])
def readConfiguration(self):
super(LOCABAL, self).readConfiguration()
alpha = config.LineConfig(self.config['LOCABAL'])
self.alpha = float(alpha['-alpha'])
def readConfiguration(self):
super(TBPR, self).readConfiguration()
options = config.LineConfig(self.config['TBPR'])
self.regT = float(options['-regT'])
def readConfiguration(self):
super(Song2vec, self).readConfiguration()
options = config.LineConfig(self.config['Song2vec'])
self.alpha = float(options['-alpha'])
self.topK = int(options['-k'])
def readConfiguration(self):
super(SVDPlusPlus, self).readConfiguration()
regY = config.LineConfig(self.config['SVDPlusPlus'])
self.regY = float(regY['-y'])
def readConfiguration(self):
super(SocialFD, self).readConfiguration()
eps = config.LineConfig(self.config['SocialFD'])
self.alpha = float(eps['-alpha'])
self.eta = float(eps['-eta'])
self.beta = float(eps['-beta'])
def readConfiguration(self):
super(TrustMF, self).readConfiguration()
regular = config.LineConfig(self.config['reg.lambda'])
self.regB = float(regular['-b'])
self.regT = float(regular['-t'])
def readParameters(self):
args = config.LineConfig(self.config['AT'])
self.eps = float(args['-eps'])
self.regAdv = float(args['-regA'])
self.advEpoch = int(args['-advEpoch'])
def readConfiguration(self):
super(EE, self).readConfiguration()
Dim = config.LineConfig(self.config['EE'])
self.Dim = int(Dim['-d'])
def readConfiguration(self):
super(SoRec, self).readConfiguration()
regZ = config.LineConfig(self.config['SoRec'])
self.regZ = float(regZ['-z'])
def readConfiguration(self):
super(CDAE, self).readConfiguration()
args = config.LineConfig(self.config['CDAE'])
self.corruption_level = float(args['-co'])
self.n_hidden = int(args['-nh'])
def readConfiguration(self):
super(RSTE, self).readConfiguration()
alpha = config.LineConfig(self.config['RSTE'])
self.alpha = float(alpha['-alpha'])
def readConfiguration(self):
super(CDAE, self).readConfiguration()
eps = config.LineConfig(self.config['CDAE'])
self.corruption_level = float(eps['-co'])
self.n_hidden = int(eps['-nh'])
self.batch_size = int(eps['-batch_size'])
def readConfiguration(self):
super(MHCN, self).readConfiguration()
args = config.LineConfig(self.config['MHCN'])
self.n_layers = int(args['-n_layer'])
self.ss_rate = float(args['-ss_rate'])
def readConfiguration(self):
super(DiffNet, self).readConfiguration()
args = config.LineConfig(self.config['DiffNet'])
self.n_layers = int(
args['-n_layer']
) #the number of layers of the recommendation module (discriminator)
def readConfiguration(self):
super(SoReg, self).readConfiguration()
alpha = config.LineConfig(self.config['SoReg'])
self.alpha = float(alpha['-alpha'])
def readConfiguration(self):
super(SREE, self).readConfiguration()
par = config.LineConfig(self.config['SREE'])
self.alpha = float(par['-alpha'])
def readConfiguration(self):
super(SocialRecommender, self).readConfiguration()
regular = config.LineConfig(self.config['reg.lambda'])
self.regS = float(regular['-s'])
def readConfiguration(self):
super(DMF, self).readConfiguration()
options = config.LineConfig(self.config['DMF'])
self.alpha = float(options['-alpha'])
self.topK = int(options['-k'])
self.negCount = int(options['-neg'])
