def __init__(self, config):
self.trainingData = [] # training data
self.testData = [] # testData
self.relation = []
self.measure = []
self.config = config
self.ratingConfig = LineConfig(config['ratings.setup'])
if self.config.contains('evaluation.setup'):
self.evaluation = LineConfig(config['evaluation.setup'])
binarized = False
bottom = 0
if self.evaluation.contains('-b'):
binarized = True
bottom = float(self.evaluation['-b'])
if self.evaluation.contains('-testSet'):
#specify testSet
self.trainingData = FileIO.loadDataSet(config,
config['ratings'],
binarized=binarized,
threshold=bottom)
self.testData = FileIO.loadDataSet(config,
self.evaluation['-testSet'],
bTest=True,
binarized=binarized,
threshold=bottom)
elif self.evaluation.contains('-ap'):
#auto partition
self.trainingData = FileIO.loadDataSet(config,
config['ratings'],
binarized=binarized,
threshold=bottom)
self.trainingData,self.testData = DataSplit.\
dataSplit(self.trainingData,test_ratio=float(self.evaluation['-ap']),binarized=binarized)
elif self.evaluation.contains('-cv'):
#cross validation
self.trainingData = FileIO.loadDataSet(config,
config['ratings'],
binarized=binarized,
threshold=bottom)
#self.trainingData,self.testData = DataSplit.crossValidation(self.trainingData,int(self.evaluation['-cv']))
else:
print('Evaluation is not well configured!')
exit(-1)
if config.contains('social'):
self.socialConfig = LineConfig(self.config['social.setup'])
self.relation = FileIO.loadRelationship(config,
self.config['social'])
print('preprocessing...')
def __init__(self,config):
self.trainingData = [] # training data
self.testData = [] # testData
self.measure = []
self.config =config
setup = LineConfig(config['record.setup'])
columns = {}
labels = setup['-columns'].split(',')
delim = ''
if setup.contains('-delim'):
delim=setup['-delim']
for col in labels:
label = col.split(':')
columns[label[0]] = int(label[1])
if self.config.contains('evaluation.setup'):
self.evaluation = LineConfig(config['evaluation.setup'])
binarized = False
bottom = 0
if self.evaluation.contains('-b'):
binarized = True
bottom = float(self.evaluation['-b'])
if self.evaluation.contains('-testSet'):
#specify testSet
self.trainingData = FileIO.loadDataSet(config['record'],columns=columns,binarized=binarized,threshold=bottom,delim=delim)
self.testData = FileIO.loadDataSet(self.evaluation['-testSet'],binarized=binarized,columns=columns,threshold=bottom,delim=delim)
elif self.evaluation.contains('-ap'):
#auto partition
self.trainingData = FileIO.loadDataSet(config['record'],columns=columns,binarized=binarized,threshold=bottom,delim=delim)
self.trainingData,self.testData = DataSplit.\
dataSplit(self.trainingData,test_ratio=float(self.evaluation['-ap']))
elif self.evaluation.contains('-byTime'):
self.trainingData = FileIO.loadDataSet(config['record'], columns=columns, binarized=binarized,threshold=bottom, delim=delim)
self.testData = []
elif self.evaluation.contains('-cv'):
#cross validation
self.trainingData = FileIO.loadDataSet(config['record'],columns=columns,binarized=binarized,threshold=bottom,delim=delim)
#self.trainingData,self.testData = DataSplit.crossValidation(self.trainingData,int(self.evaluation['-cv']))
else:
print 'Evaluation is not well configured!'
exit(-1)
# if config.contains('social'):
# self.socialConfig = LineConfig(self.config['social.setup'])
# self.relation = FileIO.loadRelationship(config,self.config['social'])
print 'preprocessing...'
def __init__(self, conf):
self.config = Config(conf)
self.userProfile = FileIO.loadDataSet(self.config,
self.config['ratings'])
self.itemProfile = defaultdict(dict)
self.attackSize = float(self.config['attackSize'])
self.fillerSize = float(self.config['fillerSize'])
self.selectedSize = float(self.config['selectedSize'])
self.targetCount = int(self.config['targetCount'])
self.targetScore = float(self.config['targetScore'])
self.threshold = float(self.config['threshold'])
self.minCount = int(self.config['minCount'])
self.maxCount = int(self.config['maxCount'])
self.outputDir = self.config['outputDir']
if not os.path.exists(self.outputDir):
os.makedirs(self.outputDir)
for user in self.userProfile:
for item in self.userProfile[user]:
self.itemProfile[item][user] = self.userProfile[user][item]
self.spamProfile = defaultdict(dict)
self.spamItem = defaultdict(list) #items rated by spammers
self.targetItems = []
self.itemAverage = {}
self.getAverageRating()
self.selectTarget()
def __init__(self,conf):
self.config = Config(conf)
self.userProfile = FileIO.loadDataSet(self.config,self.config['ratings'])
self.itemProfile = defaultdict(dict)
self.attackSize = float(self.config['attackSize'])
self.fillerSize = float(self.config['fillerSize'])
self.selectedSize = float(self.config['selectedSize'])
self.targetCount = int(self.config['targetCount'])
self.targetScore = float(self.config['targetScore'])
self.threshold = float(self.config['threshold'])
self.minCount = int(self.config['minCount'])
self.maxCount = int(self.config['maxCount'])
self.minScore = float(self.config['minScore'])
self.maxScore = float(self.config['maxScore'])
self.outputDir = self.config['outputDir']
if not os.path.exists(self.outputDir):
os.makedirs(self.outputDir)
for user in self.userProfile:
for item in self.userProfile[user]:
self.itemProfile[item][user] = self.userProfile[user][item]
self.spamProfile = defaultdict(dict)
self.spamItem = defaultdict(list) #items rated by spammers
self.targetItems = []
self.itemAverage = {}
self.getAverageRating()
self.selectTarget()
self.startUserID = 0
def __init__(self, config):
self.trainingData = [] # training data
self.testData = [] # testData
self.relation = []
self.measure = []
self.config = config
self.ratingConfig = LineConfig(config['ratings.setup'])
self.labels = FileIO.loadLabels(config['label'])
if self.config.contains('evaluation.setup'):
self.evaluation = LineConfig(config['evaluation.setup'])
if self.evaluation.contains('-testSet'):
#specify testSet
self.trainingData = FileIO.loadDataSet(config,
config['ratings'])
self.testData = FileIO.loadDataSet(config,
self.evaluation['-testSet'],
bTest=True)
elif self.evaluation.contains('-ap'):
#auto partition
self.trainingData = FileIO.loadDataSet(config,
config['ratings'])
self.trainingData,self.testData = DataSplit.\
dataSplit(self.trainingData,test_ratio=float(self.evaluation['-ap']))
elif self.evaluation.contains('-cv'):
#cross validation
self.trainingData = FileIO.loadDataSet(config,
config['ratings'])
#self.trainingData,self.testData = DataSplit.crossValidation(self.trainingData,int(self.evaluation['-cv']))
else:
print 'Evaluation is not well configured!'
exit(-1)
if config.contains('social'):
self.socialConfig = LineConfig(self.config['social.setup'])
self.relation = FileIO.loadRelationship(config,
self.config['social'])
print 'preprocessing...'
def __init__(self, conf):
self.conf = conf
if not conf.contains('ratings') and not conf.contains('social'):
print 'The config file is not in the correct format!'
exit(-1)
if conf.contains('ratings'):
ratingData = FileIO.loadDataSet(conf, conf['ratings'])
self.dao = RatingDAO(conf, ratingData)
if conf.contains('social'):
relationData = FileIO.loadRelationship(conf, conf['social'])
self.sao = SocialDAO(conf, relationData)
def __init__(self,config):
self.trainingData = [] # training data
self.testData = [] # testData
self.relation = []
self.measure = []
self.config =config
self.ratingConfig = LineConfig(config['ratings.setup'])
self.labels = FileIO.loadLabels(config['label'])
if self.config.contains('evaluation.setup'):
self.evaluation = LineConfig(config['evaluation.setup'])
if self.evaluation.contains('-testSet'):
#specify testSet
self.trainingData = FileIO.loadDataSet(config, config['ratings'])
self.testData = FileIO.loadDataSet(config, self.evaluation['-testSet'], bTest=True)
elif self.evaluation.contains('-ap'):
#auto partition
self.trainingData = FileIO.loadDataSet(config,config['ratings'])
self.trainingData,self.testData = DataSplit.\
dataSplit(self.trainingData,test_ratio=float(self.evaluation['-ap']))
elif self.evaluation.contains('-cv'):
#cross validation
self.trainingData = FileIO.loadDataSet(config, config['ratings'])
#self.trainingData,self.testData = DataSplit.crossValidation(self.trainingData,int(self.evaluation['-cv']))
else:
print 'Evaluation is not well configured!'
exit(-1)
if config.contains('social'):
self.socialConfig = LineConfig(self.config['social.setup'])
self.relation = FileIO.loadRelationship(config,self.config['social'])
print 'preprocessing...'
import sys
sys.path.append("..")
from tool.config import Config
from tool.file import FileIO
from algorithm.SoReg import SoReg
if __name__ == '__main__':
print'='*80
print'this is the algorithm of the test'
algor = -1
conf = -1
conf = Config('../conf/SoReg.conf')
trainset = []
testset = []
relation = []
ui={}
vj={}
user_item_avg={}
trainset = FileIO.loadDataSet(conf,conf['ratings'],bTest=False)
testset = FileIO.loadDataSet(conf,conf['testset'],bTest=True)
relation = FileIO.loadRelationship(conf,conf['social'])
ui,vj,user_item_avg=SoReg.buildmodel(trainset,relation)
SoReg.pred(testset,ui,vj,user_item_avg)
#sotre the data
def __init__(self, config, account_DAO=None):
self.trainingData = [] # training data
self.testData = [] # testData
self.relation = []
self.measure = []
self.config = config
self.ratingConfig = LineConfig(config['ratings.setup'])
# self.accountDAO = account_DAO
# self.currentTime = strftime("%Y-%m-%d %H-%M-%S", localtime(time()))
if self.config.contains('evaluation.setup'):
self.evaluation = LineConfig(config['evaluation.setup'])
binarized = False
bottom = 0
if self.evaluation.contains('-b'):
binarized = True
bottom = float(self.evaluation['-b'])
if self.evaluation.contains('-testSet'):
# specify testSet
self.trainingData = FileIO.loadDataSet(config,
config['ratings'],
binarized=binarized,
threshold=bottom)
self.testData = FileIO.loadDataSet(config,
self.evaluation['-testSet'],
bTest=True,
binarized=binarized,
threshold=bottom)
elif self.evaluation.contains('-ap'):
# auto partition
self.trainingData = FileIO.loadDataSet(config,
config['ratings'],
binarized=binarized,
threshold=bottom)
self.trainingData, self.testData = DataSplit. \
dataSplit(self.trainingData, test_ratio=float(self.evaluation['-ap']), binarized=binarized)
elif self.evaluation.contains('-cv'):
# cross validation
self.trainingData = FileIO.loadDataSet(config,
config['ratings'],
binarized=binarized,
threshold=bottom)
# self.trainingData,self.testData = DataSplit.crossValidation(self.trainingData,int(self.evaluation['-cv']))
elif self.evaluation.contains('--account'):
self.training_user_item = account_DAO.training_user_item
self.training_account_item = account_DAO.training_account_item
self.relation = account_DAO.relation
self.test_user_item = account_DAO.test_user_item
else:
print('Evaluation is not well configured!')
exit(-1)
if config.contains('social'):
self.socialConfig = LineConfig(self.config['social.setup'])
self.relation = FileIO.loadRelationship(config,
self.config['social'])
print('preprocessing...')
