def __generateSet(self):
triple = []
scale = set()
# find the maximum rating and minimum value
for i, entry in enumerate(self.trainingData):
userName, itemName, rating = entry
scale.add(float(rating))
self.rScale = list(scale)
self.rScale.sort()
for i, entry in enumerate(self.trainingData):
userName, itemName, rating = entry
# makes the rating within the range [0, 1].
rating = normalize(float(rating), self.rScale[-1], self.rScale[0])
self.trainingData[i][2] = rating
# order the user
if not self.user.has_key(userName):
self.user[userName] = len(self.user)
self.id2user[self.user[userName]] = userName
# order the item
if not self.item.has_key(itemName):
self.item[itemName] = len(self.item)
self.id2item[self.item[itemName]] = itemName
# userList.append
triple.append([self.user[userName], self.item[itemName], rating])
self.trainingMatrix = new_sparseMatrix.SparseMatrix(triple)
self.all_User.update(self.user)
self.all_Item.update(self.item)
for entry in self.testData:
userId, itemId, rating = entry
# order the user
if not self.user.has_key(userId):
self.all_User[userId] = len(self.all_User)
# order the item
if not self.item.has_key(itemId):
self.all_Item[itemId] = len(self.all_Item)
if not self.testSet_u.has_key(userId):
self.testSet_u[userId] = {}
self.testSet_u[userId][itemId] = rating
if not self.testSet_i.has_key(itemId):
self.testSet_i[itemId] = {}
self.testSet_i[itemId][userId] = rating
def __generateSet(self):
triple = []
scale = set()
# find the maximum rating and minimum value
for i, entry in enumerate(self.trainingData):
userName, itemName, rating = entry
scale.add(float(rating))
self.rScale = list(scale)
self.rScale.sort()
for i,entry in enumerate(self.trainingData):
userName,itemName,rating = entry
# makes the rating within the range [0, 1].
rating = normalize(float(rating), self.rScale[-1], self.rScale[0])
self.trainingData[i][2] = rating
# order the user
if userName not in self.user:
self.user[userName] = len(self.user)
self.id2user[self.user[userName]] = userName
# order the item
if itemName not in self.item:
self.item[itemName] = len(self.item)
self.id2item[self.item[itemName]] = itemName
# userList.append
self.trainSet_u[userName][itemName] = rating
self.trainSet_i[itemName][userName] = rating
self.all_User.update(self.user)
self.all_Item.update(self.item)
for entry in self.testData:
userName, itemName, rating = entry
# order the user
if userName not in self.user:
self.all_User[userName] = len(self.all_User)
# order the item
if itemName not in self.item:
self.all_Item[itemName] = len(self.all_Item)
self.testSet_u[userName][itemName] = rating
self.testSet_i[itemName][userName] = rating
def __loadRatings(self, file, bTest=False):
if not bTest:
print 'load training data...'
else:
print 'load test data...'
with open(file) as f:
ratings = f.readlines()
#ignore the headline
if self.ratingConfig.contains('-header'):
ratings = ratings[1:]
#order of the columns
order = self.ratingConfig['-columns'].strip().split()
#split data
#userList= []
u_i_r = {}
i_u_r = {}
triple = []
#find the maximum rating and minimum value
for lineNo, line in enumerate(ratings):
items = split(' |,|\t', line.strip())
if len(order) < 3:
print 'The rating file is not in a correct format. Error: Line num %d' % lineNo
exit(-1)
userId = items[int(order[0])]
itemId = items[int(order[1])]
rating = items[int(order[2])]
if float(rating) > self.rScale[0]:
self.rScale[0] = float(rating)
if float(rating) < self.rScale[1]:
self.rScale[1] = float(rating)
for lineNo, line in enumerate(ratings):
items = split(' |,|\t', line.strip())
if len(order) < 3:
print 'The rating file is not in a correct format. Error: Line num %d' % lineNo
exit(-1)
userId = items[int(order[0])]
itemId = items[int(order[1])]
rating = items[int(order[2])]
#makes the rating within the range [0, 1].
normRating = normalize(float(rating), self.rScale[0],
self.rScale[1])
#order the user
if not self.user.has_key(userId):
self.user[userId] = len(self.user)
#order the item
if not self.item.has_key(itemId):
self.item[itemId] = len(self.item)
if not u_i_r.has_key(userId):
u_i_r[userId] = []
#userList.append(userId)
u_i_r[userId].append([itemId, float(rating)])
if not i_u_r.has_key(itemId):
i_u_r[itemId] = []
i_u_r[itemId].append([userId, float(rating)])
if not bTest:
self.triple.append([userId, itemId, normRating])
triple.append(
[self.user[userId], self.item[itemId], normRating])
if not bTest:
#contruct the sparse matrix
# data=[]
# indices=[]
# indptr=[]
# offset = 0
# for uid in userList:
# uRating = [r[1] for r in u_i_r[uid]]
# uColunms = [self.item[r[0]] for r in u_i_r[uid]]
# data += uRating
# indices += uColunms
# indptr .append(offset)
# offset += len(uRating)
# indptr.append(offset)
# return sparseMatrix.SparseMatrix(data, indices, indptr)
return new_sparseMatrix.SparseMatrix(triple)
else:
# return testSet
return u_i_r, i_u_r