def testSystem(F_list, step_list,LearnRating_list,penalty_list):
# 建立 用户 到 物品 的倒排表
trainDataSet = FO.readDataSet('trainDataSet.txt')
testDataSet = FO.readDataSet('testDataSet.txt')
user_items = dict()
for user_item, rating in trainDataSet.items():
user = user_item[0]
item = user_item[1]
if user not in user_items:
user_items[user] = list()
user_items[user].append((item, rating))
mu = calMu(trainDataSet)
for F in F_list:
for step in step_list:
for LearnRating in LearnRating_list:
for penalty in penalty_list:
bu, bi, p, q = LearningBiasLFM(user_items, trainDataSet, testDataSet, F, step, LearnRating, penalty, mu)
error = 0
for user_item, rating in testDataSet.items():
predictRating = Predict(user_item[0], user_item[1], p, q, bu, bi, mu)
error += (predictRating - rating) ** 2
RMSE = math.sqrt(error / len(testDataSet))
print('RMSE=%s' % RMSE)
with open('result_ItemCF.txt','a') as fileObject:
fileObject.write(str(F)+',')
fileObject.write(str(step)+',')
fileObject.write(str(LearnRating)+',')
fileObject.write(str(penalty)+',')
fileObject.write(str(mu)+',')
fileObject.write(str(RMSE)+'\n')
def initializeSystem(F_list, step_list, LearnRating_list, penalty_list):
trainDataSet = FO.readDataSet('trainDataSet.txt')
testDataSet = FO.readDataSet('testDataSet.txt')
dataSet = {**trainDataSet, **testDataSet}
mu = calMu(dataSet) #
user_items = dict()
for user_item, rating in dataSet.items():
user = user_item[0]
item = user_item[1]
if user not in user_items:
user_items[user] = list()
user_items[user].append((item, rating))
for F in F_list:
for step in step_list:
for LearnRating in LearnRating_list:
for penalty in penalty_list:
print(F, step, LearnRating, penalty)
bu, bi, p, q = LearningBiasLFM(user_items, dataSet, dict(), F, step, LearnRating, penalty,mu)
path = 'SVD++/Model_Parameter/' + str(F) + '-' + str(step) + '-' + str(LearnRating) + '-' + str(penalty)
if not os.path.exists(path):
os.makedirs(path)
FO.WriteBuDict(path, bu)
FO.WriteBiDict(path, bi)
FO.WritePDict(path, p, F)
FO.WriteQDict(path, q, F)
def fillMatrix(F_list, step_list, LearnRating_list, penalty_list, N = 30):
trainDataSet = FO.readDataSet('trainDataSet.txt')
testDataSet = FO.readDataSet('testDataSet.txt')
userList = FO.readUserList('data/users.txt')
itemList = FO.readItemList('data/movies.txt') # 获取物品列表
dataSet = {**trainDataSet, **testDataSet}
mu = calMu(dataSet)
for F in F_list:
for step in step_list:
for LearnRating in LearnRating_list:
for penalty in penalty_list:
print(F,step,LearnRating,penalty)
path = 'SVD++/Matrix/' + str(F) + '-' + str(step) + '-' + str(LearnRating) + '-' + str(penalty)
if not os.path.exists(path):
os.makedirs(path)
bu, bi, p, q = ReadParameter(F, step, LearnRating, penalty)
for user in userList:
print(user)
rank = dict()
userRated = set([user_item[1] for user_item, value in dataSet.items() if user_item[0] == user])
UnRatedList = itemList - userRated
for item in UnRatedList:
rating = Predict(user, item, p, q, bu, bi, mu)
if math.isnan(float(rating)):
continue
rank[item] = round(rating)
if len(rank) == 0:
continue
if N > len(UnRatedList):
N = len(UnRatedList)
chooseList = random.sample(UnRatedList, N)
with open(path + '/new_ratings.txt', 'a') as fileObject:
for choose in chooseList:
fileObject.write(str(user) + '::' + str(choose) + '::' + str(rank[choose]) + '\n')
def initializeSystem(F_list, step_list, LearnRating_list, penalty_list):
trainDataSet = FO.readDataSet('trainDataSet.txt')
testDataSet = FO.readDataSet('testDataSet.txt')
dataSet = {**trainDataSet, **testDataSet}
mu = calMu(dataSet)
for F in F_list:
for step in step_list:
for LearnRating in LearnRating_list:
for penalty in penalty_list:
print(F, step, LearnRating, penalty)
bu, bi, p, q = LearningBiasLFM(dataSet, dict(), F, step,
LearnRating, penalty, mu)
path = 'SVD/Model_Parameter/' + str(F) + '-' + str(
step) + '-' + str(LearnRating) + '-' + str(penalty)
if not os.path.exists(path):
os.makedirs(path)
FO.WriteBuDict(path, bu)
FO.WriteBiDict(path, bi)
FO.WritePDict(path, p, F)
FO.WriteQDict(path, q, F)
def calUserRatingMean(dataSet):
userList = FO.readUserList('data/users.txt')
userMeanDict = dict()
for user in userList:
print(user)
UserRating = [
value for user_item, value in dataSet.items()
if user_item[0] == user
]
userMeanDict[user] = sum(UserRating) / len(UserRating)
return userMeanDict
if __name__ == '__main__':
trainDataSet = FO.readDataSet('trainDataSet.txt')
testDataSet = FO.readDataSet('testDataSet.txt')
#addDataSet = FO.readDataSet('SVD++/Matrix/5-5-0.01-0.1/new_ratings.txt')
trainDataSet = {**trainDataSet, **testDataSet}
userMeanDict = calUserRatingMean(trainDataSet)
FO.WirteRatingMean('UserCF/UserMean/DataSetUserRating_mean.txt',
userMeanDict)
#calUserSimilarity(trainDataSet)
'''
userList = FO.readUserList('data/users.txt')
userMeanDict =calUserRatingMean(trainDataSet)
FO.WirteUserRatingMean('trainDataSetUserRatingMean.txt',userMeanDict)
data = FO.readFromFile('data/ratings.txt', 'ratings')
allUserMeanDict = calUserRatingMean(data)
trainDataSet = FO.readDataSet('UserCF/trainDataSet.txt')
testDataSet = FO.readDataSet('UserCF/testDataSet.txt')
calUserSimilarity(trainDataSet,'explicit',cosSim)
'''
'''
trainDataSet = FO.readDataSet('UserCF/trainDataSet.txt')
testDataSet = FO.readDataSet('UserCF/testDataSet.txt')
itemList = FO.readItemList('data/movies.txt')
rank = predictSystem(trainDataSet, testDataSet, 1, itemList)
print(rank)
'''
timeList = [] # 记录程序运行时间
timeList.append(datetime.datetime.now())
# 加载数据
trainDataSet = FO.readDataSet('UserCF/trainDataSet.txt')
testDataSet = FO.readDataSet('UserCF/testDataSet.txt')
KList = [10, 20, 30, 40]
NList = [10, 20, 30, 40]
type_list = ['implicit', 'cosSim', 'ecludSim']
for type in type_list:
for k in KList:
for n in NList:
recall, precision, coverage, popularity = testSystem(
trainDataSet, testDataSet, K=k, N=n, type=type)
with open('UserCF/Result/result_' + type + '.txt',
'a') as fileObject:
fileObject.write(
str(k) + ',' + str(n) + ',' + str(recall) + ',' +
str(precision) + ',' + str(coverage) + ',' +
str(popularity) + '\n')
W = FO.readItemSimilarity(item, type) # 获取当前用户与其他用户的相似度
topItem = dict(
sorted(W.items(), key=operator.itemgetter(1),
reverse=True)[:K])
topSimItem = set([items[1] for items, value in topItem.items()])
topLoveItem = userLove & topSimItem
if len(topLoveItem) == 0:
continue
# print(topLoveItem)
for LoveItem in topLoveItem:
wji = W[item, LoveItem]
rui = dataSet[user, LoveItem]
rank[item] = rank.get(item, 0) + wji * rui
return dict(
sorted(rank.items(), key=operator.itemgetter(1), reverse=True)[:N])
if __name__ == '__main__':
trainDataSet = FO.readDataSet('ItemCF/trainDataSet.txt')
testDataSet = FO.readDataSet('ItemCF/testDataSet.txt')
'''
calItemSimilarity(trainDataSet, 'implicit') # 计算隐式相似度
calItemSimilarity(trainDataSet, 'explicit', cosSim) # 以余弦相似度计算显式相似度
calItemSimilarity(trainDataSet, 'explicit', ecludSim) # 以欧氏距离计算显式相似度
'''
itemList = FO.readItemList('data/movies.txt')
for i in range(1, 11):
rank = predictSystem(trainDataSet, testDataSet, i, itemList)
print(rank)
value = sum(itemRating) / len(itemRating)
itemMeanDict[item] = value
return itemMeanDict
def calUserRatingMean(dataSet):
userList = FO.readUserList('data/users.txt')
userMeanDict = dict()
for user in userList:
print(user)
UserRating = [value for user_item, value in dataSet.items() if user_item[0] == user]
userMeanDict[user] = sum(UserRating) / len(UserRating)
return userMeanDict
if __name__ == '__main__':
trainDataSet = FO.readDataSet('trainDataSet.txt')
testDataSet = FO.readDataSet('testDataSet.txt')
addDataSet = FO.readDataSet('SVD++/Matrix/10-10-0.01-0.1/new_ratings.txt')
trainDataSet = {**trainDataSet, **addDataSet}
itemMeanDict = calItemRatingMean(trainDataSet)
FO.WirteRatingMean('ItemCF/ItemMean/add_trainDataSet_mean.txt', itemMeanDict)
userMeanDict = calUserRatingMean(trainDataSet)
FO.WirteRatingMean('ItemCF/UserMean/trainDataSet_mean.txt', userMeanDict)
calItemSimilarity(trainDataSet)
'''
itemMeanDict = calItemRatingMean(trainDataSet)