def getAllUserRating(n=1,k=20, similarity=sim_pearson):
if(n==1):
traindata = loadMovieLensTrain('ml-100k/u1.base') # 加载训练集
testdata = loadMovieLensTest('ml-100k/u1.test') # 加载测试集
else:
pivot = 0.7
traindata={}
testdata={}
for line in loadfile('ml-1m/ratings.dat'):
user, movie, rating, _ = line.split('::')
# split the data by pivot
if (random.random() < pivot):
traindata.setdefault(user, {})
traindata[user][movie] = int(rating)
else:
testdata.setdefault(user, {})
testdata[user][movie] = int(rating)
inAllnum = 0
records=[]
for userid in testdata: # test集中每个用户
for item in testdata[userid]: # 对于test集合中每一个项目用base数据集,CF预测评分
rating = getRating(traindata, userid, item, k) # 基于训练集预测用户评分(用户数目<=K)
records.append([userid,item,testdata[userid][item],rating])
inAllnum = inAllnum + 1
#np.savetxt("records.txt",records,fmt='%1.4e')
#print("-------------Completed!!-----------", inAllnum)
SaveRecords(records)
return records
def getAllUserRating(fileTrain='u1.base', fileTest='u1.test',k=20, similarity=sim_pearson):
traindata = loadMovieLensTrain(fileTrain) # 加载训练集
testdata = loadMovieLensTest(fileTest) # 加载测试集
inAllnum = 0
records=[]
for userid in testdata: # test集中每个项目
for item in testdata[userid]: # 对于test集合中每一个项目用base数据集,CF预测评分
rating = getRating(traindata, userid, item, k) # 基于训练集预测用户评分(用户数目<=K)
records.append([userid,item,testdata[userid][item],rating])
inAllnum = inAllnum + 1
#np.savetxt("records.txt",records,fmt='%1.4e')
print("-------------Completed!!-----------", inAllnum)
return records
def getAllUserRating(trainfile, testfile, k=20, similarity=sim_pearson):
traindata = loadMovieLensTrain(trainfile) # 加载训练集
testdata = loadMovieLensTest(testfile) # 加载测试集
inAllnum = 0
records = []
for userid in testdata: # test集中每个用户
for item in testdata[userid]: # 对于test集合中每一个项目用base数据集,CF预测评分
rating = getRating(traindata, userid, item, k,
similarity) # 基于训练集预测用户评分(用户数目<=K)
records.append([userid, item, testdata[userid][item], rating])
inAllnum = inAllnum + 1
SaveRecords(records)
return records
def getAllUserRating(fileTrain='u1.base', fileTest='u1.test', fileResult='result.txt', similarity=sim_pearson):
prefer1 = loadMovieLensTrain(fileTrain) # 加载训练集
prefer2 = loadMovieLensTest(fileTest) # 加载测试集
inAllnum = 0
file = open(fileResult, 'a')
file.write("%s\n"%("------------------------------------------------------"))
for userid in prefer2: #test集中每个用户
for item in prefer2[userid]: #对于test集合中每一个项目用base数据集,CF预测评分
rating = getRating(prefer1, userid, item, 20) #基于训练集预测用户评分(用户数目<=K)
file.write('%s\t%s\t%s\n'%(userid, item, rating))
inAllnum = inAllnum +1
file.close()
print("-------------Completed!!-----------", inAllnum)
def getAllUserRating(fileTrain='u1.base',
fileTest='u1.test',
fileResult='result.txt',
similarity=sim_pearson):
prefer1 = loadMovieLensTrain(fileTrain)
prefer2 = loadMovieLensTest(fileTest)
inAllnum = 0
file = open(fileResult, 'a')
file.write("%s\n" %
("------------------------------------------------------"))
for userid in prefer2:
for item in prefer2[userid]:
rating = getRating(
prefer1, userid, item,
20) # predict the user's rating based on the train data
file.write('%s\t%s\t%s\n' % (userid, item, rating))
inAllnum = inAllnum + 1
file.close()
print("-------------Completed!!-----------", inAllnum)
def readData(self, train=None, test=None):
self.trainfile = train or self.trainfile
self.testfile = test or self.testfile
self.traindata = loadMovieLensTrain(train) # 加载训练集
self.testdata = loadMovieLensTest(test) # 加载测试集
def loadMovieLensResult(fileName='result.txt'):
str1 = './' # 目录的相对地址
prefer = {}
for line in open(str1 + fileName, 'r'): # 打开指定文件
(userid, movieid, rating) = line.split('\t') # 数据集中每行有4项 用户id 、项目 id 、 评分
prefer.setdefault(userid, {}) # 设置字典的默认格式,元素是user:{}字典
prefer[userid][movieid] = float(rating)
return prefer # 格式如{'user1':{itemid:rating, itemid2:rating, ,,}, {,,,}}
if __name__ == "__main__":
print("\n--------------准确率生成中 -----------\n")
count = 0
win_count = 0
prefer_result = loadMovieLensResult()
prefer_test = loadMovieLensTest()
for item_1 in prefer_result:
for item_2 in prefer_test:
if item_1 == item_2:
for item1 in prefer_result[item_1]:
for item2 in prefer_test[item_2]:
if item1 == item2:
dis = abs(prefer_result[item_1][item1] - prefer_test[item_2][item2])
if dis < 1:
win_count += 1
count += 1
print('准确率为：' + str(float(win_count)/count))
print('预测次数为：' + str(count))
print('正确预测次数为：' + str(win_count))
