else:
predict_rating = unnormalized_predict_rating / norm_similarity
return predict_rating
def Evaluation_CF_to_predict_rating(train, test, K):
sum_squared_error = 0.0
rmse = 0.0
W = userSimilarityRating(train)
count = 0
print "Evaluation"
for user in train.keys():
if user in test.keys():
test_user_item = test[
user] #key: item , value: rating user to item
for itemi in test_user_item.keys():
predict_rating = UserCF_to_predict_raring(
user, itemi, train, W, K)
if predict_rating != -1:
count += 1
real_rating = test[user][itemi]
rmse += (predict_rating - real_rating)**2
print "predict number:", count
rmse = np.sqrt(rmse / count)
return rmse
if __name__ == "__main__":
data = dp.readMoiveIdRatingFromRatings("ratings.dat", "::")
trainData, testData = dp.splitRatingData(data)
print Evaluation_CF_to_predict_rating(trainData, testData, 20)
def Evaluation_CF_rating(train, test, N):
hit = 0
totalTestItemNum = 0.0
totalRecommendationNum = 0.0
W = userSimilarityRating(train)
print "Evaluation"
for user in train.keys():
if user in test.keys():
test_user_item = test[user]
totalTestItemNum += len(test_user_item)
recommendationList = RatingUserCFRecommencd(user, train, W)
recommendationList = [
recomItem[0] for recomItem in recommendationList
]
if len(
recommendationList
) > N: #If the recommendation list's length is larger than N
recommendationList = recommendationList[0:N]
totalRecommendationNum += N
else:
totalRecommendationNum += len(recommendationList)
for itemi in recommendationList:
if itemi in test_user_item:
hit += 1
return hit * 1.0 / totalTestItemNum, hit * 1.0 / totalRecommendationNum
if __name__ == "__main__":
data = dp.readMoiveIdRatingFromRatings()
trainData, testData = dp.splitRatingData(data)
print Evaluation_CF_rating(trainData, testData, 7)
return sorted(recomList.items(), key = lambda x:x[1], reverse=True)
def Evaluation_CF_rating(train, test, N):
hit = 0
totalTestItemNum = 0.0
totalRecommendationNum = 0.0
W = userSimilarityRating(train)
print "Evaluation"
for user in train.keys():
if user in test.keys():
test_user_item = test[user]
totalTestItemNum += len(test_user_item)
recommendationList = RatingUserCFRecommencd(user,train,W)
recommendationList = [recomItem[0] for recomItem in recommendationList]
if len(recommendationList)>N: #If the recommendation list's length is larger than N
recommendationList = recommendationList[0:N]
totalRecommendationNum += N
else:
totalRecommendationNum += len(recommendationList)
for itemi in recommendationList:
if itemi in test_user_item:
hit += 1
return hit*1.0/totalTestItemNum,hit*1.0/totalRecommendationNum
if __name__ == "__main__":
data = dp.readMoiveIdRatingFromRatings()
trainData, testData = dp.splitRatingData(data)
print Evaluation_CF_rating(trainData, testData, 7)
if count < K/2:
return -1 #cant predict, here can be replaced by the average value of the item get
else:
predict_rating = unnormalized_predict_rating/norm_similarity
return predict_rating
def Evaluation_CF_to_predict_rating(train, test, K):
sum_squared_error = 0.0
rmse = 0.0
W = userSimilarityRating(train)
count = 0
print "Evaluation"
for user in train.keys():
if user in test.keys():
test_user_item = test[user] #key: item , value: rating user to item
for itemi in test_user_item.keys():
predict_rating = UserCF_to_predict_raring(user,itemi,train,W,K)
if predict_rating != -1:
count += 1
real_rating = test[user][itemi]
rmse += (predict_rating - real_rating)**2
print "predict number:", count
rmse = np.sqrt(rmse/count)
return rmse
if __name__ == "__main__":
data = dp.readMoiveIdRatingFromRatings("ratings.dat","::")
trainData, testData = dp.splitRatingData(data)
print Evaluation_CF_to_predict_rating(trainData, testData, 20)
