def CFZ(self):
u_id = []
I_id = []
r_ui_ = np.array([])
_est = np.array([])
sim_options = {'name': 'cosine', 'user_based': True}
algo = KNNWithZScore(k=40, min_k=1, sim_options=sim_options)
algo.fit(self.trainset)
for uid in (self.list):
lids = self.data[self.data.uid == uid]
a = self.data[self.data.uid == uid]
for i in range(1, len(a)):
lid = lids[i - 1:i].lid.values[0]
r_ui = lids[i - 1:i].rate.values[0]
pred = algo.predict(uid, lid, r_ui, verbose=True)
u_id.append(int(pred.uid))
I_id.append(int(pred.iid))
r_ui_ = np.append(r_ui_, pred.r_ui)
_est = np.append(_est, pred.est)
self.df_est = pd.DataFrame({
'uid': u_id,
'Iid': I_id,
'r_ui': r_ui_,
'est': _est
})
self.arr = self.df_est['uid'].unique()
self.CFWZ_ndcg_ = self.Calculate_NDCG()
def collab_recommender(train_data,
test_data,
user_based=True,
normalization=False,
k=100,
sim='cosine'):
"""
Input:
- train_data: dataframe, n*3, columns are ['userid','movieid','rating']
- test_data: dataframe, n*2, columns are ['userid', 'movieid']
- user_base: boolean, use user-based knn algorithm if True, use item-based knn algorithm if False
- normalization: boolean, conduct z-score normalization on user/item matrix if True
- k: int, number of nearest neighbors
- sim: string, define the similarity matrix from ['cosine', 'pearson', 'msd', 'pearson_baseline']
Output:
- pred_rating: dataframe, n*2, columns are ['movieid', 'rating']
"""
try:
function_log.trace('Start collaborative recommendation function')
reader = Reader(rating_scale=(1, 5))
data = Dataset.load_from_df(train_data, reader)
sim_options = {'name': sim, 'user_based': user_based}
if normalization:
algo = KNNWithZScore(k=k, sim_options=sim_options, verbose=False)
else:
algo = KNNWithMeans(k=k, sim_options=sim_options, verbose=False)
train_set = data.build_full_trainset()
algo.fit(train_set)
pred_rating = {'movieid': [], 'rating': []}
for idx in test_data.index:
pred_rating['movieid'].append(test_data.loc[idx, 'movieid'])
pred = algo.predict(test_data.loc[idx, 'userid'],
test_data.loc[idx, 'movieid'])
pred_rating['rating'].append(pred.est)
function_log.trace('Finish collaborative recommendation function')
return pd.DataFrame(pred_rating)
except ValueError:
function_log.warn("Training and test data cannot be none.")
raise ValueError
except Exception as x:
function_log.exception(
f'collaborative recommendation function failed {x}')
def CFZ(self):
sim_options = {'name': 'cosine', 'user_based': True}
algo = KNNWithZScore(k=40, min_k=1, sim_options=sim_options)
algo.fit(self.trainset)
for uid in (self.list):
lids = self.data[self.data.uid == uid]
a = self.data[self.data.uid == uid]
for i in range(1, len(a)):
lid = lids[i - 1:i].lid.values[0]
r_ui = lids[i - 1:i].rate.values[0]
pred = algo.predict(uid, lid, r_ui, verbose=True)
return pred
def computeKNNZScoreMovie(data, test_np):
"""Compute the k-NN with z score item based method and return the predictions on the test
The method is on all the data and got the following settings:
- Similarity function : Pearson baseline, item based
- Number of closest neighbors : 108
data : data frame which represent the train set
test_np : data frame on which the prediction will be returned
return : test_np with a column of prediction named 'knnzscore_item_rating'"""
trainset, test = dataTrainSurprise(data, test_np)
sim_options = {'name':'pearson_baseline','user_based': False}
knnz_algo = KNNWithZScore(k = 108, sim_options =sim_options).fit(trainset)
test['knnzscore_item_rating'] = test[['user_id', 'movie_id']] \
.apply(lambda row: knnz_algo.predict(row['user_id'], row['movie_id'])[3], axis=1)
return test
r_ui1 = 4
r_ui2 = 4
r_ui3 = 1
r_ui4 = 3
verboseFlag = True
# get a prediction for specific users and items.
print("KNNBaseLine:")
predBaseLine1 = algoBaseLine.predict(uid1, iid1, r_ui = r_ui1, verbose = verboseFlag)
predBaseLine2 = algoBaseLine.predict(uid2, iid2, r_ui = r_ui2, verbose = verboseFlag)
predBaseLine3 = algoBaseLine.predict(uid3, iid3, r_ui = r_ui3, verbose = verboseFlag)
predBaseLine4 = algoBaseLine.predict(uid4, iid4, r_ui = r_ui4, verbose = verboseFlag)
print("\nKNNBasic:")
predBasic1 = algoBasic.predict(uid1, iid1, r_ui = r_ui1, verbose = verboseFlag)
predBasic2 = algoBasic.predict(uid2, iid2, r_ui = r_ui2, verbose = verboseFlag)
predBasic3 = algoBasic.predict(uid3, iid3, r_ui = r_ui3, verbose = verboseFlag)
predBasic4 = algoBasic.predict(uid4, iid4, r_ui = r_ui4, verbose = verboseFlag)
print("\nKNNWithMeans:")
predWithMeans1 = algoWithMeans.predict(uid1, iid1, r_ui = r_ui1, verbose = verboseFlag)
predWithMeans2 = algoWithMeans.predict(uid2, iid2, r_ui = r_ui2, verbose = verboseFlag)
predWithMeans3 = algoWithMeans.predict(uid3, iid3, r_ui = r_ui3, verbose = verboseFlag)
predWithMeans4 = algoWithMeans.predict(uid4, iid4, r_ui = r_ui4, verbose = verboseFlag)
print("\nKNNWithZScore:")
predWithZScore1 = algoWithZScore.predict(uid1, iid1, r_ui = r_ui1, verbose = verboseFlag)
predWithZScore2 = algoWithZScore.predict(uid2, iid2, r_ui = r_ui2, verbose = verboseFlag)
predWithZScore3 = algoWithZScore.predict(uid3, iid3, r_ui = r_ui3, verbose = verboseFlag)
predWithZScore4 = algoWithZScore.predict(uid4, iid4, r_ui = r_ui4, verbose = verboseFlag)
predWithMeans2 = algoWithMeans.predict(uid2,
iid2,
r_ui=r_ui2,
verbose=verboseFlag)
predWithMeans3 = algoWithMeans.predict(uid3,
iid3,
r_ui=r_ui3,
verbose=verboseFlag)
predWithMeans4 = algoWithMeans.predict(uid4,
iid4,
r_ui=r_ui4,
verbose=verboseFlag)
print("\nKNNWithZScore:")
predWithZScore1 = algoWithZScore.predict(uid1,
iid1,
r_ui=r_ui1,
verbose=verboseFlag)
predWithZScore2 = algoWithZScore.predict(uid2,
iid2,
r_ui=r_ui2,
verbose=verboseFlag)
predWithZScore3 = algoWithZScore.predict(uid3,
iid3,
r_ui=r_ui3,
verbose=verboseFlag)
predWithZScore4 = algoWithZScore.predict(uid4,
iid4,
r_ui=r_ui4,
verbose=verboseFlag)
algo3 = KNNWithMeans(k=40, min_k=1, sim_options=sim_options2, verbose=True)
algo3.fit(data_train.build_full_trainset())
pred1 = []
pred_f1 = []
pred2 = []
pred_f2 = []
pred3 = []
pred_f3 = []
with open("./data/testing.dat", "r", encoding='utf-8') as f:
for line in f.readlines():
line_data = line.strip().split(",")
a = algo1.predict(str(line_data[0]), str(line_data[1]), None, True,
True)[3]
b = algo2.predict(str(line_data[0]), str(line_data[1]), None, True,
True)[3]
c = algo3.predict(str(line_data[0]), str(line_data[1]), None, True,
True)[3]
pred1.append(int(round(a)))
pred_f1.append(a)
pred2.append(int(round(b)))
pred_f2.append(b)
pred3.append(int(round(c)))
pred_f3.append(c)
with open("./雷雨轩_PB18111791_4.txt", "w") as f:
for ratings in pred1:
f.write(str(ratings) + "\n")
with open("./4_float.txt", "w") as f:
for ratings in pred_f1:
pred1 = algo1.predict(uid, iid, verbose=True)
#KNNWithMeans
algo2 = KNNWithMeans(k=30,
sim_options={
'name': 'cosine',
'user_based': False
},
verbose=True)
algo2.fit(trainset)
pred2 = algo2.predict(uid, iid, verbose=True)
#KNNWithZScore f
algo3 = KNNWithZScore(k=30,
sim_options={
'name': 'MSD',
'user_based': True
},
verbose=True)
algo3.fit(trainset)
pred3 = algo3.predict(uid, iid, verbose=True)
#KNNBaseline
algo4 = KNNBaseline(k=30,
sim_options={
'name': 'MSD',
'user_based': True
},
verbose=True)
algo4.fit(trainset)
pred4 = algo4.predict(uid, iid, verbose=True)
reader = Reader(line_format='user item rating timestamp',
sep=',',
skip_lines=1)
data = Dataset.load_from_file('./ratings.csv', reader=reader)
train_set = data.build_full_trainset()
from surprise import KNNWithZScore
algo = KNNWithZScore(k=50,
sim_options={
'user_based': False,
'verbose': 'True'
})
algo.fit(train_set)
uid = str(196)
iid = str(332)
pred = algo.predict(uid, iid, r_ui=4, verbose=True)
kf = KFold(n_splits=3)
for trainset, testset in kf.split(data):
algo.fit(trainset)
predictions = algo.test(testset)
#计算RMSE,AME
accuracy.rmse(predictions, verbose=True)
accuracy.mae(predictions, verbose=True)
### 使用协同过滤正态分布 User based
from surprise import KNNWithZScore
algo = KNNWithZScore(k=50,
sim_options={
'user_based': False,
'verbose': 'True'
