def SlopeOne_train(self):
'''
seed：int-3划分训练集测试集的随机种子
k：int-40，最大邻居数量
options：dict-{'name': 'pearson', 'user_based': False}，算法的选项，默认为Pearson相似度，基于项目的方法
'''
self.algos = []
df = self.trainDatas
names = locals()
r = Reader(rating_scale=(1, 5))
# 读取、划分数据;训练预测数据
total = Dataset.load_from_df(df[['uid', 'iid', 'total']], reader=r)
total_train = total.build_full_trainset()
total_algo = SlopeOne()
total_algo.fit(total_train)
self.algos.append(total_algo)
for i in range(1, self.no_of_criteria + 1):
names['c' + str(i)] = Dataset.load_from_df(
df[['uid', 'iid', 'c' + str(i)]], reader=r)
names['c' + str(i) +
'_train'] = names.get('c' + str(i)).build_full_trainset()
names['algo_c' + str(i)] = SlopeOne()
names.get('algo_c' + str(i)).fit(names.get('c' + str(i) +
'_train'))
self.algos.append(names.get('algo_c' + str(i)))
def slope_one(test, train, all):
start = time.time()
reader = Reader(rating_scale=(0.5, 5))
data = Dataset.load_from_df(train[['userId', 'movieId', 'rating']], reader)
test_data = Dataset.load_from_df(test[['userId', 'movieId', 'rating']],
reader)
trainset = data.build_full_trainset()
testset = test_data.build_full_trainset().build_testset()
algo = SlopeOne()
algo.fit(trainset)
fit = time.time()
fit_time = fit - start
predictions = algo.test(testset)
uid = []
mid = []
rate = []
for i in range(len(predictions)):
uid.append(predictions[i].uid)
mid.append(predictions[i].iid)
rate.append(predictions[i].est)
out = {'userId': uid, 'movieId': mid, 'rating': rate}
out = pd.DataFrame.from_dict(out)
predict_time = time.time() - fit
overall = predict_time + fit - start
return out, [fit_time, predict_time, overall]
def surprise_slopeOne(train_file, test_file):
"""
SlopeOne with Surprise library.
Compute the predictions on a test_set after training on a train_set using the method SlopeOne from Surprise.
Args:
train_file (string): path to created test file
test_file (string): path to created train file
Hyperparameters:
-
Returns:
numpy array: predictions
"""
print("slopeone")
algo = SlopeOne()
fold = [(train_file, test_file)]
reader = Reader(line_format='user item rating', sep=',')
data = Dataset.load_from_folds(fold, reader=reader)
pkf = PredefinedKFold()
for trainset, testset in pkf.split(data):
# Train
algo.fit(trainset)
# Predict
predictions = algo.test(testset)
pred = np.zeros(len(predictions))
for i in range(len(predictions)):
val = predictions[i].est
pred[i] = val
return pred
def SlopeOne_alg():
print('Using SlopeOne')
alg = SlopeOne()
print(alg)
alg.fit(trainset)
predictions = alg.test(testset)
print(accuracy.rmse(predictions))
def get(self, user_id):
# SQL query
conn = mysql.connect()
cursor = conn.cursor()
df = pd.read_sql_query("SELECT * FROM story_reviews", conn)
# Data and Model
reader = Reader(rating_scale=(1, 5))
data = Dataset.load_from_df(df[['user_id', 'story_id', 'star']], reader)
model = SlopeOne()
# Training
training_set = data.build_full_trainset()
model.fit(training_set)
# Prediction
anti_training_set = training_set.build_anti_testset()
prediction_set = [x for x in anti_training_set if x[0]==user_id]
predictions = model.test(prediction_set)
# Return Top N Recommendations
n = 10
predictions.sort(key=lambda x:x.est, reverse=True)
top_n_predictions = predictions[:n]
story_recommendations = []
for predictionItem in top_n_predictions:
story_recommendations.append(predictionItem.iid)
return jsonify(recommendations = story_recommendations)
def slopeOne(trainset, testset):
# Slope One
print("\n" + "-" * 5 + " SlopeOne algorithm using surprise package " +
"-" * 5)
algo = SlopeOne()
algo.fit(trainset)
predictions = algo.test(testset)
rmse = accuracy.rmse(predictions)
mae = accuracy.mae(predictions)
return rmse, mae, predictions
def SlopeOne(self, namefile, uid, iid, rati, value_uid, value_iid):
test_data = pd.read_csv('./container/' + namefile)
dt = pd.DataFrame(test_data)
# Retrieve the trainset.
reader = Reader(rating_scale=(0, 100))
data = Dataset.load_from_df(dt[[uid, iid, rati]], reader)
trainset = data.build_full_trainset()
algo = SlopeOne()
algo.fit(trainset)
pred = algo.predict(float(value_uid),
float(value_iid),
r_ui=1,
verbose=True)
#var_rmse = accuracy.rmse(pred)
#return result to json
jsondata = {}
jsondata["uid"] = pred.uid
jsondata["idd"] = pred.iid
jsondata["rati"] = round(pred.est, 2)
return jsondata
def SlopeOne_from_to(self, namefile, uid, iid, rati, from_uid, to_uid,
from_iid, to_iid):
test_data = pd.read_csv('./container/' + namefile)
dt = pd.DataFrame(test_data)
# Retrieve the trainset.
reader = Reader(rating_scale=(0, 100))
data = Dataset.load_from_df(dt[[uid, iid, rati]], reader)
trainset = data.build_full_trainset()
algo = SlopeOne()
algo.fit(trainset)
arr = []
for value_uid in range(from_uid, to_uid):
for value_iid in range(from_iid, to_iid):
pred = algo.predict(value_uid, value_iid, r_ui=1, verbose=True)
tempdata = []
tempdata.append(pred.uid)
tempdata.append(pred.iid)
tempdata.append(round(pred.est, 2))
arr.append(tempdata)
#return result to json
return arr
def slopeone(train, test, ids, Xtest, Xids):
"""
Item based algorithm, reduces overfitting
Argument : train, the trainset
test, the testset
ids, unknown ratings
Xtest, predicted ratings for testset, to be used for final blending
Xids, predicted ratings for unknown ratings, to be used for final blending
"""
print('SlopeOne')
algo = SlopeOne()
#Train algorithm on training set
algo.fit(train)
#Predict on train and compute RMSE
predictions = algo.test(train.build_testset())
print(' Training RMSE: ', accuracy.rmse(predictions, verbose=False))
#Predict on test and compute RMSE
predictions = algo.test(test)
rmse = accuracy.rmse(predictions, verbose=False)
print(' Test RMSE: ', rmse)
preds_test = np.zeros(len(predictions))
for j, pred in enumerate(predictions):
preds_test[j] = pred.est
#Predict unknown ratings
preds_ids = []
for i in range(len(ids[0])):
pred = algo.predict(str(ids[0][i]), str(ids[1][i]))
preds_ids.append(pred.est)
Xtest.append(preds_test)
Xids.append(preds_ids)
return rmse, Xtest, Xids, preds_test, preds_ids
def slope_one(self):
"""
SlopeOne to reflect how much one item is liked over than another.
Returns:
predictions_df: The predictions of the model on the test data in
Pandas Data Frame format
"""
algorithm = SlopeOne()
predictions = algorithm.fit(self.train_data).test(self.test_data)
predictions_df = self.data.test_df.copy()
predictions_df['Rating'] = [x.est for x in predictions]
if self.test_purpose:
self.evalueate_model(predictions_df['Rating'], 'Surprise slope_one')
return predictions_df
def fit_slopeone(trainset):
logging.info(f'Recommendation System: Fit model - SlopeOne')
model = SlopeOne()
model_fitted = model.fit(trainset)
return model_fitted
from surprise import accuracy
from surprise.model_selection import KFold
import pandas as pd
import io
import pandas as pd
# 读取物品（电影）名称信息
def read_item_names():
file_name = ('./movies.csv')
data = pd.read_csv('./movies.csv')
rid_to_name = {}
name_to_rid = {}
for i in range(len(data['movieId'])):
rid_to_name[data['movieId'][i]] = data['title'][i]
name_to_rid[data['title'][i]] = data['movieId'][i]
return rid_to_name, name_to_rid
# 数据读取
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()
# 使用SlopeOne算法
algo = SlopeOne()
algo.fit(train_set)
# 对指定用户和商品进行评分预测
uid = str(196)
iid = str(302)
pred = algo.predict(uid, iid, r_ui=4, verbose=True)
# #### Run cross-validation with the best algo (in the specific case SlopeOne)
# In[14]:
# SlopeOne algorithm gave us the best rmse, therefore, we will train and predict with SlopeOne
print('Executing SlopeOne')
algo = SlopeOne()
cross_validate(algo, data, measures=['RMSE'], cv=3, verbose=False)
# #### Train and test the chosen algorithm
# In[15]:
trainset, testset = s_train_test_split(data, test_size=0.25)
predictions = algo.fit(trainset).test(testset)
accuracy.rmse(predictions)
# #### Get detailed results for predictions/recommendations
# In[16]:
# inspect our predictions in details
def get_Iu(uid):
""" return the number of items clicked by given user
args:
uid: the id of the user
returns:
the number of items clicked by the user
from surprise import Dataset
from surprise import accuracy
from surprise import SlopeOne
from surprise.model_selection import train_test_split
# Load the movielens-100k dataset UserID::MovieID::Rating::Timestamp
data = Dataset.load_builtin('ml-1m')
trainset, testset = train_test_split(data, test_size=.15)
# Configura o algoritmo. K = número de vizinhos. Name = Tipo de medida de similiradade. User based = filtragem por usuário ou item.
print("Usando o algoritmo SlopeOne")
algoritmo = SlopeOne()
algoritmo.fit(trainset)
# Selecionamos o usuário e o filme que será analisado
# User 49. Tem entre 18 e 24 anos. É programador e mora em Huston, Texas
uid = str(49)
# Filme visto e avaliado: Negotiator, The (1998)::Action|Thriller. Avaliação 4
iid = str(2058) # raw item id
# get a prediction for specific users and items.
print("Predição de avaliação: ")
pred = algoritmo.predict(uid, iid, r_ui=4, verbose=True)
# run the trained model against the testset
test_pred = algoritmo.test(testset)
# Avalia RMSE
start = time.time()
alg_SVD.fit(data_train.build_full_trainset())
end = time.time()
print("***********************************************")
print("Exe time:")
print(end - start)
# %% Best Hyper-parameters Training - Slope One
alg_SL1 = SlopeOne()
start = time.time()
alg_SL1.fit(data_train.build_full_trainset())
end = time.time()
print("***********************************************")
print("Exe time:")
print(end - start)
# %% Best Hyper-parameters Training - KNN
sim_options = {
'name': 'msd',
'user_based': True # compute similarities between users
}
alg_KNN = KNNBasic(sim_options=sim_options)
start = time.time()
listOfRMSE.append(accuracy.rmse(predictionscoClustering))
models.append('CoClustering')
# ## SlopeOne Implementation
# In[89]:
from surprise import SlopeOne
slopeOne = SlopeOne()
# Train the algorithm on the trainset, and predict ratings for the testset
trainsetslopeOne = dataCoClustering.build_full_trainset()
slopeOne.fit(trainsetslopeOne)
testslopeOne = trainsetslopeOne.build_anti_testset()
predictionsslopeOne = slopeOne.test(testslopeOne)
accuracy.rmse(predictionsslopeOne)
listOfRMSE.append(accuracy.rmse(predictionsslopeOne))
models.append('SlopeOne')
# In[91]:
models
for i in range(5):
movieRecc = topMovies[i]
movieRawID = movieRecc[0]
movieName = movie[movieRawID]
print(str(i+1) + '. ' + movieName )
#################predictions using Slope-One
print('')
print('Making more recommendations...')
algo2 = SlopeOne()
algo2.fit(trainset)
predictions2 = algo2.test(testset)
dictMovies2 = get_top_n(predictions2)
topMovies2 = dictMovies2.get(672)
print('')
print('Here are the top 5 recommendations based on Slope-One! ')
for i in range(5):
movieRecc2 = topMovies2[i]
movieRawID2 = movieRecc2[0]
movieName2 = movie[movieRawID2]
print(str(i+1) + '. ' + movieName2 )
# coding=utf-8
from surprise import Dataset
from surprise import Reader
from surprise import accuracy
from surprise import NMF
from surprise import SlopeOne
from surprise.model_selection import train_test_split
from surprise import dump
filePath = r'E:\library\Final_lib\collaboration\coll2.csv'
reader = Reader(line_format='user item rating', sep=',', rating_scale=(1, 5))
data = Dataset.load_from_file(filePath, reader=reader)
trainset, testset = train_test_split(data, test_size=0.2)
# algo = BaselineOnly()
# algo.fit(trainset)
algo = SlopeOne()
algo.fit(trainset)
predictions = algo.test(testset)
accuracy.mae(predictions)
accuracy.rmse(predictions)
accuracy.fcp(predictions)
dump.dump(r'E:\library\Final_lib\collaboration\ungrouped_algo\SlopeOne.txt',
predictions=predictions,
algo=algo)
'''
from surprise import accuracy
from surprise import Dataset
from surprise import SlopeOne
from surprise.model_selection import train_test_split
# 加载movielens-100k数据集
data = Dataset.load_builtin('ml-100k')
# 训练集和测试集划分
train, test = train_test_split(data, test_size=.15)
# SlopeOne算法
slope = SlopeOne()
slope.fit(train)
# 预测第222用户对第750电影评分
uid = str(222)
iid = str(750)
pred = slope.predict(uid, iid, r_ui=5, verbose=True)
# ######结果如下######
# user: 222
# item: 750
# r_ui = 5.00
# est = 3.97
# {'was_impossible': False}
# 预测第222用户对第750电影评分为3.97
test_pred = slope.test(test)