lr = LogisticRegression(C=0.1, penalty='l2')
lr.fit(train_X_lr, train_y)
# test_predict = vectorizer.transform([{'尼泊尔': 1},
# {'赵本山': 1, '赵薇': 1, '张曼玉': 1, 'rat': '8.0',
# 'ravg': 3.85714,
# 'rcount': 7.0,
# 'rmax': 5.0,
# 'rmedian': 4.0,
# 'rmin': 2.0,
# 'rsum': 27.0},
# {'克里斯·派恩': 1, '扎克瑞·昆图': 1, '佐伊·索尔达娜': 1,'西蒙·佩吉':1, '安东·叶利钦':1, '林诣彬':1 ,
# '美国':1,
# 'rat': '8.0',
# 'ravg': 3.85714,
# 'rcount': 7.0,
# 'rmax': 5.0,
# 'rmedian': 4.0,
# 'rmin': 2.0,
# 'rsum': 27.0}])
# print(lr.predict_proba(test_predict))
lr_predict_final = lr.predict_proba(X_predict)
update_lr_rat(df_data, lr_predict_final.tolist())
print(lr.classes_)
if __name__ == '__main__':
sched_util.schedule_(10, task_func=process_task)
start_time = datetime.datetime.now()
conn = common.get_connection()
df_comment_new_data_ldim = get_comment_data()
conn = common.get_connection()
for i in df_comment_new_data_ldim.index:
print(df_comment_new_data_ldim.iloc[i]['MOVIEID'],
df_comment_new_data_ldim.iloc[i]['USERID'])
ibmovie_list = get_ibmovie_by_movieid(
df_comment_new_data_ldim.iloc[i]['MOVIEID'], conn)
for j in ibmovie_list:
is_exist = exist_in_comment(
j[0], df_comment_new_data_ldim.iloc[i]['USERID'], conn)
if is_exist:
print('exist in comment')
else:
insert_or_update_recmovie(
j[0], df_comment_new_data_ldim.iloc[i]['USERID'],
df_comment_new_data_ldim.iloc[i]['MOVIEID'], conn)
#update_comment_new_data_flag(df_comment_new_data_ldim.iloc[i]['ID'], conn)
conn.commit()
end_time = datetime.datetime.now()
print(end_time - start_time)
print('finish process movie based recall task:' +
str(datetime.datetime.now()))
if __name__ == '__main__':
sched_util.schedule_(60, func_main)
conn)
test_file_lr_base_url = cfg.get_config_property('test_file_lr_t_url', conn)
train_file_lr = train_file_lr_base_url % time_now_str
test_file_lr = test_file_lr_base_url % time_now_str
# 转换为libsvm格式数据
dump_svmlight_file(train_X_lr, train_y_lr_, train_file_lr)
dump_svmlight_file(test_X_lr, test_y_lr_, test_file_lr)
cfg.set_config_property(train_file_fm, 'train_file_fm_url', conn)
cfg.set_config_property(test_file_fm, 'test_file_fm_url', conn)
cfg.set_config_property(train_file_lr, 'train_file_lr_url', conn)
cfg.set_config_property(test_file_lr, 'test_file_lr_url', conn)
dict2vec_save_url = cfg.get_config_property('dict2vec', conn)
with open(dict2vec_save_url, 'wb') as f:
pkl.dump(v, f)
scaler_save_url = cfg.get_config_property('scaler', conn)
with open(scaler_save_url, 'wb') as f:
pkl.dump(scaler, f)
end_time = datetime.datetime.now()
print(end_time - start_time)
print('finish process comment to libsvm task:' +
str(datetime.datetime.now()))
if __name__ == '__main__':
sched_util.schedule_(60, process_task)
start_time = datetime.datetime.now()
conn = common.get_connection()
df_comment_new_data_ldim = get_comment_data()
conn = common.get_connection()
for i in df_comment_new_data_ldim.index:
print(df_comment_new_data_ldim.iloc[i]['MOVIEID'],
df_comment_new_data_ldim.iloc[i]['USERID'])
ibmovie_list = get_ibmovie_by_movieid(
df_comment_new_data_ldim.iloc[i]['MOVIEID'], conn)
for j in ibmovie_list:
is_exist = exist_in_comment(
j[0], df_comment_new_data_ldim.iloc[i]['USERID'], conn)
if is_exist:
print('exist in comment')
else:
insert_or_update_recmovie(
j[0], df_comment_new_data_ldim.iloc[i]['USERID'],
df_comment_new_data_ldim.iloc[i]['MOVIEID'], conn)
#update_comment_new_data_flag(df_comment_new_data_ldim.iloc[i]['ID'], conn)
conn.commit()
end_time = datetime.datetime.now()
print(end_time - start_time)
print('finish process movie based recall task:' +
str(datetime.datetime.now()))
if __name__ == '__main__':
sched_util.schedule_(10 * 60 * 1000, func_main)