def __init__(self):
start_time = time.time()
model_parameter_ins = model_parameter()
data_name = model_parameter_ins.flags.FLAGS.data_name
self.FLAGS = model_parameter_ins.get_parameter(data_name).FLAGS
log_ins = create_log(data_name=data_name,
model_name=self.FLAGS.model_name,
lr=self.FLAGS.learning_rate)
self.logger = log_ins.logger
self.logger.info("hello world the experiment begin")
self.logger.info("the model parameter is : " +
str(self.FLAGS.flag_values_dict()))
prepare_data_ins = DataLoader(self.FLAGS)
self.logger.info("start loading dataset!")
self.train_set, self.test_set = prepare_data_ins.load_train_test()
print('test event len: %d' % (len(self.test_set)))
self.logger.info("dataset loaded!")
self.logger.info("DataHandle Process cost time: %.2fs" %
(time.time() - start_time))
start_time = time.time()
self.emb = history_embedding(is_training=self.FLAGS.is_training,
type_num=self.FLAGS.type_num,
max_seq_len=self.FLAGS.max_seq_len,
sims_len=self.FLAGS.sims_len,
FLAGS=self.FLAGS)
self.logger.info('get train test data process cost: %.2fs' %
(time.time() - start_time))
ndcg_value_sum = ndcg_value_sum + ndcg_value
break
print("P Pop the recall rate is: " + str(topk) + " " +
str(recall_count / length))
print("P Pop the ndcg value is: " + str(topk) + " " +
str(ndcg_value_sum / length))
print('error:' + str(error))
return
if __name__ == "__main__":
start_time = time.time()
model_parameter_ins = model_parameter()
experiment_name = model_parameter_ins.flags.FLAGS.experiment_name
FLAGS = model_parameter_ins.get_parameter(experiment_name).FLAGS
FLAGS.type = sys.argv[1]
log_ins = create_log(type=FLAGS.type,
experiment_type=FLAGS.experiment_type,
version=FLAGS.version)
logger = log_ins.logger
logger.info("hello world the experiment begin")
# logger.info("The model parameter is :" + str(self.FLAGS._parse_flags()))
if FLAGS.type == "yoochoose":
get_origin_data_ins = Get_yoochoose_data(FLAGS=FLAGS)
def __init__(self):
start_time = time.time()
model_parameter_ins = model_parameter()
experiment_name = model_parameter_ins.flags.FLAGS.experiment_name
self.FLAGS = model_parameter_ins.get_parameter(experiment_name).FLAGS
log_ins = create_log(type=self.FLAGS.type, experiment_type=self.FLAGS.experiment_type,
version=self.FLAGS.version)
self.logger = log_ins.logger
self.logger.info("hello world the experiment begin")
# logger.info("The model parameter is :" + str(self.FLAGS._parse_flags()))
#init data and embeding
get_origin_data_ins = Get_origin_data(FLAGS=self.FLAGS)
if self.FLAGS.experiment_type == "dib" \
or self.FLAGS.experiment_type == "no_emb" \
or self.FLAGS.experiment_type == "slirec" \
or self.FLAGS.experiment_type == "lstur" \
or self.FLAGS.experiment_type == "sasrec" \
or self.FLAGS.experiment_type == "grurec" \
or self.FLAGS.experiment_type == "bert" \
or self.FLAGS.experiment_type == "dmpn" \
or self.FLAGS.experiment_type == "atrank"\
or self.FLAGS.experiment_type == "dmpn2"\
or self.FLAGS.experiment_type == "dmpn3"\
or self.FLAGS.experiment_type == "dmpn4"\
or self.FLAGS.experiment_type == "dfm":
prepare_data_behavior_ins = prepare_data_behavior(self.FLAGS, get_origin_data_ins.origin_data)
elif self.FLAGS.experiment_type == "bpr":
prepare_data_behavior_ins = prepare_data_bpr(self.FLAGS, get_origin_data_ins.origin_data)
self.logger.info('DataHandle Process.\tCost time: %.2fs' % (time.time() - start_time))
start_time = time.time()
#embedding
if self.FLAGS.experiment_type == "no_emb":
config_file = "config/no_embedding__dic.csv"
self.emb = No_embedding(self.FLAGS.is_training, config_file)
elif self.FLAGS.experiment_type == "bpr":
self.emb = Bprmf_embedding(self.FLAGS.is_training,self.FLAGS.embedding_config_file,
prepare_data_behavior_ins.user_count,
prepare_data_behavior_ins.item_count)
else:
self.emb = Lstur_embedding(self.FLAGS.is_training, self.FLAGS.embedding_config_file,
prepare_data_behavior_ins.user_count,
prepare_data_behavior_ins.item_count,
prepare_data_behavior_ins.category_count,
self.FLAGS.max_len)
self.train_set, self.test_set = prepare_data_behavior_ins.get_train_test()
self.logger.info('Get Train Test Data Process.\tCost time: %.2fs' % (time.time() - start_time))
# self.item_category_dic = prepare_data_behavior_ins.item_category_dic
self.global_step = 0
self.one_epoch_step = 0
self.now_epoch = 0
def __init__(self):
start_time = time.time()
model_parameter_ins = model_parameter()
experiment_name = model_parameter_ins.flags.FLAGS.experiment_name
self.FLAGS = model_parameter_ins.get_parameter(experiment_name).FLAGS
log_ins = create_log(type=self.FLAGS.type,
experiment_type=self.FLAGS.experiment_type,
version=self.FLAGS.version)
self.logger = log_ins.logger
self.logger.info("hello world the experiment begin")
# logger.info("The model parameter is :" + str(self.FLAGS._parse_flags()))
if self.FLAGS.type == "yoochoose":
get_origin_data_ins = Get_yoochoose_data(FLAGS=self.FLAGS)
get_origin_data_ins.getDataStatistics()
elif self.FLAGS.type == "movielen":
get_origin_data_ins = Get_movie_data(FLAGS=self.FLAGS)
get_origin_data_ins.getDataStatistics()
if self.FLAGS.type == "tmall":
get_origin_data_ins = Get_tmall_data(FLAGS=self.FLAGS)
elif self.FLAGS.type == "movie_tv":
get_origin_data_ins = Get_amazon_data_movie_tv(FLAGS=self.FLAGS)
get_origin_data_ins.getDataStatistics()
elif self.FLAGS.type == "elec":
get_origin_data_ins = Get_amazon_data_elec(FLAGS=self.FLAGS)
get_origin_data_ins.getDataStatistics()
elif self.FLAGS.type == "music":
get_origin_data_ins = Get_amazon_data_music(FLAGS=self.FLAGS)
get_origin_data_ins.getDataStatistics()
elif self.FLAGS.type == 'taobaoapp':
get_origin_data_ins = Get_taobaoapp_data(FLAGS=self.FLAGS)
get_origin_data_ins.getDataStatistics()
elif self.FLAGS.type == "beauty":
get_origin_data_ins = Get_amazon_data_beauty(FLAGS=self.FLAGS)
get_origin_data_ins.getDataStatistics()
elif self.FLAGS.type == "brightkite":
get_origin_data_ins = Get_BrightKite_data(FLAGS=self.FLAGS)
get_origin_data_ins.getDataStatistics()
elif self.FLAGS.type == "order":
get_origin_data_ins = Get_Order_data(FLAGS=self.FLAGS)
get_origin_data_ins.getDataStatistics()
#get_train_test_ins = Get_train_test(FLAGS=self.FLAGS,origin_data=get_origin_data_ins.origin_data)
prepare_data_behavior_ins = prepare_data_base(
self.FLAGS, get_origin_data_ins.origin_data)
self.train_set, self.test_set = prepare_data_behavior_ins.get_train_test(
)
#fetch part of test_data
#if len(self.train_set) > 2000000:
#self.test_set = random.sample(self.train_set,2000000)
#self.test_set = self.test_set.sample(3500)
self.logger.info('DataHandle Process.\tCost time: %.2fs' %
(time.time() - start_time))
start_time = time.time()
self.emb = Behavior_embedding_time_aware_attention(
is_training=self.FLAGS.is_training,
user_count=prepare_data_behavior_ins.user_count,
item_count=prepare_data_behavior_ins.item_count,
category_count=prepare_data_behavior_ins.category_count,
max_length_seq=self.FLAGS.length_of_user_history)
self.logger.info('Get Train Test Data Process.\tCost time: %.2fs' %
(time.time() - start_time))
self.item_category_dic = prepare_data_behavior_ins.item_category_dic
self.global_step = 0
self.one_epoch_step = 0
self.now_epoch = 0
def __init__(self):
start_time = time.time()
model_parameter_ins = model_parameter()
experiment_name = model_parameter_ins.flags.FLAGS.experiment_name
self.FLAGS = model_parameter_ins.get_parameter(experiment_name).FLAGS
def __init__(self):
start_time = time.time()
model_parameter_ins = model_parameter()
data_name = model_parameter_ins.flags.FLAGS.data_name
self.FLAGS = model_parameter_ins.get_parameter(data_name).FLAGS
