get_origin_data_ins = Get_amazon_data_movie_tv(FLAGS=FLAGS)
get_origin_data_ins.getDataStatistics()
elif FLAGS.type == "music":
get_origin_data_ins = Get_amazon_data_music(FLAGS=FLAGS)
get_origin_data_ins.getDataStatistics()
elif FLAGS.type == "elec":
get_origin_data_ins = Get_amazon_data_elec(FLAGS=FLAGS)
get_origin_data_ins.getDataStatistics()
elif FLAGS.type == 'taobaoapp':
get_origin_data_ins = Get_taobaoapp_data(FLAGS=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(
FLAGS, get_origin_data_ins.origin_data)
prepare_data_behavior_ins.map_process()
train_set, test_set = prepare_data_behavior_ins.get_train_test()
# fetch part of test_data
# if len(self.test_set) > 10000:
# self.test_set = random.sample(self.test_set,10000)
# self.test_set = self.test_set.sample(3500)
logger.info('DataHandle Process.\tCost time: %.2fs' %
(time.time() - start_time))
start_time = time.time()
top_pop_ins = top_pop_model(train_set, prepare_data_behavior_ins)
top_pop_ins.cal_p_pop(1)
top_pop_ins.cal_p_pop(5)
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