config['latent_dim'] = config['latent_dim_mf']
engine =New_Gloabl_sum_embedding_MLPEngine(config)
# DataLoader for training
sample_generator = SampleGenerator(ratings=data_rating, train=data_rating_train, test=data_rating_test)
# Train this model
evaluate_data = sample_generator.evaluate_data
sample_train_data = sample_generator.sample_train_data
print("TRAINING:---------------------")
engine.evaluate(sample_train_data, epoch_id=0, save=False)
print("TESTING:----------------------")
hit_ratio_max, ndcg_max = engine.evaluate(evaluate_data, epoch_id=0)
for epoch in range(config['num_epoch']):
print('Epoch {} starts !'.format(epoch))
print('-' * 80)
train_loader = sample_generator.instance_a_train_loader(config['num_negative'], config['batch_size'])
engine.train_an_epoch(train_loader, epoch_id=epoch)
#print("TRAINING:-----------------")
#engine.evaluate(sample_train_data, epoch, save=False)
print("TESTING:------------------")
hit_ratio, ndcg = engine.evaluate(evaluate_data, epoch_id=epoch)
if hit_ratio_max <= hit_ratio or ndcg_max <= ndcg:
hit_ratio_max = max(hit_ratio_max, hit_ratio)
ndcg_max = max(ndcg_max, ndcg)
# Load Data
ml1m_dir = 'data/ml-1m/ratings.dat'
ml1m_rating = pd.read_csv(ml1m_dir, sep='::', header=None, names=['uid', 'mid', 'rating', 'timestamp'], engine='python')
# Reindex
user_id = ml1m_rating[['uid']].drop_duplicates().reindex() #drop_duplicates > 중복 제거
user_id['userId'] = np.arange(len(user_id)) #arange > array return, range > list return
ml1m_rating = pd.merge(ml1m_rating, user_id, on=['uid'], how='left')
item_id = ml1m_rating[['mid']].drop_duplicates()
item_id['itemId'] = np.arange(len(item_id))
ml1m_rating = pd.merge(ml1m_rating, item_id, on=['mid'], how='left')
ml1m_rating = ml1m_rating[['userId', 'itemId', 'rating', 'timestamp']]
print('Range of userId is [{}, {}]'.format(ml1m_rating.userId.min(), ml1m_rating.userId.max()))
print('Range of itemId is [{}, {}]'.format(ml1m_rating.itemId.min(), ml1m_rating.itemId.max()))
# DataLoader for training
sample_generator = SampleGenerator(ratings=ml1m_rating)
evaluate_data = sample_generator.evaluate_data
# Specify the exact model
config = gmf_config
engine = GMFEngine(config)
# config = mlp_config
# engine = MLPEngine(config)
# config = neumf_config
# engine = NeuMFEngine(config)
for epoch in range(config['num_epoch']):
print('Epoch {} starts !'.format(epoch))
print('-' * 80)
train_loader = sample_generator.instance_a_train_loader(config['num_negative'], config['batch_size'])
engine.train_an_epoch(train_loader, epoch_id=epoch)
hit_ratio, ndcg = engine.evaluate(evaluate_data, epoch_id=epoch)
engine.save(config['alias'], epoch, hit_ratio, ndcg)