print(nb_train)
validate_data_path = data_dir + 'validate.txt'
validate_instances = utils.read_instances_lines_from_file(validate_data_path)
nb_validate = len(validate_instances)
print(nb_validate)
test_data_path = data_dir + 'test.txt'
test_instances = utils.read_instances_lines_from_file(test_data_path)
nb_test = len(test_instances)
print(nb_test)
### build knowledge ###
print("@Build knowledge")
MAX_SEQ_LENGTH, item_dict, reversed_item_dict, item_probs = utils.build_knowledge(train_instances, validate_instances)
print("#Statistic")
NB_ITEMS = len(item_dict)
print(" + Maximum sequence length: ", MAX_SEQ_LENGTH)
print(" + Total items: ", NB_ITEMS)
print('density of C matrix: %.6f' % (real_adj_matrix.nnz * 1.0 / NB_ITEMS / NB_ITEMS))
batch_size = args.batch_size
# train_loader = data_utils.generate_data_loader(train_instances, load_param['batch_size'], item_dict, MAX_SEQ_LENGTH, is_bseq=True, is_shuffle=True)
# valid_loader = data_utils.generate_data_loader(validate_instances, load_param['batch_size'], item_dict, MAX_SEQ_LENGTH, is_bseq=True, is_shuffle=False)
test_loader = data_utils.generate_data_loader(test_instances, batch_size, item_dict, MAX_SEQ_LENGTH, is_bseq=True, is_shuffle=False)
pre_trained_model = model.RecSysModel(load_param, MAX_SEQ_LENGTH, item_probs, real_adj_matrix.todense(), device, model_data_type)
pre_trained_model.to(device, dtype= model_data_type)
optimizer = torch.optim.RMSprop(pre_trained_model.parameters(), lr= 0.001)
nb_predict = args.nb_predict
topk = args.topk
ex_file = args.example_file
data_dir = f_dir
train_data_path = data_dir + 'train_lines.txt'
train_instances = utils.read_instances_lines_from_file(train_data_path)
nb_train = len(train_instances)
# print(nb_train)
test_data_path = data_dir + 'test_lines.txt'
test_instances = utils.read_instances_lines_from_file(test_data_path)
nb_test = len(test_instances)
# print(nb_test)
# print("---------------------@Build knowledge-------------------------------")
MAX_SEQ_LENGTH, item_dict, reversed_item_dict, item_probs, item_freq_dict, user_dict = utils.build_knowledge(
train_instances + test_instances)
if not os.path.exists(o_dir):
os.makedirs(o_dir)
saved_file = os.path.join(o_dir, model_name)
# print("Save model in ", saved_file)
f = np.load(saved_file, item_probs)
item_probs = f['item_probs']
# print(item_probs)
pop_model = POP(item_dict, reversed_item_dict, item_probs)
if ex_file is not None:
ex_instances = utils.read_instances_lines_from_file(ex_file)
else:
ex_instances = test_instances
for i in random.sample(ex_instances, nb_predict):
validate_instances = utils.read_file_as_lines(validate_file)
nb_validate = len(validate_instances)
total_validate_batches = utils.compute_total_batches(nb_validate,
config.batch_size)
print(" + Total validating sequences: ", nb_validate)
print(" + #batches in validate ", total_validate_batches)
testing_instances = utils.read_file_as_lines(testing_file)
nb_test = len(testing_instances)
total_test_batches = utils.compute_total_batches(nb_test, config.batch_size)
print(" + Total testing sequences: ", nb_test)
print(" + #batches in test ", total_test_batches)
# Create dictionary
print("@Build knowledge")
MAX_SEQ_LENGTH, item_dict = utils.build_knowledge(training_instances,
validate_instances)
print("#Statistic")
NB_ITEMS = len(item_dict)
print(" + Maximum sequence length: ", MAX_SEQ_LENGTH)
print(" + Total items: ", NB_ITEMS)
model_dir = output_dir + "/models"
if config.train_mode:
with tf.Session(config=gpu_config) as sess:
# Init the network
net = procedure.create_network(sess, MAX_SEQ_LENGTH, NB_ITEMS, config)
sess.run(tf.global_variables_initializer())
# Train the network
train_generator = utils.seq_batch_generator(training_instances,
print(nb_train)
validate_data_path = data_dir + 'validate.txt'
valid_instances = utils.read_instances_lines_from_file(validate_data_path)
nb_validate = len(valid_instances)
print(nb_validate)
test_data_path = data_dir + 'test.txt'
test_instances = utils.read_instances_lines_from_file(test_data_path)
nb_test = len(test_instances)
print(nb_test)
### build knowledge ###
print("---------------------@Build knowledge-------------------------------")
MAX_SEQ_LENGTH, item_dict, reversed_item_dict, item_probs, user_consumption_dict = utils.build_knowledge(
train_instances, valid_instances, test_instances)
config_param = dict()
config_param['batch_size'] = 16
print('---------------------Create data loader--------------------')
train_loader = data_utils.generate_data_loader(train_instances[:1000],
config_param['batch_size'],
item_dict,
MAX_SEQ_LENGTH,
is_bseq=True,
is_shuffle=True)
valid_loader = data_utils.generate_data_loader(valid_instances[:500],
config_param['batch_size'],
item_dict,
MAX_SEQ_LENGTH,
is_bseq=True,