def main():
command_line = parseArgs()
path_to_train = './'+command_line.data+'/rsc15_train_full.txt'
path_to_test = './' + command_line.data+'/rsc15_test.txt'
path_to_train = path_to_test
print(path_to_train)
print(path_to_test)
data = pd.read_csv(path_to_train, sep='\t', dtype={'ItemId': np.int64})
valid = pd.read_csv(path_to_test, sep='\t', dtype={'ItemId': np.int64})
args = Args()
args.n_items = len(data['ItemId'].unique())
args.learning_rate = command_line.lr
args.is_training = command_line.train
args.test_model = command_line.test
args.hidden_act = command_line.hidden_act
args.final_act = command_line.final_act
args.loss = command_line.loss
args.layers = command_line.layer
args.batch_size = command_line.size
args.n_epochs = command_line.epoch
args.checkpoint_dir = command_line.checkpoint_dir
args.dropout_p_hidden = 1.0 if args.is_training == 0 else command_line.dropout
args.weight_decay = command_line.weight_decay
args.rnn_size = command_line.rnn_size
args.optimize = command_line.optimize
args.evaluate_train = command_line.evaluate_train
with tf.Session() as sess:
print("\n\n\nBEGIN: Batch size: {}, Loss: {}".format(args.batch_size, args.loss))
gru = model.GRU4Rec(sess, args)
if args.is_training:
print("Traing only")
gru.fit(data)
if not args.is_training:
if args.evaluate_train == 1:
valid = data
result = []
for i in range(0,args.n_epochs): #number epoch
tf.reset_default_graph()
with tf.Session() as eval_sess:
args.test_model = i
gru = model.GRU4Rec(eval_sess, args)
res = evaluate.evaluate_model(gru, data, valid, batch_size=args.batch_size)
print('Epoch {}\tRecall@20: {}\tMRR@20: {}'.format(i,res[0], res[1]))
result.append(res)
if args.evaluate_train == 1:
with open(args.checkpoint_dir + '_result_in_train.txt', 'w') as file:
for rs in result:
file.write('{}\t{}\n'.format(rs[0], rs[1]))
else:
with open(args.checkpoint_dir+'_result_'+str(args.batch_size)+'.txt','w') as file:
for rs in result:
file.write('{}\t{}\n'.format(rs[0], rs[1]))
def main():
command_line = parseArgs()
data = pd.read_csv(PATH_TO_TRAIN, sep='\t', dtype={'ItemId': np.int64})
valid = pd.read_csv(PATH_TO_TEST, sep='\t', dtype={'ItemId': np.int64})
# 参数
args = Args()
args.n_items = len(data['ItemId'].unique())
args.layers = command_line.layer
args.rnn_size = command_line.size
args.n_epochs = command_line.epoch
args.learning_rate = command_line.lr
args.is_training = command_line.train
args.test_model = command_line.test
args.hidden_act = command_line.hidden_act
args.final_act = command_line.final_act
args.loss = command_line.loss
args.dropout_p_hidden = 1.0 if args.is_training == 0 else command_line.dropout
print(args.dropout_p_hidden)
# print data stat
data_stat = data_utils.DataUtils(data, valid, args)
data_stat.session_stat()
if not os.path.exists(args.checkpoint_dir):
os.mkdir(args.checkpoint_dir)
gpu_config = tf.ConfigProto()
gpu_config.gpu_options.allow_growth = True
with tf.Session(config=gpu_config) as sess:
gru = model.GRU4Rec(sess, args)
if args.is_training:
gru.fit(data)
else:
res = evaluation.evaluate_sessions_batch(gru, data, valid)
print('Recall@20: {}\tMRR@20: {}'.format(res[0], res[1]))
def main(_):
#if not os.path.exists(FLAGS.checkpoint_dir):
# os.mkdir(FLAGS.checkpoint_dir)
data = pd.read_csv(FLAGS.train, sep='\t')
valid = pd.read_csv(FLAGS.test, sep='\t')
FLAGS.n_items = len(data['ItemId'].unique())
print("total_items:",FLAGS.n_items)
gru4rec_hps = model.GRU4Rec_HParams(reset_after_session=FLAGS.reset_after_session, layers=FLAGS.layers,
rnn_size=FLAGS.rnn_size, loss=FLAGS.loss, final_act=FLAGS.final_act,
hidden_act=FLAGS.hidden_act, dropout_p_hidden=FLAGS.dropout_p_hidden,
batch_size=FLAGS.batch_size, optimizer=FLAGS.optimizer, learning_rate=FLAGS.lr,
decay=FLAGS.decay, decay_steps=FLAGS.decay_steps, sigma=FLAGS.sigma,
grad_cap=FLAGS.grad_cap, init_as_normal=FLAGS.init_as_normal, n_sample=FLAGS.n_sample,
sample_alpha=FLAGS.sample_alpha, smoothing=FLAGS.smoothing, n_epochs=FLAGS.n_epochs)
session_hps = model.Session_HParams(n_items=FLAGS.n_items, session_key=FLAGS.session_key,
item_key=FLAGS.item_key, time_key=FLAGS.time_key,
train_random_order=FLAGS.train_random_order, time_sort=FLAGS.time_sort)
gpu_config = tf.ConfigProto()
gpu_config.gpu_options.allow_growth = True
logger.info('rnn_size:%3s, batch_size:%3s, lr:%6s, optimizer:%5s',
FLAGS.rnn_size, FLAGS.batch_size, FLAGS.lr,FLAGS.optimizer)
with tf.Session(config=gpu_config) as sess:
gru = model.GRU4Rec(gru4rec_hps, session_hps, sess, FLAGS.is_training)
sess.run(tf.global_variables_initializer())
gru.fit(data, valid)
if __name__ == '__main__':
command_line = parseArgs()
data = pd.read_csv(PATH_TO_TRAIN, sep='\t', dtype={'ItemId': np.int64})
valid = pd.read_csv(PATH_TO_TEST, sep='\t', dtype={'ItemId': np.int64})
args = Args()
args.n_items = len(data['ItemId'].unique())
args.layers = command_line.layer
args.rnn_size = command_line.size
args.n_epochs = command_line.epoch
args.learning_rate = command_line.lr
args.is_training = command_line.train
args.test_model = command_line.test
args.hidden_act = command_line.hidden_act
args.final_act = command_line.final_act
args.loss = command_line.loss
args.dropout_p_hidden = 1.0 if args.is_training == 0 else command_line.dropout
print(args.dropout_p_hidden)
if not os.path.exists(args.checkpoint_dir):
os.mkdir(args.checkpoint_dir)
gpu_config = tf.ConfigProto()
gpu_config.gpu_options.allow_growth = True
with tf.Session(config=gpu_config) as sess:
gru = model.GRU4Rec(sess, args)
if args.is_training:
gru.fit(data)
else:
res = evaluation.evaluate_sessions_batch(gru, data, valid)
print('Recall@20: {}\tMRR@20: {}'.format(res[0], res[1]))
ARGS.rnn_size = COMMAND_LINE.size
ARGS.n_epochs = COMMAND_LINE.epoch
ARGS.learning_rate = COMMAND_LINE.lr
ARGS.is_training = COMMAND_LINE.train
ARGS.test_model = COMMAND_LINE.test
ARGS.hidden_act = COMMAND_LINE.hidden_act
ARGS.final_act = COMMAND_LINE.final_act
ARGS.loss = COMMAND_LINE.loss
ARGS.dropout_p_hidden = 1.0 if ARGS.is_training == 0 else COMMAND_LINE.dropout
print(ARGS.dropout_p_hidden)
if not os.path.exists(ARGS.checkpoint_dir):
os.mkdir(ARGS.checkpoint_dir)
GPU_CONFIG = tf.ConfigProto()
#GPU_CONFIG.gpu_options.allow_growth = True
with tf.Session(config=GPU_CONFIG) as sess:
GRU = model.GRU4Rec(sess, ARGS)
START_TIME = time.time()
if ARGS.is_training:
OUTPUT = open('train_results.txt', 'w')
GRU.fit(DATA)
OUTPUT.close()
TRAINING_TIME = time.time()
print("Training time =", TRAINING_TIME - START_TIME, "seconds")
else:
TEST_OUTPUT = open('test_results.txt', 'w')
print("\n\nEvaluating Model....\n", file=TEST_OUTPUT)
RES = evaluation.evaluate_sessions_batch(GRU, DATA, DATA)
print('Recall@1: {}'.format(RES[0][0]), file=TEST_OUTPUT)
print('MRR@1: {}'.format(RES[1][0]), file=TEST_OUTPUT)
print('Recall@2: {}'.format(RES[0][1]), file=TEST_OUTPUT)
print('MRR@2: {}'.format(RES[1][1]), file=TEST_OUTPUT)
args.dropout_p_hidden = 1.0 if args.is_training == 0 else 0.5
# if not os.path.exists(args.checkpoint_dir):
# os.mkdir(args.checkpoint_dir)
gpu_config = tf.ConfigProto()
gpu_config.gpu_options.allow_growth = True
mrr_list = []
for i in range(10):
params = find_param()
print('param searching round =', i)
print(params)
args.layers = params['layers']
args.rnn_size = params['rnn_size']
args.learning_rate = float(params['learning_rate']) # cast to float
tf.reset_default_graph()
with tf.Session(config=gpu_config) as sess:
args.is_training = True
gru = model.GRU4Rec(sess, args)
gru.fit(data)
tf.reset_default_graph() # reset graph
with tf.Session(config=gpu_config) as sess:
args.is_training = False
gru = model.GRU4Rec(sess, args) # instantiate again
res = evaluation.evaluate_sessions_batch(gru, data, valid)
print('Recall@25: {}\tMRR@25: {} \n'.format(res[0], res[1]))
