# Load data
print("Loading data...")
trainset = Dataset('../../data/'+FLAGS.dataset+'/train.ss')
devset = Dataset('../../data/'+FLAGS.dataset+'/dev.ss')
testset = Dataset('../../data/'+FLAGS.dataset+'/test.ss')
alldata = np.concatenate([trainset.t_docs, devset.t_docs, testset.t_docs], axis=0)
embeddingpath = '../../data/'+FLAGS.dataset+'/embedding.txt'
embeddingfile, wordsdict = data_helpers.load_embedding(embeddingpath, alldata, FLAGS.embedding_dim)
del alldata
print("Loading data finished...")
usrdict, prddict = trainset.get_usr_prd_dict()
trainbatches = trainset.batch_iter(usrdict, prddict, wordsdict, FLAGS.n_class, FLAGS.batch_size,
FLAGS.num_epochs, FLAGS.max_sen_len, FLAGS.max_doc_len)
devset.genBatch(usrdict, prddict, wordsdict, FLAGS.batch_size,
FLAGS.max_sen_len, FLAGS.max_doc_len, FLAGS.n_class)
testset.genBatch(usrdict, prddict, wordsdict, FLAGS.batch_size,
FLAGS.max_sen_len, FLAGS.max_doc_len, FLAGS.n_class)
with tf.Graph().as_default():
session_config = tf.ConfigProto(
allow_soft_placement=FLAGS.allow_soft_placement,
log_device_placement=FLAGS.log_device_placement
)
session_config.gpu_options.allow_growth = True
sess = tf.Session(config=session_config)
with sess.as_default():
huapataha = huapahata(
topf1 = 0.
toprmse = 0.
better_dev_acc = 0.
better_dev_rmse = 100
predict_round = 0
test_f1 = 0.0
for ii in range(FLAGS.num_epochs):
sum_len = len(trainset.t_label)
counts = sum_len / 10000 + 1
global_steps = 0
for count in range(counts):
trainbatches = trainset.batch_iter(count, wordsdict,
FLAGS.n_class,
FLAGS.batch_size, 1,
FLAGS.max_sen_len,
FLAGS.max_doc_len)
# Training loop. For each batch...
for tr_batch in trainbatches:
train_step(tr_batch)
current_step = tf.train.global_step(sess, global_step)
if current_step % FLAGS.evaluate_every == 0 or ii == FLAGS.num_epochs:
predict_round += 1
print("\nEvaluation round %d:" % (predict_round))
print "==========devset==========="
predict(devset, name="dev")
#print("dev_acc: %.4f dev_RMSE: %.4f dev_MAE: %.4f" % (dev_acc, dev_rmse,dev_mae))
test_f1 = predict(testset, name="test")
#print("test_acc: %.4f test_RMSE: %.4f test_MAE: %.4f" % (test_acc, test_rmse,test_mae)