sess.run(tf.global_variables_initializer())
for epoch in range(num_epoch):
for _ in range(num_batch_per_epoch):
batch = data.get_train_batch(batch_size)
batch_X = [
np.array([wv[w] for w in tweet.words]) for tweet in batch
]
batch_y = [int(tweet.label == "bull") for tweet in batch]
_, _ = rnn.train(batch_X, batch_y, sess)
## accuracy check, train, valid, test sets
train_X = [
np.array([wv[w] for w in tweet.words]) for tweet in data.train
]
train_y = [int(tweet.label == "bull") for tweet in data.train]
train_ent, train_acc = rnn.cal_accuracy(train_X, train_y, sess)
valid_X = [
np.array([wv[w] for w in tweet.words]) for tweet in data.valid
]
valid_y = [int(tweet.label == "bull") for tweet in data.valid]
_, valid_acc = rnn.cal_accuracy(valid_X, valid_y, sess)
test_X = [
np.array([wv[w] for w in tweet.words]) for tweet in data.test
]
test_y = [int(tweet.label == "bull") for tweet in data.test]
_, test_acc = rnn.cal_accuracy(test_X, test_y, sess)
print("Current epoch", epoch, "\tCross entropy", train_ent,
"\tTraining accuracy", train_acc, "\tValidate accuracy",
rnn = RNN("gru", hidden_size, embedding_size, lr=lr)
rnn.build_graph(embedding=True, vocab_size=len(w2i), embedding_size=100)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for epoch in range(num_epoch):
for _ in range(num_batch_per_epoch):
batch = data.get_train_batch(batch_size)
batch_X = [np.array(tweet.word_indexes) for tweet in batch]
batch_y = [int(tweet.label=="bull") for tweet in batch]
_, _= rnn.train(batch_X, batch_y, sess, embedding=True)
## accuracy check, train, valid, test sets
train_X = [np.array(tweet.word_indexes) for tweet in data.train]
train_y = [int(tweet.label == "bull") for tweet in data.train]
train_ent, train_acc = rnn.cal_accuracy(train_X, train_y, sess, embedding=True)
valid_X = [np.array(tweet.word_indexes) for tweet in data.valid]
valid_y = [int(tweet.label == "bull") for tweet in data.valid]
_, valid_acc = rnn.cal_accuracy(valid_X, valid_y, sess, embedding=True)
test_X = [np.array(tweet.word_indexes) for tweet in data.test]
test_y = [int(tweet.label == "bull") for tweet in data.test]
_, test_acc = rnn.cal_accuracy(test_X, test_y, sess, embedding=True)
print("Current epoch", epoch, "\tCross entropy", train_ent,
"\tTraining accuracy", train_acc,
"\tValidate accuracy", valid_acc,
"\tTest accuracy", test_acc)
