def get_response(message):
line = str.encode(message)
if len(line) > 0 and line[-1] == '\n':
line = line[:-1]
if line == '':
response = 'What did you say?'
output_file.write('Human: ' + message + '\n' + 'Bot: ' +
str(response) + '\n')
return message, response
token_ids = data_utils.sentence2id(enc_vocab, line)
if len(token_ids) > max_length:
response = ('The maximum length I can handle is ', max_length)
output_file.write('Human: ' + message + '\n' + 'Bot: ' +
str(response) + '\n')
return message, response
bucket_id = chatbot.find_right_bucket(len(token_ids))
encoder_inputs, decoder_inputs, decoder_masks = data_utils.get_batch(
[(token_ids, [])], bucket_id, batch_size=1)
_, _, output_logits = chatbot.run_step(sess, model, encoder_inputs,
decoder_inputs, decoder_masks,
bucket_id, True)
response = chatbot.construct_response(output_logits, inv_dec_vocab)
output_file.write('Human: ' + message + '\n' + 'Bot: ' + str(response) +
'\n')
return message, response
def chat(question):
"""
In test mode, we don"t to create the backward path.
"""
_, enc_vocab = data_utils.load_vocab(
os.path.join(config.DATA_PATH, "vocab.enc"))
# `inv_dec_vocab` <type "list">: id2word.
inv_dec_vocab, _ = data_utils.load_vocab(
os.path.join(config.DATA_PATH, "vocab.dec"))
model = ChatBotModel(True, batch_size=1)
model.build_graph()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
check_restore_parameters(sess, saver)
output_file = open(os.path.join(config.DATA_PATH,
config.TERMINAL_OUTPUT),
"a+",
encoding="utf-8")
# Decode from standard input.
max_length = config.BUCKETS[-1][0]
print(
"Welcome to TensorBro. Say something. Enter to exit. Max length is",
max_length)
line = question
if hasattr(line, "decode"):
# If using Python 2
# FIXME: UnicodeError when deleting Chinese in terminal.
line = line.decode("utf-8")
if len(line) > 0 and line[-1] == "\n":
line = line[:-1]
if not line:
pass
output_file.write("HUMAN ++++ " + line + "\n")
# Get token-ids for the input sentence.
token_ids = data_utils.sentence2id(enc_vocab, line)
if len(token_ids) > max_length:
print("Max length I can handle is:", max_length)
# line = _get_user_input()
pass
# Which bucket does it belong to?
bucket_id = find_right_bucket(len(token_ids))
# Get a 1-element batch to feed the sentence to the model.
encoder_inputs, decoder_inputs, decoder_masks = data_utils.get_batch(
[(token_ids, [])], bucket_id, batch_size=1)
# Get output logits for the sentence.
_, _, output_logits = run_step(sess, model, encoder_inputs,
decoder_inputs, decoder_masks,
bucket_id, True)
response = construct_response(output_logits, inv_dec_vocab)
print(response)
output_file.write("BOT ++++ " + response + "\n")
output_file.write("=============================================\n")
output_file.close()
def chat():
""" in test mode, we don't to create the backward path """
_, enc_vocab = data_utils.load_vocab(
os.path.join(config.PROCESSED_PATH, 'vocab.enc'))
inv_dec_vocab, _ = data_utils.load_vocab(
os.path.join(config.PROCESSED_PATH, 'vocab.dec'))
model = ChatBotModel(True, batch_size=1)
model.build_graph()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
check_restore_parameters(sess, saver)
output_file = open(
'/Users/EleanorLeung/Documents/CITS4404/chatbot/output_convo.txt',
'a+')
# Decode from standard input.
max_length = config.BUCKETS[-1][0]
print('Talk to me! Enter to exit. Max length is', max_length)
while True:
line = str.encode(get_user_input())
if len(line) > 0 and line[-1] == '\n':
line = line[:-1]
if line == '':
break
output_file.write('HUMAN: ' + str(line) + '\n')
token_ids = data_utils.sentence2id(enc_vocab, line)
if len(token_ids) > max_length:
print('Max length I can handle is:', max_length)
line = get_user_input()
continue
bucket_id = find_right_bucket(len(token_ids))
# Get a 1-element batch to feed the sentence to the model.
encoder_inputs, decoder_inputs, decoder_masks = data_utils.get_batch(
[(token_ids, [])], bucket_id, batch_size=1)
# Get output logits for the sentence.
_, _, output_logits = run_step(sess, model, encoder_inputs,
decoder_inputs, decoder_masks,
bucket_id, True)
response = construct_response(output_logits, inv_dec_vocab)
print(response)
output_file.write('BOT: ' + response + '\n')
output_file.write('=============================================\n')
output_file.close()
def wechat_text(msg):
'''
get the response to msg
:param msg: the type of the msg is 'Text'
:return: response to msg by using seq2seq model
'''
text = msg["Text"]
token_ids = data_utils.sentence2id(enc_vocab, text)
if len(token_ids) > max_length:
print("Max length I can handle is:", max_length)
# line = _get_user_input()
# Which bucket does it belong to?
bucket_id = find_right_bucket(len(token_ids))
# Get a 1-element batch to feed the sentence to the model.
encoder_inputs, decoder_inputs, decoder_masks = data_utils.get_batch(
[(token_ids, [])], bucket_id, batch_size=1)
# Get output logits for the sentence.
_, _, output_logits = run_step(sess, model, encoder_inputs, decoder_inputs,
decoder_masks, bucket_id, True)
response = construct_response(output_logits, inv_dec_vocab)
return response
def seq_pred(question):
_, enc_vocab = data_utils.load_vocab(os.path.join(config.DATA_PATH, "vocab.enc"))
inv_dec_vocab, _ = data_utils.load_vocab(os.path.join(config.DATA_PATH, "vocab.dec"))
model = ChatBotModel(True, batch_size=1)
model.build_graph()
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
check_restore_parameters(sess, saver)
max_length = config.BUCKETS[-1][0]
line = question
if hasattr(line, "decode"):
# If using Python 2
# FIXME: UnicodeError when deleting Chinese in terminal.
line = line.decode("utf-8")
if len(line) > 0 and line[-1] == "\n":
line = line[:-1]
if not line:
pass
token_ids = data_utils.sentence2id(enc_vocab, line)
if len(token_ids) > max_length:
line = question
pass
bucket_id = find_right_bucket(len(token_ids))
# Get a 1-element batch to feed the sentence to the model.
encoder_inputs, decoder_inputs, decoder_masks = data_utils.get_batch(
[(token_ids, [])], bucket_id, batch_size=1)
# Get output logits for the sentence.
_, _, output_logits = run_step(sess, model, encoder_inputs,
decoder_inputs, decoder_masks,
bucket_id, True)
response = construct_response(output_logits, inv_dec_vocab)
answer = response
return answer