def log_predictions(sentences, nn_model, w2v_model, index_to_token, no_predictions, stats_info=None):
with codecs.open(PREDICTIONS_FILE+'_'+str(no_predictions), 'w', 'utf-8') as predictions:
for sent in sentences:
prediction = predict_sentence(sent, nn_model, w2v_model, index_to_token)
# _logger.info('[%s] -> [%s]' % (sent, prediction))
print "WRITING PREDICTIONS"
predictions.write(prediction + '\n')
def predict():
# preprocess the dialog and get index for its vocabulary
processed_dialog_lines, index_to_token = \
get_processed_dialog_lines_and_index_to_token(CORPUS_PATH, PROCESSED_CORPUS_PATH, TOKEN_INDEX_PATH)
# dualize iterator
dialog_lines_for_w2v, dialog_lines_for_nn = tee(processed_dialog_lines)
_logger.info('-----')
# use gensim realisatino of word2vec instead of keras embeddings due to extra flexibility
w2v_model = w2v.get_dialogs_model(W2V_PARAMS, dialog_lines_for_w2v)
_logger.info('-----')
nn_model = get_nn_model(token_dict_size=len(index_to_token))
while True:
input_sentence = raw_input('> ')
predict_sentence(input_sentence, nn_model, w2v_model, index_to_token)
def log_predictions(sentences,
nn_model,
w2v_model,
index_to_token,
stats_info=None):
for sent in sentences:
prediction = predict_sentence(sent, nn_model, w2v_model,
index_to_token)
_logger.info('[%s] -> [%s]' % (sent, prediction))
def log_predictions(sentences, nn_model, w2v_model, index_to_token, stats_info=None):
for sent in sentences:
prediction = predict_sentence(sent, nn_model, w2v_model, index_to_token)
_logger.info("[%s] -> [%s]" % (sent, prediction))
