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))