parse.py 文件源码

def main(model_dir, test_sentences_file, test_pos_file, out_file, beam_size):
    model, params, hyper_params, all_s2i = load_model(model_dir)
    if beam_size:
        hyper_params['beam_size'] = beam_size

    beam = BeamDecoder(params, all_s2i, hyper_params['beam_size'])

    pos_tags = load_pos_tags(test_pos_file)
    sentences = load_sentences(test_sentences_file)
    test_data = zip(sentences, pos_tags)

    word_count = 0
    time_started = time()

    with open(out_file, "w") as fh:
        processed = 0
        for word_seq, pos_seq in test_data:
            word_count += len(word_seq)
            predicted_conf, predicted_tree = beam.decode(word_seq, pos_seq)
            processed += 1
            print(predicted_tree.to_export(processed), file=fh)
            if processed % 5 == 0:
                print("processed %d"%processed, file=stderr)
                stderr.flush()
    time_ended = time()
    sents_per_sec = len(sentences)/(time_ended-time_started)
    words_per_sec = word_count/(time_ended-time_started)
    print("sents/sec: %f words/sec: %f"%(sents_per_sec, words_per_sec), file=stderr)