data_util.py 文件源码

def words_to_char_sequence(words_list, tk):
    """Convert words list to chars sequence

    # Arguments
        words: word list, (sentence_len, word_len)

    # Output shape
        (sentence_len, MAX_SEQUENCE_LENGTH, MAX_CHAR_PER_WORD)
    """
    c_seqs = np.zeros((len(words_list),
                       TrainConfig.MAX_SEQUENCE_LENGTH,
                       TrainConfig.MAX_CHAR_PER_WORD), dtype='int32')
    for w_i in xrange(len(words_list)):
        words = words_list[w_i]
        fixed_ws = np.zeros((TrainConfig.MAX_SEQUENCE_LENGTH,
                             TrainConfig.MAX_CHAR_PER_WORD), dtype='int32')
        ws = tk.texts_to_sequences(words)
        ws = pad_sequences(ws, maxlen=TrainConfig.MAX_CHAR_PER_WORD)
        if TrainConfig.MAX_SEQUENCE_LENGTH < len(words):
            max_word_len = TrainConfig.MAX_SEQUENCE_LENGTH
        else:
            max_word_len = len(words)
        fixed_ws[:max_word_len, :] = ws[:max_word_len, :]
        c_seqs[w_i] = fixed_ws
    return c_seqs