qaData.py 文件源码

def sentenceToIndex(sentence, word2idx, maxLen):
    """
    ??????????embeddings??????

    :param sentence: ??
    :param word2idx: ?????
    :param maxLen: ???????
    :return: ??????????
    """
    unknown = word2idx.get("UNKNOWN", 0)
    num = word2idx.get("NUM", len(word2idx))
    index = [unknown] * maxLen
    i = 0
    for word in jieba.cut(sentence):
        if word in word2idx:
            index[i] = word2idx[word]
        else:
            if re.match("\d+", word):
                index[i] = num
            else:
                index[i] = unknown
        if i >= maxLen - 1:
            break
        i += 1
    return index