停用词过滤

stop_word_path = "InferenceSystem/src/I5_algorithm/NLP数据集合/停词库/stop_word_for_chinese.txt"

def del_element(strings,symbles):
    srcrep = {i:'' for i in symbles }
    rep = dict((re.escape(k), v) for k, v in srcrep.items())
    pattern = re.compile("|".join(rep.keys()))
    return pattern.sub(lambda m: rep[re.escape(m.group(0))], strings)

def filter_stop_word(strings,stop_word=np.loadtxt(stop_word_path,dtype=str)):
    return del_element(strings,stop_word)

src = '资源来源网络，侵删 很好的资料，赶快学起来'
filter_stop_word(src)

filter_stop_word(src,'， ')