participle.py 文件源码

def get_all_keywords(file_name):
    word_lists = []  # ?????
    jieba.enable_parallel(8)
    with codecs.open(file_name, 'r', encoding='utf-8') as f:
        Lists = f.readlines()  # ????
        for List in Lists:
            cut_list = list(jieba.cut(List))
            for word in cut_list:
                word_lists.append(word)
    word_lists_set = set(word_lists)  # ??????
    word_lists_set = list(word_lists_set)
    length = len(word_lists_set)
    print u"??%d????" % length
    information = pd.read_excel('/Users/huazi/Desktop/zhanlang2.xlsx')
    world_number_list = []
    word_copy=[]
    for w in word_lists_set:
        if (len(w) == 1):
            continue
        if (word_lists.count(w) > 3):
            world_number_list.append(word_lists.count(w))
            word_copy.append(w)
    information['key'] = word_copy
    information['count'] = world_number_list
    information.to_excel('sun_2.xlsx')


# ????