根据词汇输出词频(Python)

import jieba


def method():
    counts = {}  # 建立空字典counts
    with open('./data.txt', 'r', encoding='utf-8') as p:  # 读取文件
        txts = p.readlines()
    for txt in txts:
        words = jieba.lcut(txt, cut_all=True)  # 结巴全模式分词，并保存在words中

        # 判断word长度等于2的，作为字典counts的键，并用.get()方法进行赋值。
        for word in words:
            if len(word) == 2:
                counts[word] = counts.get(word, 0) + 1

    ls = list(counts.items())  # 将字典转化为列表ls并排序
    ls.sort(key=lambda x: int(x[1]), reverse=True)
    # print(ls)
    for i in range(10):
        print("{0}:{1}".format(ls[i][0], ls[i][-1]))  # 输出前10个词汇及次数


def main():
    method()


if __name__ == '__main__':
    main()

侵权删