python学习 第十一个程序 汉语文本词频统计

标签：tin   continue   pen   .so   第三方   ems   enc   nts   lis   

# CalThreeKingdoms.py
import jieba

‘‘‘
安装第三方库 中文分词jieba
    pip install jieba
统计三国演义中出现次数最多的人
‘‘‘

txt = open("threekingdoms.txt", "rt", encoding="utf-8").read()
# 排除出现频率较高的非人名
exclude = ["却说", "二人", "不可", "荆州", "不能", "如此", "将军", "商议",
           "如何", "主公", "军士", "左右", "军马", "引兵", "次日", "大喜",
           "天下", "东吴", "于是", "今日", "不敢", "魏兵", "陛下", "一人",
           "都督", "人马", "不知", "汉中", "只见", "众将", "后主", "上马",
           "大叫", "蜀兵", "太守", "此人", "夫人", "先主", "后人", "背后",
           "城中", "天子", "一面", "何不", "大军", "忽报", "先生", "百姓",
           "何故", "然后", "先锋", "不如", "赶来"]
words = jieba.lcut(txt)
counts = {}
for word in words:
    if len(word) == 1 or word in exclude:
        continue
    elif word in ["丞相"]:
        word = "曹操"
    elif word in ["玄德", "玄德曰"]:
        word = "刘备"
    elif word in ["孔明", "孔明曰"]:
        word = "诸葛亮"
    elif word in ["关公", "云长"]:
        word = "关羽"
    counts[word] = counts.get(word, 0) + 1
counts = list(counts.items())
counts.sort(key=lambda x: x[1], reverse=True)
for i in range(15):
    word, count = counts[i]
    print("{:<10}: {:>10}".format(word, count))

python学习 第十一个程序 汉语文本词频统计

标签：tin   continue   pen   .so   第三方   ems   enc   nts   lis   

原文地址：https://www.cnblogs.com/wumingoo1/p/10324180.html