包含去除標(biāo)點符號和換行、空格等因素

import pandas as pddef question1():words = ['賈寶玉', '寶玉', '林黛玉', '黛玉']with open("HLM-UTF-8.txt", 'r', encoding='UTF-8') as r:lines = r.readlines()with open('result1.txt', 'w', encoding='UTF-8') as w:for word in words:w.write(word + '出現(xiàn)的行數(shù)及行如下：\n')for line in lines:if word in line:w.write(str(lines.index(line) + 1) + line)w.close()r.close()def question2():result = {}with open("HLM-UTF-8.txt", 'r', encoding='UTF-8') as r:lines = r.readlines()for line in lines:line = line.strip()for char in '!"#$&()*+,-./:;<=>?@[\\]^_{|}·~‘’\n\'＂＃＄％＆＇（）＊＋，－／：；＜＝＞＠［＼］＾＿｀｛｜｝～｟｠｢｣､　、〃〈〉《》「」『』【】〔〕〖〗?????〝〞????–—‘’?“”??…?﹏﹑﹔·！？｡。\u3000':line = line.replace(char, "")for char in line:if char in list(result.keys()):result[char] += 1else:result[char] = 1df = pd.DataFrame(result, index=[0]).Tdf.to_csv("result2.csv", encoding='utf-8-sig')r.close()def question3():result = {}with open('JaneEyre.txt', 'r') as r:lines = r.readlines()for line in lines:line = line.lower()for char in '!"#$&()*+,-./:;<=>?@[\\]^_{|}·~‘’\u3000\n\'':line = line.replace(char, "")words = line.split(' ')for word in words:if word in list(result.keys()):result[word] += 1else:result[word] = 1del result['']df = pd.DataFrame(result, index=[0]).Tdf.to_csv("result3.csv")r.close()if __name__ == '__main__':# question1()question2()# question3()

總結(jié)

以上是生活随笔為你收集整理的Python 统计红楼梦、Jane Eyre词频方法的全部內(nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯，歡迎將生活随笔推薦給好友。