Python在文件中对字母、单词频度统计

读入给定的文本文件“hamlet.txt”，编写两个函数分别实现:

1) 统计所有字母的出现频度,依据频度从高到低，显示前5个字母及其频度，同时把结果写入文件“hamlet_字母频度.txt”。

2) 统计所有单词的出现频度,依据频度从高到低，显示前10个单词及其频度，同时把结果写入文件“hamlet_单词频度.txt”。

 

import re
from collections import Counter
f=open("hamlet.txt", "r", encoding="utf-8")
line = f.readlines()
f.close()
txt = ""
for i in line:
    txt += i
txt=txt.lower()
def Read01():
    letters = ""
    for i in txt:
        if i.islower():
            letters+=i
    letterf = Counter(letters)
    letterf = sorted(letterf.items(), key=lambda x:x[1], reverse=True)
    of = open("./hamlet_字母频度.txt", 'w')
    print(letterf, file=of)
    of.close()
    print("字母频度:")
    counts = 0
    for i in letterf:
        counts += 1
        if counts > 5:
            break
        print(i)

def Read02():
    words = re.split("[,， |\n]",txt)
    words_ = []
    for w in words:
        if re.match(r'[A-Za-z0-9_]', w):
            words_.append(w)
    wordf = Counter(words_)
    wordf = sorted(wordf.items(), key=lambda x: x[1], reverse=True)
    of = open("./hamlet_单词频度.txt", 'w')
    print(wordf, file=of)
    of.close()
    print("单词频度:")
    counts=0
    for i in wordf:
        counts+=1
        if counts > 10:
            break
        print(i)
Read01()
print("*"*50)
Read02()

字母频度统计数据：

 

 

单词频度统计数据：

 

运行结果：