综合练习:词频统计

代码如下:

# -*- coding:utf-8 -*-

fo=open('/Users/Administrator/Desktop/song.txt','r')
song=fo.read()
fo.close()

symbol = list(''',.?!’:"“”-%$''')
for i in symbol:
    song = song.replace(i, ' ')
song = song.lower()
split = song.split()
word = {}
for i in split:
    count = song.count(i)
    word[i] = count
words = '''
a an the in on to at and of is was are were i he she you your they us their our it or for be too do no 
that s so as but it's
'''
prep = words.split()
for i in prep:
    if i in word.keys():
        del(word[i])
word = sorted(word.items(), key=lambda item: item[1], reverse=True)
for i in range(10):
    print(word[i])

运行截图:

原文地址:https://www.cnblogs.com/131li/p/8649542.html