词频统计实例

实例：词频统计

#词频统计
import pprint
text = """
The Python Software Foundation (PSF) is a 501(c)(3) non-profit corporation that holds the intellectual 
property rights behind the Python programming language. We manage the open source licensing for Python 
version 2.1 and later and own and protect the trademarks associated with Python. We also run the North 
American PyCon conference annually, support other Python conferences around the world, and fund Python 
related development with our grants program and by funding special projects. 
"""
punctuation = "n~@#$%^&*()_-+=<>?/,.:;{}[]|\'\""  # 标点符号
for i in punctuation:
        if i in text:
            text.replace(i,' ')#去除标点符号
text_list = text.split(' ')#空格分开
text_list = [x.strip() for x in text_list]#去除换行符
number = set(text_list)#去重，准换为集合
word_number = {}
for word in number:
    word_number[word] = text_list.count(word)#计数，字典对应起来
sort_list = sorted(word_number.items(),key=lambda x:x[1],reverse=True)#排序
pprint.pprint(sort_list)

//输出
[('the', 6),
 ('Python', 5),
 ('and', 5),
 ('with', 2),
 ('We', 2),
 ('', 1),
 ('trademarks', 1),
 ('other', 1),
 ('program', 1),
 ('run', 1),
 ('is', 1),
 ('behind', 1),
 ('for', 1),
 ('protect', 1),
 ('Foundation', 1),
 ('also', 1),
 ('intellectual', 1),
 ('fund', 1),
 ('Python.', 1),
 ('our', 1),
 ('by', 1),
 ('special', 1),
 ('North', 1),
 ('conference', 1),
 ('that', 1),
 ('annually,', 1),
 ('manage', 1),
 ('programming', 1),
 ('version', 1),
 ('American', 1),
 ('own', 1),
 ('related', 1),
 ('Software', 1),
 ('source', 1),
 ('conferences', 1),
 ('property', 1),
 ('holds', 1),
 ('licensing', 1),
 ('501(c)(3)', 1),
 ('development', 1),
 ('later', 1),
 ('(PSF)', 1),
 ('associated', 1),
 ('The', 1),
 ('world,', 1),
 ('funding', 1),
 ('2.1', 1),
 ('projects.', 1),
 ('a', 1),
 ('rights', 1),
 ('language.', 1),
 ('corporation', 1),
 ('grants', 1),
 ('non-profit', 1),
 ('open', 1),
 ('PyCon', 1),
 ('support', 1),
 ('around', 1)]

进程已结束,退出代码0