08 分布式计算MapReduce--词频统计

import re

import collections

def count_word(path):

    result={}

    with open(path) as file_process:

        texts = file_process.read()

        # 小写

        texts = texts.lower()

        # 过滤标点

        texts = re.sub("\"|,|\.|!|\?"," ",texts)

        for word in texts.split():

            if word not in result:

                result[word]=0

            result[word] +=1

        return result

def sort_by_count(d):

    # 排序

    d = collections.OrderedDict(sorted(d.items(), key=lambda t: -t[1]))

    return d

# 文件名

file_name = "./english.txt"

dword = count_word(file_name)

dword = sort_by_count(dword)

# 输出

for key, value in dword.items():

    print(key, value, sep=":")