walden词频统计0

#输出py:%%writefile walden.py
#打开并读取文件、
file=open(r'C:\Users\Administrator\Desktop\Walden.txt','r')
lines=file.readlines()

#要把每行拆成单词
words = []
for line in lines:
    # 1 print(line.split(" "))
    tmp_list=line.split(" ")
    for word in tmp_list:
        words.append(word)
words

#对words中每一个元素出现的个数
#统计结果保存到字典中，字典的key是单词，value是单词初选的次数
word_count = {}
word_set = set(words)
for word in word_set:
    count_num = words.count(word)
    word_count[word] = count_num
word_count     
#words.count('pages')

#对word_count字典进行排序，按照出现的次数（value）进行降序排列
#sorted(word_count.items())
sorted(word_count.items(),key=lambda item: item[1],reverse=True)
#word_count.items()