python学习文本词频统计，hamlet.txt，三国演义.txt

python学习文本词频统计，hamlet.txt，三国演义.txt，英文文章使用split(),中文文章使用jieba.lcut()。

hamlet.txt，三国演义.txt文本的下载地址：https://download.csdn.net/download/tommycsdn/16607738

excludes={"the","and","of","you","a","i","my","in","to","it","is","not"}
def getText():
    txt=open("hamlet.txt","r").read()
    txt=txt.lower()
    for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_`{|}~':
        txt=txt.replace(ch," ")
    return txt
hamletTxt=getText()
words=hamletTxt.split()
counts={}
for word in words:
    counts[word]=counts.get(word,0)+1
for word in excludes:
    del(counts[word])
items=list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
for i in range(10):
    word,count=items[i]
    print("{0:<10}{1:5}".format(word,count))

import jieba
excludes={"将军","却说","荆州","二人","不可","不能","如此"}
txt=open("三国演义.txt","r",encoding='utf-8').read()
words=jieba.lcut(txt)
counts={}
for word in words:
    if len(word)==1:
        continue
    elif word=="诸葛亮" or word=="孔明曰":
        rword="孔明"
    elif word=="关公" or word=="云长":
        rword="关羽"
    elif word=="玄德" or word=="玄德曰":
        rword="刘备"
    elif word=="孟德" or word=="丞相":
        rword="曹操"
    else:
        rword=word
    counts[rword]=counts.get(rword,0)+1
for word in excludes:
    del(counts[word])
items=list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)
for i in range(20):
    word,count=items[i]
    print("{0:<10}{1:<5}".format(word,count))