实例9：基本统计值计算

代码：

def getNum():     #获取用户不定长度的输入

nums = []

iNumStr = input("请输入数字(回车退出): ")

while iNumStr != "":  nums.append(eval(iNumStr))

iNumStr = input("请输入数字(回车退出): ")

return nums

def mean(numbers):   #计算平均值  s = 0.0

for num in numbers:  

s = s + num

return s / len(numbers)

实例10：文本词频统计

英文词频统计

程序代码：

#CalHamletV1.py

defgetText():

txt= open("hamlet.txt", "r").read()

txt= txt.lower()

forch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':  txt = txt.replace(ch, " ")

returntxt

hamletTxt= getText()

words      = hamletTxt.split()

counts= {}

forword in words:

counts[word]= counts.get(word,0) + 1  items =list(counts.items())

items.sort(key=lambdax:x[1], reverse=True)

fori in range(10):

word,count = items[i]

print("{0:<10}{1:>5}".format(word,count))

程序代码分析（略）

中文词频统计

程序代码：

#CalThreeKingdomsV1.py

importjieba

txt= open("threekingdoms.txt", "r",encoding="utf-8").read()  words= jieba.lcut(txt)

counts= {}

forword in words:

iflen(word) == 1:

continue

else:

counts[word]= counts.get(word,0) + 1 

items= list(counts.items()) 

items.sort(key=lambdax:x[1], reverse=True) 

fori in range(15):

word,count = items[i] print("{0:<10}{1:>5}".format(word, count))

出场人物统计：

#CalThreeKingdomsV2.py

importjieba

txt= open("threekingdoms.txt", "r",encoding="utf-8").read() excludes = {"将军","却说","荆州","二人","不可","不能","如此"} words = jieba.lcut(txt)

counts= {}

forword in words:

iflen(word) == 1:

continue

elifword == "诸葛亮" or word == "孔明曰":  rword = "孔明"

elifword == "关公" or word == "云长":  rword = "关羽"

elifword == "玄德" or word == "玄德曰":  rword = "刘备"

elifword == "孟德" or word == "丞相":

rword= "曹操"

else:

rword= word

counts[rword]= counts.get(rword,0) + 1

forword in excludes:

delcounts[word]

items= list(counts.items()) items.sort(key=lambda x:x[1], reverse=True) 

fori in range(10):

word,count = items[i]

print("{0:<10}{1:>5}".format(word,count))