第二部分 程序的控制结构 - 3

Computer are goos at following instructions,but not at reading your mind.
— Donald Knuth

组合数据类型

基本统计值计算

from math import sqrt
def getNum():
    nums =[] #list
    iNumStr =input("Please enter number：")
    while iNumStr !="":
        nums.append(eval(iNumStr))
        iNumStr = input("Please enter number：（exit by 'enter')")
    return nums

def mean(numbers):
    s=0.0
    for num in numbers:
        s = s+num
    return s/len(numbers)

def dev(numbers,mean):
    sdev =0.0
    for num in numbers:
        sdev += (num-mean)**2
    return sqrt(sdev/(len(numbers)-1))

def median(numbers):
    sorted(numbers)
    size =len(numbers)
    if size % 2 ==0:
        med = (numbers[size//2-1]+numbers[size//2])
    else:
        med = numbers[size//2]
    return med

n=getNum()
m=mean(n)
print("The mean is ：{},The variance is :{},The median number is :{}.".format(m,dev(n,m),median(n)))

Please enter number：>? 99
Please enter number：（exit by 'enter')>? 98
Please enter number：（exit by 'enter')>? 97
Please enter number：（exit by 'enter')>? 96
Please enter number：（exit by 'enter')>? 95
Please enter number：（exit by 'enter')>? 
The mean is ：97.0,The variance is :1.5811388300841898,The median number is :97.

带排除的哈姆雷特英文词频统计

#e10.2CalHamlet.py
excludes = {"the","and","of","you","a","i","my","in"}
def getText():
    txt = open("hamlet.txt", "r").read()
    txt = txt.lower()
    for ch in '!"#$%&()*+,-./:;<=>?@[\\]^_‘{|}~':
        txt = txt.replace(ch, " ")   #将文本中特殊字符替换为空格
    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))

三国演义中文人名词频统计

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