Python语言程序设计基础（第2版） 课后题 第六章

课后题是配套的参考答案

#e10.1CalHamlet.py
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
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))

the        1086
and         967
to          757
of          675
you         555
a           554
i           551
my          520
in          433
it          419

#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))

to          757
it          419
that        388
ham         358
is          346
not         314
his         304
this        298
with        278
but         273

#e10.3CalThreeKingdoms.py
import jieba
excludes = {}#{"将军","却说","丞相"}
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:  #排除单个字符的分词结果
        continue
    else:
        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(15):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

Building prefix dict from the default dictionary ...
Loading model cost 1.020 seconds.
Prefix dict has been built succesfully.


曹操          953
孔明          836
将军          772
却说          656
玄德          585
关公          510
丞相          491
二人          469
不可          440
荆州          425
玄德曰         390
孔明曰         390
不能          384
如此          378
张飞          358

#e10.4CalThreeKingdoms.py
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))

曹操         1451
孔明         1383
刘备         1252
关羽          784
张飞          358

#6.1
from random import randint
def randd():
    pword=''
    for i in range(8):
         u = randint(0,62)
         if u>=10:
             if 90<(u+55)<97:
                 pword+=chr(u+62)
             else:
                 pword+=chr(u+55)
             print("{} ".format(u+55),end="") 
         else:
             pword+='%d'%u
    return pword

def main():
     for i in range(1,11):
         print("生成的第{}个密码是：{}".format(i,randdd()))
main()

115 99 65 75 生成的第1个密码是：7scA5K69
100 98 97 76 71 72 81 109 生成的第2个密码是：dbaLGHQm
115 67 67 65 112 104 66 生成的第3个密码是：sCCAphB3
116 113 72 90 75 108 109 生成的第4个密码是：tq9HZKlm
66 114 71 66 80 生成的第5个密码是：6BrG6B2P
89 103 95 114 80 87 生成的第6个密码是：Y3gfrP2W
95 108 111 71 87 115 生成的第7个密码是：floG3Ws0
101 75 81 75 71 生成的第8个密码是：eKQ52K4G
84 77 93 82 107 116 70 生成的第9个密码是：T4MdRktF
84 83 79 77 104 89 89 生成的第10个密码是：TSOM5hYY

#6.2
def main():
     num=[]
     n=input("请输入一组数字(或者直接按回车结束程序):")
     while n!="":
         num.append(eval(n))
         n=input("请输入一组数字(或者直接按回车结束程序):")
     else:
         print("正在处理，请稍等")
         judge(num)
        
def judge(n):
     if len(n) == len(set(n)):
         print("鉴定完毕，没有重复的元素")
     else:
         print("有重复的元素，总共有{}个".format(len(n)-len(set(n))))
main()

请输入一组数字(或者直接按回车结束程序):56
请输入一组数字(或者直接按回车结束程序):25
请输入一组数字(或者直接按回车结束程序):56
请输入一组数字(或者直接按回车结束程序):22
请输入一组数字(或者直接按回车结束程序):11
请输入一组数字(或者直接按回车结束程序):
正在处理，请稍等
有重复的元素，总共有1个

#6.4
txt=input("请输入您想输入的英文句子：")
counts={}
ex=[',','.','?','!',':','"',';']

for i in txt:
     if i == " " or i in ex:
         continue
     else:
         if ord(i)<97:
             i=chr(ord(i)+32)
         counts[i]=counts.get(i,0)+1
        
items=list(counts.items())
items.sort(key=lambda x:x[1],reverse=True)

for u in range(len(items)):
     alpha,count=items[u]
     print("{} -> {}".format(alpha,count))

请输入您想输入的英文句子：hsgstge
s -> 2
g -> 2
h -> 1
t -> 1
e -> 1

#6.6
import jieba.posseg as ps

txt = open('红楼梦.txt','r',encoding = 'utf-8').read()
exclude = ['明白']
counts = {}

def countFigures():
    words = ps.cut(txt)
    for w in words:
        if len(w.word) == 1:
            continue
        if w.flag == 'nr':
            counts[w.word] = counts.get(w.word, 0) + 1
    for key in exclude:
        del(counts[key])
    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))
        
countFigures()

宝玉         3748
贾母         1252
凤姐         1129
王夫人        1011
老太太         966
黛玉          870
宝钗          747
贾琏          679
凤姐儿         470
薛姨妈         453
贾政          433
探春          432
紫鹃          406
小丫头         287
贾珍          284
邢夫人         284
林黛玉         280
尤氏          267
薛蟠          237
贾蓉          176