Python零基础入门习题（六）红楼梦人物出场次数统计

前言

        Python语言简单易用，可读性强。在了解基础语法后，你就可以来尝试解决以下的题目。放心，本系列的文章都对新手非常友好。

---

一、生日悖论

生日悖论是指在不少于 23 个人中至少有两人生日相同的概率大于 50%。

请你验证一下。

import random
n=int(input("样本次数："))
cou=0
for num in range(n):
    birth=[]
    for i in range(60):
        a=random.randint(1,365)
        birth.append(a)
    if len(birth)!=len(set(birth)):
        cou+=1
print("{:.2f}%".format(cou/n*100))

二、绘制函数

import turtle
import math
turtle.speed(0)
turtle.penup()
turtle.goto(200,200)
turtle.pendown()
turtle.write("n=1 黑色 \n n=3 绿色 \n n=5 红色 \n n=7 黄色",False,'center',font=('arial',10,'bold')) #提示词
for n in range(1,8,2):
    turtle.penup()
    turtle.goto(-600,10*4*math.sin(0)/math.pi)
    turtle.pendown()
    if n==3:    turtle.color('green') #改变函数颜色
    elif n==5:    turtle.color('red')
    elif n==7:     turtle.color('yellow')
    x=0
    while(x<=50):
        y=0
        for k in range(1,n+1,2): #绘制函数
            y=y+4*math.sin(k*x)/(k*math.pi)
        turtle.goto(20*x-600,20*y)
        x+=0.02
turtle.exitonclick()

三、随机密码生成

请编写程序随机生成八组包含大小写字母及数字的密码。

import random
list=[]
password=()
for i in range(65,91):
    list.append(chr(i))
for i in range(97,123):
    list.append(chr(i))
for i in range(10):
    list.append(i) #大小写字母及数字
for i in range(10):
    password=tuple(random.sample(list,8)) #随机密码
    for j in range(8):
        print(password[j],end="")
    print("\n")

四、找出红楼梦中出场次数前30位的人物

提示：利用jieba库

#-*- coding : utf-8-*-
# coding:unicode_escape
import jieba
txt = open(r'dizhi\红楼梦.txt', 'r',encoding='GB18030').read()
# 利用分词函数lcut(),把txt中的句子分成词汇，存储在words中
words = jieba.lcut(txt)

#定义一个空集合或字典 counts
counts = {}

excludes={"一个","quot","什么","我们","那里","如今","你们","说道","知道","起来","这里","出来","姑娘","他们","众人","奶奶","自己",
          "一面","只见","两个","怎么","不是","不知","这个","听见","这样","进来","咱们","告诉","就是","东西","回来","大家","没有",
          "只是","只得","这些","丫头","不敢","出去","所以","不过","不好","姐姐","过来","的话","一时","不能","心里","如此","银子",
          "今日","答应","几个","二人","还有","说话","只管","一回","这么","那边","外头","打发","自然","这话","那些","今儿","罢了",
          "屋里","听说","小丫头","如何","问道","妹妹","看见","不用","人家","媳妇","原来","家里","一声","一句","不得","进去","到底",
          "这会子","姊妹","回去","过去","别人","丫鬟","连忙","还是","婆子","心中","身上","里头","方才","只有","不成","哥哥","小厮",
          "有人","于是","明白","这是","一日","起身","一件","那个","怎么样","已经","跟前","果然","有些","谁知","瞧瞧","不肯","只怕",
          "不必","越发","难道","好些","主意","吩咐","况且","母亲","不如","喜欢","不要","一处","此时","便是","上来","因此","看着",
          "不见","放心","女儿","素日","房中","想着","人来","还要","一样","在家","明日","言语","为什么","且说","不觉","别的","半日",
          "多少","想起","然后","走来","正是","许多","正说","一般","跟着","一会"}

#遍历变量words中的所有词汇
#如果是一个字，则不进行统计（人名没有一个字的）
#如果不是一个字，则counts[word](键值为word的词进行累计（counts[word] = counts.get(word,0) + 1））
for word in words:
    if len(word) == 1: #排除单个字符的分词结果
        continue
    elif word == "老太太" or word == "太太" or word == "老祖宗" or word == "史太君":
        rword = "贾母"
    elif word == "王熙凤" or word == "熙凤" or word == "凤辣子" or word == "凤姐儿":
        rword = "凤姐"
    elif word == "林黛玉" or word == "黛玉道" or word == "林丫头" or word == "林妹妹":
        rword = "黛玉"
    elif word == "宝姑娘" or word == "宝丫头" or word == "蘅芜君" or word == "宝姐姐":
        rword = "宝钗"
    elif word == "老爷" or word == "贾政道":
        rword = "贾政"
    elif word == "宝二爷" or word == "贾宝玉":
        rword = "宝玉"
    else:
        rword=word
    counts[rword] = counts.get(rword,0) + 1
#counts[word] = counts.get(word,0)+1 是对进行计数word出现的频率进行统计，当word不在words时，返回值是0，当word在words中时，返回+1，以此进行累计计数。

for word in excludes:
    del(counts[word])

items = list(counts.items())
# 把counts的项（键值对）转成序列。
items.sort(key=lambda x:x[1], reverse=True)
#sort是对列表（items)进行排序的函数，reverse=False 是升序，默认,reverse=True是降序；<列表名>.sort(key=none, reverse=False)没有返回值，但对原序列进行排序。
#那这个key=lambda x: x[1] 是什么意思呢，这个lambda是一个隐函数，在这里可以不用管它，记得有这个就可以，后面的x: x[1] 为对前面的对象中的第二维数据（即value）的值进行排序。

#打印前30位信息键值对。
for i in range(30):
    word, count = items[i]
    print ("{0:<10}{1:>5}".format(word, count))

五、打印5种食品

a,b="tomato","potato"
food=(a,b,"cucumber","coconut","spinach")
for j in range(5):
print(food[j])

下面这种方法会报错，想一想，为什么？ 

a,b="tomato","potato"
food=(a,b,"cucumber","coconut","spinach")
food[1]="water"
for j in range(5):
print(food[j])

a,b="tomato","potato"
food=(a,b,"cucumber","coconut","spinach")
a,b="water","juice"
food=(a,b,"cucumber","coconut","spinach")
for j in range(5):
    print(food[j])

---

总结

以上就是本文全部内容，你学会了吗？