第四次作业（刘帅）

要求：
1.初始化start_day，end_day两个日期
from datetime import datetime
start_day=datetime(2019,4,1)
end_day=datetime(2019,4,30)
其它时间数据生成要用datetime或date模块的方法编程实现
2.不能使用calendar模块生成

from datetime import datetime
from datetime import *
start_day = datetime(2019, 4, 1)
end_day = datetime(2019, 4, 30)
a = end_day-start_day
amount = a.days + 1
first = start_day.isoweekday()
k = 0
count = 0
print("\t\t\t2019年4月")
print("星期日 星期一 星期二 星期三 星期四 星期五 星期六")
while k<=first:
    k+=1
    count+=1
    print("\t", end="")
 
day = 1
while day <= amount:
    print(day, end="\t")
    day += 1
    count += 1
    if (count % 7 == 0):
        print("\n")

 

设计题2：

1.参考“三国演义”词频统计程序，实现对红楼梦出场人物的频次统计。
2.（可选）
将红楼梦出场人物的频次统计结果用词云显示。

import jieba
excludes = {"什么","我们","那里","一个","如今","说道","起来","知道","姑娘","这  里","出来","他们",
            "众人","自己","你们","太太","只见","怎么","奶奶","两个","没有","不是","不知","一面",
            "这个","这个","听见","这样","进来","咱们","告诉","就是","东西","平儿","袭人","回来", 
            "只是","老爷","大家","只得","薛姨妈","姐姐","贾政","只管","晴雯","贾珍",
            "这么","说话","一回","那边","这话","外头","打发","丫头","今日","银子","几个","答应",
            "这些","不敢","出去","所以","不过","的话","不好","鸳鸯","一时","不能","过来","心里",
            "二人","自然","今儿","罢了","还有","屋里","如此","那些","听说","小丫头","邢夫人",
            "如何","问道","看见","紫鹃","妹妹","人家","不用","媳妇","香菱","原来","一声","一句"
          }
txt = open(r"D:\Pyhon\project\venv\Scripts\红楼梦.txt", "r", encoding='utf-8').read()
words  = jieba.lcut(txt)#精确模式的分词函数，返回一个列表数据类型
#print(type(words)) #words的数据类型
counts = {}  #定义一个字典
for word in words:
    if len(word) == 1:
        continue
    elif word == "宝玉" or word == "二爷" or word == "怡红公子" or word == "富贵闲人" or word == "无事忙" or word == "宝哥哥" or word == "宝兄弟" or word == "宝叔叔" or word == "混世魔王" or word == "绛洞花王" or word == "浊玉" or word == "遮天大王" or word == "槛内人": 
        rword = "贾宝玉"
    elif word == "黛玉" or word == "潇湘妃子" or word == "林妹妹" or word == "林姑娘" or word == "颦儿" or word == "颦颦":
        rword = "林黛玉"
    elif word == "宝钗" or word == "蘅芜君" or word == "宝姐姐" or word == "宝丫头" or word == "宝姑娘":
        rword = "薛宝钗"
    elif word == "熙凤" or word == "琏二奶奶" or word=="凤辣子" or word=="凤哥儿" or word=="凤丫头" or word == "脂粉英雄" or word=="凤姐" or word=="凤姐儿":
        rword = "王熙凤"
    elif word == "贾母" or word == "老太太" or word == "史太君" or word == "老祖宗":
        rword = "贾母"
    elif word == "枕霞旧友" or word == "史大姑娘" or word == "云妹妹"  or word == "湘云":
        rword = "史湘云"
    elif word == "探春" or word == "三姑娘" or word == "蕉下客":
        rword = "贾探春" 
    elif word == "刘姥姥" or word == "母蝗虫":
        rword = "刘姥姥"  
    elif word == "琏二爷" or word == "贾琏道":
        rword = "贾琏"
    elif word == "王夫人道":
        rword = "王夫人"    
    else:
        rword = word
    counts[rword] = counts.get(rword,0) + 1 #词汇加入字典
for word in excludes:
    del(counts[word])  #从字典中删除无用词
items = list(counts.items())#字典转换为列表

#lambda是一个隐函数，是固定写法，以下命令的意思就是按照记录的第2列排序
items.sort(key=lambda x:x[1], reverse=True)

for i in range(10): #出现的词频统计
    word, count = items[i] #将键和值分别赋予列表word和countf
    print ("{0:<10}{1:>5}".format(word, count))#0:<10左对齐，宽度10，”>5"右对齐