1.三国人物分析

import jieba
from wordcloud import WordCloud
import  numpy as np 
with open('./novel/threekingdom.txt','r',encoding='utf-8')as f:
    words=f.read()
    counts={}
    excludes = {"将军", "却说", "丞相", "二人", "不可", "荆州", "不能", "如此", "商议",
                "如何", "主公", "军士", "军马", "左右", "次日", "引兵", "大喜", "天下",
                "东吴", "于是", "今日", "不敢", "魏兵", "陛下", "都督", "人马", "不知",
                "孔明曰", "玄德曰", "刘备", "云长"}
    words_list=jieba.lcut(words)
    print(words_list)
    for word in words_list:
        if len(word)<=1:
            continue
        else:
            # 更新字典中的值
            counts[word]=counts.get(word,0)+1
    print(counts)

    #词语过滤，删除无关词，重复词
    counts['孔明'] = counts['孔明'] + counts['孔明曰']
    counts['玄德'] = counts['玄德'] + counts['玄德曰'] + counts['刘备']
    counts['关公'] = counts['关公'] + counts['云长']
    for word in excludes:
        del counts[word]
    #排序
    items =list(counts.items())
    print(items)

    def sort_by_count(x):
        return x[1]
    items.sort(key=sort_by_count,reverse=True)

    li=[]

    for i in range(10):
        #序列解包
        role,count=items[i]
        print(role,count)
        for _ in range(count):
            li.append(role)

    text=' '.join(li)
    WordCloud(
        font_path="msyh.ttc",
        background_color='white',
        width=800,
        height=600,
        #相邻两个重复词之间的匹配
        collocations=False
    ).generate(text).to_file('TOP10.png')

2.匿名函数

• 结构 lambda x1,x2....xn:表达式

sum_num=lambda x1,x2:x1+x2
print(sum_num(2,3))

name_info_list = [
    ('张三',4500),
    ('李四',9900),
    ('王五',2000),
    ('赵六',5500),
]
name_info_list.sort(key=lambda x:x[1],reverse=True)
print(name_info_list)

3.列表推导式

• 列表推导式，列表解析多个字典解析
• 常规方式创建列表

li=[]
for i in range(10):
    li.append(i)
print(li)

• 列表推导式创建列表
• [表达式 for 临时变量 in 可迭代对象 可追加条件]

print([i for i in range(10)])

• 常规方式的列表解析

#筛选出列表中所有的偶数
li =[]
for i in range(10):
    if i%2==0:
        li.append(i)
print(li)

• 列表推导式列表解析

print([i for i in range(10) if i%2==0])

• 字典解析

#字典解析
#生成100个学生的成绩
from random import randint
stu_grades = {'student{}'.format(i):randint(50, 100) for i in range(1, 101)}
print(stu_grades)

#筛选大于60分的所有学生
print({k:v for k,v in stu_grades.items() if v>60})

4.matplotlib各种图的制作

导入

from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import  numpy as np

绘制正弦曲线

使用100个点 绘制[0,2π]正弦曲线
.linspace左闭右闭区间的等差数列
x=np.linspace(0,2*np.pi,num=100)
print(x)
y=np.sin(x)

正弦余弦在同一坐标下
cosy=np.cos(x)
plt.plot(x,y,linestyle='--',label='sin(x)')
plt.plot(x,cosy,label='cos(x)')
plt.xlabel('时间(s)')
plt.ylabel('电压(v)')
plt.title('欢迎来到python世界')
#图例
plt.legend()
plt.show()

正弦曲线图.png

绘制柱状图

import string
from random import randint
# print(string.ascii_uppercase[:6])
x=['口红{}'.format(x) for x in string.ascii_uppercase[:5]]
y=[randint(200,500) for _ in range(5) ]
print(x)
print(y)
plt.xlabel('口红品牌')
plt.ylabel('口红价格')
#显示柱状图
plt.bar(x,y)
plt.show()

柱状图.png

绘制饼图

• .pie(字典的value 转换成列表，labels=字典的keys转换为列表，精确度)

import string
from random import randint
counts=[randint(1500,9000) for _ in range(6)]
labels=['员工{}'.format(x) for x in string.ascii_lowercase[:6]]
#距离圆心点的距离
explode=[0.1,0,0,0,0,0]
colors = ['red', 'purple','blue', 'yellow','gray','green']
plt.pie(counts,explode=explode,shadow=True,labels=labels,autopct='%1.1f%%')
#象限位置
plt.legend(loc=2)
#不重叠
plt.axis('equal')
plt.show()

饼图.png

绘制散点图

#均值为0，标准差为1的正态分布数据
x=np.random.normal(0,1,1000000)
y=np.random.normal(0,1,1000000)
#alpha透明度
plt.scatter(x,y,alpha=0.1)
plt.show()

散点图.png

红楼梦人物出现饼图

#红楼梦top10人物饼图
import jieba
from wordcloud import WordCloud
from matplotlib import pyplot as plt
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
import  numpy as np
with open('./novel/all.txt','r',encoding='utf-8')as f:
    words=f.read()
    counts={}
    excludes={"什么", "一个", "我们", "你们", "如今", "说道", "太太", "知道", "姑娘",
                "起来", "这里", "出来", "众人", "那里", "自己", "一面", "只见", "两个",
                "没有", "怎么", "不是", "不知", "这个", "听见", "奶奶", "老太太", "不知",
                "这样", "进来", "咱们", "就是", "东西", "告诉", "回来", "只是", "大家",
                "老爷", "只得", "丫头", "这些", "他们", "不敢", "出去", "所以", "贾宝玉",
                "林黛玉", "薛宝钗", "凤姐儿", "王熙凤"}
    words_list=jieba.lcut(words)
    for word in words_list:
        if len(word)<=1:
            continue
        else:
            # 更新字典中的值
            counts[word]=counts.get(word,0)+1
    # print(counts)

    #词语过滤
    counts['贾母'] = counts['贾母'] + counts['老太太']
    counts['黛玉'] = counts['黛玉'] + counts['林黛玉']
    counts['宝玉'] = counts['宝玉'] + counts['贾宝玉']
    counts['宝钗'] = counts['宝钗'] + counts['薛宝钗']
    counts['老爷'] = counts['老爷'] + counts['贾政']
    counts['王夫人'] = counts['王夫人'] + counts['太太']
    counts['凤姐'] = counts['凤姐儿'] + counts['凤姐'] + counts['王熙凤']
    for word in excludes:
        del counts[word]
    #排序
    items=list(counts.items())
    def sort_by_count(x):
        return x[1]
    items.sort(key=sort_by_count, reverse=True)
    print(items)
    li=[]
    for i in range(10):
        role, count = items[i]
        print(role, count)
        for _ in range(count):
            li.append(role)

    #饼图
    cs=[items[i][1] for i in range(10)]
    label=[items[i][0] for i in range(10)]
    plt.pie(cs,labels=label,autopct='%1.1f%%')
    plt.legend(loc=2)
    plt.axis('equal')
    plt.show()

红楼梦.png

三国.png