Python第三天

匿名函数

1. 结构

lambda x1,x2...xn:表达式

2. 参数

参数有无限个，但是表达式只有一个
例如：

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('排序后：', name_info_list)
stu_info = [
    {"name": 'zs', "age": '18'},
    {"name": 'ls', "age": '19'},
    {"name": 'ww', "age": '20'},
    {"name": 'tq', "age": '21'},
]
stu_info.sort(key=lambda i: i['age'], reverse=True)
print('排序后：', stu_info)

列表推导式和字典解析

推导式comprehensions（又称解析式），是Python的一种独有特性。推导式是可以从一个数据序列构建另一个新的数据序列的结构体。

1. 列表推导式：列表推导式 ： [表达式 for 临时变量 in 可迭代对象 可以追加的条件]

2. 字典解析

字典推导和列表推导的使用方法是类似的，只不中括号该改成大括号。直接举例说明：
例1：

image.png

例2：

image.png

matplotlib库

matplotlib是Python编程语言及其数值数学扩展包 NumPy的可视化操作界面。它利用通用的图形用户界面工具包，如Tkinter, wxPython, Qt或GTK+，向应用程序嵌入式绘图提供了应用程序接口（API）。此外，matplotlib还有一个基于图像处理库（如开放图形库OpenGL）的pylab接口，其设计与MATLAB非常类似--尽管并不怎么好用。SciPy就是用matplotlib进行图形绘制。

1. 绘制曲线图

import numpy as np

plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False


x=np.linspace(0,2*np.pi,num=100)
print(x)
y=np.sin(x)
plt.plot(x,y,color='g',linestyle='--',label='sin(x)')

cosy=np.cos(x)

plt.plot(x,cosy, color='r',label='cos(x)')
plt.xlabel('时间(s)')
plt.ylabel('电压(v)')
plt.title('欢迎来到python世界')

plt.legend()
plt.show()

2. 绘制散点图

import numpy as np
import matplotlib.pyplot as plt
 
N = 1000
x = np.random.randn(N)
y = np.random.randn(N)
 
plt.scatter(x, y)
 
plt.show()

3.绘制柱状图

import string
from random import randint
# print(string.ascii_uppercase[0:6])
# ['A', 'B', 'C'...]
x = ['口红{}'.format(x) for x in string.ascii_uppercase[0:5]]

y = [randint(200, 500) for _ in range(5)]
print(x)
print(y)
plt.xlabel('口红品牌')
plt.ylabel('价格（元）')
plt.bar(x, y)
plt.show()

4. 绘制饼图

from random import randint
import string
counts = [randint(3500, 9000) for _ in range(6)]
labels = ['员工{}'.format(x) for x in string.ascii_lowercase[:6] ]
# 距离圆心点距离
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%%',colors=colors)
plt.legend(loc=2)
plt.axis('equal')
plt.show()

实例练习

三国人物top10饼状图

from wordcloud import WordCloud
import jieba
import imageio

mask = imageio.imread('./china.jpg')
# 1.读取小说内容
with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
    words = f.read()

    counts = {}  # {‘曹操’:234，‘回寨’:56}
    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"}
    # 2. 分词
    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] = 取出字典中原来键对应的值 + 1
            # counts[word] = counts[word] + 1  # counts[word]如果没有就要报错
            # 字典。get（k） 如果字典中没有这个键 返回 NONE
            counts[word] = counts.get(word, 0) + 1

    print(len(counts))
    # 3. 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]

    # 4.排序 [(), ()]
    items = list(counts.items())
    print(items)

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

    items.sort(key=lambda i: i[1], reverse=True)

    li=[]
    peo_li=[]
    for i in range(10):
        # 序列解包
        role, count = items[i]
        a={'name':'','count':0}
        a['name']=role
        a['count']=count
        peo_li.append(a)
        print(role, count)
        for _ in range(count):      #_是告诉看代码的人循环里不需要使用临时变量
            li.append(role)

    # 5得出结论
    text=' '.join(li)
    WordCloud(
        font_path='msyh.ttc',
        background_color='white',
        width=800,
        height=600,
        mask=mask,
        #相邻两个值的重复
        collocations=False
    ).generate(text).to_file('Top10.png')

    #用饼图显示人物
    from random import randint
    import string
    from matplotlib import pyplot as plt

    plt.rcParams["font.sans-serif"] = ['SimHei']
    plt.rcParams['axes.unicode_minus'] = False

    counts = []
    labels = []
    for i in range(len(peo_li)):
        counts.append(peo_li[i]['count'])
        labels.append(peo_li[i]['name'])
    # 距离圆心点距离
    explode = [0.1, 0, 0, 0, 0, 0,0,0,0,0]
    #colors = ['red', 'purple', 'blue', 'yellow', 'gray', 'green']
    plt.pie(counts, explode=explode, shadow=True, labels=labels, autopct = '%1.1f%%')
    plt.legend(loc=2)
    plt.axis('equal')
    plt.show()

image.png

红楼梦练习

from wordcloud import WordCloud
import jieba
import imageio

mask = imageio.imread('./china.jpg')
# 1.读取小说内容
with open('./novel/all.txt', 'r', encoding='utf-8') as f:
    words = f.read()
    #print(words)
    counts = {}
    excludes = {"什么", "一个", "我们", "你们", "如今", "说道", "知道", "起来", "这里",
               "出来", "众人", "那里", "自己", "一面", "只见", "太太", "两个", "没有",
               "怎么", "不是", "不知", "这个", "听见", "这样", "进来", "咱们", "就是",
               "老太太", "东西", "告诉", "回来", "只是", "大家", "姑娘", "奶奶", "凤姐儿","分节"}
    # 2. 分词
    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] = 取出字典中原来键对应的值 + 1
            # counts[word] = counts[word] + 1  # counts[word]如果没有就要报错
            # 字典。get（k） 如果字典中没有这个键 返回 NONE
            counts[word] = counts.get(word, 0) + 1

    print(len(counts))
    # 3. 词语过滤,删除无关词，重复词
    counts['贾母'] =  counts['贾母'] +  counts['老太太']
    counts['宝钗'] = counts['宝钗'] + counts['薛宝钗']
    counts['凤姐'] = counts['凤姐儿'] + counts['王熙凤'] +counts['凤姐']
    counts['宝玉'] = counts['贾宝玉'] +counts['宝玉']
    counts['王夫人'] = counts['王夫人'] + counts['太太']
    counts['黛玉'] = counts['黛玉'] + counts['林黛玉']
    counts['贾政']=counts['贾政']+counts['老爷']
    for word in excludes:
        del counts[word]

    # 4.排序 [(), ()]
    items = list(counts.items())
    #print(items)


    items.sort(key=lambda i: i[1], reverse=True)

    li=[]
    peo_li=[]
    for i in range(10):
        # 序列解包
        role, count = items[i]
        a={'name':'','count':0}
        a['name']=role
        a['count']=count
        peo_li.append(a)
        print(role, count)
        for _ in range(count):      #_是告诉看代码的人循环里不需要使用临时变量
            li.append(role)

    # 5得出结论
    text=' '.join(li)
    WordCloud(
        font_path='msyh.ttc',
        background_color='white',
        width=800,
        height=600,
        mask=mask,
        #相邻两个值的重复
        collocations=False
    ).generate(text).to_file('红楼Top10.png')

    #用饼图显示人物
    from random import randint
    import string
    from matplotlib import pyplot as plt

    plt.rcParams["font.sans-serif"] = ['SimHei']
    plt.rcParams['axes.unicode_minus'] = False

    counts = []
    labels = []
    for i in range(len(peo_li)):
        counts.append(peo_li[i]['count'])
        labels.append(peo_li[i]['name'])
    # 距离圆心点距离
    explode = [0.1, 0, 0, 0, 0, 0,0,0,0,0]
    #colors = ['red', 'purple', 'blue', 'yellow', 'gray', 'green']
    plt.pie(counts, explode=explode, shadow=True, labels=labels, autopct = '%1.1f%%')
    plt.legend(loc=2)
    plt.axis('equal')
    plt.show()

image.png