一、lambda表达式——匿名函数

1. 定义：lambda x1, x2....xn: 表达式
2. 特点：参数可以是无限多个，但是表达式只有一个，即返回值
3. 应用例子

#应用于只使用一次的函数，如排序时
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)

stu_info = [
    {"name":'zhangsan', "age":18},
    {"name":'lisi', "age":30},
    {"name":'wangwu', "age":99},
    {"name":'tiaqi', "age":3},
]
stu_info.sort(key=lambda i:i['age'])
print(stu_info)

二、列表推导式

1. 定义：[表达式 for 临时变量 in 可迭代对象 可以追加条件]
2. 使用例子

#筛选出偶数
print([i for i in range(10) if i%2 == 0])

# 筛选出列表中大于0的数
from random import randint
num_list = [randint(-10, 10) for _ in range(10)]#在-10和10之间生成10个随机数
print(num_list)
print([i for i in num_list if i>0])

# 筛选大于 60分的所有学生
stu_grades = {'student{}'.format(i):randint(50, 100) for i in range(1, 101)}# 生成100个学生的成绩
print({k: v for k, v in stu_grades.items() if v >60})

三、使用matplotlib绘图库进行图表绘制

折线图——plot

#使用100个点绘制[0,2π]正弦曲线图
x = np.linspace(0,2*np.pi,num=100)#linspace() 左闭右闭区间的等差数列
print(x)
siny = np.sin(x)
cosy = np.cos(x)
plt.plot(x,siny,color='r',label='sin(x)',linestyle=':')
plt.plot(x,cosy,color='b',label='cos(x)')
plt.xlabel('时间/s')
plt.ylabel('电压/V')
plt.title('welcome')
plt.legend() #图例
plt.show()

柱状图——bar

import string
from random import randint
x = ['口红{}'.format(x) for x in string.ascii_letters[:5]]
y = [randint(200,500) for _ in range(5)]
print(x)
print(y)
plt.xlabel('品牌')
plt.ylabel('销量')
plt.title('销量表')
plt.bar(x,y)
plt.show()

饼图——pie

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)#loc参数指定图例位于第几象限
plt.axis('equal')#使图例和图不重叠
plt.show()

散点图——scatter

均值为 0 标准差为1 的正态分布数据
x = np.random.normal(0, 1, 1000)
y = np.random.normal(0, 1, 1000)
plt.scatter(x, y, alpha=0.1)
plt.show()

四、文本分析

三国演义人名词频分析

import jieba
from wordcloud import WordCloud
import imageio
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/threekingdom.txt", "r", encoding="UTF-8") as f:
    words = f.read()
    counts = {}
    word_list = jieba.lcut(words)
    for word in word_list:
        if len(word)<=1:
            continue
        else:
            counts[word] = counts.get(word, 0) + 1
    print(counts)

    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"]
    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"}
    for word in excludes:
        del counts[word]
    #将字典转化成元组型列表
    items = list(counts.items())
    items.sort(key=lambda x:x[1], reverse=True)

    #序列解包
    li = []
    for i in range(10):
        role, count = items[i]
        print(role, count)
        for _ in range(count):#_表示循环里面用不到这个临时变量
            li.append(role)

    text = " ".join(li)
    WordCloud(
        font_path = "msyh.ttc",
        background_color = 'white',
        width = 800,
        height = 600,
        collocations = False,
        mask = imageio.imread('./china.jpg')
    ).generate(text).to_file("TOP10.jpg")

    #将词频前十的人名生成饼图
    name = []
    times = []
    for i in range(0,10):
        name.append(items[i][0])
        times.append(items[i][1])
    print(name)
    print(times)
    plt.pie(times, explode=[0.3,0,0,0,0,0,0,0,0,0], shadow=True, labels=name, autopct='%1.1f%%')
    plt.legend(loc=2)#loc参数指定图例位于第几象限
    plt.axis('equal')#使图例和图不重叠
    plt.show()

TOP10词云

三国词频前十人名饼图

红楼梦人名词频分析

#找出人名词频前13的人物
import jieba
from wordcloud import WordCloud
import imageio
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/dreamoftheredchamber.txt", "r", encoding="UTF-8") as f:
    words = f.read()
    counts = {}
    word_list = jieba.lcut(words)
    for word in word_list:
        if len(word)<=1:
            continue
        else:
            counts[word] = counts.get(word, 0) + 1

    counts["贾母"] = counts["贾母"] + counts["老太太"]
    counts["贾政"] = counts["贾政"] + counts["老爷"]
    counts["凤姐"] = counts["凤姐"] + counts["凤姐儿"] + counts["王熙凤"]
    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['王夫人'] = counts['王夫人'] + counts['太太']
    excludes = {"老太太", "什么", "一个", "我们", "你们", "如今", "说道", "知道", "姑娘",
                "起来", "这里", "出来", "众人", "那里", "奶奶", "自己", "太太", "只见",
                "两个", "没有", "怎么", "一面", "不是", "不知", "这个", "听见", "这样",
                "进来", "咱们", "就是", "东西", "告诉", "回来", "只是", "大家", "老爷",
                "只得", "丫头", "他们", "不敢", "出去", "这些", "所以", "不过", "不好",
                "姐姐", "凤姐儿", "的话", "一时", "王熙凤", "薛宝钗", "林黛玉", "贾宝玉"}
    for word in excludes:
        del counts[word]
    items = list(counts.items())#将字典转化成元组型列表
    items.sort(key=lambda x:x[1], reverse=True)
    print(items)

    li = []
    for i in range(13):
        role, count = items[i]
        print(role, count)
        for _ in range(count):#_表示循环里面用不到这个临时变量
            li.append(role)

    text = " ".join(li)
    WordCloud(
        font_path = "msyh.ttc",
        background_color = 'white',
        width = 800,
        height = 600,
        collocations = False,
        mask = imageio.imread('./china.jpg')
    ).generate(text).to_file("TOP13.jpg")

TOP13词云