1.三国演义Top10人物分析

import jieba
from wordcloud import WordCloud
import imageio
# 1.读取小说内容
with open('./novel/threekingdom.txt', 'r', encoding='utf-8') as f:
    words = f.read()
    counts = {} # counts = {'姓名':出现频率}
    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
                # 字典.get(k)  如果字典中没有这个键 ，(返回NONE)添加一个默认值：0
                counts[word] = counts.get(word, 0) + 1
    print(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)
    # 用列表解析排序
    items.sort(key=lambda x: x[1], reverse=True)
    # print(items)
    li = []  # ['孔明', '孔明', '孔明',..., '曹操'...]
    for i in range(10):
        # 序列解包
        role, count = items[i]
        print(role, count)
        # _ 是告诉看代码的人，循环里面不需要使用临时变量
        for _ in range(count):
            li.append(role)
        # 得出结论
        # 绘制中文词云，在WordCloud()里面设置参数
        text = ' '.join(li)
        wc = WordCloud(
            font_path='msyh.ttc',
            background_color='white',
            width=800,
            height=600,
            # 相邻两个重复词之间的匹配，关掉
            collocations=False
        ).generate(text)
        wc.to_file('三国TOP10人物词云.png')

效果图

三国人物.png

2.匿名函数(lambda)

• lambda x1, x2, ...xn: 表达式

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

• 参数可以是无限多，表达式只有一个

#从大到小
name_info_list = [
    ('张三', 4500),
    ('李四', 9500),
    ('王五', 2000),
    ('赵六', 5500),
]
name_info_list.sort(key=lambda x: x[1], reverse=True)
print(name_info_list)


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

3.列表推导式

用普通for 创建列表

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

使用列表推导式创建列表
结构：[表达式 for 临时变量 in 可迭代对象 可以追加条件]

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

4. 列表解析

普通筛选出列表中所有的偶数

# 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)

使用列表解析筛选偶数

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

筛选出列表中 大于0 的数

# 随机生成(-10, 10)的10个数
from random import randint
num_list = [randint(-10, 10) for _ in range(10)]
print(num_list)
# 输出num_list中 大于0 的数
print([i for i in num_list if i > 0])

5.字典解析

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})

6.绘图

6.1绘制[0, 2π]正余弦曲线图

from matplotlib import pyplot as plt
import numpy as np
# 处理中文乱码
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False

# 使用100个点  绘制[0, 2π]正弦曲线图
# .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)
# 正弦和余弦在同一坐标系下
cosy = np.cos(x)
plt.plot(x, y, color='g', linestyle='--')
plt.plot(x, cosy, color='r')
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()

6.2绘制柱状图

# 切片
# print(string.ascii_uppercase[0: 6])
# 结果：ABCDEF

# 柱状图
from matplotlib import pyplot as plt
# 处理中文乱码
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
x = ['口红{}'.format() 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('价格（元）')
plt.bar(x, y)
plt.show()

6.3绘制饼图

# 饼图
from matplotlib import pyplot as plt
# 处理中文乱码
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
from random import randint
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]
color = ['red', 'purple', 'blue', 'yellow', 'gray', 'green']
plt.pie(counts, explode=explode, shadow=True, labels=labels, autopct='%1.1f%%', colors=color)
plt.axis('equal')
plt.legend(loc=2)
plt.show()

6.4绘制散点图

from matplotlib import pyplot as plt
import numpy as np
# 均值为 0 标准差为 1 的正态分布数据
x = np.random.normal(0, 1, 100)
y = np.random.normal(0, 1, 100)
plt.scatter(x, y)
plt.show()

6.5绘制有透明度的散点图

from matplotlib import pyplot as plt
import numpy as np
x = np.random.normal(0, 1, 100)
y = np.random.normal(0, 1, 100)
# alpha透明度
plt.scatter(x, y, alpha=0.1)
plt.show()