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()
