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
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
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
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
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