三国演义人物分析
import jieba
from wordcloud import WordCloud
import imageio
from matplotlib import pyplot as plt
from random import randint
import string
import numpy as np
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# 1.读取小说内容
mask = imageio.imread('./china.jpg')
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)
for word in words_list:
if len(word)<=1:
continue
else:
#更新字典中的词
# counts[word]=取出字典中对应的值+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，返回是none
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[(),()]
# 字典转换成列表
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 x:x[1],reverse=True)
li=[] #['孔明','孔明'....]
ui={}
for i in range(10):
# 序列解包
role,count=items[i]
print( role,count)
ui[role]=count
#_是告诉看代码的人，循环里面不需要临时变量
for _ in range(count):
li.append((role))
print(ui)
lab=ui.keys()
cou=ui.values()
#饼图展示
print(lab)
print(cou)
plt.pie(cou, labels=lab, shadow=True,autopct='%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()
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,
mask=mask
).generate(text).to_file('TOP10.png')
饼图
词云
匿名函数 lambda
结构:
lambda x1,x2....xn:表达式
sum_num = lambda x1,x2: x1+x2
print(sum_num(2,3))
# 参数可以是无限多个，但是表达式只有一个
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":8},
]
stu_info.sort(key=lambda i:i['age'])
print(stu_info)
列表推导式
# 普通for循环
li=[]
for i in range(10):
li.append(i)
print(li)
# 列表推导式
# [for 临时变量 in 可迭代对象 可以追加条件]
print([i for i in range(10)])
- 列表解析
#筛选出列表中的所有偶数
li=[]
for i in range(10):
if i%2 ==0:
li.append(i)
print(li)
# 使用列表解析
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
# 生成随机数
num_list=[randint(-10,10) for _ in range(10)]
print(num_list)
# 筛选大于0的数
print([i for i in num_list if i>0])
字典解析
stu_grades={'student{}'.format(i):randint(50,100)for i in range(1,101)}
print(stu_grades)
# 筛选大于60分的
print({k:v for k,v in stu_grades.items() if v>60})
matplotlib
- 导入曲线图plt.plot(x,y)
from matplotlib import pyplot as plt
import numpy as np
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下
cosy=np.cos(x)
plt.plot(x,y,color='g',linestyle='--',label='sin(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')
# 图例
plt.legend()
plt.show()
曲线图
- 柱状图plt.bar(x,y)
import string
from random import randint
print(string.ascii_uppercase[0:6])
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('价格（元）')
plt.bar(x,y)
# plt.plot(x,y)
plt.show()
[图片上传中...(image.png-b81f00-1564484037887-0)]
柱状图
- 饼图pit.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_uppercase[:6]]
# 距离圆心点的距离
explode=[0.1,0,0,0,0,0]
color=['r','purple','b','y','gray','green']
plt.pie(counts,labels=labels,explode=explode,shadow=True,colors=color, autopct='%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()
饼图
- 散点图plt.scatter(x,y)
# 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
红楼梦人物分析
import jieba
from wordcloud import WordCloud
import imageio
from matplotlib import pyplot as plt
from random import randint
import string
import numpy as np
plt.rcParams["font.sans-serif"] = ['SimHei']
plt.rcParams['axes.unicode_minus'] = False
# 1.读取小说内容
# mask = imageio.imread('./china.jpg')
with open('novel/all.txt','r',encoding='utf-8') as f:
words=f.read()
counts={} #{'曹操'：234，'回寨'：56}
excludes = {'什么','一个','我们','你们','如今','出来','众人','那里','奶奶','太太','一面',
'只见','知道','姑娘','起来','两个','这里','没有','怎么','不是','不知','这个',
'听见','这样','进来','咱们','就是','东西','平儿','告诉','袭人','回来','只是',
'大家','只得','丫头','这些','老爷','他们','不敢','出去','自己','所以','老太太'
,'说道','不过','不好','姐姐','老太太'}
# 2.分词
words_list=jieba.lcut(words)
for word in words_list:
if len(word)<=1:
continue
else:
#更新字典中的词
# counts[word]=取出字典中对应的值+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，返回是none
counts[word]=counts.get(word,0) + 1
print(counts)
# 3.词语过滤，删除无关词，重复词
for word in excludes:
del counts[word]
# 4.排序[(),()]
# 字典转换成列表
items=list(counts.items())
print(items)
items.sort(key=lambda x:x[1],reverse=True)
li=[] #['孔明','孔明'....]
ui={}
for i in range(10):
# 序列解包
role,count=items[i]
print( role,count)
ui[role]=count
#_是告诉看代码的人，循环里面不需要临时变量
for _ in range(count):
li.append((role))
print(ui)
lab=ui.keys()
cou=ui.values()
print(lab)
print(cou)
plt.pie(cou, labels=lab, shadow=True,autopct='%1.1f%%')
plt.legend(loc=2)
plt.axis('equal')
plt.show()
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,
# mask=mask
).generate(text).to_file('TOP11.png')