HW4

# -*- coding: utf-8 -*-



# In[1]:



import pandas as pd

import numpy as np

import seaborn as sns

import os



# In[2]:

os.chdir(r'E:\Python_learning\data_science\task_0529\HW4')

auto = pd.read_csv("auto_ins.csv",encoding = 'gbk')

auto.head()



# In[3]:

#对loss重新编码为1/0，有数值为1，命名为loss_flag

auto['loss_flag'] = auto['Loss'].apply(lambda x: 1 if x!=0 else 0)

auto.head()



# In[4]:

#对loss_flag分布情况进行描述分析

auto.loss_flag.value_counts()



# In[5]:

auto.loss_flag.value_counts().plot(kind ='bar')



# In[6]:

#分析是否出险和年龄、驾龄、性别、婚姻状态等变量之间的关系

sns.boxplot(x = 'loss_flag', y = 'Age', data = auto)



# In[7]:

sns.boxplot(x = 'loss_flag', y = 'vAge', data = auto)



# In[8]:

from pylab import mpl

mpl.rcParams['font.sans-serif'] = ['SimHei'] # 指定默认字体

mpl.rcParams['axes.unicode_minus'] = False # 解决保存图像是负号'-'显示为方块的问题



pd.crosstab(auto.loss_flag,auto.Gender).plot(kind = "bar")

pd.crosstab(auto.loss_flag,auto.Marital).plot(kind = "bar")



# In[9]:

loss_gender =pd.crosstab(auto.loss_flag,auto.Gender)

loss_gender



# In[10]:

loss_gender["sum"] = loss_gender.sum(1)

loss_gender



# In[11]:

loss_gender = loss_gender.div(loss_gender.sum(1),axis = 0)

loss_gender



# In[12]:

loss_gender[["女","男"]].plot(kind = 'bar', stacked = "True")



# In[13]:

loss_Ma =pd.crosstab(auto.loss_flag,auto.Marital)

loss_Ma["sum"] = loss_Ma.sum(1)

loss_Ma



# In[14]:

loss_Ma = loss_Ma.div(loss_Ma.sum(1),axis = 0)

loss_Ma



# In[]:



# In[15]:

loss_Ma[["已婚","未婚"]].plot(kind = 'bar', stacked = "True")