In [2]:

    

# import libraries
%matplotlib inline
import matplotlib.pyplot as plt
import seaborn as sns
import numpy as np; import pandas as pd


    

In [3]:

    

claims = pd.read_csv('insurance.csv')


    

In [4]:

    

claims.shape


    

    
Out[4]:





(1338, 7)

In [5]:

    

claims.columns


    

    
Out[5]:





Index(['age', 'sex', 'bmi', 'children', 'smoker', 'region', 'charges'], dtype='object')

In [6]:

    

claims.head()


    

    
Out[6]:






  

    

      

      
age
      
sex
      
bmi
      
children
      
smoker
      
region
      
charges
    
  
  

    

      
0
      
19
      
female
      
27.900
      
0
      
yes
      
southwest
      
16884.92400
    
    

      
1
      
18
      
male
      
33.770
      
1
      
no
      
southeast
      
1725.55230
    
    

      
2
      
28
      
male
      
33.000
      
3
      
no
      
southeast
      
4449.46200
    
    

      
3
      
33
      
male
      
22.705
      
0
      
no
      
northwest
      
21984.47061
    
    

      
4
      
32
      
male
      
28.880
      
0
      
no
      
northwest
      
3866.85520
    
  

In [7]:

    

sns.distplot(claims.charges)


    

    
Out[7]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fdb58d30fd0>






    

In [8]:

    

sns.violinplot(x="sex", y="charges", data=claims)


    

    
Out[8]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fdb58c4b550>






    

In [9]:

    

sns.violinplot(x="sex", y="charges", hue='smoker', data=claims)


    

    
Out[9]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fdb533a1ac8>






    

In [10]:

    

sns.violinplot(x='sex', y='charges', hue='smoker', data=claims, inner='quartile')


    

    
Out[10]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fdb533a1780>






    

In [11]:

    

claims.children.unique()


    

    
Out[11]:





array([0, 1, 3, 2, 5, 4])

In [12]:

    

sns.violinplot(x='children', y='charges', hue='smoker', data=claims, inner='quartile')


    

    
Out[12]:





<matplotlib.axes._subplots.AxesSubplot at 0x7fdb5312b2b0>






    

In [16]:

    

g = sns.PairGrid(claims, hue='smoker')
g.map_diag(plt.hist)
g.map_offdiag(plt.scatter)
g.add_legend();


    

In [18]:

    

g = sns.PairGrid(claims, hue='sex')
g.map_diag(plt.hist)
g.map_offdiag(plt.scatter)
g.add_legend();


    

In [20]:

    

g = sns.pairplot(claims, hue='sex', diag_kind="kde")


    

In [21]:

    

g = sns.pairplot(claims, hue='smoker', diag_kind="kde")


    

In [ ]: