In [25]:

    

import pandas as pd
%matplotlib inline


df = pd.read_csv("data/heights_weights_genders.csv")


    

In [26]:

    

df.head()


    

    
Out[26]:






  

    

      

      
Gender
      
Height
      
Weight
    
  
  

    

      
0
      
Male
      
73.847017
      
241.893563
    
    

      
1
      
Male
      
68.781904
      
162.310473
    
    

      
2
      
Male
      
74.110105
      
212.740856
    
    

      
3
      
Male
      
71.730978
      
220.042470
    
    

      
4
      
Male
      
69.881796
      
206.349801
    
  

In [27]:

    

maledf = df[(df['Gender'] == 'Male')]


    

In [28]:

    

femaledf = df[(df['Gender'] == 'Female')]


    

In [30]:

    

maledf.corr()


    

    
Out[30]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.862979
    
    

      
Weight
      
0.862979
      
1.000000
    
  

In [31]:

    

maledf.plot(kind='scatter',y='Weight',x='Height')


    

    
Out[31]:





<matplotlib.axes._subplots.AxesSubplot at 0x27a57d18588>






    

In [32]:

    

femaledf.corr()


    

    
Out[32]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.849609
    
    

      
Weight
      
0.849609
      
1.000000
    
  

In [33]:

    

femaledf.plot(kind='scatter',y='Weight',x='Height')


    

    
Out[33]:





<matplotlib.axes._subplots.AxesSubplot at 0x27a57d346d8>






    

In [ ]: