In [1]:

    

import pandas as pd
import matplotlib
%matplotlib inline


    

In [2]:

    

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


    

In [3]:

    

df.head()


    

    
Out[3]:






  

    

      

      
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 [4]:

    

df[df['Gender'] == 'Male'].corr()


    

    
Out[4]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.862979
    
    

      
Weight
      
0.862979
      
1.000000
    
  

In [10]:

    

ax = df[df['Gender'] == 'Male'].plot(kind = 'scatter', x = 'Weight', y = 'Height')
ax.set_ylim((50, 85))
ax.set_xlim((40, 280))


    

    
Out[10]:





(40, 280)






    

In [5]:

    

df[df['Gender'] == 'Female'].corr()


    

    
Out[5]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.849609
    
    

      
Weight
      
0.849609
      
1.000000
    
  

In [11]:

    

ax = df[df['Gender'] == 'Female'].plot(kind = 'scatter', x = 'Weight', y = 'Height')
ax.set_ylim((50, 85))
ax.set_xlim((40, 280))


    

    
Out[11]:





(40, 280)






    

In [ ]: