In [15]:

    

import pandas as pd
import matplotlib.pyplot as plt
%matplotlib inline


    

In [2]:

    

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


    

    
Out[2]:






  

    

      

      
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 [16]:

    

plt.style.use('ggplot')
fig, ax = plt.subplots(figsize=(10,5))
for category, group in df.groupby('Gender'):

    ax.plot(group['Height'], group['Weight'], marker='o', linestyle='', label=category,markersize=10, markeredgewidth=0, alpha=.5)
    ax.legend(loc='upper left')


    

In [13]:

    

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


    

    
Out[13]:





0.86297884861631291

In [14]:

    

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


    

    
Out[14]:





0.8496085914186009

In [ ]: