In [1]:

    

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


    

In [2]:

    

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


    

    




(10000, 3)






    
Out[2]:





Index(['Gender', 'Height', 'Weight'], dtype='object')

In [3]:

    

plt.style.use('fivethirtyeight')
fig, ax = plt.subplots(figsize=(8,4))
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 [4]:

    

df.head(5)

#print("The correlation is", df.corr()['MdHHIncE']['RecycleRate'])


    

    
Out[4]:






  

    

      

      
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 [5]:

    

print("Male correlation:", df[df['Gender']=='Male'].corr()['Height']['Weight'])
print("Female correlation:", df[df['Gender']=='Female'].corr()['Height']['Weight'])
print("Whole dataset correlation:", df.corr()['Height']['Weight'])
print("Simpson's paradox!?")


    

    




Male correlation: 0.862978848616
Female correlation: 0.849608591419
Whole dataset correlation: 0.924756298741
Simpson's paradox!?