In [11]:

    

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


    

In [2]:

    

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


    

In [4]:

    

df.head()


    

    
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]:

    

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


    

    
Out[5]:





<matplotlib.axes._subplots.AxesSubplot at 0x10aedf710>






    

In [24]:

    

df.corr()


    

    
Out[24]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.924756
    
    

      
Weight
      
0.924756
      
1.000000
    
  

In [23]:

    

fig, ax = plt.subplots(figsize=(10,5))
ax.set_prop_cycle('color',['LIGHTPINK','LIGHTSKYBLUE'])

for gender, selection in df.groupby("Gender"):
    ax.plot(selection['Height'], selection["Weight"], label=gender,marker='o',linestyle="", markeredgewidth=0)

ax.legend(loc='upper left')


    

    
Out[23]:





<matplotlib.legend.Legend at 0x10b9f7c18>






    

In [25]:

    

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


    

    
Out[25]:





0.86297884861631291

In [27]:

    

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


    

    
Out[27]:





0.8496085914186009

In [ ]: