In [11]:

    

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


    

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 [6]:

    

df_men = df[df["Gender"] == 'Male']


    

In [7]:

    

df_men.corr()


    

    
Out[7]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.862979
    
    

      
Weight
      
0.862979
      
1.000000
    
  

In [19]:

    

df_men.plot(kind='scatter', x='Height', y='Weight', figsize=(10,5), alpha=0.5)


    

    
Out[19]:





<matplotlib.axes._subplots.AxesSubplot at 0x10d3f2048>






    

In [8]:

    

df_women = df[df["Gender"] == 'Female']


    

In [9]:

    

df_women.corr()


    

    
Out[9]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.849609
    
    

      
Weight
      
0.849609
      
1.000000
    
  

In [18]:

    

df_women.plot(kind='scatter', x='Height', y='Weight', figsize=(10,5), alpha = 0.5, c='r')


    

    
Out[18]:





<matplotlib.axes._subplots.AxesSubplot at 0x10cf643c8>






    

In [24]:

    

# both in one graph

ax = df_women.plot(kind='scatter', x='Height', y='Weight', figsize=(10,5), c='r', alpha=0.5)
df_men.plot(ax = ax, kind='scatter', x='Height', y='Weight', alpha = 0.5)

ax.set_title("Weight correlates with height")
ax.set_xlabel('Height [in inches]')
ax.set_ylabel('Weight [in pounds]')

plt.savefig('Quick_sketch.png')


    

In [ ]: