In [16]:

    

import pandas as pd
import matplotlib.pyplot as plt
import scipy
%matplotlib inline
plt.style.use('ggplot')


    

In [17]:

    

df=pd.read_csv('//Users/mercyemelike/Desktop/Lede-Program/algorithms/class4/homework/data/heights_weights_genders.csv')


    

In [18]:

    

df.head()


    

    
Out[18]:






  

    

      

      
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 [27]:

    

fig, (ax1, ax2) = plt.subplots(nrows=1, ncols=2)

df[df['Gender'] == 'Male'].plot(x='Height', y='Weight', legend=False, ax=ax1, sharex=True, sharey=True, kind='scatter')
ax1.set_title("Male")

df[df['Gender'] == 'Female'].plot(x='Height', y='Weight', legend=False, ax=ax2, sharex=True, sharey=True, kind='scatter')
ax2.set_title("Female")

plt.tight_layout()


    

In [29]:

    

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


    

    
Out[29]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.862979
    
    

      
Weight
      
0.862979
      
1.000000
    
  

In [30]:

    

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


    

    
Out[30]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.849609
    
    

      
Weight
      
0.849609
      
1.000000
    
  

In [ ]: