In [1]:

    

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


    

In [3]:

    

df=pd.read_csv('/home/sean/git/algorithms/class4/homework/data/heights_weights_genders.csv')


    

In [5]:

    

df.groupby(by='Gender').describe()


    

    
Out[5]:






  

    

      

      

      
Height
      
Weight
    
    

      
Gender
      

      

      

    
  
  

    

      
Female
      
count
      
5000.000000
      
5000.000000
    
    

      
mean
      
63.708774
      
135.860093
    
    

      
std
      
2.696284
      
19.022468
    
    

      
min
      
54.263133
      
64.700127
    
    

      
25%
      
61.894441
      
122.934096
    
    

      
50%
      
63.730924
      
136.117583
    
    

      
75%
      
65.563565
      
148.810926
    
    

      
max
      
73.389586
      
202.237214
    
    

      
Male
      
count
      
5000.000000
      
5000.000000
    
    

      
mean
      
69.026346
      
187.020621
    
    

      
std
      
2.863362
      
19.781155
    
    

      
min
      
58.406905
      
112.902939
    
    

      
25%
      
67.174679
      
173.887767
    
    

      
50%
      
69.027709
      
187.033546
    
    

      
75%
      
70.988744
      
200.357802
    
    

      
max
      
78.998742
      
269.989699
    
  

In [6]:

    

male_df=df[df['Gender']=='Male']


    

In [7]:

    

female_df=df[df['Gender']=='Female']


    

In [30]:

    

ax.scatter?


    

In [45]:

    

fig, ax = plt.subplots()
fitm = np.polyfit(male_df['Height'], male_df['Weight'], deg=1)
fitf = np.polyfit(female_df['Height'], female_df['Weight'], deg=1)
ax.plot(female_df['Height'], fit[0] * female_df['Height'] + fitf[1], color='magenta', alpha=0.5)
ax.scatter(female_df['Height'], female_df['Weight'], alpha=0.1, c='pink', linewidths=0)
ax.plot(male_df['Height'], fit[0] * male_df['Height'] + fitm[1], color='cyan', alpha=0.5)
ax.scatter(male_df['Height'], male_df['Weight'], alpha=0.1, c='blue', linewidths=0)


    

    
Out[45]:





<matplotlib.collections.PathCollection at 0x7f110ed08e80>






    

In [36]:

    

df.corr()


    

    
Out[36]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.924756
    
    

      
Weight
      
0.924756
      
1.000000
    
  

In [37]:

    

male_df.corr()


    

    
Out[37]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.862979
    
    

      
Weight
      
0.862979
      
1.000000
    
  

In [38]:

    

female_df.corr()


    

    
Out[38]:






  

    

      

      
Height
      
Weight
    
  
  

    

      
Height
      
1.000000
      
0.849609
    
    

      
Weight
      
0.849609
      
1.000000
    
  

In [ ]: