In [39]:

    

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


    

In [40]:

    

file_path = "/Users/szabolcs/dev/git/DAT210x/Module3/Datasets/"
file_name = "wheat.data"

df = pd.read_csv(file_path + file_name)
df.head()


    

    
Out[40]:






  

    

      

      
id
      
area
      
perimeter
      
compactness
      
length
      
width
      
asymmetry
      
groove
      
wheat_type
    
  
  

    

      
0
      
0
      
15.26
      
14.84
      
0.8710
      
5.763
      
3.312
      
2.221
      
5.220
      
kama
    
    

      
1
      
1
      
14.88
      
14.57
      
0.8811
      
5.554
      
3.333
      
1.018
      
4.956
      
kama
    
    

      
2
      
2
      
14.29
      
14.09
      
0.9050
      
5.291
      
3.337
      
2.699
      
4.825
      
kama
    
    

      
3
      
3
      
13.84
      
13.94
      
0.8955
      
5.324
      
3.379
      
2.259
      
4.805
      
kama
    
    

      
4
      
4
      
16.14
      
14.99
      
0.9034
      
5.658
      
3.562
      
1.355
      
5.175
      
kama
    
  

In [41]:

    

df.asymmetry.plot.hist(title="Asymmetry", bins=8)
plt.show()


    

In [42]:

    

wheat_types = df.wheat_type.unique()
print(wheat_types)
plt.figure()
for wtype in wheat_types:
    df[df.wheat_type == wtype].asymmetry.plot.hist(alpha=0.4)
plt.show()


    

    




['kama' 'canadian' 'rosa']






    

In [46]:

    

plt.figure()
wheat_df = df[["asymmetry", "perimeter"]]
wheat_df.plot.hist(alpha=0.5)
plt.show()


    

    






<matplotlib.figure.Figure at 0x10f5dbba8>






    

In [ ]: