In [1]:

    

import pandas as pd
import matplotlib.pyplot as plt
import matplotlib
%matplotlib inline
from pandas.tools.plotting import parallel_coordinates
df = pd.read_csv('Datasets/wheat.data')
df.head(5)


    

    
Out[1]:






  

    

      

      
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 [2]:

    

del df['id']
df.head(5)


    

    
Out[2]:






  

    

      

      
area
      
perimeter
      
compactness
      
length
      
width
      
asymmetry
      
groove
      
wheat_type
    
  
  

    

      
0
      
15.26
      
14.84
      
0.8710
      
5.763
      
3.312
      
2.221
      
5.220
      
kama
    
    

      
1
      
14.88
      
14.57
      
0.8811
      
5.554
      
3.333
      
1.018
      
4.956
      
kama
    
    

      
2
      
14.29
      
14.09
      
0.9050
      
5.291
      
3.337
      
2.699
      
4.825
      
kama
    
    

      
3
      
13.84
      
13.94
      
0.8955
      
5.324
      
3.379
      
2.259
      
4.805
      
kama
    
    

      
4
      
16.14
      
14.99
      
0.9034
      
5.658
      
3.562
      
1.355
      
5.175
      
kama
    
  

In [3]:

    

df.corr()


    

    
Out[3]:






  

    

      

      
area
      
perimeter
      
compactness
      
length
      
width
      
asymmetry
      
groove
    
  
  

    

      
area
      
1.000000
      
0.994341
      
0.600312
      
0.645418
      
0.801616
      
-0.205876
      
0.786096
    
    

      
perimeter
      
0.994341
      
1.000000
      
0.520544
      
0.657490
      
0.783188
      
-0.196360
      
0.813256
    
    

      
compactness
      
0.600312
      
0.520544
      
1.000000
      
0.360060
      
0.756165
      
-0.315668
      
0.236184
    
    

      
length
      
0.645418
      
0.657490
      
0.360060
      
1.000000
      
0.197228
      
-0.102325
      
0.669887
    
    

      
width
      
0.801616
      
0.783188
      
0.756165
      
0.197228
      
1.000000
      
-0.249378
      
0.619865
    
    

      
asymmetry
      
-0.205876
      
-0.196360
      
-0.315668
      
-0.102325
      
-0.249378
      
1.000000
      
-0.039248
    
    

      
groove
      
0.786096
      
0.813256
      
0.236184
      
0.669887
      
0.619865
      
-0.039248
      
1.000000
    
  

In [6]:

    

import matplotlib.pyplot as plt

plt.imshow(df.corr(), cmap=plt.cm.Blues, interpolation='nearest')
plt.colorbar()
tick_marks = [i for i in range(len(df.columns))]
plt.xticks(tick_marks, df.columns, rotation='vertical')
plt.yticks(tick_marks, df.columns)


    

    
Out[6]:





([<matplotlib.axis.YTick at 0x2519473d320>,
  <matplotlib.axis.YTick at 0x2519472cf98>,
  <matplotlib.axis.YTick at 0x251947a62b0>,
  <matplotlib.axis.YTick at 0x251947a8828>,
  <matplotlib.axis.YTick at 0x251948382e8>,
  <matplotlib.axis.YTick at 0x25194838cf8>,
  <matplotlib.axis.YTick at 0x2519483b748>,
  <matplotlib.axis.YTick at 0x2519483f198>],
 <a list of 8 Text yticklabel objects>)