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 [43]:

    

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


    

    




---------------------------------------------------------------------------
KeyError                                  Traceback (most recent call last)
<ipython-input-43-eae48cbd3db8> in <module>()
      1 plt.figure()
----> 2 wheat_df = df[wheat_types]
      3 wheat_df.plot.hist(alpha=0.5)
      4 plt.show

/Users/szabolcs/anaconda/lib/python3.5/site-packages/pandas/core/frame.py in __getitem__(self, key)
   2051         if isinstance(key, (Series, np.ndarray, Index, list)):
   2052             # either boolean or fancy integer index
-> 2053             return self._getitem_array(key)
   2054         elif isinstance(key, DataFrame):
   2055             return self._getitem_frame(key)

/Users/szabolcs/anaconda/lib/python3.5/site-packages/pandas/core/frame.py in _getitem_array(self, key)
   2095             return self.take(indexer, axis=0, convert=False)
   2096         else:
-> 2097             indexer = self.ix._convert_to_indexer(key, axis=1)
   2098             return self.take(indexer, axis=1, convert=True)
   2099 

/Users/szabolcs/anaconda/lib/python3.5/site-packages/pandas/core/indexing.py in _convert_to_indexer(self, obj, axis, is_setter)
   1228                 mask = check == -1
   1229                 if mask.any():
-> 1230                     raise KeyError('%s not in index' % objarr[mask])
   1231 
   1232                 return _values_from_object(indexer)

KeyError: "['kama' 'canadian' 'rosa'] not in index"





    






<matplotlib.figure.Figure at 0x11289ba90>

In [ ]: