In [3]:

    

'''
LESSION 6

GroupBy function
'''

# Import libraries
import pandas as pd
import sys
print('Python version ' + sys.version)
print('Pandas version ' + pd.__version__)


    

    




Python version 2.7.13 |Anaconda 4.3.0 (64-bit)| (default, Dec 19 2016, 13:29:36) [MSC v.1500 64 bit (AMD64)]
Pandas version 0.19.2

In [4]:

    

# Our small data set
d = {'one':[1,1,1,1,1],
     'two':[2,2,2,2,2],
     'letter':['a','a','b','b','c']}

# Create dataframe
df = pd.DataFrame(d)
df


    

    
Out[4]:






  

    

      

      
letter
      
one
      
two
    
  
  

    

      
0
      
a
      
1
      
2
    
    

      
1
      
a
      
1
      
2
    
    

      
2
      
b
      
1
      
2
    
    

      
3
      
b
      
1
      
2
    
    

      
4
      
c
      
1
      
2
    
  

In [5]:

    

# Create group object
one = df.groupby('letter')

# Apply sum function
one.sum()


    

    
Out[5]:






  

    

      

      
one
      
two
    
    

      
letter
      

      

    
  
  

    

      
a
      
2
      
4
    
    

      
b
      
2
      
4
    
    

      
c
      
1
      
2
    
  

In [6]:

    

letterone = df.groupby(['letter','one']).sum()
letterone


    

    
Out[6]:






  

    

      

      

      
two
    
    

      
letter
      
one
      

    
  
  

    

      
a
      
1
      
4
    
    

      
b
      
1
      
4
    
    

      
c
      
1
      
2
    
  

In [7]:

    

letterone.index


    

    
Out[7]:





MultiIndex(levels=[[u'a', u'b', u'c'], [1]],
           labels=[[0, 1, 2], [0, 0, 0]],
           names=[u'letter', u'one'])

In [8]:

    

letterone = df.groupby(['letter','one'], as_index=False).sum()
letterone


    

    
Out[8]:






  

    

      

      
letter
      
one
      
two
    
  
  

    

      
0
      
a
      
1
      
4
    
    

      
1
      
b
      
1
      
4
    
    

      
2
      
c
      
1
      
2
    
  

In [9]:

    

letterone.index


    

    
Out[9]:





Int64Index([0, 1, 2], dtype='int64')

In [ ]:

    




    

In [ ]:

    




    

In [ ]:

    




    

In [ ]: