In [1]:

    

from gtable import Table
from gtable.joins import inner_join, full_outer_join
import numpy as np

t1 = Table()
t1.add_column('a', [1, 2, 2, 3, 3, 4, 5, 6])
t1.add_column('b', [1, 2, 3])

t2 = Table()
t2.add_column('a', [2, 3, 4])
t2.add_column('b', [1, 1, 1])
t2.add_column('c', [5, 6, 7])


    

In [2]:

    

t3 = inner_join(t1, t2, 'b')


    

In [3]:

    

t3.data


    

    
Out[3]:





[array([1, 1, 1]), array([1, 1, 1]), array([5, 6, 7])]

In [4]:

    

%%timeit
inner_join(t1, t2, 'b')


    

    




202 µs ± 1.03 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

In [5]:

    

df1 = t1.to_pandas()
df2 = t2.to_pandas()


    

In [ ]:

    

df1


    

    
Out[ ]:







  

    

      

      
a
      
b
    
  
  

    

      
0
      
1
      
1.0
    
    

      
1
      
2
      
2.0
    
    

      
2
      
2
      
3.0
    
    

      
3
      
3
      
NaN
    
    

      
4
      
3
      
NaN
    
    

      
5
      
4
      
NaN
    
    

      
6
      
5
      
NaN
    
    

      
7
      
6
      
NaN
    
  

In [2]:

    

t4 = full_outer_join(t1, t2, 'a')


    

    




[1 2 2 3 3 4 5 6] [2 3 4]
1 2 0 0
False False
2 2 1 0
False False
2 3 2 1
False False
3 3 3 1
False False
3 4 4 2
False False
4 4 5 2
False True
5 4 6 2
False True
5 4 6 2
False True
5 4 6 2
False True
5 4 6 2
False True
5 4 6 2
False True
11
[1 2 2 3 3 4 4 4 4 4 4] [0 1 2 3 4 5 6 6 6 6 6] [0 0 1 1 2 2 2 2 2 2 2]






    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-2-b9825a6aa391> in <module>()
----> 1 t4 = full_outer_join(t1, t2, 'a')

~/projects/gtable/gtable/joins.py in full_outer_join(table_left, table_right, column)
    138 
    139     res = Table()
--> 140     res.data = data
    141     res.index = np.vstack(index)
    142     res.keys = keys

NameError: name 'data' is not defined

In [ ]: