notebook.community

Edit and run



In [105]:

    
from pandas import Series, DataFrame
import pandas as pd



In [106]:

    
s = Series([1,2,3.0,'abc'])



In [107]:

    
s



In [108]:

    
s[3]









    Out[108]:





'abc'



In [109]:

    
s2 = Series(data=[1,3,5,7], index=['a','b','x','y'])



In [110]:

    
s2









    Out[110]:





a    1
b    3
x    5
y    7



In [111]:

    
s2.index









    Out[111]:





Index([a, b, x, y], dtype=object)



In [112]:

    
s2.name = 'a_series'



In [113]:

    
s2.index.name = 'the_index'



In [114]:

    
s2









    Out[114]:





the_index
a            1
b            3
x            5
y            7
Name: a_series



In [115]:

    
data = {'state':['Ohino','Ohino','Ohino','Nevada','Nevada'],
        'year':[2000,2001,2002,2001,2002],
        'pop':[1.5,1.7,3.6,2.4,2.9]}



In [116]:

    
df = DataFrame(data)



In [117]:

    
df



In [129]:

    
df2 = DataFrame(data,index=['one', 'two','three','four','five'],
               columns=['year','state','pop','debt'])



In [130]:

    
df2









    Out[130]:






  
    
      
      year
      state
      pop
      debt
    
  
  
    
      one
       2000
        Ohino
       1.5
       NaN
    
    
      two
       2001
        Ohino
       1.7
       NaN
    
    
      three
       2002
        Ohino
       3.6
       NaN
    
    
      four
       2001
       Nevada
       2.4
       NaN
    
    
      five
       2002
       Nevada
       2.9
       NaN



In [120]:

    
df2.index









    Out[120]:





Index([一, o, three, four, five], dtype=object)



In [121]:

    
df2.columns









    Out[121]:





Index([year, state, pop, debt], dtype=object)



In [122]:

    
type(df2['debt'])









    Out[122]:





pandas.core.series.Series



In [123]:

    
ser = Series([4.5,7.2,-5.3,3.6],index=['d','b','a','c'])



In [124]:

    
ser









    Out[124]:





d    4.5
b    7.2
a   -5.3
c    3.6



In [125]:

    
a = ['a','b','c','d','e']



In [126]:

    
ser.reindex(a)









    Out[126]:





a   -5.3
b    7.2
c    3.6
d    4.5
e    NaN



In [127]:

    
ser.reindex(a,fill_value=0)









    Out[127]:





a   -5.3
b    7.2
c    3.6
d    4.5
e    0.0



In [128]:

    
ser.reindex(a,method='ffill')









    



---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
C:\Users\zhang\<ipython-input-128-ace8a241f043> in <module>()
----> 1 ser.reindex(a,method='ffill')

D:\Python27\lib\site-packages\pandas\core\series.pyc in reindex(self, index, method, level, fill_value, limit, copy)
   2142 
   2143         new_index, indexer = self.index.reindex(index, method=method,
-> 2144                                                  level=level, limit=limit)
   2145         new_values = com.take_1d(self.values, indexer, fill_value=fill_value)
   2146         return Series(new_values, index=new_index, name=self.name)

D:\Python27\lib\site-packages\pandas\core\index.pyc in reindex(self, target, method, level, limit)
    825             else:
    826                 indexer = self.get_indexer(target, method=method,
--> 827                                            limit=limit)
    828         return target, indexer
    829 

D:\Python27\lib\site-packages\pandas\core\index.pyc in get_indexer(self, target, method, limit)
    750 
    751         if method == 'pad':
--> 752             assert(self.is_monotonic)
    753             indexer = self._engine.get_pad_indexer(target.values, limit)
    754         elif method == 'backfill':

AssertionError:



In [133]:

    
state = ['Texas','Utha','California']
df2.reindex(columns=state,method='ffill')









    Out[133]:






  
    
      
      Texas
      Utha
      California
    
  
  
    
      one
      NaN
      NaN
      NaN
    
    
      two
      NaN
      NaN
      NaN
    
    
      three
      NaN
      NaN
      NaN
    
    
      four
      NaN
      NaN
      NaN
    
    
      five
      NaN
      NaN
      NaN



In [132]:

    
df2.reindex(index=['a','b','c','d'],columns=state,method='ffill')









    



---------------------------------------------------------------------------
AssertionError                            Traceback (most recent call last)
C:\Users\zhang\<ipython-input-132-bc3d09094479> in <module>()
----> 1 df2.reindex(index=['a','b','c','d'],columns=state,method='ffill')

D:\Python27\lib\site-packages\pandas\core\frame.pyc in reindex(self, index, columns, method, level, fill_value, limit, copy)
   2244         if index is not None:
   2245             frame = frame._reindex_index(index, method, copy, level,
-> 2246                                          fill_value, limit)
   2247 
   2248         return frame

D:\Python27\lib\site-packages\pandas\core\frame.pyc in _reindex_index(self, new_index, method, copy, level, fill_value, limit)
   2320                        limit=None):
   2321         new_index, indexer = self.index.reindex(new_index, method, level,
-> 2322                                                 limit=limit)
   2323         return self._reindex_with_indexers(new_index, indexer, None, None,
   2324                                            copy, fill_value)

D:\Python27\lib\site-packages\pandas\core\index.pyc in reindex(self, target, method, level, limit)
    825             else:
    826                 indexer = self.get_indexer(target, method=method,
--> 827                                            limit=limit)
    828         return target, indexer
    829 

D:\Python27\lib\site-packages\pandas\core\index.pyc in get_indexer(self, target, method, limit)
    750 
    751         if method == 'pad':
--> 752             assert(self.is_monotonic)
    753             indexer = self._engine.get_pad_indexer(target.values, limit)
    754         elif method == 'backfill':

AssertionError:



In [138]:

    
ser









    Out[138]:





d    4.5
b    7.2
a   -5.3
c    3.6



In [139]:

    
df



In [140]:

    
ser.drop('c')









    Out[140]:





d    4.5
b    7.2
a   -5.3



In [142]:

    
df.drop(2)



In [146]:

    
df.drop(['state','pop'],axis=1)



In [155]:

    
foo = Series(data=[4.5,7.2,-5.3,3.6],index=['a','b','c','d'])
foo









    Out[155]:





a    4.5
b    7.2
c   -5.3
d    3.6



In [157]:

    
bar = Series(data=[4.5,7.2,-5.3,3.6])
bar









    Out[157]:





0    4.5
1    7.2
2   -5.3
3    3.6



In [159]:

    
foo[:2]









    Out[159]:





a    4.5
b    7.2



In [160]:

    
bar[:2]









    Out[160]:





0    4.5
1    7.2



In [166]:

    
foo[:'c']









    Out[166]:





a    4.5
b    7.2
c   -5.3



In [169]:

    
df



In [174]:

    
df.ix[:2,:2]



In [176]:

    
df.reindex(index=['a','b','c','d','e'])









    Out[176]:






  
    
      
      pop
      state
      year
    
  
  
    
      a
      NaN
       NaN
      NaN
    
    
      b
      NaN
       NaN
      NaN
    
    
      c
      NaN
       NaN
      NaN
    
    
      d
      NaN
       NaN
      NaN
    
    
      e
      NaN
       NaN
      NaN



In [177]:

    
df



In [ ]:

	pop	state	year
0	1.5	Ohino	2000
1	1.7	Ohino	2001
2	3.6	Ohino	2002
3	2.4	Nevada	2001
4	2.9	Nevada	2002

	year	state	pop	debt
one	2000	Ohino	1.5	NaN
two	2001	Ohino	1.7	NaN
three	2002	Ohino	3.6	NaN
four	2001	Nevada	2.4	NaN
five	2002	Nevada	2.9	NaN