Pandas —— 层次化索引

In [29]: data=pd.Series(np.random.randn(8),index=[['a','a','a','b','b','b','c','c'],[1,2,3,1,2,3,1,2]])

In [30]: data
Out[30]:
a  1   -0.506962
2    0.795603
3    0.368363
b  1   -0.029980
2   -0.642660
3   -0.667930
c  1   -1.707709
2    1.455244
dtype: float64

In [31]: data.index
Out[31]:
MultiIndex(levels=[[u'a', u'b', u'c'], [1, 2, 3]],
labels=[[0, 0, 0, 1, 1, 1, 2, 2], [0, 1, 2, 0, 1, 2, 0, 1]])

In [32]: data['a']
Out[32]:
1   -0.506962
2    0.795603
3    0.368363
dtype: float64

In [33]: data[:,2]
Out[33]:
a    0.795603
b   -0.642660
c    1.455244
dtype: float64

In [34]: data.unstack()
Out[34]:
1         2         3
a -0.506962  0.795603  0.368363
b -0.029980 -0.642660 -0.667930
c -1.707709  1.455244       NaN

In [36]: data.unstack().stack()
Out[36]:
a  1   -0.506962
2    0.795603
3    0.368363
b  1   -0.029980
2   -0.642660
3   -0.667930
c  1   -1.707709
2    1.455244
dtype: float64

In [40]: frame=pd.DataFrame(np.arange(12).reshape((4,3))
...: ,index=[['a','a','b','b'],[1,2,1,2]]
...: ,columns=[['A','A','B'],['Green','Red','Red']])

In [41]: frame
Out[41]:
A       B
Green Red Red
a 1     0   1   2
2     3   4   5
b 1     6   7   8
2     9  10  11