層次化索引

層次化也就是在一個軸上擁有多個索引級別

Series的層次化索引

data=Series(np.random.randn(10),index=[
    ['a','a','a','b','b','b','c','c','d','d'],
    [1,2,3,1,2,3,1,2,2,3]
])
data

a  1    0.965999
   2   -0.271733
   3    0.133910
b  1   -0.806885
   2   -0.622905
   3   -0.355330
c  1   -0.659194
   2   -1.082872
d  2   -0.043984
   3   -1.125324
dtype: float64

# 選取資料子集
data['b']
1   -0.806885
2   -0.622905
3   -0.355330
dtype: float64

data['b':'c'] # 在pandas中顧頭也顧尾

b  1   -0.806885
   2   -0.622905
   3   -0.355330
c  1   -0.659194
   2   -1.082872
dtype: float64

data.ix[['b','d']] # 按行索引名稱選擇
b  1   -0.806885
   2   -0.622905
   3   -0.355330
d  2   -0.043984
   3   -1.125324
dtype: float64

# 在內層中進行選取，選擇所有的行索引中的2這一行
data[:,2]
a   -0.271733
b   -0.622905
c   -1.082872
d   -0.043984
dtype: float64

# 層次化索引在資料重塑和基於分組的操作中扮演著重要的角色
# 這個函式會把層次化索引轉為DataFrame格式，最外層的行索引作為DataFrame的行索引，內層的索引作為列索引
data.unstack()

    1             2           3
a   0.965999    -0.271733   0.133910
b   -0.806885   -0.622905   -0.355330
c   -0.659194   -1.082872   NaN
d   NaN         -0.043984   -1.125324

# unstack()的逆運算，轉回來
data.unstack().stack()

a  1    0.965999
   2   -0.271733
   3    0.133910
b  1   -0.806885
   2   -0.622905
   3   -0.355330
c  1   -0.659194
   2   -1.082872
d  2   -0.043984
   3   -1.125324
dtype: float64
 

DataFrame的層次化索引

frame = pd.DataFrame(np.arange(12).reshape(4,3),index=[['a','a','b','b'],[1,2,1,2]],
            columns=[['ohio','ohio','color'],['green','red','green']]
            )
frame

    ohio    color
   green    red green
a   1   0   1   2
    2   3   4   5
b   1   6   7   8
    2   9   10  11

# 給層級行索引加名字
frame.index.names = ['key1','key2']
# 給層級列索引加名字
frame.columns.names = ['state','color']
frame

   state    ohio    color
   color    green   red green
key1    key2            
a   1   0   1   2
    2   3   4   5
b   1   6   7   8
    2   9   10  11

frame['ohio']

   color    green   red
key1    key2        
a   1   0   1
    2   3   4
b   1   6   7
    2   9   10
 

重排分級順序

frame

state   ohio    color
color   green   red green
key1    key2            
a   1   0   1   2
    2   3   4   5
b   1   6   7   8
    2   9   10  11

# 這裡sortlevel()括號裡的0指把key2和key1交換後按key2排序
frame.swaplevel(0,1).sortlevel(0)

    state   ohio    color
color   green   red green
key2    key1            
1   a   0   1   2
    b   6   7   8
2   a   3   4   5
    b   9   10  11


# 1指按key1排序
frame.swaplevel(0,1).sortlevel(1)

state   ohio    color
color   green   red green
key2    key1            
1   a   0   1   2
2   a   3   4   5
1   b   6   7   8
2   b   9   10  11
 

根據層次索引級別彙總統計

frame

state   ohio    color
color   green   red green
key1    key2            
a   1   0   1   2
    2   3   4   5
b   1   6   7   8
    2   9   10  11

# 以key2的1和1相加，2和2索引相加
frame.sum(level='key2')

state   ohio    color
color   green   red green
key2            
1   6   8   10
2   12  14  16

# 以行索引的green索引相加，red沒有不做改變
frame.sum(level='color',axis=1)

color   green   red
key1    key2        
a   1   2   1
    2   8   4
b   1   14  7
    2   20  10

使用DataFrame的列

frame1 = pd.DataFrame({'a':range(7),'b':range(7,0,-1),
                     'c':['one','one','one','two','two','two','two'],
                      'd':[0,1,2,0,1,2,3]
                     })

frame1

   a    b   c   d
0   0   7   one 0
1   1   6   one 1
2   2   5   one 2
3   3   4   two 0
4   4   3   two 1
5   5   2   two 2
6   6   1   two 3

#把c/d設定為行索引，預設會刪除這兩列，如果不想刪除，可以吧drop=False開啟
frame1.set_index(['c','d'])

        a   b
c   d       
one 0   0   7
    1   1   6
    2   2   5
two 0   3   4
    1   4   3
    2   5   2
    3   6   1


# reset_index會把cd設定為列索引,瞭解就行
frame2.reset_index()

   index    a   b   c   d
0   0   0   7   one 0
1   1   1   6   one 1
2   2   2   5   one 2
3   3   3   4   two 0
4   4   4   3   two 1
5   5   5   2   two 2
6   6   6   1   two 3