pandas 设置多重索引_pandas基础(2)_多重索引

<div style="font-size:16px;">
1：多重索引的构造
>>> #下面显示构造pd.MultiIndex
>>> df1=DataFrame(np.random.randint(0,150,size=(6,3)),columns=['java','html5','python'])
>>> import pandas as pd
>>> df1=DataFrame(np.random.randint(0,150,size=(6,3)),columns=['java','html5','python'],index=pd.MultiIndex.from_arrays([['张三','张三','侯少','侯少','a','a'],['M','E','M','E','M','E']]))
>>> df1#因为Python自身的原因，对汉字的识别不是太好，所以汉字被？代替了
java html5 python
???? M 2 13 76
E 141 67 84
M 116 83 8
E 70 118 125
a M 74 0 76
E 111 31 8
>>> #使用元组tuple创建
df2=DataFrame(np.random.randint(0,150,size=(6,3)),columns=['java','html','python'],index=pd.MultiIndex.from_tuples([('a','1'),('a','11'),('b','1'),('b','11'),('c','1'),('c','11')]))
>>> df2
java html python
a 1 32 144 99
11 104 101 16
b 1 93 98 41
11 59 30 45
c 1 91 17 149
11 9 28 59
>>> #使用product
df2=DataFrame(np.random.randint(0,150,size=(6,3)),columns=['java','html','python'],index=pd.MultiIndex.from_product([['zhangsan ','lisi','wangwu'],['mid','end']]))
>>> df2
java html python
zhangsan mid 50 128 54
end 3 4 91
lisi mid 4 93 110
end 116 123 122
wangwu mid 88 25 54
end 48 146 57
>>> #对dataFrame同样可以设置成多重索引
df2=DataFrame(np.random.randint(0,150,size=(3,6)),columns=pd.MultiIndex.from_product([['java','html','python'],['mid','end']]),index=['张三','李四','王五'])
>>> df2
java html python
mid end mid end mid end
???? 33 38 112 70 113 110
???? 29 46 132 91 117 128
???? 73 56 118 82 132 39
>>>
>>> df2['java','mid']#查询某一列
???? 33
???? 29
???? 73
Name: (java, mid), dtype: int32
>>> s['zhangsan':'lisi']#其实就是一个Series
Series([], dtype: int64)
>>> s.iloc[0:3]
a 0 1
1 2
b 0 3
dtype: int64
>>> #切片
>>> df2['张三':'王五']
java html python
mid end mid end mid end
???? 33 38 112 70 113 110
???? 29 46 132 91 117 128
???? 73 56 118 82 132 39
>>>df2.iloc[0:4]#推荐使用
Df2[‘张三’，‘期中’]和df2.loc[‘张三’].loc[‘期中’]
#如何一级索引有多个，对二级索引会遇到问题，也就是说，无法直接对二级进行索引
必须把二级索引变成一级索引才可以进行索引
>>> df2.stack()
html java python
???? end 70 38 110
mid 112 33 113
end 91 46 128
mid 132 29 117
end 82 56 39
mid 118 73 132
>>> #stack =堆----》行
end mid
???? html 70 112
java 38 33
python 110 113
html 91 132
java 46 29
python 128 117
html 82 118
java 56 73
python 39 132
>>> #默认为-1
2：多重索引的计算
>>> df2
java html python
mid end mid end mid end
???? 33 38 112 70 113 110
???? 29 46 132 91 117 128
???? 73 56 118 82 132 39
>>> df1.sum()
java 514
html5 312
python 377
dtype: int64
>>> df1.sum(axis=0)
java 514
html5 312
python 377
dtype: int64
>>> df1.sum(axis=1)#对列
???? M 91
E 292
M 207
E 313
a M 150
E 150
dtype: int64
>>> df1.sum(axis=1)#对列求和，得到每行的和
???? M 91
E 292
M 207
E 313
a M 150
E 150
dtype: int64
>>> df1.std

???? M 2 13 76
E 141 67 84
M 116 83 8
E 70 118