pandas的axis参数

'''
axis = 0 或 index：如果是单行操作，就是指的是某一行；如果是聚合操作，指的是跨行cross rows

axis = 1 或 columns:如果是单列操作，就指的是某一列；如果是聚合操作，指的是跨列cross columns

按哪个axis，就是这个axis要动起来（类似被for遍历），其他的axis保持不动 
'''
import pandas as pd 
import numpy as np
df = pd.DataFrame(np.arange(12).reshape(3,4),columns=['A','B','C','D'])

df

	A	B	C	D
0	0	1	2	3
1	4	5	6	7
2	8	9	10	11

#(1)单列drop，就是删除某一列
df.drop('A',axis=1)#注意，这个表达式的返回值是B,C,D下表，df仍然没有变化

	B	C	D
0	1	2	3
1	5	6	7
2	9	10	11

df

	A	B	C	D
0	0	1	2	3
1	4	5	6	7
2	8	9	10	11

#(2)单行drop，就是删除某一行
df.drop(1,axis=0)#注意索引删除的必须是Index号

	A	B	C	D
0	0	1	2	3
2	8	9	10	11

df

	A	B	C	D
0	0	1	2	3
1	4	5	6	7
2	8	9	10	11

#(3)比较难理解的，按axis=0/index执行mean的聚合操作
df.mean(axis = 0)#行的值动起来，跨行操作，每个行都要运算一次，但是列保持不动

A    4.0
B    5.0
C    6.0
D    7.0
dtype: float64

df.mean(axis = 1)#同上解释

0    1.5
1    5.5
2    9.5
dtype: float64

#再次举例，增加列,增加列的值为sum和
def get_sum_value(x):
    return x['A']+x['B']+x['C']+x['D']
df['sum_value'] = df.apply(get_sum_value,axis = 1)#也就是行不动，将一行的值求和生成新的值

df

	A	B	C	D	sum_value
0	0	1	2	3	6
1	4	5	6	7	22
2	8	9	10	11	38

df['row_sum_value'] = df.apply(get_sum_value,axis = 0)
#报错，是因为 get_sum_value是按照label取值的，如果需要axis=0运算，函数需要按照index取值？不知道是不是这个原因

---------------------------------------------------------------------------

KeyError                                  Traceback (most recent call last)

<ipython-input-17-c2186b52adab> in <module>
----> 1 df['row_sum_value'] = df.apply(get_sum_value,axis = 0)


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\frame.py in apply(self, func, axis, broadcast, raw, reduce, result_type, args, **kwds)
   6485                          args=args,
   6486                          kwds=kwds)
-> 6487         return op.get_result()
   6488 
   6489     def applymap(self, func):


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\apply.py in get_result(self)
    149             return self.apply_raw()
    150 
--> 151         return self.apply_standard()
    152 
    153     def apply_empty_result(self):


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\apply.py in apply_standard(self)
    255 
    256         # compute the result using the series generator
--> 257         self.apply_series_generator()
    258 
    259         # wrap results


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\apply.py in apply_series_generator(self)
    284             try:
    285                 for i, v in enumerate(series_gen):
--> 286                     results[i] = self.f(v)
    287                     keys.append(v.name)
    288             except Exception as e:


<ipython-input-15-0e2329bd7c2c> in get_sum_value(x)
      1 #再次举例，增加列,增加列的值为sum和
      2 def get_sum_value(x):
----> 3     return x['A']+x['B']+x['C']+x['D']
      4 df['sum_value'] = df.apply(get_sum_value,axis = 1)


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\series.py in __getitem__(self, key)
    866         key = com.apply_if_callable(key, self)
    867         try:
--> 868             result = self.index.get_value(self, key)
    869 
    870             if not is_scalar(result):


C:\ProgramData\Anaconda3\lib\site-packages\pandas\core\indexes\base.py in get_value(self, series, key)
   4373         try:
   4374             return self._engine.get_value(s, k,
-> 4375                                           tz=getattr(series.dtype, 'tz', None))
   4376         except KeyError as e1:
   4377             if len(self) > 0 and (self.holds_integer() or self.is_boolean()):


pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()


pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_value()


pandas/_libs/index.pyx in pandas._libs.index.IndexEngine.get_loc()


pandas/_libs/index_class_helper.pxi in pandas._libs.index.Int64Engine._check_type()


KeyError: ('A', 'occurred at index A')