Pandas数据排序

Pandas数据排序

.sort_index() 在指定轴上根据索引进行排序，索引排序后内容会跟随排序

import pandas as pd
import numpy as np

b = pd.DataFrame(np.arange(20).reshape(4,5),index=['c','a','d','b'])
b

	0	1	2	3	4
c	0	1	2	3	4
a	5	6	7	8	9
d	10	11	12	13	14
b	15	16	17	18	19

b.sort_index()

	0	1	2	3	4
a	5	6	7	8	9
b	15	16	17	18	19
c	0	1	2	3	4
d	10	11	12	13	14

b.sort_index(ascending=False)

	0	1	2	3	4
d	10	11	12	13	14
c	0	1	2	3	4
b	15	16	17	18	19
a	5	6	7	8	9

b.sort_index(axis=0, ascending=False) # 按行标排序，ascending：False为降序

	0	1	2	3	4
d	10	11	12	13	14
c	0	1	2	3	4
b	15	16	17	18	19
a	5	6	7	8	9

b.sort_index(axis=1, ascending=False) # 按列标排序

	4	3	2	1	0
c	4	3	2	1	0
a	9	8	7	6	5
d	14	13	12	11	10
b	19	18	17	16	15

.sort_values() 在指定轴上根据数值进行排序，默认升序

• Series.sort_values(axis=0,ascending=True)
• DataFrame.sort_values(by,axis=0,ascending=True)
  
  • by：axis轴上的某个索引或索引列表

dates = pd.date_range('20130101', periods=10)
dates

DatetimeIndex(['2013-01-01', '2013-01-02', '2013-01-03', '2013-01-04',
               '2013-01-05', '2013-01-06', '2013-01-07', '2013-01-08',
               '2013-01-09', '2013-01-10'],
              dtype='datetime64[ns]', freq='D')

df = pd.DataFrame(np.random.randn(10,4),index=dates,columns=['A','B','C','D'])
df.head()

	A	B	C	D
2013-01-01	-0.300266	0.683232	0.777509	-0.274338
2013-01-02	2.298084	-0.855524	1.462064	-0.725142
2013-01-03	0.512711	0.824380	0.384902	-1.437241
2013-01-04	0.388478	-1.265414	-1.104333	-0.447689
2013-01-05	0.273518	-0.314857	-2.545510	-1.301629

c = df.sort_values('B')
c.head()

	A	B	C	D
2013-01-01	-0.976353	-2.176075	0.255585	0.645465
2013-01-03	-1.549727	-1.876790	0.966724	0.486101
2013-01-06	-0.000467	-1.430820	-1.803610	-0.587985
2013-01-10	-0.293663	-0.691951	0.262666	-1.298977
2013-01-04	-0.032301	-0.618582	1.204373	-0.302137

c = df.sort_values('B',ascending = False)
c.head()

	A	B	C	D
2013-01-03	0.512711	0.824380	0.384902	-1.437241
2013-01-01	-0.300266	0.683232	0.777509	-0.274338
2013-01-08	0.010939	0.591777	0.143182	0.461798
2013-01-10	0.811169	0.100516	-1.385373	0.168329
2013-01-05	0.273518	-0.314857	-2.545510	-1.301629

# 指定1轴排序,这里指定1轴a行为基准排序
c = df.sort_values('2013-01-01',axis=1,ascending=False) 
c.head()

	C	B	D	A
2013-01-01	0.777509	0.683232	-0.274338	-0.300266
2013-01-02	1.462064	-0.855524	-0.725142	2.298084
2013-01-03	0.384902	0.824380	-1.437241	0.512711
2013-01-04	-1.104333	-1.265414	-0.447689	0.388478
2013-01-05	-2.545510	-0.314857	-1.301629	0.273518

---

NaN空值统一放在排序末尾

a = pd.DataFrame(np.arange(12).reshape(3,4),index=['a','b','c'])
a

	0	1	2	3
a	0	1	2	3
b	4	5	6	7
c	8	9	10	11

b = pd.DataFrame(np.arange(20).reshape(4,5),index=['c','a','d','b'])
b

	0	1	2	3	4
c	0	1	2	3	4
a	5	6	7	8	9
d	10	11	12	13	14
b	15	16	17	18	19

c = a + b
c

	0	1	2	3	4
a	5.0	7.0	9.0	11.0	NaN
b	19.0	21.0	23.0	25.0	NaN
c	8.0	10.0	12.0	14.0	NaN
d	NaN	NaN	NaN	NaN	NaN

c.sort_values(2,ascending = False)

	0	1	2	3	4
b	19.0	21.0	23.0	25.0	NaN
c	8.0	10.0	12.0	14.0	NaN
a	5.0	7.0	9.0	11.0	NaN
d	NaN	NaN	NaN	NaN	NaN

c.sort_values(2,ascending = True)

	0	1	2	3	4
a	5.0	7.0	9.0	11.0	NaN
c	8.0	10.0	12.0	14.0	NaN
b	19.0	21.0	23.0	25.0	NaN
d	NaN	NaN	NaN	NaN	NaN