Python与数据科学实战课程——第三章Pandas：Reindexing Series and DataFrame

import numpy as np
import pandas as pd
from pandas import Series,DataFrame

Series reindex

s1 = Series([1,2,3,4],index=["A","B","C","D"])
s1

A 1
B 2
C 3
D 4
dtype: int64

s1.reindex(index=["A","B","C","D","E"])

A 1.0
B 2.0
C 3.0
D 4.0
E NaN
dtype: float64

s1.reindex(index=["A","B","C","D","E"],fill_value=10)

A 1
B 2
C 3
D 4
E 10
dtype: int64

s2 = Series(["a","b","c"],index=[1,5,10])
s2

1 a
5 b
10 c
dtype: object

s2.reindex(index=range(15))

0 NaN
1 a
2 NaN
3 NaN
4 NaN
5 b
6 NaN
7 NaN
8 NaN
9 NaN
10 c
11 NaN
12 NaN
13 NaN
14 NaN
dtype: object

s2.reindex(index=range(15),method="ffill")   #ffill (forward fill，前向填充，与前面的已经赋过值一致)

0 NaN
1 a
2 a
3 a
4 a
5 b
6 b
7 b
8 b
9 b
10 c
11 c
12 c
13 c
14 c
dtype: object

reindex dataframe

df1 = DataFrame(np.random.rand(25).reshape(5,5),index=["A","B","C","D","E"],columns=["c1","c2","c3","c4","c5"])
df1

	c1	c2	c3	c4	c5
A	0.757715	0.918084	0.948077	0.742951	0.487620
B	0.588601	0.287319	0.812112	0.301332	0.672896
C	0.595671	0.151094	0.879628	0.494836	0.531921
D	0.743913	0.412434	0.675041	0.056901	0.242197
E	0.226964	0.213529	0.850152	0.606388	0.690059

df1.reindex(index=["A","B","C","D","E","F"])

	c1	c2	c3	c4	c5
A	0.757715	0.918084	0.948077	0.742951	0.487620
B	0.588601	0.287319	0.812112	0.301332	0.672896
C	0.595671	0.151094	0.879628	0.494836	0.531921
D	0.743913	0.412434	0.675041	0.056901	0.242197
E	0.226964	0.213529	0.850152	0.606388	0.690059
F	NaN	NaN	NaN	NaN	NaN

df1.reindex(columns=["c1","c2","C3","C4","C5","C6"])  
# 可以看到 reindex并不是重命名，c3->C3后，原有列内容也全部被覆盖了

	c1	c2	C3	C4	C5	C6
A	0.757715	0.918084	NaN	NaN	NaN	NaN
B	0.588601	0.287319	NaN	NaN	NaN	NaN
C	0.595671	0.151094	NaN	NaN	NaN	NaN
D	0.743913	0.412434	NaN	NaN	NaN	NaN
E	0.226964	0.213529	NaN	NaN	NaN	NaN

df1.reindex(columns=["c1","c2","c3","c4","c5","c6"])  

	c1	c2	c3	c4	c5	c6
A	0.757715	0.918084	0.948077	0.742951	0.487620	NaN
B	0.588601	0.287319	0.812112	0.301332	0.672896	NaN
C	0.595671	0.151094	0.879628	0.494836	0.531921	NaN
D	0.743913	0.412434	0.675041	0.056901	0.242197	NaN
E	0.226964	0.213529	0.850152	0.606388	0.690059	NaN

df1.reindex(index=["A","B","C","D","E","F"],columns=["c1","c2","c3","c4","c5","c6"])

	c1	c2	c3	c4	c5	c6
A	0.757715	0.918084	0.948077	0.742951	0.487620	NaN
B	0.588601	0.287319	0.812112	0.301332	0.672896	NaN
C	0.595671	0.151094	0.879628	0.494836	0.531921	NaN
D	0.743913	0.412434	0.675041	0.056901	0.242197	NaN
E	0.226964	0.213529	0.850152	0.606388	0.690059	NaN
F	NaN	NaN	NaN	NaN	NaN	NaN

上面都是对series或者dataframe进行添加index ，下面看看减少index会发生什么

s1

A 1
B 2
C 3
D 4
dtype: int64

s1.reindex(index=["A","B"])  #相当于切片

A 1
B 2
dtype: int64

df1

	c1	c2	c3	c4	c5
A	0.757715	0.918084	0.948077	0.742951	0.487620
B	0.588601	0.287319	0.812112	0.301332	0.672896
C	0.595671	0.151094	0.879628	0.494836	0.531921
D	0.743913	0.412434	0.675041	0.056901	0.242197
E	0.226964	0.213529	0.850152	0.606388	0.690059

df1.reindex(index=["A","B"])

	c1	c2	c3	c4	c5
A	0.757715	0.918084	0.948077	0.742951	0.487620
B	0.588601	0.287319	0.812112	0.301332	0.672896

更简单的删除某些index value的方式

s1

A 1
B 2
C 3
D 4
dtype: int64

s1.drop("A")

B 2
C 3
D 4
dtype: int64

df1

	c1	c2	c3	c4	c5
A	0.757715	0.918084	0.948077	0.742951	0.487620
B	0.588601	0.287319	0.812112	0.301332	0.672896
C	0.595671	0.151094	0.879628	0.494836	0.531921
D	0.743913	0.412434	0.675041	0.056901	0.242197
E	0.226964	0.213529	0.850152	0.606388	0.690059

df1.drop("A",axis=0)    #axis=0表示删除行，axis=1表示删除列。这样设定是为了避免列名和index名称一样时候发生的冲突

	c1	c2	c3	c4	c5
B	0.588601	0.287319	0.812112	0.301332	0.672896
C	0.595671	0.151094	0.879628	0.494836	0.531921
D	0.743913	0.412434	0.675041	0.056901	0.242197
E	0.226964	0.213529	0.850152	0.606388	0.690059

df1.drop("c1",axis=1)

	c2	c3	c4	c5
A	0.918084	0.948077	0.742951	0.487620
B	0.287319	0.812112	0.301332	0.672896
C	0.151094	0.879628	0.494836	0.531921
D	0.412434	0.675041	0.056901	0.242197
E	0.213529	0.850152	0.606388	0.690059