【数据分析可视化】Series和Dataframe的Reindexing

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

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

A    1
B    2
C    3
D    4
dtype: int64

 # reindex新的Series索引 （查看参数快捷键shift+tab）
s1.reindex(index=['A','B','C','D','E'])

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

# reindex并给空值索引赋值
s1.reindex(index=['A','B','C','D','E'],fill_value=10)

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

# 测试reindex的赋值方式
s2 = Series(['A','B','C'],index=[1,5,10])
s2

1     A
5     B
10    C
dtype: object

# 重新索引
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

# 函数填充值(ffill函数将重新索引前安装区间范围依次赋值)
s2.reindex(index=range(15),method='ffill')

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

# 故意漏掉C
df1 = DataFrame(np.random.rand(25).reshape([5,5]), index=['A','B','D','E','F'], columns=['c1','c2','c3','c4','c5'])
df1

# reindex恢复C-重新索引行
df1.reindex(['A','B','C','D','E','F'])

# reindex-重新索引列
df1.reindex(columns=['c1','c2','c3','c4','c5','c6'])

 # reindex-行列同时重排(新增)
df1.reindex(index=['A','B','C','D','E','F'] ,columns=['c1','c2','c3','c4','c5','c6'])

# Series（减少）
s1

A    1
B    2
C    3
D    4
dtype: int64

s1.reindex(index=['A','B'])

A    1
B    2
dtype: int64

# reindex-行列同时重排(减少)
df1

df1.reindex(['A','B'])

# 删掉的方法
s1.drop('A')

B    2
C    3
D    4
dtype: int64

# 0行1列
df1.drop('A',axis=0)

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