Pandas入门之六：重建索引

已信任
Jupyter 服务器: 本地
Python 3: Not Started
[11]



import pandas as pd
import numpy as np



[13]




df = pd.DataFrame({
    'a':pd.date_range(start='2021-07-14', periods=5, freq='D'),
    'b':[1,2,3,4,5],
    'c':[0.1,0.2,0.3,0.4,0.5]
})
df
a    b    c
0    2021-07-14    1    0.1
1    2021-07-15    2    0.2
2    2021-07-16    3    0.3
3    2021-07-17    4    0.4
4    2021-07-18    5    0.5
[14]



# 重建索引reindex
df.reindex(index=[0,2,4], columns=['a','b','d'])
a    b    d
0    2021-07-14    1    NaN
2    2021-07-16    3    NaN
4    2021-07-18    5    NaN
[16]



df.reindex(index=[0,5,6], columns=['a','b','c'],method='ffill')# 向前填充，5向前是4，所以为 5 0.5
a    b    c
0    2021-07-14    1    0.1
5    2021-07-18    5    0.5
6    2021-07-18    5    0.5
[18]



df1 = pd.DataFrame({
    'g':pd.date_range(start='2021-07-14', periods=5, freq='D'),
    'b':[1,2,3,4,5],
    'c':[0.1,0.2,0.3,0.4,0.5]
})
df1
g    b    c
0    2021-07-14    1    0.1
1    2021-07-15    2    0.2
2    2021-07-16    3    0.3
3    2021-07-17    4    0.4
4    2021-07-18    5    0.5
[19]



# 将df索引修改为像df1的索引
df.reindex_like(df1)
g    b    c
0    NaN    1    0.1
1    NaN    2    0.2
2    NaN    3    0.3
3    NaN    4    0.4
4    NaN    5    0.5
[20]



df1
g    b    c
0    2021-07-14    1    0.1
1    2021-07-15    2    0.2
2    2021-07-16    3    0.3
3    2021-07-17    4    0.4
4    2021-07-18    5    0.5
[22]



# 重命名索引
df1.rename(columns=({'g':'f','b':'hello','c':'world'}))
f    hello    world
0    2021-07-14    1    0.1
1    2021-07-15    2    0.2
2    2021-07-16    3    0.3
3    2021-07-17    4    0.4
4    2021-07-18    5    0.5
[-]