import pandas as pd
df = pd.DataFrame({
'Country':['China','China', 'India', 'India', 'America', 'Japan', 'China', 'India'],
'Income':[10000, 10000, 5000, 5002, 40000, 50000, 8000, 5000],
'Age':[5000, 4321, 1234, 4010, 250, 250, 4500, 4321]})
df
|
Age |
Country |
Income |
0 |
5000 |
China |
10000 |
1 |
4321 |
China |
10000 |
2 |
1234 |
India |
5000 |
3 |
4010 |
India |
5002 |
4 |
250 |
America |
40000 |
5 |
250 |
Japan |
50000 |
6 |
4500 |
China |
8000 |
7 |
4321 |
India |
5000 |
主要就是理解下面这句话!!!后面的是一些细节!!
一个基础的语法!!!
a=df.groupby('Country', as_index = False)['Income'].agg({
'Income_sum':'sum'})
a