pandas的group用法 apply、map、agg

Groupby的用法

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

	Country	Income	Age
0	China	10000	5000
1	China	10000	4321
2	India	5000	1234
3	India	5002	4010
4	America	40000	250
5	Japan	50000	250
6	China	8000	4500
7	India	5000	4321

按单列进行分组

df_gb = df.groupby('Country')
for index, data in df_gb:
    print(index)
    print(data)

America
   Country  Income  Age
4  America   40000  250
China
  Country  Income   Age
0   China   10000  5000
1   China   10000  4321
6   China    8000  4500
India
  Country  Income   Age
2   India    5000  1234
3   India    5002  4010
7   India    5000  4321
Japan
  Country  Income  Age
5   Japan   50000  250

按多列进行分组

df_gb = df.groupby(['Country', 'Income'])
for (index1, index2), data in df_gb:
    print((index1, index2))
    print(data)

('America', 40000)
   Country  Income  Age
4  America   40000  250
('China', 8000)
  Country  Income   Age
6   China    8000  4500
('China', 10000)
  Country  Income   Age
0   China   10000  5000
1   China   10000  4321
('India', 5000)
  Country  Income   Age
2   India    5000  1234
7   India    5000  4321
('India', 5002)
  Country  Income   Age
3   India    5002  4010
('Japan', 50000)
  Country  Income  Age
5   Japan   50000  250

agg聚合操作

df_agg = df.groupby('Country').agg(['min', 'mean', 'max'])
print(df_agg)

        Income                        Age                   
           min          mean    max   min         mean   max
Country                                                     
America  40000  40000.000000  40000   250   250.000000   250
China     8000   9333.333333  10000  4321  4607.000000  5000
India     5000   5000.666667   5002  1234  3188.333333  4321
Japan    50000  50000.000000  50000   250   250.000000   250

num_agg = {'Age':['min', 'mean', 'max']}
print(df.groupby('Country').agg(num_agg))

          Age                   
          min         mean   max
Country                         
America   250   250.000000   250
China    4321  4607.000000  5000
India    1234  3188.333333  4321
Japan     250   250.000000   250

num_agg = {'Age':['min', 'mean', 'max'], 'Income':['min', 'max']}
print(df.groupby('Country').agg(num_agg))

          Age                    Income       
          min         mean   max    min    max
Country                                       
America   250   250.000000   250  40000  40000
China    4321  4607.000000  5000   8000  10000
India    1234  3188.333333  4321   5000   5002
Japan     250   250.000000   250  50000  50000

Apply

df

	Country	Income	Age
0	China	10000	5000
1	China	10000	4321
2	India	5000	1234
3	India	5002	4010
4	America	40000	250
5	Japan	50000	250
6	China	8000	4500
7	India	5000	4321

df['Age'].apply(lambda x:str(x)[0])

0    5
1    4
2    1
3    4
4    2
5    2
6    4
7    4
Name: Age, dtype: object