python groupby agg()

• 构造数据

  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]})
  

  　　结果如下：

   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
  

   

• 单列分组

df_gb = df.groupby('Country')
for index, data in df_gb:
    print(index)
    print(data)
输出
America
   Age  Country  Income
4  250  America   40000
China
    Age Country  Income
0  5000   China   10000
1  4321   China   10000
6  4500   China    8000
India
    Age Country  Income
2  1234   India    5000
3  4010   India    5002
7  4321   India    5000
Japan
   Age Country  Income
5  250   Japan   50000

　　

•     多列分组

  df_gb = df.groupby(['Country', 'Income'])
  for (index1, index2), data in df_gb:
      print((index1, index2))
      print(data)
   
  输出
   
  ('America', 40000)
     Age  Country  Income
  4  250  America   40000
  ('China', 8000)
      Age Country  Income
  6  4500   China    8000
  ('China', 10000)
      Age Country  Income
  0  5000   China   10000
  1  4321   China   10000
  ('India', 5000)
      Age Country  Income
  2  1234   India    5000
  7  4321   India    5000
  ('India', 5002)
      Age Country  Income
  3  4010   India    5002
  ('Japan', 50000)
     Age Country  Income
  5  250   Japan   50000
  

  　聚合函数，对分组后数据进行聚合

• 　

  df_agg = df.groupby('Country').agg(['min', 'mean', 'max'])
  print(df_agg)
  输出
     Age                    Income                     
            min         mean   max    min          mean    max
  Country                                                     
  America   250   250.000000   250  40000  40000.000000  40000
  China    4321  4607.000000  5000   8000   9333.333333  10000
  India    1234  3188.333333  4321   5000   5000.666667   5002
  Japan     250   250.000000   250  50000  50000.000000  50000
  

  对分组后的部分列进行聚合

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