分组聚合后unstacking

# 读取employee数据集，求出每个种族的平均工资
employee = pd.read_csv('data/employee.csv')
employee.groupby('RACE')['BASE_SALARY'].mean().astype(int)

RACE
American Indian or Alaskan Native    60272
Asian/Pacific Islander               61660
Black or African American            50137
Hispanic/Latino                      52345
Others                               51278
White                                64419
Name: BASE_SALARY, dtype: int32

# 对种族和性别分组，求平均工资
agg = employee.groupby(['RACE', 'GENDER'])['BASE_SALARY'].mean().astype(int)
agg
'''
RACE                               GENDER
American Indian or Alaskan Native  Female    60238
                                   Male      60305
Asian/Pacific Islander             Female    63226
                                   Male      61033
Black or African American          Female    48915
                                   Male      51082
Hispanic/Latino                    Female    46503
                                   Male      54782
Others                             Female    63785
                                   Male      38771
White                              Female    66793
                                   Male      63940
Name: BASE_SALARY, dtype: int32
'''

#stack: 将数据从”表格结构“变成”花括号结构“，即将其列索引变成行索引。
#unstack,数据从”花括号结构“变成”表格结构“，将数据的行索引转换为列索引
agg.unstack('GENDER')

GENDER	Female	Male
RACE
American Indian or Alaskan Native	60238	60305
Asian/Pacific Islander	63226	61033
Black or African American	48915	51082
Hispanic/Latino	46503	54782
Others	63785	38771
White	66793	63940

# 对索引层RACE做unstack
agg.unstack('RACE')

RACE	American Indian or Alaskan Native	Asian/Pacific Islander	Black or African American	Hispanic/Latino	Others	White
GENDER
Female	60238	63226	48915	46503	63785	66793
Male	60305	61033	51082	54782	38771	63940

#unstack处理multiIndex
# 按RACE和GENDER分组，求工资的平均值、最大值和最小值
agg2 = employee.groupby(['RACE', 'GENDER'])['BASE_SALARY'].agg(['mean', 'max', 'min']).astype(int)
agg2

		mean	max	min
RACE	GENDER
American Indian or Alaskan Native	Female	60238	98536	26125
	Male	60305	81239	26125
Asian/Pacific Islander	Female	63226	130416	26125
	Male	61033	163228	27914
Black or African American	Female	48915	150416	24960
	Male	51082	275000	26125
Hispanic/Latino	Female	46503	126115	26125
	Male	54782	165216	26104
Others	Female	63785	63785	63785
	Male	38771	38771	38771
White	Female	66793	178331	27955
	Male	63940	210588	26125

# 此时unstack('GENDER')会生成多级列索引，可以用stack和unstack调整结构
agg2.unstack('GENDER')

	mean		max		min
GENDER	Female	Male	Female	Male	Female	Male
RACE
American Indian or Alaskan Native	60238	60305	98536	81239	26125	26125
Asian/Pacific Islander	63226	61033	130416	163228	26125	27914
Black or African American	48915	51082	150416	275000	24960	26125
Hispanic/Latino	46503	54782	126115	165216	26125	26104
Others	63785	38771	63785	38771	63785	38771
White	66793	63940	178331	210588	27955	26125