Hive高阶聚合函数 GROUPING SETS、Cube、Rollup
GROUPING SETS
GROUPING SETS作为GROUP BY的子句，允许开发人员在GROUP BY语句后面指定多个统计选项，可以简单理解为多条group by语句通过union all把查询结果聚合起来结合起来，下面是几个实例可以帮助我们了解，
以acorn_3g.test_xinyan_reg为例：
[dp@YZSJHL19-87 xjob]$ hive -e "use acorn_3g;desc test_xinyan_reg;"
user_id bigint None
device_id int None 手机，平板
os_id int None 操作系统类型
app_id int None 手机app_id
client_version string None 客户端版本
from_id int None 四级渠道
几个实例：
| grouping sets语句 | 等价hive |
|---|---|
| select device_id,os_id,app_id,count(user_id) from test_xinyan_reg group by device_id,os_id,app_id grouping sets((device_id)) | SELECT device_id,null,null,count(user_id) FROM test_xinyan_reg group by device_id |
| select device_id,os_id,app_id,count(user_id) from test_xinyan_reg group by device_id,os_id,app_id grouping sets((device_id,os_id)) | SELECT device_id,os_id,null,count(user_id) FROM test_xinyan_reg group by device_id,os_id |
| select device_id,os_id,app_id,count(user_id) from test_xinyan_reg group by device_id,os_id,app_id grouping sets((device_id,os_id),(device_id)) | SELECT device_id,os_id,null,count(user_id) FROM test_xinyan_reg group by device_id,os_id UNION ALL SELECT device_id,null,null,count(user_id) FROM test_xinyan_reg group by device_id |
| select device_id,os_id,app_id,count(user_id) from test_xinyan_reg group by device_id,os_id,app_id grouping sets((device_id),(os_id),(device_id,os_id),()) | SELECT device_id,null,null,count(user_id) FROM test_xinyan_reg group by device_id UNION ALL SELECT null,os_id,null,count(user_id) FROM test_xinyan_reg group by os_id UNION ALL SELECT device_id,os_id,null,count(user_id) FROM test_xinyan_reg group by device_id,os_id UNION ALL SELECT null,null,null,count(user_id) FROM test_xinyan_reg |
CUBE函数
cube简称数据魔方，可以实现hive多个任意维度的查询，cube(a,b,c)则首先会对(a,b,c)进行group by，然后依次是(a,b),(a,c),(a),(b,c),(b),©,最后在对全表进行group by，他会统计所选列中值的所有组合的聚合
cube即为grouping sets的简化过程函数
实例：
select device_id,os_id,app_id,client_version,from_id,count(user_id)
from test_xinyan_reg
group by device_id,os_id,app_id,client_version,from_id with cube;
等价Hql:
SELECT device_id,null,null,null,null ,count(user_id) FROM test_xinyan_reg group by device_id
UNION ALL
SELECT null,os_id,null,null,null ,count(user_id) FROM test_xinyan_reg group by os_id
UNION ALL
SELECT device_id,os_id,null,null,null ,count(user_id) FROM test_xinyan_reg group by device_id,os_id
UNION ALL
SELECT null,null,app_id,null,null ,count(user_id) FROM test_xinyan_reg group by app_id
UNION ALL
SELECT device_id,null,app_id,null,null ,count(user_id) FROM test_xinyan_reg group by device_id,app_id
UNION ALL
SELECT null,os_id,app_id,null,null ,count(user_id) FROM test_xinyan_reg group by os_id,app_id
UNION ALL
SELECT device_id,os_id,app_id,null,null ,count(user_id) FROM test_xinyan_reg group by device_id,os_id,app_id
UNION ALL
SELECT null,null,null,client_version,null ,count(user_id) FROM test_xinyan_reg group by client_version
UNION ALL
SELECT device_id,null,null,client_version,null ,count(user_id) FROM test_xinyan_reg group by device_id,client_version
UNION ALL
SELECT null,os_id,null,client_version,null ,count(user_id) FROM test_xinyan_reg group by os_id,client_version
UNION ALL
SELECT device_id,os_id,null,client_version,null ,count(user_id) FROM test_xinyan_reg group by device_id,os_id,client_version
UNION ALL
SELECT null,null,app_id,client_version,null ,count(user_id) FROM test_xinyan_reg group by app_id,client_version
UNION ALL
SELECT device_id,null,app_id,client_version,null ,count(user_id) FROM test_xinyan_reg group by device_id,app_id,client_version
UNION ALL
SELECT null,os_id,app_id,client_version,null ,count(user_id) FROM test_xinyan_reg group by os_id,app_id,client_version
UNION ALL
SELECT device_id,os_id,app_id,client_version,null ,count(user_id) FROM test_xinyan_reg group by device_id,os_id,app_id,client_version
UNION ALL
SELECT null,null,null,null,from_id ,count(user_id) FROM test_xinyan_reg group by from_id
UNION ALL
SELECT device_id,null,null,null,from_id ,count(user_id) FROM test_xinyan_reg group by device_id,from_id
UNION ALL
SELECT null,os_id,null,null,from_id ,count(user_id) FROM test_xinyan_reg group by os_id,from_id
UNION ALL
SELECT device_id,os_id,null,null,from_id ,count(user_id) FROM test_xinyan_reg group by device_id,os_id,from_id
UNION ALL
SELECT null,null,app_id,null,from_id ,count(user_id) FROM test_xinyan_reg group by app_id,from_id
UNION ALL
SELECT device_id,null,app_id,null,from_id ,count(user_id) FROM test_xinyan_reg group by device_id,app_id,from_id
UNION ALL
SELECT null,os_id,app_id,null,from_id ,count(user_id) FROM test_xinyan_reg group by os_id,app_id,from_id
UNION ALL
SELECT device_id,os_id,app_id,null,from_id ,count(user_id) FROM test_xinyan_reg group by device_id,os_id,app_id,from_id
UNION ALL
SELECT null,null,null,client_version,from_id ,count(user_id) FROM test_xinyan_reg group by client_version,from_id
UNION ALL
SELECT device_id,null,null,client_version,from_id ,count(user_id) FROM test_xinyan_reg group by device_id,client_version,from_id
UNION ALL
SELECT null,os_id,null,client_version,from_id ,count(user_id) FROM test_xinyan_reg group by os_id,client_version,from_id
UNION ALL
SELECT device_id,os_id,null,client_version,from_id ,count(user_id) FROM test_xinyan_reg group by device_id,os_id,client_version,from_id
UNION ALL
SELECT null,null,app_id,client_version,from_id ,count(user_id) FROM test_xinyan_reg group by app_id,client_version,from_id
UNION ALL
SELECT device_id,null,app_id,client_version,from_id ,count(user_id) FROM test_xinyan_reg group by device_id,app_id,client_version,from_id
UNION ALL
SELECT null,os_id,app_id,client_version,from_id ,count(user_id) FROM test_xinyan_reg group by os_id,app_id,client_version,from_id
UNION ALL
SELECT device_id,os_id,app_id,client_version,from_id ,count(user_id) FROM test_xinyan_reg group by device_id,os_id,app_id,client_version,from_id
UNION ALL
SELECT null,null,null,null,null ,count(user_id) FROM test_xinyan_reg
ROLL UP
rollup可以实现从右到做递减多级的统计，显示统计某一层次结构的聚合。
实例:
select device_id,os_id,app_id,client_version,from_id,count(user_id)
from test_xinyan_reg
group by device_id,os_id,app_id,client_version,from_id with rollup;
等价Hql:
select device_id,os_id,app_id,client_version,from_id,count(user_id)
from test_xinyan_reg
group by device_id,os_id,app_id,client_version,from_id
grouping sets ((device_id,os_id,app_id,client_version,from_id),(device_id,os_id,app_id,client_version),(device_id,os_id,app_id),(device_id,os_id),(device_id),());