hive 中的grouping set，cube，roll up函數

GROUPING SETS

GROUPING SETS做爲GROUP BY的子句，容許開發人員在GROUP BY語句後面指定多個統計選項，能夠簡單理解爲多條group by語句經過union all把查詢結果聚合起來結合起來，下面是幾個實例能夠幫助咱們瞭解，

以acorn_3g.test_xinyan_reg爲例：

[dp@YZSJHL19-87 xjob]$ hive -e "use acorn_3g;desc test_xinyan_reg;"
user_id                 bigint                  None                 
device_id               int                     None   手機，平板             
os_id                   int                     None   操做系統類型             
app_id                  int                     None   手機app_id             
client_version          string                  None   客戶端版本             
from_id                 int                     None   四級渠道

grouping sets語句	等價hive語句
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

 

cube簡稱數據魔方，能夠實現hive多個任意維度的查詢，cube(a,b,c)則首先會對(a,b,c)進行group by，而後依次是(a,b),(a,c),(a),(b,c),(b),(c),最後在對全表進行group by，他會統計所選列中值的全部組合的聚合

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;

等價於如下sql

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能夠實現從右到作遞減多級的統計，顯示統計某一層次結構的聚合。

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;

等價於如下sql

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),());

Grouping_ID

當咱們沒有統計某一列時，它的值顯示爲null，這可能與列自己就有null值衝突，這就須要一種方法區分是沒有統計仍是值原本就是null。（grouping_id其實就是所統計各列二進制和）

Column1 (key)	Column2 (value)
1	NULL
1	1
2	2
3	3
3	NULL
4	5

hsql：

 SELECT key, value, GROUPING__ID, count(*) from T1 GROUP BY key, value WITH ROLLUP

結果：

NULL	NULL	0     00	6
1	NULL	1     10	2
1	NULL	3     11	1
1	1	3     11	1
2	NULL	1     10	1
2	2	3     11	1
3	NULL	1     10	2
3	NULL	3     11	1
3	3	3     11	1
4	NULL	1     10	1
4	5	3     11	1

GROUPING__ID轉變爲二進制，若是對應位上有值爲null，說明這列自己值就是null。