hive窗口分析函数
转载http://lxw1234.com/archives/2015/04/193.htm
GROUPING SETS,GROUPING__ID,CUBE,ROLLUP
这几个分析函数通常用于OLAP中，不能累加，而且需要根据不同维度上钻和下钻的指标统计，比如，分小时、天、月的UV数。
Hive版本为 apache-hive-0.13.1
数据准备：
- 2015-03,2015-03-10,cookie1
- 2015-03,2015-03-10,cookie5
- 2015-03,2015-03-12,cookie7
- 2015-04,2015-04-12,cookie3
- 2015-04,2015-04-13,cookie2
- 2015-04,2015-04-13,cookie4
- 2015-04,2015-04-16,cookie4
- 2015-03,2015-03-10,cookie2
- 2015-03,2015-03-10,cookie3
- 2015-04,2015-04-12,cookie5
- 2015-04,2015-04-13,cookie6
- 2015-04,2015-04-15,cookie3
- 2015-04,2015-04-15,cookie2
- 2015-04,2015-04-16,cookie1
- CREATE EXTERNAL TABLE lxw1234 (
- month STRING,
- day STRING,
- cookieid STRING
- ) ROW FORMAT DELIMITED
- FIELDS TERMINATED BY ','
- stored as textfile location '/tmp/lxw11/';
- hive> select * from lxw1234;
- OK
- 2015-03 2015-03-10 cookie1
- 2015-03 2015-03-10 cookie5
- 2015-03 2015-03-12 cookie7
- 2015-04 2015-04-12 cookie3
- 2015-04 2015-04-13 cookie2
- 2015-04 2015-04-13 cookie4
- 2015-04 2015-04-16 cookie4
- 2015-03 2015-03-10 cookie2
- 2015-03 2015-03-10 cookie3
- 2015-04 2015-04-12 cookie5
- 2015-04 2015-04-13 cookie6
- 2015-04 2015-04-15 cookie3
- 2015-04 2015-04-15 cookie2
- 2015-04 2015-04-16 cookie1
GROUPING SETS
在一个GROUP BY查询中，根据不同的维度组合进行聚合，等价于将不同维度的GROUP BY结果集进行UNION ALL
- SELECT
- month,
- day,
- COUNT(DISTINCT cookieid) AS uv,
- GROUPING__ID
- FROM lxw1234
- GROUP BY month,day
- GROUPING SETS (month,day)
- ORDER BY GROUPING__ID;
- month day uv GROUPING__ID
- ------------------------------------------------
- 2015-03 NULL 5 1
- 2015-04 NULL 6 1
- NULL 2015-03-10 4 2
- NULL 2015-03-12 1 2
- NULL 2015-04-12 2 2
- NULL 2015-04-13 3 2
- NULL 2015-04-15 2 2
- NULL 2015-04-16 2 2
- 等价于
- SELECT month,NULL,COUNT(DISTINCT cookieid) AS uv,1 AS GROUPING__ID FROM lxw1234 GROUP BY month
- UNION ALL
- SELECT NULL,day,COUNT(DISTINCT cookieid) AS uv,2 AS GROUPING__ID FROM lxw1234 GROUP BY day
再如：
- SELECT
- month,
- day,
- COUNT(DISTINCT cookieid) AS uv,
- GROUPING__ID
- FROM lxw1234
- GROUP BY month,day
- GROUPING SETS (month,day,(month,day))
- ORDER BY GROUPING__ID;
- month day uv GROUPING__ID
- ------------------------------------------------
- 2015-03 NULL 5 1
- 2015-04 NULL 6 1
- NULL 2015-03-10 4 2
- NULL 2015-03-12 1 2
- NULL 2015-04-12 2 2
- NULL 2015-04-13 3 2
- NULL 2015-04-15 2 2
- NULL 2015-04-16 2 2
- 2015-03 2015-03-10 4 3
- 2015-03 2015-03-12 1 3
- 2015-04 2015-04-12 2 3
- 2015-04 2015-04-13 3 3
- 2015-04 2015-04-15 2 3
- 2015-04 2015-04-16 2 3
- 等价于
- SELECT month,NULL,COUNT(DISTINCT cookieid) AS uv,1 AS GROUPING__ID FROM lxw1234 GROUP BY month
- UNION ALL
- SELECT NULL,day,COUNT(DISTINCT cookieid) AS uv,2 AS GROUPING__ID FROM lxw1234 GROUP BY day
- UNION ALL
- SELECT month,day,COUNT(DISTINCT cookieid) AS uv,3 AS GROUPING__ID FROM lxw1234 GROUP BY month,day
其中的 GROUPING__ID，表示结果属于哪一个分组集合。
CUBE
根据GROUP BY的维度的所有组合进行聚合。
- SELECT
- month,
- day,
- COUNT(DISTINCT cookieid) AS uv,
- GROUPING__ID
- FROM lxw1234
- GROUP BY month,day
- WITH CUBE
- ORDER BY GROUPING__ID;
- month day uv GROUPING__ID
- --------------------------------------------
- NULL NULL 7 0
- 2015-03 NULL 5 1
- 2015-04 NULL 6 1
- NULL 2015-04-12 2 2
- NULL 2015-04-13 3 2
- NULL 2015-04-15 2 2
- NULL 2015-04-16 2 2
- NULL 2015-03-10 4 2
- NULL 2015-03-12 1 2
- 2015-03 2015-03-10 4 3
- 2015-03 2015-03-12 1 3
- 2015-04 2015-04-16 2 3
- 2015-04 2015-04-12 2 3
- 2015-04 2015-04-13 3 3
- 2015-04 2015-04-15 2 3
- 等价于
- SELECT NULL,NULL,COUNT(DISTINCT cookieid) AS uv,0 AS GROUPING__ID FROM lxw1234
- UNION ALL
- SELECT month,NULL,COUNT(DISTINCT cookieid) AS uv,1 AS GROUPING__ID FROM lxw1234 GROUP BY month
- UNION ALL
- SELECT NULL,day,COUNT(DISTINCT cookieid) AS uv,2 AS GROUPING__ID FROM lxw1234 GROUP BY day
- UNION ALL
- SELECT month,day,COUNT(DISTINCT cookieid) AS uv,3 AS GROUPING__ID FROM lxw1234 GROUP BY month,day
ROLLUP
是CUBE的子集，以最左侧的维度为主，从该维度进行层级聚合。
- 比如，以month维度进行层级聚合：
- SELECT
- month,
- day,
- COUNT(DISTINCT cookieid) AS uv,
- GROUPING__ID
- FROM lxw1234
- GROUP BY month,day
- WITH ROLLUP
- ORDER BY GROUPING__ID;
- month day uv GROUPING__ID
- ---------------------------------------------------
- NULL NULL 7 0
- 2015-03 NULL 5 1
- 2015-04 NULL 6 1
- 2015-03 2015-03-10 4 3
- 2015-03 2015-03-12 1 3
- 2015-04 2015-04-12 2 3
- 2015-04 2015-04-13 3 3
- 2015-04 2015-04-15 2 3
- 2015-04 2015-04-16 2 3
- 可以实现这样的上钻过程：
- 月天的UV->月的UV->总UV
- --把month和day调换顺序，则以day维度进行层级聚合：
-
- SELECT
- day,
- month,
- COUNT(DISTINCT cookieid) AS uv,
- GROUPING__ID
- FROM lxw1234
- GROUP BY day,month
- WITH ROLLUP
- ORDER BY GROUPING__ID;
-
-
- day month uv GROUPING__ID
- -------------------------------------------------------
- NULL NULL 7 0
- 2015-04-13 NULL 3 1
- 2015-03-12 NULL 1 1
- 2015-04-15 NULL 2 1
- 2015-03-10 NULL 4 1
- 2015-04-16 NULL 2 1
- 2015-04-12 NULL 2 1
- 2015-04-12 2015-04 2 3
- 2015-03-10 2015-03 4 3
- 2015-03-12 2015-03 1 3
- 2015-04-13 2015-04 3 3
- 2015-04-15 2015-04 2 3
- 2015-04-16 2015-04 2 3
-
- 可以实现这样的上钻过程：
- 天月的UV->天的UV->总UV
- （这里，根据天和月进行聚合，和根据天聚合结果一样，因为有父子关系，如果是其他维度组合的话，就会不一样
窗口函数与分析函数
应用场景：
（1）用于分区排序
（2）动态Group By
（3）Top N
（4）累计计算
（5）层次查询
窗口函数
FIRST_VALUE：取分组内排序后，截止到当前行，第一个值
LAST_VALUE： 取分组内排序后，截止到当前行，最后一个值
LEAD(col,n,DEFAULT) ：用于统计窗口内往下第n行值。第一个参数为列名，第二个参数为往下第n行（可选，默认为1），第三个参数为默认值（当往下第n行为NULL时候，取默认值，如不指定，则为NULL）
LAG(col,n,DEFAULT) ：与lead相反，用于统计窗口内往上第n行值。第一个参数为列名，第二个参数为往上第n行（可选，默认为1），第三个参数为默认值（当往上第n行为NULL时候，取默认值，如不指定，则为NULL）
OVER从句
1、使用标准的聚合函数COUNT、SUM、MIN、MAX、AVG
2、使用PARTITION BY语句，使用一个或者多个原始数据类型的列
3、使用PARTITION BY与ORDER BY语句，使用一个或者多个数据类型的分区或者排序列
4、使用窗口规范，窗口规范支持以下格式：
(ROWS | RANGE) BETWEEN (UNBOUNDED | [num]) PRECEDING AND ([num] PRECEDING | CURRENT ROW | (UNBOUNDED | [num]) FOLLOWING)
(ROWS | RANGE) BETWEEN CURRENT ROW AND (CURRENT ROW | (UNBOUNDED | [num]) FOLLOWING)
(ROWS | RANGE) BETWEEN [num] FOLLOWING AND (UNBOUNDED | [num]) FOLLOWING
- 1
- 2
- 3
当ORDER BY后面缺少窗口从句条件，窗口规范默认是 RANGE BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW.
当ORDER BY和窗口从句都缺失, 窗口规范默认是 ROW BETWEEN UNBOUNDED PRECEDING AND UNBOUNDED FOLLOWING.
OVER从句支持以下函数， 但是并不支持和窗口一起使用它们。
Ranking函数: Rank, NTile, DenseRank, CumeDist, PercentRank.
Lead 和 Lag 函数.
分析函数
ROW_NUMBER() 从1开始，按照顺序，生成分组内记录的序列,比如，按照pv降序排列，生成分组内每天的pv名次,ROW_NUMBER()的应用场景非常多，再比如，获取分组内排序第一的记录;获取一个session中的第一条refer等。
RANK() 生成数据项在分组中的排名，排名相等会在名次中留下空位
DENSE_RANK() 生成数据项在分组中的排名，排名相等会在名次中不会留下空位
CUME_DIST 小于等于当前值的行数/分组内总行数。比如，统计小于等于当前薪水的人数，所占总人数的比例
PERCENT_RANK 分组内当前行的RANK值-1/分组内总行数-1
NTILE(n) 用于将分组数据按照顺序切分成n片，返回当前切片值，如果切片不均匀，默认增加第一个切片的分布。NTILE不支持ROWS BETWEEN，比如 NTILE(2) OVER(PARTITION BY cookieid ORDER BY createtime ROWS BETWEEN 3 PRECEDING AND CURRENT ROW)。
Hive2.1.0及以后支持Distinct
在聚合函数（SUM, COUNT and AVG）中，支持distinct，但是在ORDER BY 或者 窗口限制不支持。
COUNT(DISTINCT a) OVER (PARTITION BY c)
- 1
Hive 2.2.0中在使用ORDER BY和窗口限制时支持distinct
COUNT(DISTINCT a) OVER (PARTITION BY c ORDER BY d ROWS BETWEEN 1 PRECEDING AND 1 FOLLOWING)
- 1
Hive2.1.0及以后支持在OVER从句中支持聚合函数
SELECT rank() OVER (ORDER BY sum(b))
FROM T
GROUP BY a;
- 1
- 2
- 3
测试数据集：
## COUNT、SUM、MIN、MAX、AVG
select
user_id,
user_type,
sales,
--默认为从起点到当前行
sum(sales) OVER(PARTITION BY user_type ORDER BY sales asc) AS sales_1,
--从起点到当前行，结果与sales_1不同。
sum(sales) OVER(PARTITION BY user_type ORDER BY sales asc ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS sales_2,
--当前行+往前3行
sum(sales) OVER(PARTITION BY user_type ORDER BY sales asc ROWS BETWEEN 3 PRECEDING AND CURRENT ROW) AS sales_3,
--当前行+往前3行+往后1行
sum(sales) OVER(PARTITION BY user_type ORDER BY sales asc ROWS BETWEEN 3 PRECEDING AND 1 FOLLOWING) AS sales_4,
--当前行+往后所有行
sum(sales) OVER(PARTITION BY user_type ORDER BY sales asc ROWS BETWEEN CURRENT ROW AND UNBOUNDED FOLLOWING) AS sales_5,
--分组内所有行
SUM(sales) OVER(PARTITION BY user_type) AS sales_6
from
order_detail
order by
user_type,
sales,
user_id
+----------+------------+--------+----------+----------+----------+----------+----------+----------+--+
| user_id | user_type | sales | sales_1 | sales_2 | sales_3 | sales_4 | sales_5 | sales_6 |
+----------+------------+--------+----------+----------+----------+----------+----------+----------+--+
| liiu | new | 1 | 2 | 2 | 2 | 4 | 22 | 23 |
| qibaqiu | new | 1 | 2 | 1 | 1 | 2 | 23 | 23 |
| zhangsa | new | 2 | 4 | 4 | 4 | 7 | 21 | 23 |
| wanger | new | 3 | 7 | 7 | 7 | 12 | 19 | 23 |
| lilisi | new | 5 | 17 | 17 | 15 | 21 | 11 | 23 |
| qishili | new | 5 | 17 | 12 | 11 | 16 | 16 | 23 |
| wutong | new | 6 | 23 | 23 | 19 | 19 | 6 | 23 |
| lisi | old | 1 | 1 | 1 | 1 | 3 | 6 | 6 |
| wangshi | old | 2 | 3 | 3 | 3 | 6 | 5 | 6 |
| liwei | old | 3 | 6 | 6 | 6 | 6 | 3 | 6 |
+----------+------------+--------+----------+----------+----------+----------+----------+----------+--+
注意:
结果和ORDER BY相关,默认为升序
如果不指定ROWS BETWEEN,默认为从起点到当前行;
如果不指定ORDER BY，则将分组内所有值累加;
关键是理解ROWS BETWEEN含义,也叫做WINDOW子句：
PRECEDING：往前
FOLLOWING：往后
CURRENT ROW：当前行
UNBOUNDED：无界限（起点或终点）
UNBOUNDED PRECEDING：表示从前面的起点
UNBOUNDED FOLLOWING：表示到后面的终点
其他COUNT、AVG，MIN，MAX，和SUM用法一样。
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
## first_value与last_value
select
user_id,
user_type,
ROW_NUMBER() OVER(PARTITION BY user_type ORDER BY sales) AS row_num,
first_value(user_id) over (partition by user_type order by sales desc) as max_sales_user,
first_value(user_id) over (partition by user_type order by sales asc) as min_sales_user,
last_value(user_id) over (partition by user_type order by sales desc) as curr_last_min_user,
last_value(user_id) over (partition by user_type order by sales asc) as curr_last_max_user
from
order_detail;
+----------+------------+----------+-----------------+-----------------+---------------------+---------------------+--+
| user_id | user_type | row_num | max_sales_user | min_sales_user | curr_last_min_user | curr_last_max_user |
+----------+------------+----------+-----------------+-----------------+---------------------+---------------------+--+
| wutong | new | 7 | wutong | qibaqiu | wutong | wutong |
| lilisi | new | 6 | wutong | qibaqiu | qishili | lilisi |
| qishili | new | 5 | wutong | qibaqiu | qishili | lilisi |
| wanger | new | 4 | wutong | qibaqiu | wanger | wanger |
| zhangsa | new | 3 | wutong | qibaqiu | zhangsa | zhangsa |
| liiu | new | 2 | wutong | qibaqiu | qibaqiu | liiu |
| qibaqiu | new | 1 | wutong | qibaqiu | qibaqiu | liiu |
| liwei | old | 3 | liwei | lisi | liwei | liwei |
| wangshi | old | 2 | liwei | lisi | wangshi | wangshi |
| lisi | old | 1 | liwei | lisi | lisi | lisi |
+----------+------------+----------+-----------------+-----------------+---------------------+---------------------+--+
## lead与lag
select
user_id,device_id,
lead(device_id) over (order by sales) as default_after_one_line,
lag(device_id) over (order by sales) as default_before_one_line,
lead(device_id,2) over (order by sales) as after_two_line,
lag(device_id,2,'abc') over (order by sales) as before_two_line
from
order_detail;
+----------+-------------+-------------------------+--------------------------+-----------------+------------------+--+
| user_id | device_id | default_after_one_line | default_before_one_line | after_two_line | before_two_line |
+----------+-------------+-------------------------+--------------------------+-----------------+------------------+--+
| qibaqiu | fds | fdsfagwe | NULL | 543gfd | abc |
| liiu | fdsfagwe | 543gfd | fds | f332 | abc |
| lisi | 543gfd | f332 | fdsfagwe | dfsadsa323 | fds |
| wangshi | f332 | dfsadsa323 | 543gfd | hfd | fdsfagwe |
| zhangsa | dfsadsa323 | hfd | f332 | 65ghf | 543gfd |
| liwei | hfd | 65ghf | dfsadsa323 | fds | f332 |
| wanger | 65ghf | fds | hfd | dsfgg | dfsadsa323 |
| qishili | fds | dsfgg | 65ghf | 543gdfsd | hfd |
| lilisi | dsfgg | 543gdfsd | fds | NULL | 65ghf |
| wutong | 543gdfsd | NULL | dsfgg | NULL | fds |
+----------+-------------+-------------------------+--------------------------+-----------------+------------------+--+
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
## RANK、ROW_NUMBER、DENSE_RANK
select
user_id,user_type,sales,
RANK() over (partition by user_type order by sales desc) as r,
ROW_NUMBER() over (partition by user_type order by sales desc) as rn,
DENSE_RANK() over (partition by user_type order by sales desc) as dr
from
order_detail;
+----------+------------+--------+----+-----+-----+--+
| user_id | user_type | sales | r | rn | dr |
+----------+------------+--------+----+-----+-----+--+
| wutong | new | 6 | 1 | 1 | 1 |
| qishili | new | 5 | 2 | 2 | 2 |
| lilisi | new | 5 | 2 | 3 | 2 |
| wanger | new | 3 | 4 | 4 | 3 |
| zhangsa | new | 2 | 5 | 5 | 4 |
| qibaqiu | new | 1 | 6 | 6 | 5 |
| liiu | new | 1 | 6 | 7 | 5 |
| liwei | old | 3 | 1 | 1 | 1 |
| wangshi | old | 2 | 2 | 2 | 2 |
| lisi | old | 1 | 3 | 3 | 3 |
+----------+------------+--------+----+-----+-----+--+
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
## NTILE
select
user_type,sales,
--分组内将数据分成2片
NTILE(2) OVER(PARTITION BY user_type ORDER BY sales) AS nt2,
--分组内将数据分成3片
NTILE(3) OVER(PARTITION BY user_type ORDER BY sales) AS nt3,
--分组内将数据分成4片
NTILE(4) OVER(PARTITION BY user_type ORDER BY sales) AS nt4,
--将所有数据分成4片
NTILE(4) OVER(ORDER BY sales) AS all_nt4
from
order_detail
order by
user_type,
sales
+------------+--------+------+------+------+----------+--+
| user_type | sales | nt2 | nt3 | nt4 | all_nt4 |
+------------+--------+------+------+------+----------+--+
| new | 1 | 1 | 1 | 1 | 1 |
| new | 1 | 1 | 1 | 1 | 1 |
| new | 2 | 1 | 1 | 2 | 2 |
| new | 3 | 1 | 2 | 2 | 3 |
| new | 5 | 2 | 2 | 3 | 4 |
| new | 5 | 2 | 3 | 3 | 3 |
| new | 6 | 2 | 3 | 4 | 4 |
| old | 1 | 1 | 1 | 1 | 1 |
| old | 2 | 1 | 2 | 2 | 2 |
| old | 3 | 2 | 3 | 3 | 2 |
+------------+--------+------+------+------+----------+--+
求取sale前20%的用户ID
select
user_id
from
(
select
user_id,
NTILE(5) OVER(ORDER BY sales desc) AS nt
from
order_detail
)A
where nt=1;
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
## CUME_DIST、PERCENT_RANK
select
user_id,user_type,sales,
--没有partition,所有数据均为1组
CUME_DIST() OVER(ORDER BY sales) AS cd1,
--按照user_type进行分组
CUME_DIST() OVER(PARTITION BY user_type ORDER BY sales) AS cd2
from
order_detail;
+----------+------------+--------+------+----------------------+--+
| user_id | user_type | sales | cd1 | cd2 |
+----------+------------+--------+------+----------------------+--+
| liiu | new | 1 | 0.3 | 0.2857142857142857 |
| qibaqiu | new | 1 | 0.3 | 0.2857142857142857 |
| zhangsa | new | 2 | 0.5 | 0.42857142857142855 |
| wanger | new | 3 | 0.7 | 0.5714285714285714 |
| lilisi | new | 5 | 0.9 | 0.8571428571428571 |
| qishili | new | 5 | 0.9 | 0.8571428571428571 |
| wutong | new | 6 | 1.0 | 1.0 |
| lisi | old | 1 | 0.3 | 0.3333333333333333 |
| wangshi | old | 2 | 0.5 | 0.6666666666666666 |
| liwei | old | 3 | 0.7 | 1.0 |
+----------+------------+--------+------+----------------------+--+
select
user_type,sales
--分组内总行数
SUM(1) OVER(PARTITION BY user_type) AS s,
--RANK值
RANK() OVER(ORDER BY sales) AS r,
PERCENT_RANK() OVER(ORDER BY sales) AS pr,
--分组内
PERCENT_RANK() OVER(PARTITION BY user_type ORDER BY sales) AS prg
from
order_detail;
+----+-----+---------------------+---------------------+--+
| s | r | pr | prg |
+----+-----+---------------------+---------------------+--+
| 7 | 1 | 0.0 | 0.0 |
| 7 | 1 | 0.0 | 0.0 |
| 7 | 4 | 0.3333333333333333 | 0.3333333333333333 |
| 7 | 6 | 0.5555555555555556 | 0.5 |
| 7 | 8 | 0.7777777777777778 | 0.6666666666666666 |
| 7 | 8 | 0.7777777777777778 | 0.6666666666666666 |
| 7 | 10 | 1.0 | 1.0 |
| 3 | 1 | 0.0 | 0.0 |
| 3 | 4 | 0.3333333333333333 | 0.5 |
| 3 | 6 | 0.5555555555555556 | 1.0 |
+----+-----+---------------------+---------------------+--+
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
增强的聚合 Cube和Grouping 和Rollup
这几个分析函数通常用于OLAP中，不能累加，而且需要根据不同维度上钻和下钻的指标统计，比如，分小时、天、月的UV数。
GROUPING SETS
在一个GROUP BY查询中，根据不同的维度组合进行聚合，等价于将不同维度的GROUP BY结果集进行UNION ALL,
其中的GROUPING__ID，表示结果属于哪一个分组集合。
select
user_type,
sales,
count(user_id) as pv,
GROUPING__ID
from
order_detail
group by
user_type,sales
GROUPING SETS(user_type,sales)
ORDER BY
GROUPING__ID;
+------------+--------+-----+---------------+--+
| user_type | sales | pv | grouping__id |
+------------+--------+-----+---------------+--+
| old | NULL | 3 | 1 |
| new | NULL | 7 | 1 |
| NULL | 6 | 1 | 2 |
| NULL | 5 | 2 | 2 |
| NULL | 3 | 2 | 2 |
| NULL | 2 | 2 | 2 |
| NULL | 1 | 3 | 2 |
+------------+--------+-----+---------------+--+
select
user_type,
sales,
count(user_id) as pv,
GROUPING__ID
from
order_detail
group by
user_type,sales
GROUPING SETS(user_type,sales,(user_type,sales))
ORDER BY
GROUPING__ID;
+------------+--------+-----+---------------+--+
| user_type | sales | pv | grouping__id |
+------------+--------+-----+---------------+--+
| old | NULL | 3 | 1 |
| new | NULL | 7 | 1 |
| NULL | 1 | 3 | 2 |
| NULL | 6 | 1 | 2 |
| NULL | 5 | 2 | 2 |
| NULL | 3 | 2 | 2 |
| NULL | 2 | 2 | 2 |
| old | 3 | 1 | 3 |
| old | 2 | 1 | 3 |
| old | 1 | 1 | 3 |
| new | 6 | 1 | 3 |
| new | 5 | 2 | 3 |
| new | 3 | 1 | 3 |
| new | 1 | 2 | 3 |
| new | 2 | 1 | 3 |
+------------+--------+-----+---------------+--+
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
- 34
- 35
- 36
- 37
- 38
- 39
- 40
- 41
- 42
- 43
- 44
- 45
- 46
- 47
- 48
- 49
- 50
- 51
- 52
- 53
- 54
- 55
- 56
- 57
CUBE
根据GROUP BY的维度的所有组合进行聚合。
select
user_type,
sales,
count(user_id) as pv,
GROUPING__ID
from
order_detail
group by
user_type,sales
WITH CUBE
ORDER BY
GROUPING__ID;
+------------+--------+-----+---------------+--+
| user_type | sales | pv | grouping__id |
+------------+--------+-----+---------------+--+
| NULL | NULL | 10 | 0 |
| new | NULL | 7 | 1 |
| old | NULL | 3 | 1 |
| NULL | 6 | 1 | 2 |
| NULL | 5 | 2 | 2 |
| NULL | 3 | 2 | 2 |
| NULL | 2 | 2 | 2 |
| NULL | 1 | 3 | 2 |
| old | 3 | 1 | 3 |
| old | 2 | 1 | 3 |
| old | 1 | 1 | 3 |
| new | 6 | 1 | 3 |
| new | 5 | 2 | 3 |
| new | 3 | 1 | 3 |
| new | 2 | 1 | 3 |
| new | 1 | 2 | 3 |
+------------+--------+-----+---------------+--+
- 1
- 2
- 3
- 4
- 5
- 6
- 7
- 8
- 9
- 10
- 11
- 12
- 13
- 14
- 15
- 16
- 17
- 18
- 19
- 20
- 21
- 22
- 23
- 24
- 25
- 26
- 27
- 28
- 29
- 30
- 31
- 32
- 33
ROLLUP
是CUBE的子集，以最左侧的维度为主，从该维度进行层级聚合。
select
user_type,
sales,
count(user_id) as pv,
GROUPING__ID
from
order_detail
group by
user_type,sales
WITH ROLLUP
ORDER BY
GROUPING__ID;
+------------+--------+-----+---------------+--+
| user_type | sales | pv | grouping__id |
+------------+--------+-----+---------------+--+
| NULL | NULL | 10 | 0 |
| old | NULL | 3 | 1 |
| new | NULL | 7 | 1 |
| old | 3 | 1 | 3 |
| old | 2 | 1 | 3 |
| old | 1 | 1 | 3 |
| new | 6 | 1 | 3 |
| new | 5 | 2 | 3 |
| new | 3 | 1 | 3 |
| new | 2 | 1 | 3 |
| new | 1 | 2 | 3 |
+------------+--------+-----+---------------+--+