我有一个类似以下的表格(示例here):
CREATE TABLE topics (
name varchar(64),
url varchar(253),
statistic integer,
pubdate timestamp
);
INSERT INTO topics VALUES
('a', 'b', 100, TIMESTAMP '2011-05-16 15:36:38'),
('a', 'c', 110, TIMESTAMP '2014-04-01 00:00:00'),
('a', 'd', 120, TIMESTAMP '2014-04-01 00:00:00'),
('a', 'e', 90, TIMESTAMP '2011-05-16 15:36:38'),
('a', 'f', 80, TIMESTAMP '2014-04-01 00:00:00'),
('a', 'g', 70, TIMESTAMP '2011-05-16 15:36:38'),
('a', 'h', 150, TIMESTAMP '2014-04-01 00:00:00'),
('a', 'i', 50, TIMESTAMP '2011-05-16 15:36:38'),
('b', 'j', 10, TIMESTAMP '2014-04-01 00:00:00'),
('b', 'k', 11, TIMESTAMP '2011-05-16 15:36:38'),
('b', 'l', 12, TIMESTAMP '2014-04-01 00:00:00'),
('b', 'm', 9, TIMESTAMP '2011-05-16 15:36:38'),
('b', 'n', 8, TIMESTAMP '2014-04-01 00:00:00'),
('b', 'o', 7, TIMESTAMP '2011-05-16 15:36:38'),
('b', 'p', 15, TIMESTAMP '2014-04-01 00:00:00'),
('b', 'q', 5, TIMESTAMP '2011-05-16 15:36:38'),
('b', 'r', 2, TIMESTAMP '2014-04-01 00:00:00')
我想根据每个(statistic
)组合中的name, date(pubdate)
值_来获取前两行。
换句话说,我想GROUP BY name, date(pubdate)
,但没有聚合函数,而是只根据每个组中的statistic
取前两行作为结果。 (因此,我知道它实际上不是GROUP BY
,而是greatest-n-per-group
。)
我正在将Google Big Query与标准SQL配合使用。我看过其他一些solutions,但不确定在这种情况下如何获得结果。
所需结果:
name url statistic date
a b 100 2011-05-16
a e 90 2011-05-16
a h 150 2014-04-01
a d 120 2014-04-01
b m 9 2011-05-16
b k 11 2011-05-16
b l 12 2014-04-01
b p 15 2014-04-01
答案 0 :(得分:2)
使用ARRAY_AGG
函数:
SELECT
name,
DATE(pubdate) AS pubdate,
ARRAY_AGG(STRUCT(url, statistic) ORDER BY statistic DESC LIMIT 2) AS top_urls
FROM dataset.table
GROUP BY name, pubdate
您可以使用带有UNNEST
的子查询来获取没有数组的行作为输出:
SELECT name, pubdate, url, statistic
FROM (
SELECT
name,
DATE(pubdate) AS pubdate,
ARRAY_AGG(STRUCT(url, statistic) ORDER BY statistic DESC LIMIT 2) AS top_urls
FROM dataset.table
GROUP BY name, pubdate
), UNNEST(top_urls)
答案 1 :(得分:1)
以下是用于BigQuery标准SQL
script_sample.sh
您可以使用问题中的示例数据来测试,玩游戏,如下例所示
#standardSQL
SELECT * EXCEPT(arr) FROM (
SELECT name, DATE(pubdate) day,
ARRAY_AGG(STRUCT(url, statistic) ORDER BY statistic DESC LIMIT 2) arr
FROM `project.dataset.table`
GROUP BY name, day
), UNNEST(arr)
-- ORDER BY name, day
有结果
#standardSQL
WITH `project.dataset.table` AS (
SELECT 'a' name, 'b' url, 100 statistic, TIMESTAMP '2011-05-16 15:36:38' pubdate UNION ALL
SELECT 'a', 'c', 110, '2014-04-01 00:00:00' UNION ALL
SELECT 'a', 'd', 120, '2014-04-01 00:00:00' UNION ALL
SELECT 'a', 'e', 90, '2011-05-16 15:36:38' UNION ALL
SELECT 'a', 'f', 80, '2014-04-01 00:00:00' UNION ALL
SELECT 'a', 'g', 70, '2011-05-16 15:36:38' UNION ALL
SELECT 'a', 'h', 150, '2014-04-01 00:00:00' UNION ALL
SELECT 'a', 'i', 50, '2011-05-16 15:36:38' UNION ALL
SELECT 'b', 'j', 10, '2014-04-01 00:00:00' UNION ALL
SELECT 'b', 'k', 11, '2011-05-16 15:36:38' UNION ALL
SELECT 'b', 'l', 12, '2014-04-01 00:00:00' UNION ALL
SELECT 'b', 'm', 9, '2011-05-16 15:36:38' UNION ALL
SELECT 'b', 'n', 8, '2014-04-01 00:00:00' UNION ALL
SELECT 'b', 'o', 7, '2011-05-16 15:36:38' UNION ALL
SELECT 'b', 'p', 15, '2014-04-01 00:00:00' UNION ALL
SELECT 'b', 'q', 5, '2011-05-16 15:36:38' UNION ALL
SELECT 'b', 'r', 2, '2014-04-01 00:00:00'
)
SELECT * EXCEPT(arr) FROM (
SELECT name, DATE(pubdate) day,
ARRAY_AGG(STRUCT(url, statistic) ORDER BY statistic DESC LIMIT 2) arr
FROM `project.dataset.table`
GROUP BY name, day
), UNNEST(arr)
ORDER BY name, day
答案 2 :(得分:0)
with xx as(
select name, url, statistic, pubdate, row_number() over(partition by name , url order by statistic desc) rn
from topics)
select * except(rn)
from xx
where rn <= 2;