Sql 一些示例值也会有很大帮助。您好@ErwinBrandstetter我已按要求添加了表定义和示例值。:)谢谢你能解释一下吗?我在子查询中迷失了方向,尤其是关于“第6-7天*w作为w_开始”和“第7天*w作为w_结束”的部分@christinang89:为主要
Sql 一些示例值也会有很大帮助。您好@ErwinBrandstetter我已按要求添加了表定义和示例值。:)谢谢你能解释一下吗?我在子查询中迷失了方向,尤其是关于“第6-7天*w作为w_开始”和“第7天*w作为w_结束”的部分@christinang89:为主要,sql,postgresql,date,aggregate-functions,postgresql-9.3,Sql,Postgresql,Date,Aggregate Functions,Postgresql 9.3,一些示例值也会有很大帮助。您好@ErwinBrandstetter我已按要求添加了表定义和示例值。:)谢谢你能解释一下吗?我在子查询中迷失了方向,尤其是关于“第6-7天*w作为w_开始”和“第7天*w作为w_结束”的部分@christinang89:为主要问题添加了解决方案和史诗般的解释。感谢您的史诗般解释@ErwinBrandstetter!!像这样的答案让我如此热爱SO社区:)@christinang89:添加了更多优化。特别是,尽早排除“不可能”的用户,以减少处理的行数。还有最新的小提琴。
一些示例值也会有很大帮助。您好@ErwinBrandstetter我已按要求添加了表定义和示例值。:)谢谢你能解释一下吗?我在子查询中迷失了方向,尤其是关于“第6-7天*w作为w_开始”和“第7天*w作为w_结束”的部分@christinang89:为主要问题添加了解决方案和史诗般的解释。感谢您的史诗般解释@ErwinBrandstetter!!像这样的答案让我如此热爱SO社区:)@christinang89:添加了更多优化。特别是,尽早排除“不可能”的用户,以减少处理的行数。还有最新的小提琴。
CREATE TABLE requests (
id text PRIMARY KEY, -- id of the request
amount bigint, -- sum of requests made by accounts_id to recipient_id,
-- aggregated on a daily basis based on "date"
accounts_id text, -- id of the user
recipient_id text, -- id of the recipient
date timestamp -- date that the request was made in YYYY-MM-DD
);
INSERT INTO requests2
VALUES
('1', 19, 'a1', 'b1', '2014-10-05 00:00:00'),
('2', 19, 'a2', 'b2', '2014-10-06 00:00:00'),
('3', 85, 'a3', 'b3', '2014-10-07 00:00:00'),
('4', 11, 'a1', 'b4', '2014-10-13 00:00:00'),
('5', 2, 'a2', 'b5', '2014-10-14 00:00:00'),
('6', 50, 'a3', 'b5', '2014-10-15 00:00:00'),
('7', 787323, 'a1', 'b6', '2014-10-17 00:00:00'),
('8', 33, 'a2', 'b8', '2014-10-18 00:00:00'),
('9', 14, 'a3', 'b9', '2014-10-19 00:00:00'),
('10', 11, 'a4', 'b10', '2014-10-19 00:00:00'),
('11', 1628, 'a1', 'b11', '2014-10-25 00:00:00'),
('13', 101, 'a2', 'b11', '2014-10-25 00:00:00');
Date | # Active users
-----------+---------------
10-01-2014 | 600
10-02-2014 | 703
10-03-2014 | 891
SELECT count(*)
FROM
(SELECT accounts_id
FROM requests
WHERE "date" BETWEEN '2014-10-01'::date - interval '2 weeks' AND '2014-10-01'::date - interval '1 week'
GROUP BY accounts_id HAVING sum(amount) > 10) week_1
JOIN
(SELECT accounts_id
FROM requests
WHERE "date" BETWEEN '2014-10-01'::date - interval '3 weeks' AND '2014-10-01'::date - interval '2 week'
GROUP BY accounts_id HAVING sum(amount) > 10) week_2 ON week_1.accounts_id = week_2.accounts_id
JOIN
(SELECT accounts_id
FROM requests
WHERE "date" BETWEEN '2014-10-01'::date - interval '4 weeks' AND '2014-10-01'::date - interval '3 week'
GROUP BY accounts_id HAVING sum(amount) > 10) week_3 ON week_2.accounts_id = week_3.accounts_id
JOIN
(SELECT accounts_id
FROM requests
WHERE "date" BETWEEN '2014-10-01'::date - interval '5 weeks' AND '2014-10-01'::date - interval '4 week'
GROUP BY accounts_id HAVING sum(amount) > 10) week_4 ON week_3.accounts_id = week_4.accounts_id
SELECT week_1."Date_series",
count(*)
FROM
(SELECT to_char(DAY::date, 'YYYY-MM-DD') AS "Date_series",
accounts_id
FROM generate_series('2014-10-01'::date, CURRENT_DATE, '1 day') DAY, requests
WHERE to_char(DAY::date, 'YYYY-MM-DD')::date BETWEEN requests.date::date - interval '2 weeks' AND requests.date::date - interval '1 week'
GROUP BY "Date_series",
accounts_id HAVING sum(amount) > 10) week_1
JOIN
(SELECT to_char(DAY::date, 'YYYY-MM-DD') AS "Date_series",
accounts_id
FROM generate_series('2014-10-01'::date, CURRENT_DATE, '1 day') DAY, requests
WHERE to_char(DAY::date, 'YYYY-MM-DD')::date BETWEEN requests.date::date - interval '3 weeks' AND requests.date::date - interval '2 week'
GROUP BY "Date_series",
accounts_id HAVING sum(amount) > 10) week_2 ON week_1.accounts_id = week_2.accounts_id
AND week_1."Date_series" = week_2."Date_series"
JOIN
(SELECT to_char(DAY::date, 'YYYY-MM-DD') AS "Date_series",
accounts_id
FROM generate_series('2014-10-01'::date, CURRENT_DATE, '1 day') DAY, requests
WHERE to_char(DAY::date, 'YYYY-MM-DD')::date BETWEEN requests.date::date - interval '4 weeks' AND requests.date::date - interval '3 week'
GROUP BY "Date_series",
accounts_id HAVING sum(amount) > 10) week_3 ON week_2.accounts_id = week_3.accounts_id
AND week_2."Date_series" = week_3."Date_series"
JOIN
(SELECT to_char(DAY::date, 'YYYY-MM-DD') AS "Date_series",
accounts_id
FROM generate_series('2014-10-01'::date, CURRENT_DATE, '1 day') DAY, requests
WHERE to_char(DAY::date, 'YYYY-MM-DD')::date BETWEEN requests.date::date - interval '5 weeks' AND requests.date::date - interval '4 week'
GROUP BY "Date_series",
accounts_id HAVING sum(amount) > 10) week_4 ON week_3.accounts_id = week_4.accounts_id
AND week_3."Date_series" = week_4."Date_series"
GROUP BY week_1."Date_series"
CREATE TABLE requests (
id int
, accounts_id int -- (id of the user)
, recipient_id int -- (id of the recipient)
, date date -- (date that the request was made in YYYY-MM-DD)
, amount int -- (# of requests by accounts_id for the day)
);
SELECT accounts_id
FROM (
SELECT w.w, r.accounts_id
FROM (
SELECT w
, day - 6 - 7 * w AS w_start
, day - 7 * w AS w_end
FROM (SELECT '2014-10-31'::date - 1 AS day) d -- effective date here
, generate_series(0,3) w
) w
JOIN requests r ON r."date" BETWEEN w_start AND w_end
GROUP BY w.w, r.accounts_id
HAVING sum(r.amount) > 10
) sub
GROUP BY 1
HAVING count(*) = 4;
CREATE FUNCTION f_active_users (_now date = now()::date, _days int = 3)
RETURNS TABLE (day date, users int) AS
$func$
WITH r AS (
SELECT accounts_id, date, sum(amount)::int AS amount
FROM requests
WHERE date BETWEEN _now - (27 + _days) AND _now - 1
GROUP BY accounts_id, date
)
SELECT date + 1, count(w_ct = 4 OR NULL)::int
FROM (
SELECT accounts_id, date
, count(w_amount > 10 OR NULL)
OVER (PARTITION BY accounts_id, dow ORDER BY date DESC
ROWS BETWEEN CURRENT ROW AND 3 FOLLOWING) AS w_ct
FROM (
SELECT accounts_id, date, dow
, sum(amount) OVER (PARTITION BY accounts_id ORDER BY date DESC
ROWS BETWEEN CURRENT ROW AND 6 FOLLOWING) AS w_amount
FROM (SELECT _now - i AS date, i%7 AS dow
FROM generate_series(1, 27 + _days) i) d -- period of interest
CROSS JOIN (
SELECT accounts_id FROM r
GROUP BY 1
HAVING count(*) > 3 AND sum(amount) > 39 -- enough rows & requests
AND max(date) > min(date) + 15) a -- can cover 4 weeks
LEFT JOIN r USING (accounts_id, date)
) sub1
WHERE date > _now - (22 + _days) -- cut off 6 trailing days now - useful?
) sub2
GROUP BY date
ORDER BY date DESC
LIMIT _days
$func$ LANGUAGE sql STABLE;
SELECT * FROM f_active_users('2014-10-31', 5);
SELECT * FROM f_active_users();
CREATE INDEX foo ON requests (date, accounts_id, amount);