从一组重叠的日期范围中查找共同的日期范围
Find common date range from a set of overlapping date ranges
如何从一组给定的日期范围中找到重叠的（共同的）日期范围？
需要在考虑特定程序 (PID) 的所有事件 (EID) 的情况下找到重叠（常见）日期范围。
示例：程序 (PID=13579) 有两个事件 (EID=2) 的日期范围。
之前发布于 link
我已经在这里检查过（但没用）：Link
示例架构和数据：
CREATE TABLE #EventsTBL
(
PID INT,
EID INT,
StartDate DATETIME,
EndDate DATETIME
);
INSERT INTO #EventsTBL
VALUES
(13579, '1', '01 Jan 2018', '31 Mar 2019'),
(13579, '2', '01 Feb 2018', '31 May 2018'),
(13579, '2', '01 Jul 2018', '31 Jan 2019'),
(13579, '7', '01 Mar 2018', '31 Mar 2019'),
(13579, '5', '01 Feb 2018', '30 Apr 2018'),
(13579, '5', '01 Oct 2018', '31 Mar 2019'),
(13579, '8', '01 Jan 2018', '30 Apr 2018'),
(13579, '8', '01 Jun 2018', '31 Dec 2018'),
(13579, '13', '01 Jan 2018', '31 Mar 2019'),
(13579, '6', '01 Apr 2018', '31 May 2018'),
(13579, '6', '01 Sep 2018', '30 Nov 2018'),
(13579, '4', '01 Feb 2018', '31 Jan 2019'),
(13579, '19', '01 Mar 2018', '31 Jul 2018'),
(13579, '19', '01 Oct 2018', '28 Feb 2019'),
--
(13570, '16', '01 Feb 2018', '30 Jun 2018'),
(13570, '16', '01 Aug 2018', '31 Aug 2018'),
(13570, '16', '01 Oct 2018', '28 Feb 2019'),
(13570, '23', '01 Mar 2018', '30 Jun 2018'),
(13570, '23', '01 Nov 2018', '31 Jan 2019');
输出应该是：
PID StartDate EndDate
13579 01-Apr-2018 30-Apr-2018
13579 01-Oct-2018 30-Nov-2018
13570 01-Mar-2018 30-Jun-2018
13570 01-Nov-2018 31-Jan-2019
好的，所以我生成了一个 CTE，其中包含所有正在考虑的日期的日期。
对于这些日期中的每一个，我都生成了 FLAG=1，我认为我检测到了重叠。
然后我使用 row_number() 作为 'islands' 问题的标准解决方案，我正在输出 flag= 的 'islands' 的开始和结束时间1
希望对您有所帮助，我得到了 13570 的结果，但据我了解 'overlap' 整个 13579 重叠。也许那部分需要进一步解释、改编。如果你能想出如何按照你的规则生成FLAG，排名部分仍然适用
CREATE TABLE #EventsTBL
(
PID INT,
EID INT,
StartDate DATETIME,
EndDate DATETIME
);
INSERT INTO #EventsTBL
VALUES
(13579, '1', '01 Jan 2018', '31 Mar 2019'),
(13579, '2', '01 Feb 2018', '31 May 2018'),
(13579, '2', '01 Jul 2018', '31 Jan 2019'),
(13579, '7', '01 Mar 2018', '31 Mar 2019'),
(13579, '5', '01 Feb 2018', '30 Apr 2018'),
(13579, '5', '01 Oct 2018', '31 Mar 2019'),
(13579, '8', '01 Jan 2018', '30 Apr 2018'),
(13579, '8', '01 Jun 2018', '31 Dec 2018'),
(13579, '13', '01 Jan 2018', '31 Mar 2019'),
(13579, '6', '01 Apr 2018', '31 May 2018'),
(13579, '6', '01 Sep 2018', '30 Nov 2018'),
(13579, '4', '01 Feb 2018', '31 Jan 2019'),
(13579, '19', '01 Mar 2018', '31 Jul 2018'),
(13579, '19', '01 Oct 2018', '28 Feb 2019'),
--
(13570, '16', '01 Feb 2018', '30 Jun 2018'),
(13570, '16', '01 Aug 2018', '31 Aug 2018'),
(13570, '16', '01 Oct 2018', '28 Feb 2019'),
(13570, '23', '01 Mar 2018', '30 Jun 2018'),
(13570, '23', '01 Nov 2018', '31 Jan 2019');
SELECT count(enddate) FROM (SELECT CAST('19660423' as date) dt) A LEFT JOIN #EventsTBL B ON A.dt = b.StartDate;
WITH MIN_MAX AS (SELECT MIN(StartDate) S , MAX(EndDate) E FROM #EventsTBL ),
ALL_DATES AS (SELECT S DT FROM MIN_MAX
UNION ALL
SELECT DATEADD(day,1,DT) FROM ALL_DATES WHERE DT < (SELECT E FROM MIN_MAX)
),
BuildFlags AS (SELECT P.pid,
DT,
COUNT(e.PID ) CNT,
CASE WHEN COUNT(e.pid) > 1 THEN 1 ELSE 0 END FLAG,
row_number() OVER(partition by p.pid order by DT) RN
FROM ALL_DATES A CROSS JOIN (SELECT DISTINCT E2.pid FROM #EventsTBL E2) P
LEFT JOIN
#EventsTBL E ON P.PID = E.pid AND
A.DT BETWEEN E.StartDate AND E.EndDate GROUP BY P.pid,DT),
AddRanks AS (SELECT *,rn - row_number()over(partition by pid,flag order by dt) groupRank FROM BuildFlags)
select pid,min(dt) as start, max(dt) as ending from AddRanks
where flag = 1
group by pid,grouprank
order by pid,min(dt)
option(maxrecursion 0)
编辑 - 我想我明白你的意思了，你想将 pid 和 eid 组合成唯一的 pid 和 eid，以及那里的日期。然后您定义一个重叠，因为所有 pid 和 eid 都同时处于活动状态。所以我想出了这个修改
;WITH MIN_MAX AS (SELECT MIN(StartDate) S , MAX(EndDate) E FROM #EventsTBL ),
ALL_DATES AS (SELECT S DT FROM MIN_MAX
UNION ALL
SELECT DATEADD(day,1,DT) FROM ALL_DATES WHERE DT < (SELECT E FROM MIN_MAX)
),
GROUPED AS (SELECT Q.pid,Q.eid,q.dt,case when max(tx.pid) is null then 0 else 1 end YES from (Select * FROM All_Dates cross join (select distinct pid,eid from #EventsTBL) AQ) Q
LEFT JOIN #EventsTBL TX ON TX.PID = Q.pid and tx.EID = Q.eid and
Q.DT BETWEEN TX.StartDate AND TX.EndDate GROUP BY q.pid,q.eid,q.dt
),
BuildFlags AS (SELECT g.pid,g.dt, row_number() OVER(partition by g.pid order by g.DT) RN,
CASE WHEN WQ.tot = (SELECT count(distinct g2.eid) FROM grouped g2 WHERE g2.PID = G.pid and g2.dt=g.dt and g2.yes=1) then 1 else 0 end FLAG
FROM GROUPED G cross apply (select count(distinct E9.eid) tot FROM #EventsTBL E9 WHERE E9.PID = G.pid) WQ)
,AddRanks AS (SELECT *,rn - row_number()over(partition by pid,flag order by dt) groupRank FROM BuildFlags)
select pid,min(dt) as start, max(dt) as ending from AddRanks
where flag = 1
group by pid,grouprank
order by pid,min(dt)
option(maxrecursion 0);
此答案计算重叠间隔的数量。它假定具有相同 EID 的日期范围不重叠。以下是带有内联解释的查询：
DECLARE @EventsTBL TABLE (PID INT, EID INT, StartDate DATETIME, EndDate DATETIME);
INSERT INTO @EventsTBL VALUES
(13579, 1, '01 Jan 2018', '31 Mar 2019'),
(13579, 2, '01 Feb 2018', '31 May 2018'),
(13579, 2, '01 Jul 2018', '31 Jan 2019'),
(13579, 7, '01 Mar 2018', '31 Mar 2019'),
(13579, 5, '01 Feb 2018', '30 Apr 2018'),
(13579, 5, '01 Oct 2018', '31 Mar 2019'),
(13579, 8, '01 Jan 2018', '30 Apr 2018'),
(13579, 8, '01 Jun 2018', '31 Dec 2018'),
(13579, 13, '01 Jan 2018', '31 Mar 2019'),
(13579, 6, '01 Apr 2018', '31 May 2018'),
(13579, 6, '01 Sep 2018', '30 Nov 2018'),
(13579, 4, '01 Feb 2018', '31 Jan 2019'),
(13579, 19, '01 Mar 2018', '31 Jul 2018'),
(13579, 19, '01 Oct 2018', '28 Feb 2019'),
(13570, 16, '01 Feb 2018', '30 Jun 2018'),
(13570, 16, '01 Aug 2018', '31 Aug 2018'),
(13570, 16, '01 Oct 2018', '28 Feb 2019'),
(13570, 23, '01 Mar 2018', '30 Jun 2018'),
(13570, 23, '01 Nov 2018', '31 Jan 2019');
WITH cte1 AS (
/*
* augment the data with the number of distinct EID per PID
* we will need this later
*/
SELECT e.PID, a.EIDCount, StartDate, EndDate
FROM @EventsTBL AS e
JOIN (
SELECT PID, COUNT(DISTINCT EID) AS EIDCount
FROM @EventsTBL
GROUP BY PID
) AS a ON e.PID = a.PID
), cte2 AS (
/*
* build a list of "points in time" at which an event started or ended
* and the number concurrent events changed
* the zero value rows are required!
*/
SELECT PID, EIDCount, StartDate AS pdate, 1 AS pval
FROM cte1
UNION ALL
SELECT PID, EIDCount, EndDate, 0
FROM cte1
UNION ALL
SELECT PID, EIDCount , DATEADD(DAY, 1, EndDate), -1
FROM cte1
), cte3 AS (
/*
* calculate running sum of pval over dates; minus ones first
*/
SELECT PID, EIDCount, pdate, SUM(pval) OVER (PARTITION BY PID ORDER BY pdate, pval) AS evtcount
FROM cte2
), cte4 AS (
/*
* consolidate data for same dates and we are done with the main part
*/
SELECT PID, EIDCount, pdate, MAX(evtcount) AS evtcount
FROM cte3
GROUP BY PID, EIDCount, pdate
), cte5 AS (
/*
* assign "change flag" to rows where number of concurrent events
* enters or exits the required count w.r.t. previous row
*/
SELECT PID, EIDCount, pdate, evtcount, CASE
WHEN evtcount < EIDCount AND LAG(evtcount) OVER (PARTITION BY PID ORDER BY pdate) < EIDCount THEN 0
WHEN evtcount = EIDCount AND LAG(evtcount) OVER (PARTITION BY PID ORDER BY pdate) = EIDCount THEN 0
ELSE 1
END AS chg
FROM cte4
), cte6 AS (
/*
* convert "change flag" to "group numbers" over consecutive rows using running sum
*/
SELECT PID, EIDCount, pdate, evtcount, SUM(chg) OVER (PARTITION BY PID ORDER BY pdate) AS grp
FROM cte5
)
/*
* group rows by pid and group numbers
*/
SELECT PID, MIN(pdate) AS StartDate, MAX(pdate) AS EndDate
FROM cte6
WHERE evtcount = EIDCount
GROUP BY PID, grp
ORDER BY PID, StartDate
如何从一组给定的日期范围中找到重叠的（共同的）日期范围？
需要在考虑特定程序 (PID) 的所有事件 (EID) 的情况下找到重叠（常见）日期范围。
示例：程序 (PID=13579) 有两个事件 (EID=2) 的日期范围。
之前发布于 link
我已经在这里检查过（但没用）：Link
示例架构和数据：
CREATE TABLE #EventsTBL
(
PID INT,
EID INT,
StartDate DATETIME,
EndDate DATETIME
);
INSERT INTO #EventsTBL
VALUES
(13579, '1', '01 Jan 2018', '31 Mar 2019'),
(13579, '2', '01 Feb 2018', '31 May 2018'),
(13579, '2', '01 Jul 2018', '31 Jan 2019'),
(13579, '7', '01 Mar 2018', '31 Mar 2019'),
(13579, '5', '01 Feb 2018', '30 Apr 2018'),
(13579, '5', '01 Oct 2018', '31 Mar 2019'),
(13579, '8', '01 Jan 2018', '30 Apr 2018'),
(13579, '8', '01 Jun 2018', '31 Dec 2018'),
(13579, '13', '01 Jan 2018', '31 Mar 2019'),
(13579, '6', '01 Apr 2018', '31 May 2018'),
(13579, '6', '01 Sep 2018', '30 Nov 2018'),
(13579, '4', '01 Feb 2018', '31 Jan 2019'),
(13579, '19', '01 Mar 2018', '31 Jul 2018'),
(13579, '19', '01 Oct 2018', '28 Feb 2019'),
--
(13570, '16', '01 Feb 2018', '30 Jun 2018'),
(13570, '16', '01 Aug 2018', '31 Aug 2018'),
(13570, '16', '01 Oct 2018', '28 Feb 2019'),
(13570, '23', '01 Mar 2018', '30 Jun 2018'),
(13570, '23', '01 Nov 2018', '31 Jan 2019');
输出应该是：
PID StartDate EndDate
13579 01-Apr-2018 30-Apr-2018
13579 01-Oct-2018 30-Nov-2018
13570 01-Mar-2018 30-Jun-2018
13570 01-Nov-2018 31-Jan-2019
好的，所以我生成了一个 CTE，其中包含所有正在考虑的日期的日期。
对于这些日期中的每一个，我都生成了 FLAG=1，我认为我检测到了重叠。
然后我使用 row_number() 作为 'islands' 问题的标准解决方案，我正在输出 flag= 的 'islands' 的开始和结束时间1
希望对您有所帮助，我得到了 13570 的结果，但据我了解 'overlap' 整个 13579 重叠。也许那部分需要进一步解释、改编。如果你能想出如何按照你的规则生成FLAG，排名部分仍然适用
CREATE TABLE #EventsTBL
(
PID INT,
EID INT,
StartDate DATETIME,
EndDate DATETIME
);
INSERT INTO #EventsTBL
VALUES
(13579, '1', '01 Jan 2018', '31 Mar 2019'),
(13579, '2', '01 Feb 2018', '31 May 2018'),
(13579, '2', '01 Jul 2018', '31 Jan 2019'),
(13579, '7', '01 Mar 2018', '31 Mar 2019'),
(13579, '5', '01 Feb 2018', '30 Apr 2018'),
(13579, '5', '01 Oct 2018', '31 Mar 2019'),
(13579, '8', '01 Jan 2018', '30 Apr 2018'),
(13579, '8', '01 Jun 2018', '31 Dec 2018'),
(13579, '13', '01 Jan 2018', '31 Mar 2019'),
(13579, '6', '01 Apr 2018', '31 May 2018'),
(13579, '6', '01 Sep 2018', '30 Nov 2018'),
(13579, '4', '01 Feb 2018', '31 Jan 2019'),
(13579, '19', '01 Mar 2018', '31 Jul 2018'),
(13579, '19', '01 Oct 2018', '28 Feb 2019'),
--
(13570, '16', '01 Feb 2018', '30 Jun 2018'),
(13570, '16', '01 Aug 2018', '31 Aug 2018'),
(13570, '16', '01 Oct 2018', '28 Feb 2019'),
(13570, '23', '01 Mar 2018', '30 Jun 2018'),
(13570, '23', '01 Nov 2018', '31 Jan 2019');
SELECT count(enddate) FROM (SELECT CAST('19660423' as date) dt) A LEFT JOIN #EventsTBL B ON A.dt = b.StartDate;
WITH MIN_MAX AS (SELECT MIN(StartDate) S , MAX(EndDate) E FROM #EventsTBL ),
ALL_DATES AS (SELECT S DT FROM MIN_MAX
UNION ALL
SELECT DATEADD(day,1,DT) FROM ALL_DATES WHERE DT < (SELECT E FROM MIN_MAX)
),
BuildFlags AS (SELECT P.pid,
DT,
COUNT(e.PID ) CNT,
CASE WHEN COUNT(e.pid) > 1 THEN 1 ELSE 0 END FLAG,
row_number() OVER(partition by p.pid order by DT) RN
FROM ALL_DATES A CROSS JOIN (SELECT DISTINCT E2.pid FROM #EventsTBL E2) P
LEFT JOIN
#EventsTBL E ON P.PID = E.pid AND
A.DT BETWEEN E.StartDate AND E.EndDate GROUP BY P.pid,DT),
AddRanks AS (SELECT *,rn - row_number()over(partition by pid,flag order by dt) groupRank FROM BuildFlags)
select pid,min(dt) as start, max(dt) as ending from AddRanks
where flag = 1
group by pid,grouprank
order by pid,min(dt)
option(maxrecursion 0)
编辑 - 我想我明白你的意思了，你想将 pid 和 eid 组合成唯一的 pid 和 eid，以及那里的日期。然后您定义一个重叠，因为所有 pid 和 eid 都同时处于活动状态。所以我想出了这个修改
;WITH MIN_MAX AS (SELECT MIN(StartDate) S , MAX(EndDate) E FROM #EventsTBL ),
ALL_DATES AS (SELECT S DT FROM MIN_MAX
UNION ALL
SELECT DATEADD(day,1,DT) FROM ALL_DATES WHERE DT < (SELECT E FROM MIN_MAX)
),
GROUPED AS (SELECT Q.pid,Q.eid,q.dt,case when max(tx.pid) is null then 0 else 1 end YES from (Select * FROM All_Dates cross join (select distinct pid,eid from #EventsTBL) AQ) Q
LEFT JOIN #EventsTBL TX ON TX.PID = Q.pid and tx.EID = Q.eid and
Q.DT BETWEEN TX.StartDate AND TX.EndDate GROUP BY q.pid,q.eid,q.dt
),
BuildFlags AS (SELECT g.pid,g.dt, row_number() OVER(partition by g.pid order by g.DT) RN,
CASE WHEN WQ.tot = (SELECT count(distinct g2.eid) FROM grouped g2 WHERE g2.PID = G.pid and g2.dt=g.dt and g2.yes=1) then 1 else 0 end FLAG
FROM GROUPED G cross apply (select count(distinct E9.eid) tot FROM #EventsTBL E9 WHERE E9.PID = G.pid) WQ)
,AddRanks AS (SELECT *,rn - row_number()over(partition by pid,flag order by dt) groupRank FROM BuildFlags)
select pid,min(dt) as start, max(dt) as ending from AddRanks
where flag = 1
group by pid,grouprank
order by pid,min(dt)
option(maxrecursion 0);
此答案计算重叠间隔的数量。它假定具有相同 EID 的日期范围不重叠。以下是带有内联解释的查询：
DECLARE @EventsTBL TABLE (PID INT, EID INT, StartDate DATETIME, EndDate DATETIME);
INSERT INTO @EventsTBL VALUES
(13579, 1, '01 Jan 2018', '31 Mar 2019'),
(13579, 2, '01 Feb 2018', '31 May 2018'),
(13579, 2, '01 Jul 2018', '31 Jan 2019'),
(13579, 7, '01 Mar 2018', '31 Mar 2019'),
(13579, 5, '01 Feb 2018', '30 Apr 2018'),
(13579, 5, '01 Oct 2018', '31 Mar 2019'),
(13579, 8, '01 Jan 2018', '30 Apr 2018'),
(13579, 8, '01 Jun 2018', '31 Dec 2018'),
(13579, 13, '01 Jan 2018', '31 Mar 2019'),
(13579, 6, '01 Apr 2018', '31 May 2018'),
(13579, 6, '01 Sep 2018', '30 Nov 2018'),
(13579, 4, '01 Feb 2018', '31 Jan 2019'),
(13579, 19, '01 Mar 2018', '31 Jul 2018'),
(13579, 19, '01 Oct 2018', '28 Feb 2019'),
(13570, 16, '01 Feb 2018', '30 Jun 2018'),
(13570, 16, '01 Aug 2018', '31 Aug 2018'),
(13570, 16, '01 Oct 2018', '28 Feb 2019'),
(13570, 23, '01 Mar 2018', '30 Jun 2018'),
(13570, 23, '01 Nov 2018', '31 Jan 2019');
WITH cte1 AS (
/*
* augment the data with the number of distinct EID per PID
* we will need this later
*/
SELECT e.PID, a.EIDCount, StartDate, EndDate
FROM @EventsTBL AS e
JOIN (
SELECT PID, COUNT(DISTINCT EID) AS EIDCount
FROM @EventsTBL
GROUP BY PID
) AS a ON e.PID = a.PID
), cte2 AS (
/*
* build a list of "points in time" at which an event started or ended
* and the number concurrent events changed
* the zero value rows are required!
*/
SELECT PID, EIDCount, StartDate AS pdate, 1 AS pval
FROM cte1
UNION ALL
SELECT PID, EIDCount, EndDate, 0
FROM cte1
UNION ALL
SELECT PID, EIDCount , DATEADD(DAY, 1, EndDate), -1
FROM cte1
), cte3 AS (
/*
* calculate running sum of pval over dates; minus ones first
*/
SELECT PID, EIDCount, pdate, SUM(pval) OVER (PARTITION BY PID ORDER BY pdate, pval) AS evtcount
FROM cte2
), cte4 AS (
/*
* consolidate data for same dates and we are done with the main part
*/
SELECT PID, EIDCount, pdate, MAX(evtcount) AS evtcount
FROM cte3
GROUP BY PID, EIDCount, pdate
), cte5 AS (
/*
* assign "change flag" to rows where number of concurrent events
* enters or exits the required count w.r.t. previous row
*/
SELECT PID, EIDCount, pdate, evtcount, CASE
WHEN evtcount < EIDCount AND LAG(evtcount) OVER (PARTITION BY PID ORDER BY pdate) < EIDCount THEN 0
WHEN evtcount = EIDCount AND LAG(evtcount) OVER (PARTITION BY PID ORDER BY pdate) = EIDCount THEN 0
ELSE 1
END AS chg
FROM cte4
), cte6 AS (
/*
* convert "change flag" to "group numbers" over consecutive rows using running sum
*/
SELECT PID, EIDCount, pdate, evtcount, SUM(chg) OVER (PARTITION BY PID ORDER BY pdate) AS grp
FROM cte5
)
/*
* group rows by pid and group numbers
*/
SELECT PID, MIN(pdate) AS StartDate, MAX(pdate) AS EndDate
FROM cte6
WHERE evtcount = EIDCount
GROUP BY PID, grp
ORDER BY PID, StartDate