查找连续日期范围和它们发生的次数row_id

Question

我有一张表格，它为每个公司显示与它们相关的联系人以及关系持续的日期。我想要做的是为每家公司制定一个关系存在的范围集合以及在此期间链接的联系人数量。

（我找不到在搜索领域的可比性问题，所以道歉，如果这是一个重复）

对于下面的示例数据：

CREATE TABLE #overlap 
(
contact_id NVARCHAR(255) 
,company_id NVARCHAR(255) 
,relationship_started DATETIME 
,relationship_ended DATETIME 
) 

INSERT INTO #overlap VALUES ('19CB6330-8559-4357-BF70-8F2EBAE4CF90','AECA7DFD-4551-455A-B01D-0000AE19B712','2006-07-25 00:00:00.000','2010-04-11 10:52:00.000') 
INSERT INTO #overlap VALUES ('90331A59-EED3-47D5-8885-4648825FE06F','AECA7DFD-4551-455A-B01D-0000AE19B712','2007-07-31 00:00:00.000','2007-08-24 01:09:00.000') 
INSERT INTO #overlap VALUES ('CFF414A7-4AB7-4C38-9915-6A107C9044AE','AECA7DFD-4551-455A-B01D-0000AE19B712','2008-01-11 00:00:00.000','2008-02-05 08:23:00.000') 
INSERT INTO #overlap VALUES ('EC520389-4B84-429B-97D2-9653CFC47669','AECA7DFD-4551-455A-B01D-0000AE19B712','2008-01-01 00:00:00.000','2011-02-08 09:00:00.000') 

我想以下结果：

CREATE TABLE #results 
(
company_id NVARCHAR(255) 
,start_date DATETIME 
,end_date DATETIME 
,relationship_number INT 
,num_contacts INT 
) 
INSERT INTO #results VALUES('AECA7DFD-4551-455A-B01D-0000AE19B712','2006-07-25 00:00:00.000','2007-07-31 00:00:00.000',1,1) 
INSERT INTO #results VALUES('AECA7DFD-4551-455A-B01D-0000AE19B712','2007-07-31 00:00:00.000','2007-08-24 01:09:00.000',2,2) 
INSERT INTO #results VALUES('AECA7DFD-4551-455A-B01D-0000AE19B712','2007-08-24 01:09:00.000','2008-01-01 00:00:00.000',3,1) 
INSERT INTO #results VALUES('AECA7DFD-4551-455A-B01D-0000AE19B712','2008-01-01 00:00:00.000','2008-01-11 00:00:00.000',4,2) 
INSERT INTO #results VALUES('AECA7DFD-4551-455A-B01D-0000AE19B712','2008-01-11 00:00:00.000','2008-02-05 08:23:00.000',5,3) 
INSERT INTO #results VALUES('AECA7DFD-4551-455A-B01D-0000AE19B712','2008-02-05 08:23:00.000','2010-04-11 10:52:00.000',6,2) 
INSERT INTO #results VALUES('AECA7DFD-4551-455A-B01D-0000AE19B712','2010-04-11 10:52:00.000','2011-02-08 09:00:00.000',7,1) 

我开始使用这组开始日期（然后重复结束日期），但可能不知道如何使用组CONTIN区分优惠范围

DENSE_RANK() OVER 
     (PARTITION BY company_id 
     ORDER BY DATEPART(YEAR, relationship_started)*12 + DATEPART(MONTH, relationship_started)) AS start_group 

任何指针在正确的方向感激地收到！ :)

编辑以包括更多的样本数据：

CREATE TABLE #overlap 
(
contact_id NVARCHAR(255) 
,company_id NVARCHAR(255) 
,relationship_started DATETIME 
,relationship_ended DATETIME 
) 

INSERT INTO #overlap VALUES ('19CB6330-8559-4357-BF70-8F2EBAE4CF90','AECA7DFD-4551-455A-B01D-0000AE19B712','2006-07-25 00:00:00.000','2010-04-11 10:52:00.000') 
INSERT INTO #overlap VALUES ('90331A59-EED3-47D5-8885-4648825FE06F','AECA7DFD-4551-455A-B01D-0000AE19B712','2007-07-31 00:00:00.000','2007-08-24 01:09:00.000') 
INSERT INTO #overlap VALUES ('CFF414A7-4AB7-4C38-9915-6A107C9044AE','AECA7DFD-4551-455A-B01D-0000AE19B712','2008-01-11 00:00:00.000','2008-02-05 08:23:00.000') 
INSERT INTO #overlap VALUES ('EC520389-4B84-429B-97D2-9653CFC47669','AECA7DFD-4551-455A-B01D-0000AE19B712','2008-01-01 00:00:00.000','2011-02-08 09:00:00.000') 
INSERT INTO #overlap VALUES ('E892EF8B-962F-4974-A3ED-60F6E916DB86','0B10F07D-3662-454B-8FAC-87E5AE92EE8D','2008-07-01 00:00:00.000','2011-02-08 09:00:00.000') 
INSERT INTO #overlap VALUES ('76F944E1-E9C8-486E-912B-4A322F5F0A05','6FB62827-A27C-4110-BBA4-BC04C84C0219','2010-12-06 00:00:00.000','2011-02-08 13:00:00.000') 
INSERT INTO #overlap VALUES ('69E3768C-3118-48E1-B590-8A7D02726227','6FB62827-A27C-4110-BBA4-BC04C84C0219','1950-01-01 00:00:00.000','2010-12-06 00:00:00.000') 

Answer 1

WITH Dates 
    AS (SELECT company_id, relationship_started As Date 
     FROM #overlap 
     UNION 
     SELECT company_id, relationship_ended 
     FROM #overlap), 
    T 
    AS (SELECT COUNT(*)        AS Cnt, 
       d.Date, 
       ROW_NUMBER() OVER (PARTITION BY d.company_id ORDER BY (d.Date)) AS RN, 
       d.company_id 
     FROM Dates d 
       left JOIN #overlap o 
        ON d.Date >= relationship_started 
        and d.Date < relationship_ended 
        and d.company_id = o.company_id 
     group by d.Date, 
        d.company_id) 
SELECT t1.company_id, 
     t1.Date, 
     t2.Date, 
     ROW_NUMBER() over (PARTITION BY t1.company_id order by (select 0)) as relationship_number, 
     t1.Cnt 
FROM T t1 
     JOIN T t2 
     ON t2.RN = t1.RN + 1 AND t1.company_id = t2.company_id 
ORDER BY t1.company_id, t1.Date 

Answer 2

我不能完全做到，但 - 但也许这输入可带你进入正确的方向。

我的想法是创建两个CTE（公用表表达式），它将列出新关系开始时的日期（值为+1）以及关系结束时的值（值为-1 ）。

因此，基本上，您会得到一个关于与该公司关系发生变化的历史清单。

我现在走到这一步：

;WITH DatesStarted AS 
(SELECT relationship_started AS 'TheDate', 1 AS 'Delta' 
FROM #overlap 
), 
DatesEnded AS 
(SELECT relationship_ended AS 'TheDate', -1 AS 'Delta' 
FROM #overlap 
) 
SELECT * 
FROM DatesStarted 
UNION 
SELECT * 
FROM DatesEnded 
ORDER BY thedate 

，我得到的输出是这样的：

TheDate    Delta 
2006-07-25 00:00:00.000 1 
2007-07-31 00:00:00.000 1 
2007-08-24 01:09:00.000 -1 
2008-01-01 00:00:00.000 1 
2008-01-11 00:00:00.000 1 
2008-02-05 08:23:00.000 -1 
2010-04-11 10:52:00.000 -1 
2011-02-08 09:00:00.000 -1 

所以给这个，你现在应该生成插入到你的结果表....还没有完成（我必须跑开会） - 但也许这有助于你开始！

Answer 3

我相信这个答案适用于多家公司。评论嵌入到代码中：

WITH company_dates (company_id, date) AS (
    /* get all relevant dates */ 
    SELECT company_id, relationship_started AS date 
    FROM #overlap 
    UNION 
    SELECT company_id, relationship_ended 
    FROM #overlap 
) 
, sequenced_dates (company_id, date, sequence) AS (
    /* assign dates a sequence for easy joining */ 
    SELECT company_id, date, row_number() OVER (PARTITION BY company_id ORDER BY DATE) AS sequence 
    FROM company_dates 
) 
SELECT d1.company_id, d1.date AS start_date, d2.date AS end_date, row_number() OVER (PARTITION BY d1.company_id ORDER BY d1.date) AS relationship_number, count(*) AS numContacts 
FROM sequenced_dates d1 
JOIN sequenced_dates d2 /* join to get start and end date for each region */ 
    ON d1.company_id = d2.company_id 
    AND d1.sequence = d2.sequence-1 
JOIN #overlap o /* join to get all involved relationships */ 
    ON o.company_id = d1.company_id 
    AND o.relationship_started <= d1.date 
    AND o.relationship_ended >= d2.date 
GROUP BY d1.company_id, d1.date, d2.date 
ORDER BY d1.company_Id, d1.date 

Answer 4

这是我的解决方案，用于记录。

不知何故，我已经设法重构了一下，所以它对我来说已经不再是巨大的了。尽管如此，执行计划表示它的性能不如公认的解决方案。

;WITH 
dates AS (
    SELECT 
    company_id, 
    date   = relationship_started, 
    count_change = +1 
    FROM #overlap 
    UNION ALL 
    SELECT 
    company_id, 
    date   = relationship_ended, 
    count_change = -1 
    FROM #overlap 
), 
sorted_dates AS (
    SELECT 
    company_id, 
    date, 
    count_change, 
    rownum = ROW_NUMBER() OVER (PARTITION BY company_id ORDER BY date) 
    FROM (
    SELECT 
     company_id, 
     date, 
     count_change = SUM(count_change) 
    FROM dates 
    GROUP BY company_id, date 
    HAVING SUM(count_change) <> 0 
) s 
) 
SELECT 
    sd1.company_id, 
    start_date   = MAX(sd2.date), 
    end_date   = sd1.date, 
    relationship_number = MAX(sd2.rownum), 
    num_contacts  = SUM(sd2.count_change) 
FROM sorted_dates sd1 
    INNER JOIN sorted_dates sd2 ON sd1.company_id = sd2.company_id 
    AND sd2.rownum BETWEEN 1 AND sd1.rownum - 1 
GROUP BY sd1.company_id, sd1.date