SQL查询日期间隔以比较不相邻的行吗？

编程问答 2022-08-11

问题描述

我想为数据中的每个ID单元在每个窗口中标记至少31天的第一个日期。

ROW  ID    INDEX_DATE
1    ABC   1/1/2019
2    ABC   1/7/2019
3    ABC   1/21/2019
4    ABC   2/2/2019
5    ABC   2/9/2019
6    ABC   3/6/2019
7    DEF   1/5/2019
8    DEF   2/1/2019
9    DEF   2/8/2019

所需行为1、4、6、7和9；它们要么是给定INDEX_DATE的第一个ID，要么发生在先前标记的INDEX_DATE之后至少31天。我发现的每个建议都将LAG()或LEAD与窗口函数一起使用，但是我只能得到它们来比较相邻的行。例如，需要将第4行与第1行进行比较，以便在完成31天的展示期后将其标识为第一行。

我尝试了以下操作：
数据

DROP TABLE tTest IF EXISTS; 
CREATE TEMP TABLE tTest
(
ROWN    INT,ID VARCHAR(3),INDEX_DATE DATE
) ;
GO

INSERT INTO tTEST VALUES (1,'ABC','1/1/2019');
INSERT INTO tTEST VALUES (2,'1/7/2019');
INSERT INTO tTEST VALUES (3,'1/21/2019');
INSERT INTO tTEST VALUES (4,'2/2/2019');
INSERT INTO tTEST VALUES (5,'2/9/2019');
INSERT INTO tTEST VALUES (6,'3/6/2019');
INSERT INTO tTEST VALUES (7,'DEF','1/5/2019');
INSERT INTO tTEST VALUES (8,'2/1/2019');
INSERT INTO tTEST VALUES (9,'2/8/2019');
GO

查询：

DROP TABLE TTEST2 IF EXISTS;
CREATE TEMP TABLE TTEST2 AS (
WITH 
RN_CTE(ROWN,ID,INDEX_DATE,RN) AS (
        SELECT *,ROW_NUMBER() OVER (PARTITION BY ID ORDER BY INDEX_DATE)
        FROM tTEST),MIN_CTE(ROWN,RN) AS (SELECT * FROM RN_CTE WHERE RN=1),DIFF_CTE(ROWN,RN,DAY_DIFF) AS (
        SELECT RN.*,DATE(RN.INDEX_DATE + INTERVAL '30 DAYS') 
        FROM RN_CTE AS RN
                JOIN MIN_CTE AS MC ON RN.ID=MC.ID
        WHERE RN.RN=1
           OR RN.INDEX_DATE > MC.INDEX_DATE + INTERVAL '30 DAYS' ),MIN_DIFF_CTE AS (
        SELECT ID,DAY_DIFF,MIN(ROWN) AS MIN_ROW
        FROM DIFF_CTE
        GROUP BY ID,DAY_DIFF)
SELECT T.*
FROM MIN_DIFF_CTE AS MDC
        JOIN tTEST AS T ON MDC.MIN_ROW = T.ROWN
ORDER BY ID,INDEX_DATE
);

结果：

SELECT * FROM TTEST2 ORDER BY ID,INDEX_DATE;    
ROWN ID INDEX_DATE
1   ABC 2019-01-01
4   ABC 2019-02-02
5   ABC 2019-02-09
6   ABC 2019-03-06
7   DEF 2019-01-05
9   DEF 2019-02-08

INDEX_DATE = 2019-02-09的第5行不应出现在输出中，因为它距第4行INDEX_DATE不到31天。

解决方法

类似这样的事情。 CTE会为每个ID转换以及31天的滚动找到最小ROW值的唯一窗口。

数据

drop table if exists #tTEST;
go
select * INTO #tTEST from (values 
(1,'abc','1/1/2019'),(2,'1/7/2019'),(3,'1/21/2019'),(4,'2/2/2019'),(5,'2/9/2019'),(6,'3/6/2019'),(7,'def','1/5/2019'),(8,'2/1/2019'),(9,'2/8/2019')) V([ROW],ID,INDEX_DATE);

查询

;with
rn_cte([ROW],INDEX_DATE,rn) as (
    select *,row_number() over (partition by ID order by INDEX_DATE)
    from #tTEST),min_cte([ROW],rn) as (select * from rn_cte where rn=1),diff_cte([ROW],rn,day_diff) as (
    select rn.*,datediff(d,mc.INDEX_DATE,rn.INDEX_DATE)/31
    from rn_cte rn
         join min_cte mc on rn.ID=mc.ID
    where rn.rn=1 
          or datediff(d,rn.INDEX_DATE)/31>0),min_diff_cte as (
    select ID,day_diff,min([ROW]) min_row
    from diff_cte 
    group by ID,day_diff)
select t.*
from min_diff_cte mdc
     join #tTEST t on mdc.min_row=t.ROW
order by 1;

输出

ROW ID  INDEX_DATE
1   abc 1/1/2019
4   abc 2/2/2019
6   abc 3/6/2019
7   def 1/5/2019
9   def 2/8/2019
netezzasqlsqlwindow-functions