SQL 服务器 - 选择未更改数据的时间段
SQL Server - Selecting periods without changes in data
我想要做的是 select 时间段,其中 table 中的其余数据是 stable 基于一列并检查是否有变化在此期间的第二列值中。
Table:
create table #stable_periods
(
[Date] date,
[Car_Reg] nvarchar(10),
[Internal_Damages] int,
[External_Damages] int
)
insert into #stable_periods
values ('2015-08-19', 'ABC123', 10, 10),
('2015-08-18', 'ABC123', 9, 10),
('2015-08-17', 'ABC123', 8, 9),
('2015-08-16', 'ABC123', 9, 9),
('2015-08-15', 'ABC123', 10, 10),
('2015-08-14', 'ABC123', 10, 10),
('2015-08-19', 'ABC456', 5, 3),
('2015-08-18', 'ABC456', 5, 4),
('2015-08-17', 'ABC456', 8, 4),
('2015-08-16', 'ABC456', 9, 4),
('2015-08-15', 'ABC456', 10, 10),
('2015-01-01', 'ABC123', 1, 1),
('2015-01-01', 'ABC456', NULL, NULL);
--select * from #stable_periods
-- Unfortunately I can’t post pictures yet but you get the point of how the table looks like
我想收到的是
Car_Reg FromDate ToDate External_Damages Have internal damages changed in this period?
ABC123 2015-08-18 2015-08-19 10 Yes
ABC123 2015-08-16 2015-08-17 9 Yes
ABC123 2015-08-14 2015-08-15 10 No
ABC123 2015-01-01 2015-01-01 1 No
ABC456 2015-08-19 2015-08-19 3 No
ABC456 2015-08-16 2015-08-18 4 Yes
ABC456 2015-08-15 2015-08-15 10 No
ABC456 2015-01-01 2015-01-01 NULL NULL
基本上是建立 [External_Damages] 不变的周期框架,并检查 [Internal_Damages] 是否在同一时期内发生变化(无论多少次)。
我花了很多时间尝试,但我担心我的抽象思维水平太低了……
很高兴看到任何建议。
谢谢,
巴尔托斯
我认为这是 Islands Problem 的一种形式。
这是使用 ROW_NUMBER
和 GROUP BY
的解决方案:
WITH CTE AS(
SELECT *,
RN = DATEADD(DAY, - ROW_NUMBER() OVER(PARTITION BY Car_reg, External_Damages ORDER BY [Date]), [Date])
FROM #stable_periods
)
SELECT
Car_Reg,
FromDate = MIN([Date]),
ToDate = MAX([Date]) ,
External_Damages,
Change =
CASE
WHEN MAX(External_Damages) IS NULL THEN NULL
WHEN COUNT(DISTINCT Internal_Damages) > 1 THEN 'Yes'
ELSE 'No'
END
FROM CTE c
GROUP BY Car_Reg, External_Damages, RN
ORDER BY Car_Reg, ToDate DESC
我想要做的是 select 时间段,其中 table 中的其余数据是 stable 基于一列并检查是否有变化在此期间的第二列值中。
Table:
create table #stable_periods
(
[Date] date,
[Car_Reg] nvarchar(10),
[Internal_Damages] int,
[External_Damages] int
)
insert into #stable_periods
values ('2015-08-19', 'ABC123', 10, 10),
('2015-08-18', 'ABC123', 9, 10),
('2015-08-17', 'ABC123', 8, 9),
('2015-08-16', 'ABC123', 9, 9),
('2015-08-15', 'ABC123', 10, 10),
('2015-08-14', 'ABC123', 10, 10),
('2015-08-19', 'ABC456', 5, 3),
('2015-08-18', 'ABC456', 5, 4),
('2015-08-17', 'ABC456', 8, 4),
('2015-08-16', 'ABC456', 9, 4),
('2015-08-15', 'ABC456', 10, 10),
('2015-01-01', 'ABC123', 1, 1),
('2015-01-01', 'ABC456', NULL, NULL);
--select * from #stable_periods
-- Unfortunately I can’t post pictures yet but you get the point of how the table looks like
我想收到的是
Car_Reg FromDate ToDate External_Damages Have internal damages changed in this period?
ABC123 2015-08-18 2015-08-19 10 Yes
ABC123 2015-08-16 2015-08-17 9 Yes
ABC123 2015-08-14 2015-08-15 10 No
ABC123 2015-01-01 2015-01-01 1 No
ABC456 2015-08-19 2015-08-19 3 No
ABC456 2015-08-16 2015-08-18 4 Yes
ABC456 2015-08-15 2015-08-15 10 No
ABC456 2015-01-01 2015-01-01 NULL NULL
基本上是建立 [External_Damages] 不变的周期框架,并检查 [Internal_Damages] 是否在同一时期内发生变化(无论多少次)。 我花了很多时间尝试,但我担心我的抽象思维水平太低了…… 很高兴看到任何建议。
谢谢,
巴尔托斯
我认为这是 Islands Problem 的一种形式。
这是使用 ROW_NUMBER
和 GROUP BY
的解决方案:
WITH CTE AS(
SELECT *,
RN = DATEADD(DAY, - ROW_NUMBER() OVER(PARTITION BY Car_reg, External_Damages ORDER BY [Date]), [Date])
FROM #stable_periods
)
SELECT
Car_Reg,
FromDate = MIN([Date]),
ToDate = MAX([Date]) ,
External_Damages,
Change =
CASE
WHEN MAX(External_Damages) IS NULL THEN NULL
WHEN COUNT(DISTINCT Internal_Damages) > 1 THEN 'Yes'
ELSE 'No'
END
FROM CTE c
GROUP BY Car_Reg, External_Damages, RN
ORDER BY Car_Reg, ToDate DESC