I have a dataset with 3 columns. Table name is #test. I want to create the 4th column ("Result") that satisfies some conditions. The terms are as follows:
Get if the first Resolved value of a contact is 0.
Get if the first value after 1 in the Resolved column is 0. If they continue as 0, do not include them.
These conditions must be applied separately for each contact.
I am sharing the example below.
Thank you.
I hope this can help :
DECLARE #TMP table (
ContactCode int,
HistoryDate date,
Resolved bit
)
INSERT INTO #TMP VALUES
(466, '2022-02-28',0),
(466, '2022-03-31',1),
(466, '2022-04-30',0),
(466, '2022-05-31',0),
(466, '2022-06-30',1),
(466, '2022-07-31',0),
(467, '2022-02-28',0),
(467, '2022-03-31',0),
(467, '2022-04-30',0),
(467, '2022-05-31',0),
(467, '2022-06-30',1),
(467, '2022-07-31',0)
SELECT
ContactCode,
HistoryDate,
Resolved,
CASE
WHEN
ROW_NUMBER() OVER(PARTITION BY ContactCode ORDER BY HistoryDate ASC) = 1
OR LAG(Resolved, 1, 0) OVER(PARTITION BY ContactCode ORDER BY HistoryDate ASC) = 1
THEN 0
ELSE NULL
END AS Result
FROM #TMP
Result :
ContactCode
HistoryDate
Resolved
Result
466
2022-02-28
0
0
466
2022-03-31
1
NULL
466
2022-04-30
0
0
466
2022-05-31
0
NULL
466
2022-06-30
1
NULL
466
2022-07-31
0
0
467
2022-02-28
0
0
467
2022-03-31
0
NULL
467
2022-04-30
0
NULL
467
2022-05-31
0
NULL
467
2022-06-30
1
NULL
467
2022-07-31
0
0
ROW_NUMBER() allows you to 'order' your data in a partition (here your partition is your ContactCode and order by HistoryDate). You then whant the first one (ROW_NUMBER() ... = 1)
LAG() will look for the previous value of Resolved, if it's a 1 you print 0for your current row.
Related
I'm trying to get the first BEG_PERIOD date immediately after the last but one record of X (DEF_ENDING) of each user (USER_ID).
So I have this:
USER_ID
BEG_PERIOD
END_PERIOD
DEF_ENDING
159
01-07-2022
31-07-2022
X
159
25-09-2022
15-10-2022
X
159
01-11-2022
13-11-2022
159
14-11-2022
21-12-2022
X
159
01-01-2023
30-01-2023
X
414
01-04-2022
31-05-2022
X
414
01-07-2022
30-09-2022
414
01-10-2022
01-12-2022
X
480
01-07-2022
30-06-2022
480
01-07-2022
30-08-2022
X
480
02-09-2022
01-11-2022
X
503
15-03-2022
16-06-2022
X
503
19-07-2022
23-07-2022
503
24-07-2022
31-10-2022
503
01-11-2022
21-12-2022
X
The dates I need are the ones in bold
Can you help me?
I tried this but I only get the latest dates :(
SELECT
p.USER_ID,
p.BEG_PERIOD
FROM
PERIODS p
INNER JOIN PERIODS p2 ON
p.USER_ID = p2.USER_ID
AND
p.BEG_PERIOD = (
SELECT
MAX( BEG_PERIOD )
FROM
PERIODS
WHERE
PERIODS.USER_ID = p.USER_ID
)
WHERE
p.USER_ID > 10
This should work based on the sample data:
with data as (
select *,
sum(case when DEF_ENDING = 'X' then 1 end)
over (partition by USER_ID order by BEG_PERIOD desc) as grp
from PERIODS
)
select
USER_ID,
min(BEG_PERIOD) as BEG_PERIOD,
min(END_PERIOD) as END_PERIOD,
min(DEF_ENDING) as DEF_ENDING
from data
where grp = 1
group by USER_ID;
If you can't rely on the two dates being minimums then:
with data as (
select *,
sum(case when DEF_ENDING = 'X' then 1 end)
over (partition by USER_ID order by BEG_PERIOD desc) as grp
from PERIODS
), data2 as (
select *,
row_number() over (partition by USER_ID order by BEG_PERIOD) as rn
from data
where grp = 1
)
select *
from data2
where rn = 1;
This can also be done entirely via subqueries if that's more appropriate at the level of your class:
select USER_ID, min(BEG_PERIOD), min(END_PERIOD), min(DEF_ENDING)
from periods p1
where p1.BEG_PERIOD > (
select max(BEG_PERIOD)
from periods p2
where p2.USER_ID = p1.USER_ID and p2.DEF_ENDING = 'X'
and exists (
select 1
from periods p3
where p3.USER_ID = p2.USER_ID and p3.DEF_ENDING = 'X'
and p3.BEG_PERIOD > p2.BEG_PERIOD
)
)
group by USER_ID;
Try the following using the ROW_NUMBER and `LAG' window functions:
/* this to assign row numbers only for rows where def_ending = 'X' */
with order_def_ending as
(
select *,
case def_ending when 'X' then
row_number() over (partition by user_id order by
case def_ending when 'X' then 1 else 2 end,
end_period desc)
else null end rn,
lag(def_ending, 1, def_ending) over (partition by user_id order by end_period) pde /* previous end_period value */
from yourTbl
),
lag_rn as
(
select *,
lag(rn) over (partition by user_id order by end_period) prn /* previous row_number value */
from order_def_ending
)
select user_id, beg_period, end_period, def_ending
from lag_rn
where (
prn = 2 or /* when there are multiple rows with def_ending = 'X' */
(prn = 1 and rn is null) /* when there is only one row with def_ending = 'X' */
) and pde = 'X' /* ensure that the previous value of def_ending is = 'X' */
order by user_id, end_period
See demo
I think, this works on SQL server 2008
with periods as(
select USER_ID, cast(BEG_PERIOD as date)BEG_PERIOD,cast(END_PERIOD as date)END_PERIOD,DEF_ENDING
from (values
(159,'01-07-2022','31-07-2022','X')
,(159,'25-09-2022','15-10-2022','X')
,(159,'01-11-2022','13-11-2022',null)
,(159,'14-11-2022','21-12-2022','X')
,(159,'01-01-2023','30-01-2023','X')
,(414,'01-04-2022','31-05-2022','X')
,(414,'01-07-2022','30-09-2022',null)
,(414,'01-10-2022','01-12-2022','X')
,(480,'01-07-2022','30-06-2022',null)
,(480,'01-07-2022','30-08-2022','X')
,(480,'02-09-2022','01-11-2022','X')
,(503,'15-03-2022','16-06-2022','X')
,(503,'19-07-2022','23-07-2022',null)
,(503,'24-07-2022','31-10-2022',null)
,(503,'01-11-2022','21-12-2022','X')
)t(USER_ID, BEG_PERIOD, END_PERIOD, DEF_ENDING)
)
,cte as (
select *
,(select sum(case when def_ending='X' then 1 else 0 end)
from periods t2 where t2.user_id=t1.USER_ID and t2.BEG_PERIOD>=t1.BEG_PERIOD
) N -- last but one has N=2, all next N=1 (reverse order of counts)
from periods t1
)
select *
,(select min(t2.BEG_PERIOD)
from cte t2 where t2.user_id=t1.USER_ID and t2.N=1
) LastButOne -- first after last but one with N=1
from cte t1
Result
USER_ID
BEG_PERIOD
END_PERIOD
DEF_ENDING
N
LastButOne
159
2022-07-01
2022-07-31
X
4
2023-01-01
159
2022-09-25
2022-10-15
X
3
2023-01-01
159
2022-11-01
2022-11-13
NULL
2
2023-01-01
159
2022-11-14
2022-12-21
X
2
2023-01-01
159
2023-01-01
2023-01-30
X
1
2023-01-01
414
2022-04-01
2022-05-31
X
2
2022-07-01
414
2022-07-01
2022-09-30
NULL
1
2022-07-01
414
2022-10-01
2022-12-01
X
1
2022-07-01
480
2022-07-01
2022-06-30
NULL
2
2022-09-02
480
2022-07-01
2022-08-30
X
2
2022-09-02
480
2022-09-02
2022-11-01
X
1
2022-09-02
503
2022-03-15
2022-06-16
X
2
2022-07-19
503
2022-07-19
2022-07-23
NULL
1
2022-07-19
503
2022-07-24
2022-10-31
NULL
1
2022-07-19
503
2022-11-01
2022-12-21
X
1
2022-07-19
About Parallel Data Warehouse,
as mentioned here, Non-PDW versions of SQL Server before 2012 do not support the ORDER BY clause with aggregate functions like MIN.
Windowing function support was considerably extended in 2012, compared with the basic implementation available starting with SQL Server 2005. The extensions were made available in Parallel Data Warehouse before being incorporated in the box product.
My question involves how to identify an index discharge.
The index discharge is the earliest discharge. On that date, the 30 day window starts. Any admissions during that time period are considered readmissions, and they should be ignored. Once the 30 day window is over, then any subsequent discharge is considered an index and the 30 day window begins again.
I can't seem to work out the logic for this. I've tried different windowing functions, I've tried cross joins and cross applies. The issue I keep encountering is that a readmission cannot be an index admission. It must be excluded.
I have successfully written a while loop to solve this problem, but I'd really like to get this in a set based format, if it's possible. I haven't been successful so far.
Ultimate goal is this -
id
AdmitDate
DischargeDate
MedicalRecordNumber
IndexYN
1
2021-03-03 00:00:00.000
2021-03-09 13:20:00.000
X0090362
1
4
2021-03-05 00:00:00.000
2021-03-10 16:00:00.000
X0012614
1
6
2021-05-18 00:00:00.000
2021-05-21 22:20:00.000
X0012614
1
7
2021-06-21 00:00:00.000
2021-07-08 13:30:00.000
X0012614
1
8
2021-02-03 00:00:00.000
2021-02-09 17:00:00.000
X0019655
1
10
2021-03-23 00:00:00.000
2021-03-26 16:40:00.000
X0019655
1
11
2021-03-15 00:00:00.000
2021-03-18 15:53:00.000
X4135958
1
13
2021-05-17 00:00:00.000
2021-05-23 14:55:00.000
X4135958
1
15
2021-06-24 00:00:00.000
2021-07-13 15:06:00.000
X4135958
1
Sample code is below.
CREATE TABLE #Admissions
(
[id] INT,
[AdmitDate] DATETIME,
[DischargeDateTime] DATETIME,
[UnitNumber] VARCHAR(20),
[IndexYN] INT
)
INSERT INTO #Admissions
VALUES( 1 ,'2021-03-03' ,'2021-03-09 13:20:00.000' ,'X0090362', NULL)
,(2 ,'2021-03-27' ,'2021-03-30 19:59:00.000' ,'X0090362', NULL)
,(3 ,'2021-03-31' ,'2021-04-04 05:57:00.000' ,'X0090362', NULL)
,(4 ,'2021-03-05' ,'2021-03-10 16:00:00.000' ,'X0012614', NULL)
,(5 ,'2021-03-28' ,'2021-04-16 13:55:00.000' ,'X0012614', NULL)
,(6 ,'2021-05-18' ,'2021-05-21 22:20:00.000' ,'X0012614', NULL)
,(7 ,'2021-06-21' ,'2021-07-08 13:30:00.000' ,'X0012614', NULL)
,(8 ,'2021-02-03' ,'2021-02-09 17:00:00.000' ,'X0019655', NULL)
,(9 ,'2021-02-17' ,'2021-02-22 17:25:00.000' ,'X0019655', NULL)
,(10 ,'2021-03-23' ,'2021-03-26 16:40:00.000' ,'X0019655', NULL)
,(11 ,'2021-03-15' ,'2021-03-18 15:53:00.000' ,'X4135958', NULL)
,(12 ,'2021-04-08' ,'2021-04-13 19:42:00.000' ,'X4135958', NULL)
,(13 ,'2021-05-17' ,'2021-05-23 14:55:00.000' ,'X4135958', NULL)
,(14 ,'2021-06-09' ,'2021-06-14 12:45:00.000' ,'X4135958', NULL)
,(15 ,'2021-06-24' ,'2021-07-13 15:06:00.000' ,'X4135958', NULL)
You can use a recursive CTE to identify all rows associated with each "index" discharge:
with a as (
select a.*, row_number() over (order by dischargedatetime) as seqnum
from admissions a
),
cte as (
select id, admitdate, dischargedatetime, unitnumber, seqnum, dischargedatetime as index_dischargedatetime
from a
where seqnum = 1
union all
select a.id, a.admitdate, a.dischargedatetime, a.unitnumber, a.seqnum,
(case when a.dischargedatetime > dateadd(day, 30, cte.index_dischargedatetime)
then a.dischargedatetime else cte.index_dischargedatetime
end) as index_dischargedatetime
from cte join
a
on a.seqnum = cte.seqnum + 1
)
select *
from cte;
You can then incorporate this into an update:
update admissions
set indexyn = (case when admissions.dischargedatetime = cte.index_dischargedatetime then 'Y' else 'N' end)
from cte
where cte.id = admissions.id;
Here is a db<>fiddle. Note that I changed the type of IndexYN to a character to assign 'Y'/'N', which makes sense given the column name.
Is it possible to do the following:
I have a table that looks like this:
declare #tran_TABLE TABLE(
EOMONTH DATE,
AccountNumber INT,
CLASSIFICATION_NAME VARCHAR(50),
Value Float
)
INSERT INTO #tran_TABLE VALUES('2018-11-30','123','cat1',10)
INSERT INTO #tran_TABLE VALUES('2018-11-30','123','cat1',15)
INSERT INTO #tran_TABLE VALUES('2018-11-30','123','cat1',5 )
INSERT INTO #tran_TABLE VALUES('2018-11-30','123','cat2',10)
INSERT INTO #tran_TABLE VALUES('2018-11-30','123','cat3',12)
INSERT INTO #tran_TABLE VALUES('2019-01-31','123','cat1',5 )
INSERT INTO #tran_TABLE VALUES('2019-01-31','123','cat2',10)
INSERT INTO #tran_TABLE VALUES('2019-01-31','123','cat2',15)
INSERT INTO #tran_TABLE VALUES('2019-01-31','123','cat3',5 )
INSERT INTO #tran_TABLE VALUES('2019-01-31','123','cat3',2 )
INSERT INTO #tran_TABLE VALUES('2019-03-31','123','cat1',15)
EOMONTH AccountNumber CLASSIFICATION_NAME Value
2018-11-30 123 cat1 10
2018-11-30 123 cat1 15
2018-11-30 123 cat1 5
2018-11-30 123 cat2 10
2018-11-30 123 cat3 12
2019-01-31 123 cat1 5
2019-01-31 123 cat2 10
2019-01-31 123 cat2 15
2019-01-31 123 cat3 5
2019-01-31 123 cat3 2
2019-03-31 123 cat1 15
I want to produce a result where it will check whether in each month, for each AccountNumber (just one in this case) there exists a CLASSIFICATION_NAME cat1, cat2, cat3.
If all 3 exist for the month, then return 1 but if any are missing return 0.
The result should look like:
EOMONTH AccountNumber CLASSIFICATION_NAME
2018-11-30 123 1
2019-01-31 123 1
2019-03-31 123 0
But I want to do it as compactly as possible, without first creating a table that groups everything by CLASSIFICATION_NAME, EOMONTH and AccountNumber and then selects from that table.
For example, in the pseudo code below, is it possible to use maybe an EXISTS statement to do the group by?
SELECT
EOMONTH
,AccountNumber
,CASE WHEN EXISTS (CLASSIFICATION_NAME = 'cat1' AND 'cat2' AND 'cat3') THEN 1 ELSE 0 end
,SUM(Value) AS totalSpend
FROM #tran_TABLE
GROUP BY
EOMONTH
,AccountNumber
You could emulate this behavior by counting the distinct classifications that answer this condition (per group):
SELECT
EOMONTH
,AccountNumber
,CASE COUNT(DISTINCT CASE WHEN classification_name IN ('cat1', 'cat2', 'cat3') THEN classification_name END)
WHEN 3 THEN 1
ELSE 0
END
,SUM(Value) AS totalSpend
FROM #tran_TABLE
GROUP BY
EOMONTH
,AccountNumber
Try this-
SELECT EOMONTH,
AccountNumber,
CASE
WHEN COUNT(DISTINCT CLASSIFICATION_NAME) = 3 THEN 1
ELSE 0
END CLASSIFICATION_NAME
FROM #tran_TABLE
GROUP BY EOMONTH,AccountNumber
Output is-
2018-11-30 123 1
2019-01-31 123 1
2019-03-31 123 0
Query like this. You can count distinct values.
When you count unique values then column 'Three_Unique_Cat'. When you count exactly 'cat1','cat2','cat3' then column 'Three_Cat1_Cat2_Cat3'
SELECT
EOMONTH, AccountNumber
,CASE WHEN
COUNT(DISTINCT CLASSIFICATION_NAME)=3 THEN 1
ELSE 0
END AS 'Three_Unique_Cat'
,CASE WHEN
COUNT(DISTINCT CASE WHEN CLASSIFICATION_NAME IN ('cat1','cat2','cat3')
THEN CLASSIFICATION_NAME ELSE NULL END)=3 THEN 1
ELSE 0
END AS 'Three_Cat1_Cat2_Cat3'
,SUM(Value) AS totalSpend
FROM #tran_TABLE
GROUP BY EOMONTH, AccountNumber
Output:
EOMONTH AccountNumber Three_Unique_Cat Three_Cat1_Cat2_Cat3 totalSpend
2018-11-30 123 1 1 52
2019-01-31 123 1 1 37
2019-03-31 123 0 0 15
It's easy, just as below:
select
EOMONTH,
AccountNumber,
case when count(distinct CLASSIFICATION_NAME) = 3 then 1 else 0 end as CLASSIFICATION_NAME
from
tran_TABLE
group by
EOMONTH,
AccountNumber
I am trying to adjust the below code by adding a 2 week tolerance piece.
What it does it looks when the first time a customer (identifier) created a request and the first time it was completed and counts the days which happened in between.
However I am trying to add a tolerance piece. Which says count the number of NCO which occurred between those dates and if there were further requests past the completion date which happened within 2 weeks of the completion date then count those as well (part of the same request). Anything past 2 weeks of the completions date consider as a new request.
CREATE TABLE #temp
(
Identifier varchar(40)NOT NULL
,Created_Date DATETIME NOT NULL
,Completed_Date DATETIME NULL
,SN_Type varchar(20) NOT NULL
,SN_Status varchar(20) NOT NULL
)
;
INSERT INTO #temp
VALUES ('3333333','2017-02-14 15:00:40.000','2017-02-15 00:00:00.000','Re-Activattion', 'COMP');
INSERT INTO #temp
VALUES ('3333333','2017-05-24 16:41:04.000','2017-06-05 00:00:00.000','Re-Activattion', 'N-CO');
INSERT INTO #temp
VALUES ('3333333','2017-05-25 11:49:54.000','2017-05-26 00:00:00.000','Re-Activattion', 'COMP');
INSERT INTO #temp
VALUES ('3333333','2017-06-27 10:24:29.000',NULL,'Re-Activattion', 'ACC');
#Alex you code is accurate just I would like to be selecting the min date the record is created a 2nd time, so line 2 of the result should return min date to be 2017-05-24 16:41:04.000.
select identifier
,case
when sum(case when SN_STATUS='COMP' and SN_TYPE = 'Re-Activattion' then 1 else 0 end)>0
then str(datediff(day
,MIN(case
when SN_TYPE = 'Re-Activattion'
then Created_Date
else null
end
)
,min(case
when (SN_TYPE = 'Re-Activattion'
and SN_STATUS='COMP'
)
then Completed_Date
else null
end
)
)
)
when sum(case when SN_TYPE='Re-Activattion' then 1 else 0 end)>0
then 'NOT COMP'
else 'NO RE-ACT'
end
as RE_ACT_COMPLETION_TIME
,Sum(CASE WHEN SN_STATUS = 'N-CO' THEN 1 ELSE 0 END) as [RE-AN NCO #]
from #temp
group by identifier
;
RESULTS I AM AFTER:
Your table design is not optimal for these kinds of queries as there is no definitive record that specified order start and order end. Additionally multiple orders are stored with the same identifier.
To work around this you need to calculate/identify Order start and Order End records yourself.
One way to do it is using Common Table Expressions.
Note: I have added comments to code to explain what each section does.
-- calculate/identify Order start and Order End records
WITH cte AS
(
-- 1st Order start record i.e. earliest record in the table for a given "Identifier"
SELECT Identifier, MIN( Created_Date ) AS Created_Date, CONVERT( VARCHAR( 30 ), 'Created' ) AS RecordType, 1 AS OrderNumber
FROM #temp
GROUP BY Identifier
UNION ALL
-- All records with "COMP" status are treated as order completed events. Add 2 weeks to the completed date to create a "dummy" Order End Date
SELECT Identifier, DATEADD( WEEK, 2, Created_Date ) AS Created_Date, 'Completed' AS RecordType, ROW_NUMBER() OVER( PARTITION BY Identifier ORDER BY Created_Date ) AS OrderNumber
FROM #temp
WHERE SN_STATUS = 'COMP'
UNION ALL
-- Set the start period of the next order to be right after (3 ms) the previous Order End Date
SELECT Identifier, DATEADD( ms, 3, DATEADD( WEEK, 2, Created_Date )) AS Created_Date, 'Created' AS RecordType, ROW_NUMBER() OVER( PARTITION BY Identifier ORDER BY Created_Date ) + 1 AS OrderNumber
FROM #temp
WHERE SN_STATUS = 'COMP'
),
-- Combine Start / End records into one record
OrderGroups AS(
SELECT Identifier, OrderNumber, MIN( Created_Date ) AS OrderRangeStartDate, MAX( Created_Date ) AS OrderRangeEndDate
FROM cte
GROUP BY Identifier, OrderNumber
)
SELECT a.Identifier, a.OrderNumber, OrderRangeStartDate, OrderRangeEndDate,
case
when sum(case when SN_STATUS='COMP' and SN_TYPE = 'Re-Activattion' then 1 else 0 end)>0
then str(datediff(day
,MIN(case
when SN_TYPE = 'Re-Activattion'
then Created_Date
else null
end
)
,min(case
when (SN_TYPE = 'Re-Activattion'
and SN_STATUS='COMP'
)
then Completed_Date
else null
end
)
)
)
when sum(case when SN_TYPE='Re-Activattion' then 1 else 0 end)>0
then 'NOT COMP'
else 'NO RE-ACT'
end as RE_ACT_COMPLETION_TIME,
Sum(CASE WHEN SN_STATUS = 'N-CO' THEN 1 ELSE 0 END) as [RE-AN NCO #]
FROM OrderGroups AS a
INNER JOIN #Temp AS b ON a.Identifier = b.Identifier AND a.OrderRangeStartDate <= b.Created_Date AND b.Created_Date <= a.OrderRangeEndDate
GROUP BY a.Identifier, a.OrderNumber, OrderRangeStartDate, OrderRangeEndDate
Output:
Identifier OrderNumber OrderRangeStartDate OrderRangeEndDate RE_ACT_COMPLETION_TIME RE-AN NCO #
-------------- ------------- ----------------------- ----------------------- ---------------------- -----------
200895691 1 2016-01-27 14:25:00.000 2016-02-10 15:15:00.000 0 2
200895691 2 2016-02-10 15:15:00.003 2017-01-16 12:15:00.000 1 1
Output for the updated data set:
Identifier OrderNumber OrderRangeStartDate OrderRangeEndDate RE_ACT_COMPLETION_TIME RE-AN NCO #
------------ ------------ ----------------------- ----------------------- ---------------------- -----------
200895691 1 2017-01-11 00:00:00.000 2017-03-27 00:00:00.000 61 4
200895691 2 2017-03-27 00:00:00.003 2017-04-20 00:00:00.000 1 1
3333333 1 2017-01-27 00:00:00.000 2017-02-10 00:00:00.000 0 2
44454544 1 2017-01-27 00:00:00.000 2017-01-27 00:00:00.000 NOT COMP 1
7777691 1 2017-02-08 09:36:44.000 2017-02-22 09:36:44.000 63 1
Update 2017-10-05 in response to the comment
Input:
INSERT INTO #temp VALUES
('11111','20170203','20170203','Re-Activattion', 'COMP'),
('11111','20170206','20170202','Re-Activattion', 'N-CO');
Output:
Identifier OrderNumber OrderRangeStartDate OrderRangeEndDate RE_ACT_COMPLETION_TIME RE-AN NCO #
---------- ------------ ----------------------- ----------------------- ---------------------- -----------
11111 1 2017-02-03 00:00:00.000 2017-02-17 00:00:00.000 0 1
I have this bit of code:
;WITH MyCTE AS
(
SELECT *,
ROW_NUMBER() OVER(PARTITION BY CardUser ORDER BY CardTableID) AS NewVariation
FROM CardChecker
)
UPDATE MyCTE
SET Status = NewVariation
which currently updates the status column, however what I want to happen is over a 24 hour period, the status starts again the next day at 1, and counts again based on the CardUser like specified above:
Current data and what happens:
2 aaa 1 2015-06-25 08:00:00.000 123 1 NULL
3 ccc 1 2015-06-25 00:00:00.000 124 1 NULL
4 aaa 1 2015-06-25 17:30:00.000 125 2 NULL
5 aaa 1 2015-06-26 17:30:00.000 125 *3* NULL
what I want to happen:
2 aaa 1 2015-06-25 08:00:00.000 123 1 NULL
3 ccc 1 2015-06-25 00:00:00.000 124 1 NULL
4 aaa 1 2015-06-25 17:30:00.000 125 2 NULL
5 aaa 1 2015-06-26 17:30:00.000 125 *1* NULL
im not quite sure how I could add this to the above query so would it be possible for someone to point me in the right direction?
the main problem is the EventTime field contains both the date and the time, so adding it is as a PARTITION means the status would always be 1 based on the time parameter of the field
thanks for the help
Current CardTable structure:
CREATE TABLE CardTable (CardTableID INT IDENTITY (1,1) NOT NULL,
CardUser VARCHAR(50),
CardNumber VARCHAR(50),
EventTime DATETIME,
Status INT)
You can CONVERT() the EventTime to DATE type and then PARTITION:
;WITH MyCTE AS
(
SELECT Status,
ROW_NUMBER() OVER(PARTITION BY CardUser, CONVERT(DATE, EventTime)
ORDER BY CardTableID) AS NewVariation
FROM CardChecker
)
UPDATE MyCTE
SET Status = NewVariation
Your query basically unnecessarily updating entire table everytime. If EventTime is current date time of the system, having a flag to mark already updated status would improve the performance.
;WITH MyCTE AS
(
SELECT Status,
ROW_NUMBER() OVER(PARTITION BY CardUser, CONVERT(DATE, EventTime)
ORDER BY CardTableID) AS NewVariation
FROM CardChecker
WHERE Status IS NULL OR
CONVERT(DATE, EventTime) = CONVERT(DATE, GETDATE())
)
UPDATE MyCTE
SET Status = NewVariation