calculate days with gaps - sql-server

table:
+-----------+--------------+------------+------------+
| RequestID | RequestStaus | StartDate | EndDate |
+-----------+--------------+------------+------------+
| 1 | pending | 9/1/2015 | 10/2/2015 |
| 1 | in progress | 10/2/2015 | 10/20/2015 |
| 1 | completed | 10/20/2015 | 11/3/2015 |
| 1 | reopened | 11/3/2015 | null |
| 2 | pending | 9/5/2015 | 9/7/2015 |
| 2 | in progress | 9/7/2015 | 9/25/2015 |
| 2 | completed | 9/25/2015 | 10/7/2015 |
| 2 | reopened | 10/10/2015 | 10/16/2015 |
| 2 | completed | 10/16/2015 | null |
+-----------+--------------+------------+------------+
I would like to calculate the days opened but exclude the days between completed and reopened. For example, RequestID 1, the days opened will be (11/3/2015 - 9/1/2015) + (GetDate() - 11/3/2015), for request 2, the total days will be (10/7/2015 - 9/5/2015) + ( 10/16/2015 - 10/10/2015).
The result I want will be something like:
+-----------+-------------------------------+
| RequestID | DaysOpened |
+-----------+-------------------------------+
| 1 | 63 + (getdate() - 11/3/2015) |
| 2 | 38 |
+-----------+-------------------------------+
How do I approach this problem? thank you!

Tested. Works well. :)
Note:
1) I suppose the required result = (FirstCompleteEndDate - PendingStartDate)+(Sum of all the Reopen duration)
2) So I used the self joins. Table b provides the exact completed record which immediately follows the in process record for each RequestID. Table c provides Sum of all the Reopen duration.
--create tbl structure
create table #test (RequestID int, RequestStatus varchar(20), StartDate date, EndDate date)
go
--insert sample data
insert #test
select 1,'pending','09/01/2015','10/2/2015'
union all
select 1,'in progress','10/2/2015','10/20/2015'
union all
select 1,'completed','10/20/2015','11/3/2015'
union all
select 1,'reopened','11/3/2015',null
union all
select 2,'pending','09/05/2015','9/7/2015'
union all
select 2,'in progress','09/07/2015','9/25/2015'
union all
select 2,'completed','9/25/2015','10/7/2015'
union all
select 2,'reopened','10/10/2015','10/16/2015'
union all
select 2, 'completed','10/16/2015','11/12/2015'
union all
select 2,'reopened','11/20/2015',null
select * from #test
--below is solution
select a.RequestID, a.Startdate as [PendingStartDate], b.enddate as [FirstCompleteEndDate], c.startdate as [LatestReopenStartDate],
datediff(day,a.startdate,b.enddate)+c.ReopenDays as [days] from #test a
join (
select *, row_number()over(partition by RequestID,RequestStatus order by StartDate) as rid from #test
) as b
on a.RequestID = b.RequestID
join (
select distinct RequestID, RequestStatus, max(StartDate)over(partition by RequestID,RequestStatus) as StartDate,
Sum(Case when enddate is null then datediff(day,startdate,getdate())
when enddate is not null then datediff(day,startdate,enddate)
end)over(partition by RequestID,RequestStatus) as [ReopenDays]
from #test
where RequestStatus = 'reopened'
) as c
on b.RequestID = c.RequestID
where a.RequestStatus ='pending' and b.RequestStatus = 'completed' and b.rid = 1
Result:

Related

Join created table under condition

I am creating a code to join two different tables under a certain condition. The tables look like this
(TABLE 2)
date | deal_code | originator | servicer | random |
-----------------------------------------------------
2011 | 001 | commerzbank | SPV1 | 1 |
2012 | 001 | commerzbank | SPV1 | 12 |
2013 | 001 | commerzbank | SPV1 | 7 |
2013 | 005 | unicredit | SPV2 | 7 |
and another table
(TABLE 1)
date | deal_code | amount |
---------------------------
2011 | 001 | 100 |
2012 | 001 | 100 |
2013 | 001 | 100 |
2013 | 005 | 200 |
I would like to have this as the final result
date | deal_code | amount | originator | servicer | random |
--------------------------------------------------------------
2013 | 001 | 100 | commerzbank | SPV1 | 7 |
2013 | 005 | 200 | unicredit | SPV2 | 7 |
I created the following code
select q1.deal_code, q1.date
from table1 q1
where q1.date = (SELECT MAX(t4.date)
FROM table1 t4
WHERE t4.deal_code = q1.deal_code)
that gives me:
(TABLE 3)
date | deal_code | amount |
---------------------------
2013 | 001 | 100 |
2013 | 005 | 200 |
That is the latest observation for table 1, now I would like to have the originator and servicer information given the deal_code and date. Any suggestion? I hope to have been clear enough. Thanks.
This should do what you are looking for. Please be careful when naming columns. Date is a reserved word and is too ambiguous to be a good name for a column.
declare #Something table
(
SomeDate int
, deal_code char(3)
, originator varchar(20)
, servicer char(4)
, random int
)
insert #Something values
(2011, '001', 'commerzbank', 'SPV1', 1)
, (2012, '001', 'commerzbank', 'SPV1', 12)
, (2013, '001', 'commerzbank', 'SPV1', 7)
, (2013, '005', 'unicredit ', 'SPV2', 7)
declare #SomethingElse table
(
SomeDate int
, deal_code char(3)
, amount int
)
insert #SomethingElse values
(2011, '001', '100')
, (2012, '001', '100')
, (2013, '001', '100')
, (2013, '005', '200')
select x.SomeDate
, x.deal_code
, x.originator
, x.servicer
, x.random
, x.amount
from
(
select s.SomeDate
, s.deal_code
, s.originator
, s.servicer
, s.random
, se.amount
, RowNum = ROW_NUMBER()over(partition by s.deal_code order by s.SomeDate desc)
from #Something s
join #SomethingElse se on se.SomeDate = s.SomeDate and se.deal_code = s.deal_code
) x
where x.RowNum = 1
Looks like this would work:
DECLARE #MaxYear INT;
SELECT #MaxYear = MAX(date)
FROM table1 AS t1
INNER JOIN table2 AS t2
ON t1.deal_code = t2.deal_code;
SELECT t1.date,
t1.deal_code,
t1.amount,
t2.originator,
t2.servicer,
t2.random
FROM table1 AS t1
INNER JOIN table2 AS t2
ON t1.date = #MaxYear
AND t1.deal_code = t2.deal_code;
I agree with Sean Lange about the date column name. His method gets around the dependency on the correlated sub-query, but at the heart of things, you really just need to add an INNER JOIN to your existing query in order to get the amount column into your result set.
select
q2.date,
q2.deal_code,
q1.amount,
q2.originator,
q2.servicer,
q2.random
from
table1 q1
join
table2 q2
on q1.date = q2.date
and q1.deal_code = q2.deal_code
where q1.date = (SELECT MAX(t4.date)
FROM table1 t4
WHERE t4.deal_code = q1.deal_code)

Find records of nearest date SQL

I have a table dbo.X with DateTime column lastUpdated and a code product column CodeProd which may have hundreds of records, with CodeProd duplicated because the table is used as "stock history"
My Stored Procedure has parameter #Date, I want to get all CodeProd nearest to that date so for example if I have:
+----------+--------------+--------+
| CODEPROD | lastUpdated | STATUS |
+----------+--------------+--------+
| 10 | 2-1-2019 | C1 |
| 10 | 1-1-2019 | C2 |
| 10 | 31-12-2019 | C1 |
| 11 | 31-12-2018 | C1 |
| 11 | 30-12-2018 | C1 |
| 12 | 30-8-2018 | C3 |
+----------+--------------+--------+
and #Date= '1-1-2019'
I wanna get:
+----+--------------+------+
| 10 | 1-1-2019 | C2 |
| 11 | 31-12-2018 | C1 |
| 12 | 30-8-2018 | C3 |
+----+--------------+------+
How to find it?
You can use TOP(1) WITH TIES to get one row with nearest date for each CODEPROD which should be less than provided date.
Try like following code.
SELECT TOP(1) WITH TIES *
FROM [YourTableName]
WHERE lastupdated <= #date
ORDER BY Row_number()
OVER (
partition BY [CODEPROD]
ORDER BY lastupdated DESC);
You can use apply :
select distinct t.CODEPROD, t1.lastUpdated, t1.STATUS
from table t cross apply
( select top (1) t1.*
from table t1
where t1.CODEPROD = t.CODEPROD and t1.lastUpdated <= #date
order by t1.lastUpdated desc
) t1;

Date difference for same ID

I ve got a data set similar to
+----+------------+------------+------------+
| ID | Udate | last_code | Ddate |
+----+------------+------------+------------+
| 1 | 05/11/2018 | ACCEPTED | 13/10/2018 |
| 1 | 03/11/2018 | ATTEMPT | 13/10/2018 |
| 1 | 01/11/2018 | INFO | 13/10/2018 |
| 1 | 22/10/2018 | ARRIVED | 13/10/2018 |
| 1 | 15/10/2018 | SENT | 13/10/2018 |
+----+------------+------------+------------+
I m trying to get the date difference for each code on Udate, but for the first date I want to make datedifference between Udate and Ddate.
So I ve been trying:
DATEDIFF(DAY,LAG(Udate) OVER (PARTITION BY Shipment_Number ORDER BY Udate), Udate)
to get the difference between dates and it works so far, but I also need the first date difference between Udate and Ddate.
I was thinking about ISNULL()
Also, at the end I need an average of days between codes as well, usually they keep the same pattern. Sample output data:
+----+------------+------------+------------+------------+
| ID | Udate | last_code | Ddate | Difference |
+----+------------+------------+------------+------------+
| 1 | 05/11/2018 | ACCEPTED | 13/10/2018 | 2 |
| 1 | 03/11/2018 | ATTEMPT | 13/10/2018 | 2 |
| 1 | 01/11/2018 | INFO | 13/10/2018 | 10 |
| 1 | 22/10/2018 | ARRIVED | 13/10/2018 | 7 |
| 1 | 15/10/2018 | SENT | 13/10/2018 | 2 |
+----+------------+------------+------------+------------+
Notice that when there is no previous code, the date diff is between Udate and Ddate.
Would appreciate any idea.
Thank you.
Well, ISNULL is the way to go here.
Since you also want the average difference, you can use a common table expression to get the difference, and query it to get the average:
First, Create and populate sample data (Please save us this step in your future questions)
-- This would not be needed if you've used ISO8601 for date strings (yyyy-mm-dd | yyyymmdd)
SET DATEFORMAT DMY;
DECLARE #T AS TABLE
(
ID int,
UDate date,
last_code varchar(10),
Ddate date
) ;
INSERT INTO #T (ID, Udate, last_code, Ddate) VALUES
(1, '05/11/2018', 'ACCEPTED', '13/10/2018'),
(1, '03/11/2018', 'ATTEMPT' , '13/10/2018'),
(1, '01/11/2018', 'INFO' , '13/10/2018'),
(1, '22/10/2018', 'ARRIVED' , '13/10/2018'),
(1, '15/10/2018', 'SENT' , '13/10/2018');
The cte:
WITH CTE AS
(
SELECT ID,
Udate,
last_code,
Ddate,
DATEDIFF(
DAY,
ISNULL(
LAG(Udate) OVER(PARTITION BY ID ORDER BY Udate),
Ddate
),
UDate
) As Difference
FROM #T
)
The query:
SELECT *, AVG(Difference) OVER(PARTITION BY ID) As AverageDifference
FROM CTE;
Results:
ID Udate last_code Ddate Difference AverageDifference
1 15.10.2018 SENT 13.10.2018 2 4
1 22.10.2018 ARRIVED 13.10.2018 7 4
1 01.11.2018 INFO 13.10.2018 10 4
1 03.11.2018 ATTEMPT 13.10.2018 2 4
1 05.11.2018 ACCEPTED 13.10.2018 2 4

Compare historical rows (LAG rows) and combine changed values to single column

Compare historical rows (LAG rows based on ResultChngDt) and combine changed column values to single column. Looking for help in writing elegant/efficient SQL Server 2016 TSQL Code(without cursors).
I have a table with the structure and data like this:
+----+-------+--------------+---------------+--------+--------+--------------+
| ID | RepID | CollctedDate | CompletedDate | Result | Tcode | ResultChngDt |
+----+-------+--------------+---------------+--------+--------+--------------+
| 1 | 101 | 11/20/2017 | 12/13/2017 | | L-2190 | 12/13/2017 |
| 1 | 101 | 11/22/2017 | 12/15/2017 | POS | L-Afb | 1/5/2018 |
| 1 | 102 | 11/22/2017 | 12/15/2017 | | L-2191 | 12/15/2017 |
| 1 | 102 | 11/22/2017 | 12/15/2017 | POS | L-2192 | 12/31/2017 |
+----+-------+--------------+---------------+--------+--------+--------------+
I need to generate a report/result as follows:
+----+-------+---------------------------+--------------------------+--+
| ID | RepID | Previous | Current | |
+----+-------+---------------------------+--------------------------+--+
| 1 | 101 | CollctedDate:11/20/2017 | CollctedDate:11/22/2017 | |
| | | CompletedDate:12/13/2017 | CompletedDate:12/15/2017 | |
| | | Result: | Result:POS | |
| | | Tcode:L-2190 | Tcode:L-Afb | |
| 1 | 102 | CollctedDate:11/22/2017 | CollctedDate:11/22/2017 | |
| | | CompletedDate:12/15/2017 | CompletedDate:12/15/2017 | |
| | | Result: | Result:POS | |
| | | Tcode:L-2191 | Tcode:L-2192 | |
+----+-------+---------------------------+--------------------------+--+
CREATE TABLE [dbo].[Table1]
(
[ID] INT NULL,
[RepID] INT NULL,
[CollctedDate] DATETIME NULL,
[CompletedDate] DATETIME NULL,
[Result] VARCHAR(3) NULL,
[Tcode] VARCHAR(10) NULL,
[ResultChngDt] DATETIME NULL
) ON [PRIMARY];
GO
INSERT INTO [dbo].[Table1] ([ID], [RepID], [CollctedDate], [CompletedDate], [Result], [Tcode], [ResultChngDt])
VALUES (1, 101, N'11/20/2017', N'12/13/2017', N'', N'L-2190', N'12/13/2017')
, (1, 101, N'11/22/2017', N'12/15/2017', N'POS', N'L-Afb', N'1/5/2018')
, (1, 102, N'11/22/2017', N'12/15/2017', N'', N'L-2191', N'12/15/2017')
, (1, 102, N'11/22/2017', N'12/15/2017', N'POS', N'L-2192', N'12/31/2017')
Here's my query for your question:
WITH cte_LEADLAG AS(
SELECT ID,
RepID,
CollctedDate,
CompletedDate,
Result,
Tcode,
ResultChngDt,
CONCAT('CollectedDate:',CAST(CollctedDate AS DATETIME2), ' CompletedDate:', CAST(CompletedDate AS DATETIME2), ' Result:', Result, ' Tcode', Tcode) AS dates,
LAG(CollctedDate) OVER(PARTITION BY RepID ORDER BY CollctedDate) AS 'LAGCollectedDate' ,
lead(CollctedDate) OVER(PARTITION BY RepID ORDER BY CollctedDate) AS 'LEADCollectedDate',
LAG(CompletedDate) OVER(PARTITION BY RepID ORDER BY CompletedDate) AS 'LAGCompDate' ,
lead(CompletedDate) OVER(PARTITION BY RepID ORDER BY CompletedDate) AS 'LEADcompDate' ,
LEAD(Result) OVER(PARTITION BY RepID ORDER BY CompletedDate) AS 'LEADResult' ,
LEAD(Tcode) OVER(PARTITION BY RepID ORDER BY CompletedDate) AS 'LEADTcode'
FROM #temp
),
cte_FINAL AS(
SELECT distinct ID,
RepID,
CASE WHEN cte.LAGCollectedDate IS NULL THEN CONCAT('CollectedDate:',CAST(CollctedDate AS DATETIME2), ' CompletedDate:', CAST(CompletedDate AS DATETIME2), ' Result:', Result, ' Tcode', Tcode) end AS 'Previous',
CASE WHEN cte.LEADCollectedDate IS not NULL THEN CONCAT('CollectedDate:',CAST(cte.LEADCollectedDate AS DATETIME2), ' CompletedDate:', CAST(LEADcompDate AS DATETIME2), ' Result:', cte.LEADResult, ' Tcode', cte.LEADTcode) end AS 'Current'
FROM cte_LEADLAG AS cte
WHERE cte.LEADCollectedDate IN (SELECT MAX(LEADCollectedDate) FROM cte_LEADLAG WHERE cte_LEADLAG.RepID = cte.RepID))
)
SELECT *
FROM cte_FINAL;
Result:
with data as (
select *, row_number() over (partition by RepID order by ResultChgDt desc) as rn
from dbo.Table1
)
select
from data as d1 left outer join data as d2 on d2.rn = d1.rn + 1
where d1.rn = 1 -- I suppose you only want the two most recent??
This gives you all the data you need in a single row. You can handle report formatting to suit whatever requirements you have in whatever tool you're using for that.

Update All other Records Based on a single record

I have a table with a million records. I need to update some columns which are null based on the existing 'not null' records of a particular id based columns. I've tried with one query, it seems to be working fine but I don't have confidence in it that it will be able to update all those 1 million records exactly the way I need. I'm providing you some sample data how my table looks like.Any help will be appreciated
SELECT * INTO #TEST FROM (
SELECT 1 AS EMP_ID,10 AS DEPT_ID,15 AS ITEM_NBR ,NULL AS AMOUNT,NULL AS ITEM_NME
UNION ALL
SELECT 1,20,16,500,'ABCD'
UNION ALL
SELECT 1,30,17,NULL,NULL
UNION ALL
SELECT 2,10,15,1000,'XYZ'
UNION ALL
SELECT 2,30,16,NULL,NULL
UNION ALL
SELECT 2,40,17,NULL,NULL
) AS A
Sample data:
+--------+---------+----------+--------+----------+
| EMP_ID | DEPT_ID | ITEM_NBR | AMOUNT | ITEM_NME |
+--------+---------+----------+--------+----------+
| 1 | 10 | 15 | NULL | NULL |
| 1 | 20 | 16 | 500 | ABCD |
| 1 | 30 | 17 | NULL | NULL |
| 2 | 10 | 15 | 1000 | XYZ |
| 2 | 30 | 16 | NULL | NULL |
| 2 | 40 | 17 | NULL | NULL |
+--------+---------+----------+--------+----------+
Expected result:
+--------+---------+----------+--------+----------+
| EMP_ID | DEPT_ID | ITEM_NBR | AMOUNT | ITEM_NME |
+--------+---------+----------+--------+----------+
| 1 | 10 | 15 | 500 | ABCD |
| 1 | 20 | 16 | 500 | ABCD |
| 1 | 30 | 17 | 500 | ABCD |
| 2 | 10 | 15 | 1000 | XYZ |
| 2 | 30 | 16 | 1000 | XYZ |
| 2 | 40 | 17 | 1000 | XYZ |
+--------+---------+----------+--------+----------+
I tried this but I'm unable to conclude whether it is updating all the 1 million records properly.
SELECT * FROM #TEST T
inner JOIN #TEST T1 ON T1.EMP_ID=T.EMP_ID
WHERE T1.AMOUNT IS NOT NULL
UPDATE T SET AMOUNT=T1.AMOUNT
FROM #TEST T
inner JOIN #TEST T1 ON T1.EMP_ID=T.EMP_ID
WHERE T1.AMOUNT IS not NULL
I have used UPDATE using inner join
UPDATE T
SET T.AMOUNT = X.AMT,T.ITEM_NME=X.I_N
FROM #TEST T
JOIN
(SELECT EMP_ID,MAX(AMOUNT) AS AMT,MAX(ITEM_NME) AS I_N
FROM #TEST
GROUP BY EMP_ID) X ON X.EMP_ID = T.EMP_ID
SELECT * into #Test1
FROM #TEST
WHERE AMOUNT IS NOT NULL
For records validation run this query first
SELECT T.AMOUNT, T1.AMOUNT, T1.EMP_ID,T1.EMP_ID
FROM #TEST T
inner JOIN #TEST1 T1 ON T1.EMP_ID=T.EMP_ID
WHERE T.AMOUNT IS NULL
Begin Trans
UPDATE T
SET T.AMOUNT=T1.AMOUNT, T.ITEM_NME= = T1.ITEM_NME
FROM #TEST T
inner JOIN #TEST1 T1 ON T1.EMP_ID=T.EMP_ID
WHERE T.AMOUNT IS NULL
rollback
SELECT EMP_ID,MAX(AMOUNT) as AMOUNT MAX(ITEM_NAME) as ITEM_NAME
INTO #t
FROM #TEST
GROUP BY EMP_ID
UPDATE t SET t.AMOUNT = t1.AMOUNT, t.ITEM_NAME = t1.ITEM_NAME
FROM #TEST t INNER JOIN #t t1
ON t.emp_id = t1.emp_id
WHERE t.AMOUNT IS NULL and t.ITEM_NAME IS NULL
Use MAX aggregate function to get amount and item name for each employee and then replace null values of amount and item name with those values. For validation use COUNT function to calculate the number of rows with values of amount and item name as null. If the number of rows is zero then table is updated correctly

Resources