I have a table like this
Pcode LogId ExtDate
------------------------------
p123 2 2021-01-02
p342 3 2021-01-16
p456 4 2021-05-02
p456 5 2021-07-26
p634 6 2021-05-02
p764 7 2021-01-18
p764 8 2021-06-25
I am looking for a query which returns only those rows with column one value exists more than one.
So the output should be like this. Which means we are taking only items at which the Pcode exists more than once
Pcode LogId ExtDate
-----------------------------
p456 4 2021-05-02
p456 5 2021-07-26
p764 7 2021-01-18
p764 8 2021-06-25
I tried using dense_rank, but I got stuck here... can't move any further
select
pcode,
LogId,
extdate,
rn
from
(select
pcode,
L.logid,
extdate,
dense_rank() over (partition by pcode order by L.extdate desc) rn
from
kip_project_master P
inner join
kip_report_extraction_log L on L.LogId = P.LogId) tbl
You can try the below - demo here
select pcode,logid,extdate from
(
select *,count(pcode) over(partition by pcode) cnt from t1
)A where cnt>1
maybe ?
DROP TABLE IF EXISTS #yourtable
CREATE TABLE #yourtable(
Pcode VARCHAR(30) NOT NULL
,LogId INT
,ExtDate DATE
);
INSERT INTO #yourtable(Pcode,LogId,ExtDate) VALUES
('p123',2,'2021-01-02'),('p342',3,'2021-01-16'),('p456',4,'2021-05-02')
,('p456',5,'2021-07-26'),('p634',6,'2021-05-02'),('p764',7,'2021-01-18')
,('p764',8,'2021-06-25');
WITH cte AS
(
SELECT Pcode
FROM #yourtable
GROUP BY Pcode
HAVING (COUNT(Pcode) > 1)
)
SELECT yt.Pcode, yt.LogId, yt.ExtDate
FROM yourtable yt
INNER JOIN
cte ON yt.Pcode = cte.Pcode
Assuming another column is unique, just use exists:
select kpm.*
from kip_project_master kpm
where exists (select 1
from kip_project_master kpm2
where kpm2.pcode = kpm.pcode and kpm2.logid <> kpm.logid
)
order by kpm.pcode, kpm.logid;
In particular, this can take advantage of an index on (pcode, logid), which should make it pretty fast.
you can do this like,
select * from yourtable join (select
pcode,count(1) as cnt from yourtable group by
pcode having COUNT(1)>1)b on a.pcode=b.pcode
Related
declare #t table
(
id int,
SomeNumt int
)
insert into #t
select 1,10
union
select 2,12
union
select 3,3
union
select 4,15
union
select 5,23
select * from #t
the above select returns me the following.
id SomeNumt
1 10
2 12
3 3
4 15
5 23
How do I get the following:
id srome CumSrome
1 10 10
2 12 22
3 3 25
4 15 40
5 23 63
select t1.id, t1.SomeNumt, SUM(t2.SomeNumt) as sum
from #t t1
inner join #t t2 on t1.id >= t2.id
group by t1.id, t1.SomeNumt
order by t1.id
SQL Fiddle example
Output
| ID | SOMENUMT | SUM |
-----------------------
| 1 | 10 | 10 |
| 2 | 12 | 22 |
| 3 | 3 | 25 |
| 4 | 15 | 40 |
| 5 | 23 | 63 |
Edit: this is a generalized solution that will work across most db platforms. When there is a better solution available for your specific platform (e.g., gareth's), use it!
The latest version of SQL Server (2012) permits the following.
SELECT
RowID,
Col1,
SUM(Col1) OVER(ORDER BY RowId ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS Col2
FROM tablehh
ORDER BY RowId
or
SELECT
GroupID,
RowID,
Col1,
SUM(Col1) OVER(PARTITION BY GroupID ORDER BY RowId ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS Col2
FROM tablehh
ORDER BY RowId
This is even faster. Partitioned version completes in 34 seconds over 5 million rows for me.
Thanks to Peso, who commented on the SQL Team thread referred to in another answer.
For SQL Server 2012 onwards it could be easy:
SELECT id, SomeNumt, sum(SomeNumt) OVER (ORDER BY id) as CumSrome FROM #t
because ORDER BY clause for SUM by default means RANGE UNBOUNDED PRECEDING AND CURRENT ROW for window frame ("General Remarks" at https://msdn.microsoft.com/en-us/library/ms189461.aspx)
Let's first create a table with dummy data:
Create Table CUMULATIVESUM (id tinyint , SomeValue tinyint)
Now let's insert some data into the table;
Insert Into CUMULATIVESUM
Select 1, 10 union
Select 2, 2 union
Select 3, 6 union
Select 4, 10
Here I am joining same table (self joining)
Select c1.ID, c1.SomeValue, c2.SomeValue
From CumulativeSum c1, CumulativeSum c2
Where c1.id >= c2.ID
Order By c1.id Asc
Result:
ID SomeValue SomeValue
-------------------------
1 10 10
2 2 10
2 2 2
3 6 10
3 6 2
3 6 6
4 10 10
4 10 2
4 10 6
4 10 10
Here we go now just sum the Somevalue of t2 and we`ll get the answer:
Select c1.ID, c1.SomeValue, Sum(c2.SomeValue) CumulativeSumValue
From CumulativeSum c1, CumulativeSum c2
Where c1.id >= c2.ID
Group By c1.ID, c1.SomeValue
Order By c1.id Asc
For SQL Server 2012 and above (much better performance):
Select
c1.ID, c1.SomeValue,
Sum (SomeValue) Over (Order By c1.ID )
From CumulativeSum c1
Order By c1.id Asc
Desired result:
ID SomeValue CumlativeSumValue
---------------------------------
1 10 10
2 2 12
3 6 18
4 10 28
Drop Table CumulativeSum
A CTE version, just for fun:
;
WITH abcd
AS ( SELECT id
,SomeNumt
,SomeNumt AS MySum
FROM #t
WHERE id = 1
UNION ALL
SELECT t.id
,t.SomeNumt
,t.SomeNumt + a.MySum AS MySum
FROM #t AS t
JOIN abcd AS a ON a.id = t.id - 1
)
SELECT * FROM abcd
OPTION ( MAXRECURSION 1000 ) -- limit recursion here, or 0 for no limit.
Returns:
id SomeNumt MySum
----------- ----------- -----------
1 10 10
2 12 22
3 3 25
4 15 40
5 23 63
Late answer but showing one more possibility...
Cumulative Sum generation can be more optimized with the CROSS APPLY logic.
Works better than the INNER JOIN & OVER Clause when analyzed the actual query plan ...
/* Create table & populate data */
IF OBJECT_ID('tempdb..#TMP') IS NOT NULL
DROP TABLE #TMP
SELECT * INTO #TMP
FROM (
SELECT 1 AS id
UNION
SELECT 2 AS id
UNION
SELECT 3 AS id
UNION
SELECT 4 AS id
UNION
SELECT 5 AS id
) Tab
/* Using CROSS APPLY
Query cost relative to the batch 17%
*/
SELECT T1.id,
T2.CumSum
FROM #TMP T1
CROSS APPLY (
SELECT SUM(T2.id) AS CumSum
FROM #TMP T2
WHERE T1.id >= T2.id
) T2
/* Using INNER JOIN
Query cost relative to the batch 46%
*/
SELECT T1.id,
SUM(T2.id) CumSum
FROM #TMP T1
INNER JOIN #TMP T2
ON T1.id > = T2.id
GROUP BY T1.id
/* Using OVER clause
Query cost relative to the batch 37%
*/
SELECT T1.id,
SUM(T1.id) OVER( PARTITION BY id)
FROM #TMP T1
Output:-
id CumSum
------- -------
1 1
2 3
3 6
4 10
5 15
Select
*,
(Select Sum(SOMENUMT)
From #t S
Where S.id <= M.id)
From #t M
You can use this simple query for progressive calculation :
select
id
,SomeNumt
,sum(SomeNumt) over(order by id ROWS between UNBOUNDED PRECEDING and CURRENT ROW) as CumSrome
from #t
There is a much faster CTE implementation available in this excellent post:
http://weblogs.sqlteam.com/mladenp/archive/2009/07/28/SQL-Server-2005-Fast-Running-Totals.aspx
The problem in this thread can be expressed like this:
DECLARE #RT INT
SELECT #RT = 0
;
WITH abcd
AS ( SELECT TOP 100 percent
id
,SomeNumt
,MySum
order by id
)
update abcd
set #RT = MySum = #RT + SomeNumt
output inserted.*
For Ex: IF you have a table with two columns one is ID and second is number and wants to find out the cumulative sum.
SELECT ID,Number,SUM(Number)OVER(ORDER BY ID) FROM T
Once the table is created -
select
A.id, A.SomeNumt, SUM(B.SomeNumt) as sum
from #t A, #t B where A.id >= B.id
group by A.id, A.SomeNumt
order by A.id
The SQL solution wich combines "ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW" and "SUM" did exactly what i wanted to achieve.
Thank you so much!
If it can help anyone, here was my case. I wanted to cumulate +1 in a column whenever a maker is found as "Some Maker" (example). If not, no increment but show previous increment result.
So this piece of SQL:
SUM( CASE [rmaker] WHEN 'Some Maker' THEN 1 ELSE 0 END)
OVER
(PARTITION BY UserID ORDER BY UserID,[rrank] ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS Cumul_CNT
Allowed me to get something like this:
User 1 Rank1 MakerA 0
User 1 Rank2 MakerB 0
User 1 Rank3 Some Maker 1
User 1 Rank4 Some Maker 2
User 1 Rank5 MakerC 2
User 1 Rank6 Some Maker 3
User 2 Rank1 MakerA 0
User 2 Rank2 SomeMaker 1
Explanation of above: It starts the count of "some maker" with 0, Some Maker is found and we do +1. For User 1, MakerC is found so we dont do +1 but instead vertical count of Some Maker is stuck to 2 until next row.
Partitioning is by User so when we change user, cumulative count is back to zero.
I am at work, I dont want any merit on this answer, just say thank you and show my example in case someone is in the same situation. I was trying to combine SUM and PARTITION but the amazing syntax "ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW" completed the task.
Thanks!
Groaker
Above (Pre-SQL12) we see examples like this:-
SELECT
T1.id, SUM(T2.id) AS CumSum
FROM
#TMP T1
JOIN #TMP T2 ON T2.id < = T1.id
GROUP BY
T1.id
More efficient...
SELECT
T1.id, SUM(T2.id) + T1.id AS CumSum
FROM
#TMP T1
JOIN #TMP T2 ON T2.id < T1.id
GROUP BY
T1.id
Try this
select
t.id,
t.SomeNumt,
sum(t.SomeNumt) Over (Order by t.id asc Rows Between Unbounded Preceding and Current Row) as cum
from
#t t
group by
t.id,
t.SomeNumt
order by
t.id asc;
Try this:
CREATE TABLE #t(
[name] varchar NULL,
[val] [int] NULL,
[ID] [int] NULL
) ON [PRIMARY]
insert into #t (id,name,val) values
(1,'A',10), (2,'B',20), (3,'C',30)
select t1.id, t1.val, SUM(t2.val) as cumSum
from #t t1 inner join #t t2 on t1.id >= t2.id
group by t1.id, t1.val order by t1.id
Without using any type of JOIN cumulative salary for a person fetch by using follow query:
SELECT * , (
SELECT SUM( salary )
FROM `abc` AS table1
WHERE table1.ID <= `abc`.ID
AND table1.name = `abc`.Name
) AS cum
FROM `abc`
ORDER BY Name
I have a table like
Id WID AID DateValue
1 1 12 2015-07-10 15:14:46.770
2 1 13 2015-07-10 14:14:46.770
3 2 13 2015-07-10 13:14:46.770
4 2 13 2015-07-10 12:14:46.770
5 2 13 2015-07-10 11:14:46.770
Now, I want to get the Id value by grouping WIDAND AID, then taking the MAX value from DateValue.
The desired output is
Output:
Id
1
2
3
I tried something like this
SELECT Id, MAX(DateValue)
FROM Table1
GROUP BY WID, AID`
Though I don't want DateValue in the select but it is fine.
Can anyone help me on this
I think you want a query like this:
SELECT Id --or *
FROM (
SELECT *
, ROW_NUMBER() OVER (PARTITION BY WID, AID ORDER BY DateValue DESC) AS seqNum
FROM yourTable) dt
WHERE (SeqNum =1);
You can use a correlated subquery like so:
SELECT Id FROM Table1 t1
WHERE NOT EXISTS (
SELECT 1 FROM Table1 t2
WHERE t1.WID = t2.WID AND t1.AID = t2.AID AND t1.DateValue < t2.DateValue
)
I'm struggling to find if this is possible to use SQL Server 2008 to assign a sequence without having to use cursors. Let's say I have the following table which defines a driver's driving route going from one location to another (null means he is going from home):
RouteID SourceLocationID DestinationLocationID DriverID Created Updated
------- ---------------- --------------------- -------- ------- -------
1 NULL 219 1 10:20 10:23
2 219 266 1 10:21 10:24
3 266 NULL 1 10:22 10:25
4 NULL 54 2 10:23 10:26
5 54 NULL 2 10:24 10:27
6 NULL 300 1 10:25 10:28
7 300 NULL 1 10:26 10:29
I want to group the records between the rows where sourceLID is NULL and the destinationLID is null, so I get the following (generating a sequence number for each grouping set):
DriverID DestinationLocationID TripNumber
-------- --------------------- ----------
1 219 1 (his first trip)
1 266 1
1 300 2 (his second trip)
2 54 1
Is there a way I could use GROUP BY here rather than cursors?
a quick try:
with cte as
( select DestinationLocationID
, DriverID
, tripid = row_number()
over ( partition by driverid
order by DestinationLocationID)
from table1
where sourcelocationid is NULL
UNION ALL
select table1.DestinationLocationID
, table1.DriverID
, cte.tripid
from table1
join cte on table1.SourceLocationID=cte.DestinationLocationID
and table1.DriverID=cte.DriverID
where cte.DestinationLocationID is not null
)
select * from cte
Try this:
select driverid, destinationlocationid, count(destinationlocationid) from
(
select driverid, destinationlocationid from table1 where sourcelocationid is NULL
union all
select driverid, sourcelocationid from table1 where destinationlocationid is NULL
)A group by driverid, destinationlocationid
Try this,
Declare #t table(RouteID int, SourceLocationID int,DestinationLocationID int
,DriverID int,Created time, Updated time)
insert into #t
values(1, NULL, 219, 1, '10:20','10:23'),
(2 ,219,266, 1, '10:21','10:24'),
(3,266, NULL, 1, '10:22','10:25'),
(4, NULL, 54, 2, '10:23','10:26'),
(5,54, NULL, 2, '10:24','10:27'),
(6,NULL,300, 1, '10:25','10:28'),
(7,300,NULL, 1, '10:26','10:29')
;
WITH CTE
AS (
SELECT *
,ROW_NUMBER() OVER (
PARTITION BY DriverID ORDER BY Created
) RN
FROM #t
)
,CTE1
AS (
SELECT *
,1 TripNumber
FROM CTE
WHERE RN = 1
UNION ALL
SELECT A.*
,CASE
WHEN A.SourceLocationID IS NULL
THEN B.TripNumber + 1
ELSE B.TripNumber
END
FROM CTE1 B
INNER JOIN CTE A ON B.DriverID = A.DriverID
WHERE A.RN > B.RN
)
SELECT DISTINCT DestinationLocationID
,DriverID
,TripNumber
FROM CTE1
WHERE DestinationLocationID IS NOT NULL
ORDER BY DriverID
Use a correlated sub-query to count previous trips, plus 1 to get this trip number.
select DriverID,
DestinationLocationID,
(select count(*) + 1
from routes t2
where t1.DriverID = t2.DriverID
and t1.RouteID > t2.RouteID
and DestinationLocationID IS NULL) as TripNumber
from routes t1
where DestinationLocationID IS NOT NULL
order by DriverID, DestinationLocationID;
Executes like this:
SQL>select DriverID,
SQL& DestinationLocationID,
SQL& (select count(*) + 1
SQL& from routes t2
SQL& where t1.DriverID = t2.DriverID
SQL& and t1.RouteID > t2.RouteID
SQL& and DestinationLocationID IS NULL) as TripNumber
SQL&from routes t1
SQL&where DestinationLocationID IS NOT NULL
SQL&order by DriverID, DestinationLocationID;
DriverID DestinationLocationID TripNumber
=========== ===================== ============
1 219 1
1 266 1
1 300 2
2 54 1
4 rows found
How can I update row U with the same ID2 and latest date. I am able to write the select clause:
SELECT ID2
, MAX(Date)
FROM TABLE
GROUP BY ID2
but I have problem with update clause.
I have table:
ID1 |ID2 |Date |U
1 1 2015-02-18 NULL
2 1 2015-02-11 NULL
3 2 2015-02-17 NULL
4 2 2015-02-14 NULL
5 2 2015-02-11 NULL
6 3 2015-02-14 NULL
7 3 2015-02-10 NULL
What I want to achive:
ID1 |ID2 |Date |U
1 1 2015-02-18 Update
2 1 2015-02-11 NULL
3 2 2015-02-17 Update
4 2 2015-02-14 NULL
5 2 2015-02-11 NULL
6 3 2015-02-14 Update
7 3 2015-02-10 NULL
I will do this using CTE with Row_Number window function
;with cte as
(
select ID1 ,ID2 ,Date ,U, Row_Number() over(partition by ID2 order by Date desc) rn
From Yourtable
)
update Cte set U = 'Update'
where RN=1
When there is a tie in max date per ID2 then use Dense_rank to update both the records.
;with cte as
(
select ID1 ,ID2 ,Date ,U, Dense_Rank() over(partition by ID2 order by Date desc) rn
From Yourtable
)
update Cte set U = 'Update'
where RN=1
One approach would be to use your SELECT...MAX query to filter the TABLE. Something like this;
UPDATE T SET U = 'UPDATE'
FROM T JOIN (
SELECT ID2
, MAX(Date) AS MaxDate
FROM TABLE
GROUP BY ID2) AS X ON X.ID2 = T.ID2 AND X.MaxDate = T.Date
One point to note about this approach is that if there is more than 1 record with the max Date per ID2 then all records with the max Date will be updated.
interesting way to achieve this:
UPDATE T1
SET T1.U='Update'
FROM TestTable T1
WHERE 0=(SELECT COUNT(1) FROM TestTable T2 WHERE T1.ID2=T.ID2 AND T1.Date<T2.Date)
I had a table like
ID UserID rupees time
1 1 200 2014-01-05
---------------------------------
2 1 500 2014-04-06
----------------------------------
3 2 10 2014-05-05
----------------------------------
4 2 20 2014-05-06
----------------------------------
I want the output lie
ID UserID Rupees time CumulativeSum
1 1 200 2014-01-05 200
-------------------------------------------------
2 1 500 2014-04-06 700
-------------------------------------------------
3 2 10 2014-05-06 10
-------------------------------------------------
4 2 20 2014-05-06 30
---------------------------------------------------
How can i get this table as purput
Please try using CTE:
;With T as(
select
*,
ROW_NUMBER() over(partition by UserId order by [time]) RN
from tbl
)
select
UserID,
rupees,
[time],
(select SUM(rupees)
from T b
where b.UserID=a.UserID and b.RN<=a.RN) CumulativeSum
from T a
For records with column value time increasing, try the below query:
select
UserID,
rupees,
[time],
(select SUM(rupees)
from tbl b
where b.UserID=a.UserID and b.[time]<=a.[time]) CumulativeSum
from tbl a
For SQL Server 2012 or later, you can use SUM() with an OVER clause that specifies a ROW clause:
declare #t table (ID int,UserID int,rupees int,[time] date)
insert into #t(ID,UserID,rupees,[time]) values
(1,1,200,'20140105'),
(2,1,500,'20140406'),
(3,2, 10,'20140505'),
(4,2, 20,'20140506')
select
*,
SUM(rupees) OVER (
PARTITION BY UserID
ORDER BY id /* or time? */
ROWS BETWEEN
UNBOUNDED PRECEDING AND
CURRENT ROW)
as total
from #t
Result:
ID UserID rupees time total
----------- ----------- ----------- ---------- -----------
1 1 200 2014-01-05 200
2 1 500 2014-04-06 700
3 2 10 2014-05-05 10
4 2 20 2014-05-06 30
DECLARE #t table (UserID INT,rupees INT,DateKey Date )
INSERT INTO #t VALUES
(1,200,'2014-01-05'),
(2,300,'2014-01-06'),
(2,800,'2014-03-06')
select UserID,
rupees,
DateKey,
(SELECT SUM(rupees)from #t t
where t.rupees <= tt.rupees) from #t tt
GROUP BY UserID,rupees,DateKey
Hope this too helps you.
DECLARE #tab TABLE (id INT,userId INT,rupees INT,[time] Date)
INSERT INTO #tab VALUES
(1,1,200 ,'2014-01-05'),
(2,1,500 ,'2014-04-06'),
(3,2,10 ,'2014-05-05'),
(4,2,20 ,'2014-05-06')
SELECT LU.id,LU.userId,LU.rupees,LU.time,SUM(b.rupees) CumulativeSum
FROM (SELECT *,ROW_NUMBER() OVER (PARTITION BY userId ORDER BY [time]) R FROM #tab) B
JOIN (SELECT *,ROW_NUMBER() OVER (PARTITION BY userId ORDER BY [time]) R FROM #tab) LU
ON B.userId = LU.userId AND B.R <= LU.R
GROUP BY LU.id,LU.userId,LU.rupees,LU.time
Result
I am assuming that you are not using SQL Server 2012, which provides the cumulative sum function. The other answers use some form of the row_number() function, but these seems totally unnecessary. I usually approach cumulative sums using correlated subqueries:
select ID, UserID, rupees, [time],
(select sum(rupees)
from table t2
where t2.UserId = t.UserId and
t2.ID <= t.ID
) as CumulativeSum
from table t;
This requires having a column that uniquely identifies each row, and that seems to be the purpose of id. For performance, I would want to have an index on table(UserId, ID, rupees).
select *, SUM(rupees) OVER (
PARTITION BY UserID
ORDER BY id) as CumSum from #tbl