Can't find largest duplicate value in SQL Server - sql

I have some multiple duplicate data in my table what I am trying to do I want to fetch only the largest values from the duplicate data.
I added an image for example from which I want to get only the last two row data because the first row's first column value is lower than the others and service ids are same I am trying to do this by counting the data but can't get the final result.
Currently I am using this query to count data
SELECT
ServiceId, COUNT(*) Count_Duplicate
FROM
TestDeleteTable
GROUP BY
ServiceId
HAVING
COUNT(*) > 1
ORDER BY
COUNT(*) DESC
Thanks for any help

Following query should work for you.
SELECT ServiceId,RowId FROM
(
SELECT *, COUNT(ServiceId) OVER(PARTITION BY ServiceId ORDER BY ROWID) CT, ROW_NUMBER() OVER(PARTITION BY ServiceId ORDER BY ROWID) RN
FROM TestDeleteTable
)T
WHERE T.RN> 1 AND T.CT > 1
DEMO
Another approach can be
;WITH CTE AS
(
SELECT ServiceId, MIN(ROWID) M
FROM TestDeleteTable
GROUP BY ServiceId
HAVING COUNT(*) > 1
)
SELECT * FROM TestDeleteTable T
WHERE EXISTS
(
SELECT 1 FROM CTE C WHERE C.ServiceId=T.ServiceId AND T.ROWID > C.M
)
Or simply with a INNER JOIN with CTE like following.
;WITH CTE AS
(
SELECT ServiceId, MIN(ROWID) MinValue, Count(ServiceId) CountService
FROM #t
GROUP BY ServiceId
HAVING COUNT(*) > 1
)
SELECT T.* FROM #T T
INNER JOIN CTE C ON T.ServiceId= C.ServiceId
WHERE C.CountService> 1 AND T.ROWID > C.MinValue

Related

Random records in Oracle table based on conditions

I have a Oracle table with the following columns
Table Structure
In a query I need to return all the records with CPER>=40 which is trivial. However, apart from CPER>=40 I need to list 5 random records for each CPID.
I have attached a sample list of records. However, in my table I have around 50,000 records.
Appreciate if you can help.
Oracle solution:
with CTE as
(
select t1.*,
row_number() over(order by DBMS_RANDOM.VALUE) as rn -- random order assigned
from MyTable t1
where CPID <40
)
select *
from CTE
where rn <=5 -- pick 5 at random
union all
select t2.*, null
from my_table t2
where CPID >= 40
SQL Server:
with CTE as
(
select t1.*,
row_number() over(order by newid()) as rn -- random order assigned
from MyTable t1
where CPID <40
)
select *
from CTE
where rn <=5 -- pick 5 at random
union all
select t2.*, null
from my_table t2
where CPID >= 40
How about something like this...
SELECT *
FROM (SELECT CID,
CVAL,
CPID,
CPER,
Row_number() OVER (partition BY CPID ORDER BY CPID ASC ) AS RN
FROM Table) tmp
WHERE CPER>=40 OR pids <= 5
However, this is not random.
Assuming that you want five additional random records, you can do:
select t.*
from (select t.*,
row_number() over (partition by cpid,
(case when cper >= 40 then 1 else 2 end)
order by dbms_random.value
) as seqnum
from t
) t
where seqnum <= 5 or cper >= 40;
The row_number() is enumerating the rows for each cpid in two groups -- based on the cper value. The outer where is taking all cper values in the range you want as well as five from the other group.

Get the maximum values of column B per each distinct value of column A sql

I have this table:
I am trying to pull all records from this table for the max value in the DIST_NO column for every distinct ID in the left most column, but I still want to pull every record for each ID in which there are different Product_ID's as well.
I tried partitioning and using row_number, but I am having trouble at the moment.
Here are my desired results:
This is what my code looks like currently:
select *
from
(SELECT *,
ROW_NUMBER() OVER (PARTITION BY ID ORDER BY DIST_NO DESC) RN
FROM Table) V
WHERE RN<=3
you want the max(DIST_NO) for each ID, product_ID?
If so, you can:
SELECT
ID, product_ID, max(DIST_NO)
from table
group by ID, product_ID
If you want the detail rows related to the max row, you just need to join it back to your table:
Select
t.ID, max_dist_no, TRANSaction_ID , LINE_NO , PRODUCT_ID
from
table t inner join
(SELECT
ID, max(DIST_NO) as max_dist_no
from table
group by ID) mx on
t.ID = mx.ID and
t.DIST_NO = max_DIST_NO
Try
SELECT MT.ID
, MT.DIST_NO
, MT.TRANS_ID
, MT.LINE_NO
, MT.PRODUCT_ID
FROM MYTABLE MT
INNER JOIN (
SELECT T.ID, MAX(T.DIST_NO) as DIST_NO FROM MYTABLE T
GROUP BY T.ID
) MAX_MT ON MT.Id = MAX_MT.ID AND MT.DIST_NO = MAX_MT.DIST_NO
The sub query returns each combination of ID and Max value of DIST_NO:
SELECT T.ID, MAX(T.DIST_NO) as DIST_NO FROM MYTABLE T
GROUP BY T.ID
Joining this back to your original table will basically filter your original data-set by only these combinations of values.
Tested on PostgreSQL:
WITH t1 AS (
SELECT id, product_id, MAX(dist_no) AS dist_no
FROM test
GROUP BY 1,2)
SELECT t1.id, t1.dist_no, t2.trans_id, t2.line_no, t1.product_id
FROM test t2, t1
WHERE t1.id=t2.id AND t1.product_id=t2.product_id AND t1.dist_no=t2.dist_no
Use rank() or dense_rank():
select t.*
from (SELECT t.*
RANK() OVER (PARTITION BY ID ORDER BY DIST_NO DESC) as seqnum
FROM Table t
) t
WHERE seqnum = 1;
This is almost a literal translation of your request:
I am trying to pull all records from this table for the max value in
the DIST_NO column for every distinct ID in the left most column.
you can try something like this one :). (But is your result correct? I think there is little mistake in TRANS_ID...)
DECLARE #ExampleTable TABLE
(ID INT,
DIST_NO INT,
TRANS_ID INT,
LINE_NO INT,
PRODUCT_ID INT)
INSERT INTO #ExampleTable
( ID, DIST_NO, TRANS_ID,LINE_NO, PRODUCT_ID )
VALUES ( 102657, 1, 1105365, 1, 109119 ),
( 102657, 1, 1105366, 2, 109114 ),
( 102657, 2, 1105365, 1, 109119 ),
( 102657, 2, 1105366, 2, 109114 ),
( 104371, 1, 1190538, 1, 110981 ),
( 104371, 2, 1190538, 1, 110981 )
;WITH CTE AS ( SELECT DISTINCT ID, LINE_NO
FROM #ExampleTable)
SELECT a.ID,
x.DIST_NO,
x.TRANS_ID,
x.LINE_NO,
x.PRODUCT_ID
FROM CTE a
CROSS APPLY (SELECT TOP 1 *
FROM #ExampleTable f
WHERE a.ID = f.ID AND
a.LINE_NO = f. LINE_NO
ORDER BY DIST_NO DESC) x

Getting top 2 rows in each group without row_number() in SQL Server

I am looking for a simple query to get result of 2 rows with latest invoice date in each group. Although this task can be accomplished by a row_number() that you can see in below code ,I need an alternative to this with minimum complexity.
Code :
create table #tt
(
id int,
invoiceDT datetime
)
insert into #tt
values(1,'01-01-2016 00:12'),(1,'01-02-2016 06:16'),(1,'01-01-2016 00:16')
,(2,'01-01-2016 01:12'),(2,'04-02-2016 06:16'),(2,'01-06-2016 00:16')
select *
from (
SELECT id,invoiceDT,row_number() over(partition by id order by invoiceDT desc) as rownum
FROM #tt
)tmp
where rownum <=2
I need same result that is returned by above query
Please suggest an alternative.
Strange request, but here you go:
WITH CTE as
(
SELECT distinct id FROM #tt t1
)
SELECT x.*
FROM CTE
CROSS APPLY
(
SELECT top 2 *
FROM #tt
WHERE CTE.id = id
ORDER BY invoiceDT desc
) x

SQL query: how to distinct count of a column group by another column

In my table I need to know if each ID has one and only one ID_name. How can I write such query?
I tried:
select ID, count(distinct ID_name) as count_name
from table
group by ID
having count_name > 1
But it takes forever to run.
Any thoughts?
select ID
from YourTable
group by
ID
having count(distinct ID_name) > 1
or
select *
from YourTable yt1
where exists
(
select *
from YourTable yt2
where yt1.ID = yt2.ID
and yt1.ID_Name <> yt2.ID_Name
)
Now, most ID columns are defined as primary key and are unique. So in a regular database you'd expect both queries to return an empty set.
select tt.ID,max(tt.myRank)
from
(
select
ip.ID,ip.ID_name,
ROW_Number() over (partition by ip.ID,ip.ID_nameorder by ip.ID) as myRank
from YourTable ip
) tt
group by tt.ID
This gives you every ID with it's total number of ID_Name
If you want only those ID's which have more than one name associated just add a where clause
e.g.
select tt.ID,max(tt.myRank)
from
(
select
ip.ID,ip.ID_name,
ROW_NUMBER() over (partition by ip.ID,ip.ID_nameorder by ip.ID) as myRank
from YourTable ip
) tt
**where tt.myRank > 1**
group by tt.ID

How do I get records before and after given one?

I have the following table structure:
Id, Message
1, John Doe
2, Jane Smith
3, Error
4, Jane Smith
Is there a way to get the error record and the surrounding records? i.e. find all Errors and the record before and after them.
;WITH numberedlogtable AS
(
SELECT Id,Message,
ROW_NUMBER() OVER (ORDER BY ID) AS RN
FROM logtable
)
SELECT Id,Message
FROM numberedlogtable
WHERE RN IN (SELECT RN+i
FROM numberedlogtable
CROSS JOIN (SELECT -1 AS i UNION ALL SELECT 0 UNION ALL SELECT 1) n
WHERE Message='Error')
WITH err AS
(
SELECT TOP 1 *
FROM log
WHERE message = 'Error'
ORDER BY
id
),
p AS
(
SELECT TOP 1 l.*
FROM log
WHERE id <
(
SELECT id
FROM err
)
ORDER BY
id DESC
)
SELECT TOP 3 *
FROM log
WHERE id >
(
SELECT id
FROM p
)
ORDER BY
id
Adapt this routine to pick out your target.
DECLARE #TargetId int
SET #TargetId = 3
select *
from LogTable
where Id in (-- "before"
select max(Id)
from LogTable
where Id < #TargetId
-- target
union all select #TargetId
-- "after"
union all select min(Id)
from LogTable
where Id > #TargetId)
select id,messag from
(Select (Row_Number() over (order by ID)) as RNO, * from #Temp) as A,
(select SubRNO-1 as A,
SubRNO as B,
SubRNO+1 as C
from (Select (Row_Number() over (order by ID)) as SubRNO, * from #Temp) as C
where messag = 'Error') as B
where A.RNO = B.A or A.RNO = B.B or A.RNO = B.C
;WITH Logs AS
(
SELECT ROW_NUMBER() OVER (ORDER BY id), id, message as rownum FROM LogTable lt
)
SELECT curr.id, prev.id, next.id
FROM Logs curr
LEFT OUTER JOIN Logs prev ON curr.rownum+1=prev.rownum
RIGHT OUTER JOIN Logs next ON curr.rownum-1=next.rownum
WHERE curr.message = 'Error'
select id, message from tbl where id in (
select id from tbl where message = "error"
union
select id-1 from tbl where message = "error"
union
select id+1 from tbl where message = "error"
)
Get fixed number of rows before & after target
Using UNION for a simple, high performance query (I found selected answer WITH query above to be extremely slow)
Here is a high performance alternative to the WITH top selected answer, when you know an ID or specific identifier for a given record, and you want to select a fixed number of records BEFORE and AFTER that record. Requires a number field for ID, or something like date that can be sorted ascending / descending.
Example: You want to select the 10 records before and after a specific error was recorded, you know the error ID, and can sort by date or ID.
The following query gets (inclusive) the 1 result above, the identified record itself, and the 1 record below. After the UNION, the results are sorted again in descending order.
SELECT q.*
FROM(
SELECT TOP 2
id, content
FROM
the_table
WHERE
id >= [ID]
ORDER BY id ASC
UNION
SELECT TOP 1
id, content
FROM
the_table
WHERE
id < [ID]
ORDER BY id DESC
) q
ORDER BY q.id DESC