How to use row_number() in SQL Server - sql-server

I want to update row data where the row_number of the column (p_id) is 1.. but this syntax is providing error:
update app1
set p_id = 1
where Row_Number() = 1 over(p_id)

You can't use ROW_NUMBER() directly - you need to e.g. use a CTE (Common Table Expression) for that:
;WITH DataToUpdate AS
(
SELECT
SomeID,
p_id,
ROW_NUMBER() OVER(ORDER BY .......) AS 'RowNum'
FROM
dbo.app1
)
UPDATE DataToUpdate
SET p_id = 1
WHERE
RowNum = 1
In order to use the ROW_NUMBER function, you also need at least an ORDER BY clause to define an order by which the rows are ordered.
From your question, it's not very clear what criteria (column) you want to order by to determine your ROW_NUMBER(), and it's also not clear what kind of column there is to uniquely identify a row (so that the UPDATE can be applied)

This will update only the first employee of that age. May be used as a lottery type logic
create table emp(name varchar(3),Age int, Salary int, IncentiveFlag bit)
insert into emp values('aaa',23,90000,0);
insert into emp values('bbb',22,50000,0);
insert into emp values('ccc',63,60000,0);
insert into emp values('ddd',53,50000,0);
insert into emp values('eee',23,80000,0);
insert into emp values('fff',53,50000,0);
insert into emp values('ggg',53,50000,0);
update A
set IncentiveFlag=1
from
(
Select row_number() over (partition by Age order by age ) AS SrNo,* from emp
)A
where A.SrNo=1

TO Delete duplicates ;WITH CTE(Name,Address1,Phone,RN)
AS
(
SELECT Name,Address1,Phone,
ROW_NUMBER() OVER(PARTITION BY Name ORDER BY Name) AS RN
)
DELETE FROM CTE WHERE RN > 1

Related

row number without using the ROW_NUMBER window function

Suppose you have a table with non-unique values such as this:
CREATE TABLE accounts ( fname VARCHAR(20), lname VARCHAR(20))
GO
INSERT accounts VALUES ('Fred', 'Flintstone')
INSERT accounts VALUES ('Fred', 'Flintstone')
INSERT accounts VALUES ('Fred', 'Flintstone')
SELECT * FROM accounts
GO
Now using a ROW_NUMBER function, you can get a unique incrementing row number.
select *, ROW_NUMBER() over(order by (select null)) as rn
from accounts
But how do we this without using a ROW_NUMBER function. I tried giving each row a unique ID using NEWID() and then counting the rows as given below but it did not work as it gives me a non-unique number which does not start with 1.
Note that I do not want to alter the table to add a new column.
;with cte as
(select *
from accounts as e
cross apply (select newid()) as a(id)
)
select *, (select count(*)+1 from cte as c1 where c.id > c1.id) as rn
from cte as c
order by rn
SQL Fiddle for toying around is http://sqlfiddle.com/#!18/c270f/3/0
The following demonstrates why your code fails, but does not provide an alternative to Row_Number().
A column, TopId, is added to the final select that should get the minimum value generated by NewId() and report it in every row. Instead, a new value is generated for each row.
-- Sample data.
declare #Samples as Table ( FName VarChar(20), LName VarChar(20) );
insert into #Samples ( FName, LName ) values
( 'Fred', 'Flintstone' ), ( 'Fred', 'Flintstone' ), ( 'Fred', 'Flintstone' );
select * from #Samples;
-- Cross apply NewId() in a CTE.
;with cte as
( select *
from #Samples as S
cross apply ( select NewId() ) as Ph( Id ) )
select *, ( select count(*) from cte as c1 where c1.Id >= c.Id ) as RN,
-- The following column should output the minimum Id value from the table for every row.
-- Instead, it generates a new unique identifier for each row.
( select top 1 id from cte order by id ) as TopId
from cte as c
order by RN;
The execution plan shows that the CTE is treated as a view that is being evaluated repeatedly, thus generating conflicting Id values.
How about this:
SELECT
src.*,
SUM(DummyVal) OVER(ROWS BETWEEN UNBOUNDED PRECEDING AND CURRENT ROW) AS RowId
FROM (
SELECT a.*, 1 AS DummyVal
FROM MyTable a
) src
It's still a window function, though, not sure if that matters.
Fiddle me this
You can create an function yourself to compute the row_number,
In this example, I had to calculate an index for a lesson within a course.
Window Function version:
SELECT *, ROW_NUMBER() OVER(PARTITION BY courseId) AS row_num FROM lessons;
I created helper-function, to compute the row_number without window function:
DELIMITER $$
CREATE FUNCTION getRowNumber (lessonId int, courseId int)
RETURNS int
DETERMINISTIC
BEGIN
DECLARE count int;
select count(l2.id) into count from lessons l2 where l2.courseId=courseId
and l2.id<=lessonId;
RETURN count;
END$$
DELIMITER ;
so, the final query is:
SELECT l.*, getRowNumber(l.id,l.courseId) as row_num FROM lessons l;
got the same result as the first query!
MySQL:
SELECT #rownum := #rownum + 1 AS rank, a.*
FROM accounts a,(SELECT #rownum := 0) r;
In ORACLE it would simply be
SELECT ROWNUM, a.*
FROM accounts a;
Both without window

Oracle: Delete Duplicate Rows, Comparison Excluding ID Column [duplicate]

I'm testing something in Oracle and populated a table with some sample data, but in the process I accidentally loaded duplicate records, so now I can't create a primary key using some of the columns.
How can I delete all duplicate rows and leave only one of them?
Use the rowid pseudocolumn.
DELETE FROM your_table
WHERE rowid not in
(SELECT MIN(rowid)
FROM your_table
GROUP BY column1, column2, column3);
Where column1, column2, and column3 make up the identifying key for each record. You might list all your columns.
From Ask Tom
delete from t
where rowid IN ( select rid
from (select rowid rid,
row_number() over (partition by
companyid, agentid, class , status, terminationdate
order by rowid) rn
from t)
where rn <> 1);
(fixed the missing parenthesis)
From DevX.com:
DELETE FROM our_table
WHERE rowid not in
(SELECT MIN(rowid)
FROM our_table
GROUP BY column1, column2, column3...) ;
Where column1, column2, etc. is the key you want to use.
DELETE FROM tablename a
WHERE a.ROWID > ANY (SELECT b.ROWID
FROM tablename b
WHERE a.fieldname = b.fieldname
AND a.fieldname2 = b.fieldname2)
Solution 1)
delete from emp
where rowid not in
(select max(rowid) from emp group by empno);
Solution 2)
delete from emp where rowid in
(
select rid from
(
select rowid rid,
row_number() over(partition by empno order by empno) rn
from emp
)
where rn > 1
);
Solution 3)
delete from emp e1
where rowid not in
(select max(rowid) from emp e2
where e1.empno = e2.empno );
create table t2 as select distinct * from t1;
You should do a small pl/sql block using a cursor for loop and delete the rows you don't want to keep. For instance:
declare
prev_var my_table.var1%TYPE;
begin
for t in (select var1 from my_table order by var 1) LOOP
-- if previous var equal current var, delete the row, else keep on going.
end loop;
end;
To select the duplicates only the query format can be:
SELECT GroupFunction(column1), GroupFunction(column2),...,
COUNT(column1), column1, column2...
FROM our_table
GROUP BY column1, column2, column3...
HAVING COUNT(column1) > 1
So the correct query as per other suggestion is:
DELETE FROM tablename a
WHERE a.ROWID > ANY (SELECT b.ROWID
FROM tablename b
WHERE a.fieldname = b.fieldname
AND a.fieldname2 = b.fieldname2
AND ....so on.. to identify the duplicate rows....)
This query will keep the oldest record in the database for the criteria chosen in the WHERE CLAUSE.
Oracle Certified Associate (2008)
create table abcd(id number(10),name varchar2(20))
insert into abcd values(1,'abc')
insert into abcd values(2,'pqr')
insert into abcd values(3,'xyz')
insert into abcd values(1,'abc')
insert into abcd values(2,'pqr')
insert into abcd values(3,'xyz')
select * from abcd
id Name
1 abc
2 pqr
3 xyz
1 abc
2 pqr
3 xyz
Delete Duplicate record but keep Distinct Record in table
DELETE
FROM abcd a
WHERE ROWID > (SELECT MIN(ROWID) FROM abcd b
WHERE b.id=a.id
);
run the above query 3 rows delete
select * from abcd
id Name
1 abc
2 pqr
3 xyz
This blog post was really helpful for general cases:
If the rows are fully duplicated (all values in all columns can have copies) there are no columns to use! But to keep one you still need a unique identifier for each row in each group.
Fortunately, Oracle already has something you can use. The rowid.
All rows in Oracle have a rowid. This is a physical locator. That is, it states where on disk Oracle stores the row. This unique to each row. So you can use this value to identify and remove copies. To do this, replace min() with min(rowid) in the uncorrelated delete:
delete films
where rowid not in (
select min(rowid)
from films
group by title, uk_release_date
)
The Fastest way for really big tables
Create exception table with structure below:
exceptions_table
ROW_ID ROWID
OWNER VARCHAR2(30)
TABLE_NAME VARCHAR2(30)
CONSTRAINT VARCHAR2(30)
Try create a unique constraint or primary key which will be violated by the duplicates. You will get an error message because you have duplicates. The exceptions table will contain
the rowids for the duplicate rows.
alter table add constraint
unique --or primary key
(dupfield1,dupfield2) exceptions into exceptions_table;
Join your table with exceptions_table by rowid and delete dups
delete original_dups where rowid in (select ROW_ID from exceptions_table);
If the amount of rows to delete is big, then create a new table (with all grants and indexes) anti-joining with exceptions_table by rowid and rename the original table into original_dups table and rename new_table_with_no_dups into original table
create table new_table_with_no_dups AS (
select field1, field2 ........
from original_dups t1
where not exists ( select null from exceptions_table T2 where t1.rowid = t2.row_id )
)
Using rowid-
delete from emp
where rowid not in
(select max(rowid) from emp group by empno);
Using self join-
delete from emp e1
where rowid not in
(select max(rowid) from emp e2
where e1.empno = e2.empno );
Solution 4)
delete from emp where rowid in
(
select rid from
(
select rowid rid,
dense_rank() over(partition by empno order by rowid
) rn
from emp
)
where rn > 1
);
1. solution
delete from emp
where rowid not in
(select max(rowid) from emp group by empno);
2. sloution
delete from emp where rowid in
(
select rid from
(
select rowid rid,
row_number() over(partition by empno order by empno) rn
from emp
)
where rn > 1
);
3.solution
delete from emp e1
where rowid not in
(select max(rowid) from emp e2
where e1.empno = e2.empno );
4. solution
delete from emp where rowid in
(
select rid from
(
select rowid rid,
dense_rank() over(partition by empno order by rowid
) rn
from emp
)
where rn > 1
);
5. solution
delete from emp where rowid in
(
select rid from
(
select rowid rid,rank() over (partition by emp_id order by rowid)rn from emp
)
where rn > 1
);
DELETE from table_name where rowid not in (select min(rowid) FROM table_name group by column_name);
and you can also delete duplicate records in another way
DELETE from table_name a where rowid > (select min(rowid) FROM table_name b where a.column=b.column);
DELETE FROM tableName WHERE ROWID NOT IN (SELECT MIN (ROWID) FROM table GROUP BY columnname);
delete from dept
where rowid in (
select rowid
from dept
minus
select max(rowid)
from dept
group by DEPTNO, DNAME, LOC
);
For best performance, here is what I wrote :
(see execution plan)
DELETE FROM your_table
WHERE rowid IN
(select t1.rowid from your_table t1
LEFT OUTER JOIN (
SELECT MIN(rowid) as rowid, column1,column2, column3
FROM your_table
GROUP BY column1, column2, column3
) co1 ON (t1.rowid = co1.rowid)
WHERE co1.rowid IS NULL
);
Check below scripts -
1.
Create table test(id int,sal int);
2.
insert into test values(1,100);
insert into test values(1,100);
insert into test values(2,200);
insert into test values(2,200);
insert into test values(3,300);
insert into test values(3,300);
commit;
3.
select * from test;
You will see here 6-records.
4.run below query -
delete from
test
where rowid in
(select rowid from
(select
rowid,
row_number()
over
(partition by id order by sal) dup
from test)
where dup > 1)
select * from test;
You will see that duplicate records have been deleted.
Hope this solves your query.
Thanks :)
I didn't see any answers that use common table expressions and window functions.
This is what I find easiest to work with.
DELETE FROM
YourTable
WHERE
ROWID IN
(WITH Duplicates
AS (SELECT
ROWID RID,
ROW_NUMBER()
OVER(
PARTITION BY First_Name, Last_Name, Birth_Date)
AS RN
SUM(1)
OVER(
PARTITION BY First_Name, Last_Name, Birth_Date
ORDER BY ROWID ROWS BETWEEN UNBOUNDED PRECEDING
AND UNBOUNDED FOLLOWING)
AS CNT
FROM
YourTable
WHERE
Load_Date IS NULL)
SELECT
RID
FROM
duplicates
WHERE
RN > 1);
Somethings to note:
1) We are only checking for duplication on the fields in the partition clause.
2) If you have some reason to pick one duplicate over others you can use an order by clause to make that row will have row_number() = 1
3) You can change the number duplicate preserved by changing the final where clause to "Where RN > N" with N >= 1 (I was thinking N = 0 would delete all rows that have duplicates, but it would just delete all rows).
4) Added the Sum partition field the CTE query which will tag each row with the number rows in the group. So to select rows with duplicates, including the first item use "WHERE cnt > 1".
solution :
delete from emp where rowid in
(
select rid from
(
select rowid rid,
row_number() over(partition by empno order by empno) rn
from emp
)
where rn > 1
);
create or replace procedure delete_duplicate_enq as
cursor c1 is
select *
from enquiry;
begin
for z in c1 loop
delete enquiry
where enquiry.enquiryno = z.enquiryno
and rowid > any
(select rowid
from enquiry
where enquiry.enquiryno = z.enquiryno);
end loop;
end delete_duplicate_enq;
This is similar to the top answer but gives me a much better explain plan:
delete from your_table
where rowid in (
select max(rowid)
from your_table
group by column1, column2, column3
having count(*) > 1
);

tsq - take the highest int in duplicate row

I have the following rows in a table
name, tagid
-------
test1,1
test1,100
test2,2
test2,200
test3,3
test3,300
There are duplicates in the name.
Is there a way to select unique names by taking the highest tagid of each group?
select name,max(tagid) as highest_tagid
from tbl
group by name
;WITH cte AS
(
SELECT *, ROW_NUMBER() OVER (PARTITION BY name ORDER BY tagid DESC) AS rn
FROM table_1
)
SELECT *
FROM cte
WHERE rn = 1

SQL Update with row_number()

I want to update my column CODE_DEST with an incremental number. I have:
CODE_DEST RS_NOM
null qsdf
null sdfqsdfqsdf
null qsdfqsdf
I would like to update it to be:
CODE_DEST RS_NOM
1 qsdf
2 sdfqsdfqsdf
3 qsdfqsdf
I have tried this code:
UPDATE DESTINATAIRE_TEMP
SET CODE_DEST = TheId
FROM (SELECT Row_Number() OVER (ORDER BY [RS_NOM]) AS TheId FROM DESTINATAIRE_TEMP)
This does not work because of the )
I have also tried:
WITH DESTINATAIRE_TEMP AS
(
SELECT
ROW_NUMBER() OVER (ORDER BY [RS_NOM] DESC) AS RN
FROM DESTINATAIRE_TEMP
)
UPDATE DESTINATAIRE_TEMP SET CODE_DEST=RN
But this also does not work because of union.
How can I update a column using the ROW_NUMBER() function in SQL Server 2008 R2?
One more option
UPDATE x
SET x.CODE_DEST = x.New_CODE_DEST
FROM (
SELECT CODE_DEST, ROW_NUMBER() OVER (ORDER BY [RS_NOM]) AS New_CODE_DEST
FROM DESTINATAIRE_TEMP
) x
DECLARE #id INT
SET #id = 0
UPDATE DESTINATAIRE_TEMP
SET #id = CODE_DEST = #id + 1
GO
try this
http://www.mssqltips.com/sqlservertip/1467/populate-a-sql-server-column-with-a-sequential-number-not-using-an-identity/
With UpdateData As
(
SELECT RS_NOM,
ROW_NUMBER() OVER (ORDER BY [RS_NOM] DESC) AS RN
FROM DESTINATAIRE_TEMP
)
UPDATE DESTINATAIRE_TEMP SET CODE_DEST = RN
FROM DESTINATAIRE_TEMP
INNER JOIN UpdateData ON DESTINATAIRE_TEMP.RS_NOM = UpdateData.RS_NOM
Your second attempt failed primarily because you named the CTE same as the underlying table and made the CTE look as if it was a recursive CTE, because it essentially referenced itself. A recursive CTE must have a specific structure which requires the use of the UNION ALL set operator.
Instead, you could just have given the CTE a different name as well as added the target column to it:
With SomeName As
(
SELECT
CODE_DEST,
ROW_NUMBER() OVER (ORDER BY [RS_NOM] DESC) AS RN
FROM DESTINATAIRE_TEMP
)
UPDATE SomeName SET CODE_DEST=RN
This is a modified version of #Aleksandr Fedorenko's answer adding a WHERE clause:
UPDATE x
SET x.CODE_DEST = x.New_CODE_DEST
FROM (
SELECT CODE_DEST, ROW_NUMBER() OVER (ORDER BY [RS_NOM]) AS New_CODE_DEST
FROM DESTINATAIRE_TEMP
) x
WHERE x.CODE_DEST <> x.New_CODE_DEST AND x.CODE_DEST IS NOT NULL
By adding a WHERE clause I found the performance improved massively for subsequent updates. Sql Server seems to update the row even if the value already exists and it takes time to do so, so adding the where clause makes it just skip over rows where the value hasn't changed. I have to say I was astonished as to how fast it could run my query.
Disclaimer: I'm no DB expert, and I'm using PARTITION BY for my clause so it may not be exactly the same results for this query. For me the column in question is a customer's paid order, so the value generally doesn't change once it is set.
Also make sure you have indexes, especially if you have a WHERE clause on the SELECT statement. A filtered index worked great for me as I was filtering based on payment statuses.
My query using PARTITION by
UPDATE UpdateTarget
SET PaidOrderIndex = New_PaidOrderIndex
FROM
(
SELECT PaidOrderIndex, SimpleMembershipUserName, ROW_NUMBER() OVER(PARTITION BY SimpleMembershipUserName ORDER BY OrderId) AS New_PaidOrderIndex
FROM [Order]
WHERE PaymentStatusTypeId in (2,3,6) and SimpleMembershipUserName is not null
) AS UpdateTarget
WHERE UpdateTarget.PaidOrderIndex <> UpdateTarget.New_PaidOrderIndex AND UpdateTarget.PaidOrderIndex IS NOT NULL
-- test to 'break' some of the rows, and then run the UPDATE again
update [order] set PaidOrderIndex = 2 where PaidOrderIndex=3
The 'IS NOT NULL' part isn't required if the column isn't nullable.
When I say the performance increase was massive I mean it was essentially instantaneous when updating a small number of rows. With the right indexes I was able to achieve an update that took the same amount of time as the 'inner' query does by itself:
SELECT PaidOrderIndex, SimpleMembershipUserName, ROW_NUMBER() OVER(PARTITION BY SimpleMembershipUserName ORDER BY OrderId) AS New_PaidOrderIndex
FROM [Order]
WHERE PaymentStatusTypeId in (2,3,6) and SimpleMembershipUserName is not null
I did this for my situation and worked
WITH myUpdate (id, myRowNumber )
AS
(
SELECT id, ROW_NUMBER() over (order by ID) As myRowNumber
FROM AspNetUsers
WHERE UserType='Customer'
)
update AspNetUsers set EmployeeCode = FORMAT(myRowNumber,'00000#')
FROM myUpdate
left join AspNetUsers u on u.Id=myUpdate.id
Simple and easy way to update the cursor
UPDATE Cursor
SET Cursor.CODE = Cursor.New_CODE
FROM (
SELECT CODE, ROW_NUMBER() OVER (ORDER BY [CODE]) AS New_CODE
FROM Table Where CODE BETWEEN 1000 AND 1999
) Cursor
If table does not have relation, just copy all in new table with row number and remove old and rename new one with old one.
Select RowNum = ROW_NUMBER() OVER(ORDER BY(SELECT NULL)) , * INTO cdm.dbo.SALES2018 from
(
select * from SALE2018) as SalesSource
In my case I added a new column and wanted to update it with the equevilat record number for the whole table
id name new_column (ORDER_NUM)
1 Ali null
2 Ahmad null
3 Mohammad null
4 Nour null
5 Hasan null
6 Omar null
I wrote this query to have the new column populated with the row number
UPDATE My_Table
SET My_Table.ORDER_NUM = SubQuery.rowNumber
FROM (
SELECT id ,ROW_NUMBER() OVER (ORDER BY [id]) AS rowNumber
FROM My_Table
) SubQuery
INNER JOIN My_Table ON
SubQuery.id = My_Table.id
after executing this query I had 1,2,3,... numbers in my new column
I update a temp table with the first occurrence of part where multiple parts can be associated with a sequence number. RowId=1 returns the first occurence which I join the tmp table and data using part and sequence number.
update #Tmp
set
#Tmp.Amount=#Amount
from
(SELECT Part, Row_Number() OVER (ORDER BY [Part]) AS RowId FROM #Tmp
where Sequence_Num=#Sequence_Num
)data
where data.Part=#Tmp.Part
and data.RowId=1
and #Tmp.Sequence_Num=#Sequence_Num
I don't have a running ID in order to do what "Basheer AL-MOMANI" suggested.
I did something like this: (joined my table on myself, just to get the Row Number)
update T1 set inID = T2.RN
from (select *, ROW_NUMBER() over (order by ID) RN from MyTable) T1
inner join (select *, ROW_NUMBER() over (order by ID) RN from MyTable) T2 on T2.RN = T1.RN

autonumber in select statement in SQL Server

I would like to create a select query statement with autonumber.. like..
select * from tbl1
will give me everything from table.
The result I'd like to get is..
1 data
2 data
3 data
So how can I do to get that number..??
like..
select (for autonumber), * from tbl1
the data in my table will repeated (no unique data)
Use ROW_NUMBER:
SELECT ROW_NUMBER() OVER (ORDER BY col1) AS rn, * FROM tbl1
To filter the results based on the row number use this:
SELECT * FROM
(
SELECT ROW_NUMBER() OVER (ORDER BY col1) AS rn, * FROM tbl1
) T1
WHERE rn = 5
You may need to find the identity's offset e.g. last ID of second table:
DECLARE #lastAutoID int
SET #lastAutoID = abs(( Select max(convert(float,[ConsID]))
FROM [RXPIPEDB]...[consumption] ) )
Then use ROW_NUMBER():
#lastAutoID + ROW_NUMBER() OVER (ORDER BY oldICN_str)

Resources