Removing duplicate rows from table in Oracle

Question

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 ke

Answer 1

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".

Answer 2

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

Answer 3

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 );

Answer 4

DELETE FROM tablename a
      WHERE a.ROWID > ANY (SELECT b.ROWID
                             FROM tablename b
                            WHERE a.fieldname = b.fieldname
                              AND a.fieldname2 = b.fieldname2)