Znajdowanie duplikatów wierszy w SQL Server

Możesz uruchomić następujące zapytanie i znaleźć duplikaty za pomocą max(id) i usunąć te wiersze.

SELECT orgName, COUNT(*), Max(ID) AS dupes 
FROM organizations 
GROUP BY orgName 
HAVING (COUNT(*) > 1)

Ale będziesz musiał uruchomić to zapytanie kilka razy.

Możesz to zrobić tak:

SELECT
    o.id, o.orgName, d.intCount
FROM (
     SELECT orgName, COUNT(*) as intCount
     FROM organizations
     GROUP BY orgName
     HAVING COUNT(*) > 1
) AS d
    INNER JOIN organizations o ON o.orgName = d.orgName

Jeśli chcesz zwrócić tylko te rekordy, które można usunąć (pozostawiając po jednym z nich), możesz użyć:

SELECT
    id, orgName
FROM (
     SELECT 
         orgName, id,
         ROW_NUMBER() OVER (PARTITION BY orgName ORDER BY id) AS intRow
     FROM organizations
) AS d
WHERE intRow != 1

Edit: SQL Server 2000 nie posiada funkcji ROW_NUMBER (). Zamiast tego możesz użyć:

SELECT
    o.id, o.orgName, d.intCount
FROM (
     SELECT orgName, COUNT(*) as intCount, MIN(id) AS minId
     FROM organizations
     GROUP BY orgName
     HAVING COUNT(*) > 1
) AS d
    INNER JOIN organizations o ON o.orgName = d.orgName
WHERE d.minId != o.id

Rozwiązanie oznaczone jako poprawne nie działa dla mnie, ale znalazłem odpowiedź, która działa po prostu świetnie: Pobierz listę duplikatów wierszy w MySql

SELECT n1.* 
FROM myTable n1
INNER JOIN myTable n2 
ON n2.repeatedCol = n1.repeatedCol
WHERE n1.id <> n2.id

Możesz tego spróbować, tak będzie najlepiej dla ciebie

 WITH CTE AS
    (
    SELECT *,RN=ROW_NUMBER() OVER (PARTITION BY orgName ORDER BY orgName DESC) FROM organizations 
    )
    select * from CTE where RN>1
    go

Select * from (Select orgName,id,
ROW_NUMBER() OVER(Partition By OrgName ORDER by id DESC) Rownum
From organizations )tbl Where Rownum>1

Więc rekordy z rowum> 1 będą zduplikowanymi rekordami w Twojej tabeli. "Partition by" najpierw grupuje płyty, a następnie serializuje je, nadając im numery seryjne. Więc rownum > 1 będzie duplikatem rekordów, które mogą być usunięte jako takie.

select * from [Employees]

Do znajdowania zduplikowanego rekordu 1) Korzystanie z CTE

with mycte
as
(
select Name,EmailId,ROW_NUMBER() over(partition by Name,EmailId order by id) as Duplicate from [Employees]
)
select * from mycte

2) Za Pomocą GroupBy

select Name,EmailId,COUNT(name) as Duplicate from  [Employees] group by Name,EmailId 

select column_name, count(column_name)
from table_name
group by column_name
having count (column_name) > 1;

Src: https://stackoverflow.com/a/59242/1465252

select a.orgName,b.duplicate, a.id
from organizations a
inner join (
    SELECT orgName, COUNT(*) AS duplicate
    FROM organizations
    GROUP BY orgName
    HAVING COUNT(*) > 1
) b on o.orgName = oc.orgName
group by a.orgName,a.id

Jeśli chcesz usunąć duplikaty:

WITH CTE AS(
   SELECT orgName,id,
       RN = ROW_NUMBER()OVER(PARTITION BY orgName ORDER BY Id)
   FROM organizations
)
DELETE FROM CTE WHERE RN > 1

select orgname, count(*) as dupes, id 
from organizations
where orgname in (
    select orgname
    from organizations
    group by orgname
    having (count(*) > 1)
)
group by orgname, id

Masz kilka możliwości wyboru duplicate rows.

Dla moich rozwiązań, najpierw rozważ tę tabelę na przykład

CREATE TABLE #Employee
(
ID          INT,
FIRST_NAME  NVARCHAR(100),
LAST_NAME   NVARCHAR(300)
)

INSERT INTO #Employee VALUES ( 1, 'Ardalan', 'Shahgholi' );
INSERT INTO #Employee VALUES ( 2, 'name1', 'lname1' );
INSERT INTO #Employee VALUES ( 3, 'name2', 'lname2' );
INSERT INTO #Employee VALUES ( 2, 'name1', 'lname1' );
INSERT INTO #Employee VALUES ( 3, 'name2', 'lname2' );
INSERT INTO #Employee VALUES ( 4, 'name3', 'lname3' );

Pierwsze rozwiązanie:

SELECT DISTINCT *
FROM   #Employee;

WITH #DeleteEmployee AS (
                     SELECT ROW_NUMBER()
                            OVER(PARTITION BY ID, First_Name, Last_Name ORDER BY ID) AS
                            RNUM
                     FROM   #Employee
                 )

SELECT *
FROM   #DeleteEmployee
WHERE  RNUM > 1

SELECT DISTINCT *
FROM   #Employee

Rozwiązanie Secound : użyj pola identity

SELECT DISTINCT *
FROM   #Employee;

ALTER TABLE #Employee ADD UNIQ_ID INT IDENTITY(1, 1)

SELECT *
FROM   #Employee
WHERE  UNIQ_ID < (
    SELECT MAX(UNIQ_ID)
    FROM   #Employee a2
    WHERE  #Employee.ID = a2.ID
           AND #Employee.FIRST_NAME = a2.FIRST_NAME
           AND #Employee.LAST_NAME = a2.LAST_NAME
)

ALTER TABLE #Employee DROP COLUMN UNIQ_ID

SELECT DISTINCT *
FROM   #Employee

And end of all solution use this command

DROP TABLE #Employee

I think i know what you need musiałem wymieszać odpowiedzi i myślę, że mam rozwiązanie, które chciał:

select o.id,o.orgName, oc.dupeCount, oc.id,oc.orgName
from organizations o
inner join (
    SELECT MAX(id) as id, orgName, COUNT(*) AS dupeCount
    FROM organizations
    GROUP BY orgName
    HAVING COUNT(*) > 1
) oc on o.orgName = oc.orgName

Posiadanie max id da ci id dublicate i jeden z oryginału, o który prosił:

id org name , dublicate count (missing out in this case) 
id doublicate org name , doub count (missing out again because does not help in this case)

Tylko smutna rzecz, którą można zgasić w tej formie

id , name , dubid , name

Hope it still helps

Załóżmy, że mamy tabelę 'Student' z 2 kolumnami:

• student_id int

• student_name varchar

  Records:
  +------------+---------------------+
  | student_id | student_name        |
  +------------+---------------------+
  |        101 | usman               |
  |        101 | usman               |
  |        101 | usman               |
  |        102 | usmanyaqoob         |
  |        103 | muhammadusmanyaqoob |
  |        103 | muhammadusmanyaqoob |
  +------------+---------------------+
  

Teraz chcemy zobaczyć duplikaty rekordów Użyj tego zapytania:

select student_name,student_id ,count(*) c from student group by student_id,student_name having c>1;

+---------------------+------------+---+
| student_name        | student_id | c |
+---------------------+------------+---+
| usman               |        101 | 3 |
| muhammadusmanyaqoob |        103 | 2 |
+---------------------+------------+---+

Mam lepszą opcję, aby uzyskać zduplikowane rekordy w tabeli

SELECT x.studid, y.stdname, y.dupecount
FROM student AS x INNER JOIN
(SELECT a.stdname, COUNT(*) AS dupecount
FROM student AS a INNER JOIN
studmisc AS b ON a.studid = b.studid
WHERE (a.studid LIKE '2018%') AND (b.studstatus = 4)
GROUP BY a.stdname
HAVING (COUNT(*) > 1)) AS y ON x.stdname = y.stdname INNER JOIN
studmisc AS z ON x.studid = z.studid
WHERE (x.studid LIKE '2018%') AND (z.studstatus = 4)
ORDER BY x.stdname

Wynik powyższego zapytania pokazuje wszystkie zduplikowane nazwy z unikalnymi identyfikatorami ucznia i liczbą zduplikowanych wystąpień

Kliknij tutaj, aby zobaczyć wynik sql

Try

SELECT orgName, id, count(*) as dupes
FROM organizations
GROUP BY orgName, id
HAVING count(*) > 1;