Related
I am looking for a query which fetches me the data that is different compared to the previous row,
A sample code (with table creation and data)
create table #temp
(id int, eid int, name char(10),estid int, ecid int, epid int, etc char(5) )
insert into #temp values (1,1,'a',1,1,1,'a')
insert into #temp values (2,1,'a',1,1,1,'a')
insert into #temp values (3,1,'a',2,1,1,'a')
insert into #temp values (4,1,'a',1,1,1,'a')
insert into #temp values (5,1,'a',1,1,1,'a')
insert into #temp values (6,1,'a',1,2,1,'a')
insert into #temp values (7,1,'a',1,1,1,'a')
insert into #temp values (8,1,'a',2,1,1,'a')
insert into #temp values (9,1,'a',1,1,1,'a')
insert into #temp values (10,1,'a',1,1,1,'a')
insert into #temp values (11,2,'a',1,1,1,'a')
insert into #temp values (12,2,'a',1,1,1,'a')
insert into #temp values (13,2,'a',2,1,1,'a')
insert into #temp values (14,2,'a',1,1,1,'a')
insert into #temp values (15,2,'a',1,1,1,'a')
insert into #temp values (16,2,'a',1,2,1,'a')
insert into #temp values (17,2,'a',1,1,1,'a')
insert into #temp values (18,2,'a',2,1,1,'a')
insert into #temp values (19,2,'a',1,1,1,'a')
insert into #temp values (20,2,'a',1,1,1,'a')
I tried with some ways of getting the data as the way that i expected
SELECT * INTo #Temp_Final
FROM #temp
WHERE #temp.%%physloc%%
NOT IN (SELECT Min(b.%%physloc%%)
FROM #temp b
GROUP BY eid,name,estid,ecid,epid,etc)
ORDER BY id
SELECT * FROM #temp WHERE id not in (SELECT id FROM #Temp_Final) ORDER BY id
But i wasn't getting the result as i expected...
This is how the result needs to be
select * from #temp where id in (1,3,4,6,7,8,9,11,13,14,16,17,18,19)
You can do this with a simple self-join and appropriate comparison:
select t.*
from #temp t left outer join
#temp tprev
on t.id = tprev.id + 1
where tprev.id is null or
t.name <> tprev.name or
t.estid <> tprev.estid or
t.ecid <> tprev.ecid or
t.epid <> tprev.epid or
t.etc <> tprev.etc;
This assumes that the ids are sequential with no gaps. If the ids are not, you can get the previous id using a correlated subquery or the lag() function.
Your title says "delete" but the question seems to just want the list of such rows. You can phrase this as a delete query if you need to.
For SQL Server 2012 (SQL Fiddle)
WITH CTE
AS (SELECT *,
LAG(eid) OVER (ORDER BY id) AS prev_eid,
LAG(name) OVER (ORDER BY id) AS prev_name,
LAG(estid) OVER (ORDER BY id) AS prev_estid,
LAG(ecid) OVER (ORDER BY id) AS prev_ecid,
LAG(epid) OVER (ORDER BY id) AS prev_epid,
LAG(etc) OVER (ORDER BY id) AS prev_etc
FROM #temp)
DELETE FROM CTE
WHERE EXISTS (SELECT eid,
name,
estid,
ecid,
epid,
etc
INTERSECT
SELECT prev_eid,
prev_name,
prev_estid,
prev_ecid,
prev_epid,
prev_etc)
select
t.id,
t.eid,
t.name,
t.estid,
t.ecid,
t.epid,
t.etc
from #temp t
left join #temp d
on d.id = t.id-1
and d.eid = t.eid
and d.name = t.name
and d.estid = t.estid
and d.ecid = t.ecid
and d.epid = t.epid
and d.etc = t.etc
where d.id is null
Create table #Tbl
(
ID int not null,
Keyword nvarchar(max)
)
Insert into #Tbl Values ('0','Cryptography')
Insert into #Tbl Values ('1','Cryptography')
Insert into #Tbl Values ('4','Cryptography')
Insert into #Tbl Values ('0','SQL')
Insert into #Tbl Values ('0','SQL')
Insert into #Tbl Values ('3','Cloud Computing')
Insert into #Tbl Values ('6','Recursion')
Insert into #Tbl Values ('8','Recursion')
Insert into #Tbl Values ('0','Universe')
Insert into #Tbl Values ('0','Universe')
Insert into #Tbl Values ('7','Universe')
I need to get the titles which has more than one ID and at least one of the ID is zero.
So the expected result will be:
Cryptography
Universe
I tried below query but not able to add "at least one id is zero" condition
select Keyword,COUNT(distinct id) from #Tbl
group by Keyword
having COUNT(distinct id)>1
How can I proceed here ? Thanks for your help.
Assuming your IDs start from 0, the below should work
select Keyword,COUNT(distinct id) from #Tbl
group by Keyword
having COUNT(distinct id)>1 and MIN(id) = 0
There are many ways to do this, one example:
SELECT DISTINCT Keyword
FROM #Tbl T
WHERE EXISTS (SELECT 1 FROM #Tbl WHERE Keyword = T.Keyword
AND ID = 0)
AND EXISTS (SELECT 1 FROM #Tbl WHERE Keyword = T.Keyword
AND ID != 0)
Here is a sqlfiddle with a demo.
This should do it:
SELECT Keyword
FROM #Tbl
WHERE Keyword IN (SELECT DISTINCT Keyword FROM #Tbl WHERE ID = 0)
GROUP BY Keyword
HAVING COUNT(DISTINCT id) > 1
Here's yet another approach:
SELECT Keyword, COUNT(DISTINCT ID)
FROM #Tbl
GROUP BY Keyword
HAVING COUNT(DISTINCT ID) > ALL (SELECT COUNT(DISTINCT NULLIF(ID, 0)) UNION ALL SELECT 1)
;
Let say I have the following table (The ID is self incremental)
ID Name Serial Status
0 Pie A Fail
1 Pie A Fail
2 Pie A Pass
3 Pie B Fail
4 Pie B Pass
5 Pie C Pass
6 Pie C Fail
How can I get all the rows where the last row of each Group By (Name, Serial) is Pass?
This is the result I should get from the query. The serial C is removed since the last entry of the group by (Name, Serial) is 'Fail'
ID Name Serial Status
0 Pie A Fail
1 Pie A Fail
2 Pie A Pass
3 Pie B Fail
4 Pie B Pass
Thanks!
I would try something like this (assuming SQL Server):
DECLARE #myTable AS TABLE(
ID INT,
Name VARCHAR(10),
Serial VARCHAR(1),
[Status] VARCHAR(10))
INSERT INTO #myTable VALUES(0, 'Pie', 'A', 'Fail')
INSERT INTO #myTable VALUES(1, 'Pie', 'A', 'Fail')
INSERT INTO #myTable VALUES(2, 'Pie', 'A', 'Pass')
INSERT INTO #myTable VALUES(3, 'Pie', 'B', 'Fail')
INSERT INTO #myTable VALUES(4, 'Pie', 'B', 'Pass')
INSERT INTO #myTable VALUES(5, 'Pie', 'C', 'Pass')
INSERT INTO #myTable VALUES(6, 'Pie', 'C', 'Fail')
SELECT *
FROM #myTable
WHERE Serial NOT IN
(
--Get all Serial that end with a 'Fail'
SELECT T1.Serial
FROM #myTable T1
JOIN (
--Get Max ID for a serial
SELECT MAX(ID) as [ID] FROM #myTable GROUP BY Serial
) T2 ON T1.[ID] = T2.[ID]
WHERE T1.[Status] = 'Fail'
)
ORDER BY [ID]
or if you prefer NOT EXISTS (which is usually faster than NOT IN):
SELECT *
FROM #myTable T
WHERE NOT EXISTS
(
SELECT
T1.Serial
FROM #myTable T1
JOIN (
--Get Max ID for a serial
SELECT MAX(ID) as [ID] FROM #myTable GROUP BY Serial
) T2 ON T1.[ID] = T2.[ID]
WHERE
T1.[Status] = 'Fail'
AND T1.[Serial] = T.[Serial]
)
ORDER BY [ID]
We can use CTE to improve readability by implementing as a series of sequential steps:
Get max ids
Get serials for max ids that have status 'Fail'
Remove those rows that match the serials
It would look like this:
with maxIds as ( --Get max Ids
SELECT MAX(ID) as [ID] FROM myTable GROUP BY Serial
),
serials as ( -- Get serials for max ids that have status 'Fail'
SELECT T1.Serial FROM myTable T1 JOIN maxIds ON T1.[ID] = maxIds.[ID] WHERE [Status] = 'Fail'
)
select * from myTable where serial not in (select * from serials) -- Remove serials that match
I have a simple problem , Although i believe its simple , am not able to figure out the same.
Consider i have the below table with exactly same data as given below :
CREATE TABLE #temp
(
link varchar(255),
number INT,
fname varchar(255)
)
insert into #temp VALUES ('abc',1,'f1')
insert into #temp VALUES ('abc',2,'f2')
insert into #temp VALUES ('abc',3,'f3')
insert into #temp VALUES ('abc',4,'f6')
insert into #temp VALUES ('abc',10,'f100')
insert into #temp VALUES ('abe',-1,'f0')
insert into #temp VALUES ('abe',1,'f1')
insert into #temp VALUES ('abe',2,'f2')
insert into #temp VALUES ('abe',3,'f3')
insert into #temp VALUES ('abe',4,'f6')
insert into #temp VALUES ('abe',20,'f200')
insert into #temp VALUES ('cbe',-1,'f0')
insert into #temp VALUES ('cbe',1,'f1')
insert into #temp VALUES ('cbe',2,'f2')
insert into #temp VALUES ('cbe',3,'f3')
Now for a given link , i need to get the max 'number' and the corresponding 'fname' which has the max 'number' for the given 'link'.
1)Ex : if link is 'abc' , output should be
abc, 10, f100
2)Ex : if link if 'abe' , Output should be
abe, 20, f200
3)Now link can be also given as a pattern , like (link like 'ab%') , so output should be
abc, 10, f100
abe, 20, f200
4)if (link like 'cb%') , so output should be
cbe, 3, f3
Any help in writing this group by query. I have a solution using CAST and string concat like below , but that seems to be in-efficient.
select link,number,fname from #temp
where link like 'ab%' and link+'_'+CAST(number AS varchar(255))
in (select link+'_'+CAST(MAX(number) AS varchar(255)) from #temp
group by link)
Thanks..
Using a self join:
SELECT x.link,
x.number,
x.fname
FROM #temp x
JOIN (SELECT t.link,
MAX(t.number) AS max_number
FROM #temp t
GROUP BY t.link) y ON y.link = x.link
AND y.max_number = x.number
Using a CTE and ROW_NUMBER (SQL Server 2005+):
WITH cte AS (
SELECT x.link,
x.number,
x.fname,
ROW_NUMBER() OVER(PARTITION BY x.link
ORDER BY x.number DESC) rank
FROM #temp x)
SELECT c.link,
c.number,
c.fname
FROM cte c
WHERE c.rank = 1
I have 2 tables: sets and groups. Both are joined using a 3rd table set_has_groups.
I would like to get sets that have ALL groups that I specify
One way of doing it would be
SELECT column1, column2 FROM sets WHERE
id IN(SELECT set_id FROM set_has_group WHERE group_id = 1)
AND id IN(SELECT set_id FROM set_has_group WHERE group_id = 2)
AND id IN(SELECT set_id FROM set_has_group WHERE group_id = 3)
obviously this is not the most beautiful solution
I've also tried this:
SELECT column1, column2 FROM sets WHERE
id IN(SELECT set_id FROM set_has_group WHERE group_id IN(1,2,3) GROUP BY group_id
HAVING COUNT(*) = 3
This looks prettier but the problem is that it takes forever to execute.
While the first query runs in like 200ms the 2nd one takes more than 1 minute.
Any idea why that is?
===UPDATE:
I've played with this some more and I modified the 2nd query like this
SELECT columns FROM `set` WHERE id IN(
select set_id FROM
(
SELECT set_id FROM set_has_group
WHERE group_id IN(1,2,3)
GROUP BY set_id HAVING COUNT(*) = 3
) as temp
)
that is really fast
It's the same as the 2nd query before just that I wrap it in another temporary table
Pretty strange
I am suspecting a small mistyping in the second query.
Really, I am not sure. Probably, the second query is executed via full table scan. At the same time the first one "IN" is really transformed into "EXISTS". So, you can try to use "exists". For example:
...
where 3 = (select count(*) from set_has_group
where group_id in (1, 2, 3) and set_id = id
group by set_id)
Assuming SQL Server, here is a working example with a JOIN that should work better than the IN clauses you are using as long as you have your primary and foreign keys set correctly. I have built joined 5 sets to 3 groups, but set 4 and 5 are not a part of group 3 and will not show in the answer. However, this query is not scalable (for ex. find in group 4, 5, 7, 8 and 13 will require code modifications unless you parse input params into a table variable)
set nocount on
declare #sets table
(
Id INT Identity (1, 1),
Column1 VarChar (50),
Column2 VarChar (50)
)
declare #Set_Has_Group table
(
Set_Id Int,
Group_Id Int
)
insert into #sets values (newid(), newid())
insert into #sets values (newid(), newid())
insert into #sets values (newid(), newid())
insert into #sets values (newid(), newid())
insert into #sets values (newid(), newid())
update #sets set column1 = 'Column1 at Row ' + Convert (varchar, id)
update #sets set column2 = 'Column2 at Row ' + Convert (varchar, id)
insert into #Set_Has_Group values (1, 1)
insert into #Set_Has_Group values (1, 2)
insert into #Set_Has_Group values (1, 3)
insert into #Set_Has_Group values (2, 1)
insert into #Set_Has_Group values (2, 2)
insert into #Set_Has_Group values (2, 3)
insert into #Set_Has_Group values (3, 1)
insert into #Set_Has_Group values (3, 2)
insert into #Set_Has_Group values (3, 3)
insert into #Set_Has_Group values (4, 1)
insert into #Set_Has_Group values (4, 2)
insert into #Set_Has_Group values (5, 1)
insert into #Set_Has_Group values (5, 2)
/* your query with IN */
SELECT column1, column2 FROM #sets WHERE
id IN(SELECT set_id FROM #set_has_group WHERE group_id = 1)
AND id IN(SELECT set_id FROM #set_has_group WHERE group_id = 2)
AND id IN(SELECT set_id FROM #set_has_group WHERE group_id = 3)
/* my query with JOIN */
SELECT * -- Column1, Column2
FROM #sets sets
WHERE 3 = (
SELECT Count (1)
FROM #Set_Has_Group Set_Has_Group
WHERE 1=1
AND sets.Id = Set_Has_Group.Set_Id
AND Set_Has_Group.Group_ID IN (1, 2, 3)
Group by Set_Id
)
Here's a solution that uses a non-correlated subquery and no GROUP BY:
SELECT column1, column2
FROM sets
WHERE id IN (
SELECT g1.set_id FROM set_has_group g1
JOIN set_has_group g2 ON (g1.set_id = g3.set_id)
JOIN set_has_group g3 ON (g1.set_id = g3.set_id)
WHERE g1.group_id = 1 AND g2.group_id = 2 AND g3.group_id = 3);