I have been struggling for a while now with that problem and I need some help.
I have the following query :
CREATE TABLE Example(
Start NVARCHAR(8),
Endd NVARCHAR(8),
Col1 NVARCHAR(2),
Col2 NVARCHAR(2));
INSERT into Example (Start,Endd,Col1,Col2)
VALUES ('20130801','20140316','02','01'),
('20140317','20140319','04','02'),
('20140320','20140320','04','02'),
('20140321','20140421','02','Z8'),
('20140422','20140429','02','Z9'),
('20140430','20140902','04','02'),
('20140903','20150201','04','02'),
('20150202','20150223','04','02'),
('20150224','20150527','04','02'),
('20150528','99991231','04','02')
;
select MIN(Start)AS Start,MAX(Endd) AS Endd,Col1,Col2 from
(
SELECT top (100000000) Start, Endd,Col1, Col2,dense_rank() over(partition by Col1, Col2 order by Start,Endd) as rank
,LEAD (Col1) OVER (order by Start,Endd DESC) as l1
,LEAD (Col2) OVER (order by Start,Endd DESC) as l2
,LAG (Col1) OVER (order by Start,Endd DESC) as l11
,LAG (Col2) OVER (order by Start,Endd DESC) as l22
FROM Example sp
order by Start,Endd
)rq
GROUP BY Col1,Col2,case when (rq.l1=Col1 and rq.l2=Col2) or (rq.l11=Col1 and rq.l22=Col2) then 0 else rank end
order by Start,Endd;
My goal is to merge those data to have the following result:
However as you can see in the query result, when i have the same values for Col1 and Col2 on different time periods, the merge is not done correctly. It basically tries to merge them all in one, which create issues in the value for the new period.
Would someone be able to help me?
You were getting close in your query and you may have found a solution by now. This is a classic Islands and Gaps problem. I am giving the longer version with no use of LEAD AND LAG. You can replace perhaps 45% of the code below by using those windowing functions with perhaps a dense rank.
DECLARE #Example TABLE(
Start NVARCHAR(8),
Endd NVARCHAR(8),
Col1 NVARCHAR(2),
Col2 NVARCHAR(2));
INSERT into #Example (Start,Endd,Col1,Col2)
VALUES ('20130801','20140316','02','01'),
('20140317','20140319','04','02'),
('20140320','20140320','04','02'),
('20140321','20140421','02','Z8'),
('20140422','20140429','02','Z9'),
('20140430','20140902','04','02'),
('20140903','20150201','04','02'),
('20150202','20150223','04','02'),
('20150224','20150527','04','02'),
('20150528','99991231','04','02')
SELECT
TableID=MAX(TableID),Col1=MAX(Col1),Col2=MAX(Col2),Start=MIN(Start),Endd=MAX(Endd)
FROM
(
SELECT
TableID,Col1,Col2,Start,Endd,ChangeID=MAX(ChangeOnlyTableID)
FROM
(
SELECT
AllRecords.TableID,AllRecords.Col1,AllRecords.Col2,AllRecords.Start,AllRecords.Endd,ChangeOnlyTableID=ChangesOnly.TableID
FROM
(
SELECT * FROM
(
SELECT
This.Start,This.Endd,This.TableID,This.Col1,This.Col2,
Changed=CASE WHEN (Next.Col1=This.Col1 AND Next.Col2=This.Col2) THEN 0 ELSE 1 END
FROM
(
SELECT TableID=ROW_NUMBER() OVER(ORDER BY Start,Endd,Col1,Col2),Start,Endd,Col1,Col2 FROM #Example
)AS This
LEFT OUTER JOIN
(
SELECT TableID=ROW_NUMBER() OVER(ORDER BY Start,Endd,Col1,Col2),Start,Endd,Col1,Col2 FROM #Example
)
AS Next ON This.TableID=Next.TableID+1
)
AS ChangeMarkers
WHERE Changed=1
)
AS AllRecords
INNER JOIN
(
SELECT * FROM
(
SELECT
This.Start,This.Endd,This.TableID,This.Col1,This.Col2,
Changed=CASE WHEN (Next.Col1=This.Col1 AND Next.Col2=This.Col2) THEN 0 ELSE 1 END
FROM
(
SELECT TableID=ROW_NUMBER() OVER(ORDER BY Start,Endd,Col1,Col2),Start,Endd,Col1,Col2 FROM #Example
) AS This
LEFT OUTER JOIN
(
SELECT TableID=ROW_NUMBER() OVER(ORDER BY Start,Endd,Col1,Col2),Start,Endd,Col1,Col2 FROM #Example
) AS Next ON This.TableID=Next.TableID+1
)
AS ChangeMarkers
WHERE Changed=1
)
AS ChangesOnly ON ChangesOnly.Col1=AllRecords.Col1 AND ChangesOnly.Col2=AllRecords.Col2 AND ChangesOnly.TableID<=AllRecords.TableID
)AS JoinedResults
GROUP BY
TableID,Col1,Col2,Start,Endd
)
AS Final
GROUP BY
Col1,Col2,ChangeID
ORDER BY
MAX(TableID)
You may choose to shorten this somewhat with a few CTE's to produce a query such as:
;WITH TableWithIDs AS
(
SELECT TableID=ROW_NUMBER() OVER(ORDER BY Start,Endd,Col1,Col2),Start,Endd,Col1,Col2 FROM #Example
)
,ChangeMarkers AS
(
SELECT
This.Start,This.Endd,This.TableID,This.Col1,This.Col2,
Changed=CASE WHEN (Next.Col1=This.Col1 AND Next.Col2=This.Col2) THEN 0 ELSE 1 END
FROM
TableWithIDs AS This
LEFT OUTER JOIN TableWithIDs AS Next ON This.TableID=Next.TableID+1
)
,ChangesOnly AS
(
SELECT * FROM ChangeMarkers WHERE Changed=1
)
,
JoinedResults AS
(
SELECT
AllRecords.TableID,AllRecords.Col1,AllRecords.Col2,AllRecords.Start,AllRecords.Endd,ChangeOnlyTableID=ChangesOnly.TableID
FROM
ChangeMarkers AllRecords
INNER JOIN ChangesOnly ON ChangesOnly.Col1=AllRecords.Col1 AND ChangesOnly.Col2=AllRecords.Col2 AND ChangesOnly.TableID<=AllRecords.TableID
)
SELECT
TableID=MAX(TableID),Col1=MAX(Col1),Col2=MAX(Col2),Start=MIN(Start),Endd=MAX(Endd)
FROM
(
SELECT
TableID,Col1,Col2,Start,Endd,ChangeID=MAX(ChangeOnlyTableID)
FROM
JoinedResults
GROUP BY
TableID,Col1,Col2,Start,Endd
)
AS Final
GROUP BY
Col1,Col2,ChangeID
ORDER BY
MAX(TableID)
There are also some clever hacks that can be applied further using virtual keys however I went the most direct but more verbose route. You should be able to improve on this using a DENSE_RANK() with LEAD() OR LAG()
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
I need to concatenate the name in a recursive cross join way. I don't know how to do this, I have tried a CTE using WITH RECURSIVE but no success.
I have a table like this:
group_id | name
---------------
13 | A
13 | B
19 | C
19 | D
31 | E
31 | F
31 | G
Desired output:
combinations
------------
ACE
ACF
ACG
ADE
ADF
ADG
BCE
BCF
BCG
BDE
BDF
BDG
Of course, the results should multiply if I add a 4th (or more) group.
Native Postgresql Syntax:
SqlFiddleDemo
WITH RECURSIVE cte1 AS
(
SELECT *, DENSE_RANK() OVER (ORDER BY group_id) AS rn
FROM mytable
),cte2 AS
(
SELECT
CAST(name AS VARCHAR(4000)) AS name,
rn
FROM cte1
WHERE rn = 1
UNION ALL
SELECT
CAST(CONCAT(c2.name,c1.name) AS VARCHAR(4000)) AS name
,c1.rn
FROM cte1 c1
JOIN cte2 c2
ON c1.rn = c2.rn + 1
)
SELECT name as combinations
FROM cte2
WHERE LENGTH(name) = (SELECT MAX(rn) FROM cte1)
ORDER BY name;
Before:
I hope if you don't mind that I use SQL Server Syntax:
Sample:
CREATE TABLE #mytable(
ID INTEGER NOT NULL
,TYPE VARCHAR(MAX) NOT NULL
);
INSERT INTO #mytable(ID,TYPE) VALUES (13,'A');
INSERT INTO #mytable(ID,TYPE) VALUES (13,'B');
INSERT INTO #mytable(ID,TYPE) VALUES (19,'C');
INSERT INTO #mytable(ID,TYPE) VALUES (19,'D');
INSERT INTO #mytable(ID,TYPE) VALUES (31,'E');
INSERT INTO #mytable(ID,TYPE) VALUES (31,'F');
INSERT INTO #mytable(ID,TYPE) VALUES (31,'G');
Main query:
WITH cte1 AS
(
SELECT *, rn = DENSE_RANK() OVER (ORDER BY ID)
FROM #mytable
),cte2 AS
(
SELECT
TYPE = CAST(TYPE AS VARCHAR(MAX)),
rn
FROM cte1
WHERE rn = 1
UNION ALL
SELECT
[Type] = CAST(CONCAT(c2.TYPE,c1.TYPE) AS VARCHAR(MAX))
,c1.rn
FROM cte1 c1
JOIN cte2 c2
ON c1.rn = c2.rn + 1
)
SELECT *
FROM cte2
WHERE LEN(Type) = (SELECT MAX(rn) FROM cte1)
ORDER BY Type;
LiveDemo
I've assumed that the order of "cross join" is dependent on ascending ID.
cte1 generate DENSE_RANK() because your IDs contain gaps
cte2 recursive part with CONCAT
main query just filter out required length and sort string
The recursive query is a bit simpler in Postgres:
WITH RECURSIVE t AS ( -- to produce gapless group numbers
SELECT dense_rank() OVER (ORDER BY group_id) AS grp, name
FROM tbl
)
, cte AS (
SELECT grp, name
FROM t
WHERE grp = 1
UNION ALL
SELECT t.grp, c.name || t.name
FROM cte c
JOIN t ON t.grp = c.grp + 1
)
SELECT name AS combi
FROM cte
WHERE grp = (SELECT max(grp) FROM t)
ORDER BY 1;
The basic logic is the same as in the SQL Server version provided by #lad2025, I added a couple of minor improvements.
Or you can use a simple version if your maximum number of groups is not too big (can't be very big, really, since the result set grows exponentially). For a maximum of 5 groups:
WITH t AS ( -- to produce gapless group numbers
SELECT dense_rank() OVER (ORDER BY group_id) AS grp, name AS n
FROM tbl
)
SELECT concat(t1.n, t2.n, t3.n, t4.n, t5.n) AS combi
FROM (SELECT n FROM t WHERE grp = 1) t1
LEFT JOIN (SELECT n FROM t WHERE grp = 2) t2 ON true
LEFT JOIN (SELECT n FROM t WHERE grp = 3) t3 ON true
LEFT JOIN (SELECT n FROM t WHERE grp = 4) t4 ON true
LEFT JOIN (SELECT n FROM t WHERE grp = 5) t5 ON true
ORDER BY 1;
Probably faster for few groups. LEFT JOIN .. ON true makes this work even if higher levels are missing. concat() ignores NULL values. Test with EXPLAIN ANALYZE to be sure.
SQL Fiddle showing both.
Class| Value
-------------
A | 1
A | 2
A | 3
A | 10
B | 1
I am not sure whether it is practical to achieve this using SQL.
If the difference of values are less than 5 (or x), then group the rows (of course with the same Class)
Expected result
Class| ValueMin | ValueMax
---------------------------
A | 1 | 3
A | 10 | 10
B | 1 | 1
For fixed intervals, we can easily use "GROUP BY". But now the grouping is based on nearby row's value. So if the values are consecutive or very close, they will be "chained together".
Thank you very much
Assuming MSSQL
You are trying to group things by gaps between values. The easiest way to do this is to use the lag() function to find the gaps:
select class, min(value) as minvalue, max(value) as maxvalue
from (select class, value,
sum(IsNewGroup) over (partition by class order by value) as GroupId
from (select class, value,
(case when lag(value) over (partition by class order by value) > value - 5
then 0 else 1
end) as IsNewGroup
from t
) t
) t
group by class, groupid;
Note that this assumes SQL Server 2012 for the use of lag() and cumulative sum.
Update:
*This answer is incorrect*
Assuming the table you gave is called sd_test, the following query will give you the output you are expecting
In short, we need a way to find what was the value on the previous row. This is determined using a join on row ids. Then create a group to see if the difference is less than 5. and then it is just regular 'Group By'.
If your version of SQL Server supports windowing functions with partitioning the code would be much more readable.
SELECT
A.CLASS
,MIN(A.VALUE) AS MIN_VALUE
,MAX(A.VALUE) AS MAX_VALUE
FROM
(SELECT
ROW_NUMBER()OVER(PARTITION BY CLASS ORDER BY VALUE) AS ROW_ID
,CLASS
,VALUE
FROM SD_TEST) AS A
LEFT JOIN
(SELECT
ROW_NUMBER()OVER(PARTITION BY CLASS ORDER BY VALUE) AS ROW_ID
,CLASS
,VALUE
FROM SD_TEST) AS B
ON A.CLASS = B.CLASS AND A.ROW_ID=B.ROW_ID+1
GROUP BY A.CLASS,CASE WHEN ABS(COALESCE(B.VALUE,0)-A.VALUE)<5 THEN 1 ELSE 0 END
ORDER BY A.CLASS,cASE WHEN ABS(COALESCE(B.VALUE,0)-A.VALUE)<5 THEN 1 ELSE 0 END DESC
ps: I think the above is ANSI compliant. So should run in most SQL variants. Someone can correct me if it is not.
These give the correct result, using the fact that you must have the same number of group starts as ends and that they will both be in ascending order.
if object_id('tempdb..#temp') is not null drop table #temp
create table #temp (class char(1),Value int);
insert into #temp values ('A',1);
insert into #temp values ('A',2);
insert into #temp values ('A',3);
insert into #temp values ('A',10);
insert into #temp values ('A',13);
insert into #temp values ('A',14);
insert into #temp values ('b',7);
insert into #temp values ('b',8);
insert into #temp values ('b',9);
insert into #temp values ('b',12);
insert into #temp values ('b',22);
insert into #temp values ('b',26);
insert into #temp values ('b',67);
Method 1 Using CTE and row offsets
with cte as
(select distinct class,value,ROW_NUMBER() over ( partition by class order by value ) as R from #temp),
cte2 as
(
select
c1.class
,c1.value
,c2.R as PreviousRec
,c3.r as NextRec
from
cte c1
left join cte c2 on (c1.class = c2.class and c1.R= c2.R+1 and c1.Value < c2.value + 5)
left join cte c3 on (c1.class = c3.class and c1.R= c3.R-1 and c1.Value > c3.value - 5)
)
select
Starts.Class
,Starts.Value as StartValue
,Ends.Value as EndValue
from
(
select
class
,value
,row_number() over ( partition by class order by value ) as GroupNumber
from cte2
where PreviousRec is null) as Starts join
(
select
class
,value
,row_number() over ( partition by class order by value ) as GroupNumber
from cte2
where NextRec is null) as Ends on starts.class=ends.class and starts.GroupNumber = ends.GroupNumber
** Method 2 Inline views using not exists **
select
Starts.Class
,Starts.Value as StartValue
,Ends.Value as EndValue
from
(
select class,Value ,row_number() over ( partition by class order by value ) as GroupNumber
from
(select distinct class,value from #temp) as T
where not exists (select 1 from #temp where class=t.class and Value < t.Value and Value > t.Value -5 )
) Starts join
(
select class,Value ,row_number() over ( partition by class order by value ) as GroupNumber
from
(select distinct class,value from #temp) as T
where not exists (select 1 from #temp where class=t.class and Value > t.Value and Value < t.Value +5 )
) ends on starts.class=ends.class and starts.GroupNumber = ends.GroupNumber
In both methods I use a select distinct to begin because if you have a dulpicate entry at a group start or end things go awry without it.
Here is one way of getting the information you are after:
SELECT Under5.Class,
(
SELECT MIN(m2.Value)
FROM MyTable AS m2
WHERE m2.Value < 5
AND m2.Class = Under5.Class
) AS ValueMin,
(
SELECT MAX(m3.Value)
FROM MyTable AS m3
WHERE m3.Value < 5
AND m3.Class = Under5.Class
) AS ValueMax
FROM
(
SELECT DISTINCT m1.Class
FROM MyTable AS m1
WHERE m1.Value < 5
) AS Under5
UNION
SELECT Over4.Class,
(
SELECT MIN(m4.Value)
FROM MyTable AS m4
WHERE m4.Value >= 5
AND m4.Class = Over4.Class
) AS ValueMin,
(
SELECT Max(m5.Value)
FROM MyTable AS m5
WHERE m5.Value >= 5
AND m5.Class = Over4.Class
) AS ValueMax
FROM
(
SELECT DISTINCT m6.Class
FROM MyTable AS m6
WHERE m6.Value >= 5
) AS Over4
I have a table T with (first, second) columns. I have two rows with first=1 and second=2. I would like to delete just one of the rows. How do I do that?
;WITH CTE AS
(
SELECT TOP 1 *
FROM YourTable
WHERE first=1 and second=2
)
DELETE FROM CTE;
Or if SQL Server 2000
DELETE T
FROM (
SELECT TOP 1 *
FROM YourTable
WHERE [first]=1 and [second]=2
) T;
Then add a primary key.
You can use ROW_NUMBER().
DECLARE #T as Table(First int , Second int )
INsert Into #T
Values (1,2),
(1,2)
SELECT * FROM #T
;WITH CTE as
(SELECT ROW_NUMBER() over (order by first,second) rn , * from #T)
DELETE FROM CTE where rn = 1
select * from #T
If you change rn to include Partition by
ROW_NUMBER() over (PARTITION BY first, second order by first,second)
and change the where to be WHERE RN <> 1
you could use this as a general solution to remove any dupes on First, Second