I want to count number fullvisitorID where rank in /page_y is higher then rank in page_x. So in this case result would be 1, only 111
fullvisitorID
rank
page
111
1
/page_x
111
2
/page_y
222
1
/page_x
222
2
/page_x
333
2
/page_x
333
1
/page_y
Consider below approach
select count(*) from (
select distinct fullvisitorID
from your_table
qualify max(if(page='/page_y',rank,null)) over win > max(if(page='/page_x',rank,null)) over win
window win as (partition by fullvisitorID)
)
SELECT COUNTIF(page = '/page_y') cnt FROM (
SELECT * FROM sample_table WHERE page IN ('/page_x', '/page_y')
QUALIFY ROW_NUMBER() OVER (PARTITION BY fullvisitorID ORDER BY rank DESC) = 1
);
for count you can use COUNT and GROUP BY
SELECT fullvisitorID, COUNT(fullvisitorID), Page FROM table t1
WHERE rank = (SELECT MAX(t2.rank) FROM table t2 WHERE t2.fullvisitorID = t1.fullvisitorID)
Group By fullvisitorID, Page
You can apply a SELF JOIN between the two tables, by matching on the "fullvisitorID" field, then force
the first table to have "page_y" values
the second table to have "page_x" values
rank of the first table to have higher rank of the second table
SELECT *
FROM tab t1
INNER JOIN tab t2
ON t1.fullvisitorID = t2.fullvisitorID
AND t1.page = '/page_y'
AND t2.page = '/page_x'
AND t1.rank > t2.rank
Table separation approach:
DECLARE #t1 TABLE ( fullvisitorID INT, [rank] INTEGER,[page] VARCHAR (max)) --here where page = x
DECLARE #t2 TABLE ( fullvisitorID INT, [rank] INTEGER,[page] VARCHAR (max)) --here where page = y
INSERT INTO #t1 SELECT * FROM #test t WHERE t.[page] LIKE '/page_x'
INSERT INTO #t2 SELECT * FROM #test t WHERE t.[page] LIKE '/page_y'
SELECT COUNT(*) FROM #t1 INNER JOIN #t2 ON [#t1].fullvisitorID = [#t2].fullvisitorID WHERE [#t1].rank < [#t2].rank
Related
I have 2 tables, the first one has 10 distinct values:
,
each GlobalPnID has many values on the second table, I want to join 2 tables and select one random value of PortionKey of the second table that match the condition and move to the next GlobalPnID
SELECT TOP 10 gpnp.PortionKey, tt.GlobalPnID
from #TempTable tt
LEFT JOIN [dbo].[GlobalPartNumberPortions] gpnp ON gpnp.GlobalPnId = tt.GlobalPnID
-- tt is the first table
-- gpnp is the second
SELECT TT.GlobalPnID,X.PortionKey
FROM #TempTable AS TT
CROSS APPLY
(
SELECT TOP 1 R.PortionKey
FROM [dbo].[GlobalPartNumberPortions] AS R
WHERE R.GlobalPnId=TT.GlobalPnID
ORDER BY R.PortionID
)X
You could use Row_Number with a CTE and set the criteria you want, for example:
DECLARE #TempTable TABLE
(
globalpnid INT
)
DECLARE #GlobalPartNumberPortions TABLE
(
portionid INT,
portionkey NVARCHAR(10),
globalpnid INT
)
INSERT INTO #TempTable
(globalpnid)
VALUES (1),(2),(3),(4)
INSERT INTO #GlobalPartNumberPortions
(portionid,
portionkey,
globalpnid)
VALUES (1,'ABC',1),
(2,'XYZ',1),
(3,'AZZ',2),
(4,'QWE',3),
(5,'TYU',4);
WITH cteportion
AS (SELECT portionkey,
globalpnid,
rn = Row_number()
OVER (
partition BY globalpnid
ORDER BY RAND(CHECKSUM(NEWID()))))
FROM #GlobalPartNumberPortions)
SELECT gpnp.portionkey,
tt.globalpnid
FROM #TempTable tt
LEFT JOIN cteportion gpnp
ON tt.globalpnid = gpnp.globalpnid
AND gpnp.rn = 1
This will partition the second table by the globalpnid ordering on ORDER BY RAND(CHECKSUM(NEWID()))) and you can then use this in the join gpnp.rn = 1. In the example I've included, you'll see that GlobalPnID = 1 will alternate between ABC and XYZ.
Edit: as suggested by #Thorsten Kettner in the comment, you can order by RAND(CHECKSUM(NEWID())))
Very simple table as an example but no idea how to achieve this:
Example: Table1
ColumnA ColumnB
1 A
1 B
2 C
For two random records: I know I could do like
Select top 2 *
From Table1
order by NewID()
But now I would like to select two random records out but cannot be such a combination that has both '1' for column A, which means the result cannot accept '1 A' together with '1 B', the rest are fine.
Any ideas? Thanks in advance
DROP TABLE #T
CREATE TABLE #T(ID INT
,Vals CHAR(2)
)
INSERT INTO #T VALUES
(1,'A')
,(1,'B')
,(2,'A')
,(2,'C')
,(3,'D')
,(4,'E')
,(5,'E')
SELECT TOP 2
ID,
Vals
FROM
(
SELECT
ID
,VALS
,ROW_NUMBER() OVER(PARTITION BY ID ORDER BY NEWID()) Rnk
FROM
#T) T
WHERE
Rnk = 1
order by NewID()
Here's a way to do it, but it can get expensive if your table is very large:
;With Random As
(
Select *,
Row_Number() Over (Partition By ColumnA Order By NewId()) As RN
From Table1
)
Select Top 2 ColumnA, ColumnB
From Random
Where RN = 1
Order By NewId()
I have this table:
I am trying to pull all records from this table for the max value in the DIST_NO column for every distinct ID in the left most column, but I still want to pull every record for each ID in which there are different Product_ID's as well.
I tried partitioning and using row_number, but I am having trouble at the moment.
Here are my desired results:
This is what my code looks like currently:
select *
from
(SELECT *,
ROW_NUMBER() OVER (PARTITION BY ID ORDER BY DIST_NO DESC) RN
FROM Table) V
WHERE RN<=3
you want the max(DIST_NO) for each ID, product_ID?
If so, you can:
SELECT
ID, product_ID, max(DIST_NO)
from table
group by ID, product_ID
If you want the detail rows related to the max row, you just need to join it back to your table:
Select
t.ID, max_dist_no, TRANSaction_ID , LINE_NO , PRODUCT_ID
from
table t inner join
(SELECT
ID, max(DIST_NO) as max_dist_no
from table
group by ID) mx on
t.ID = mx.ID and
t.DIST_NO = max_DIST_NO
Try
SELECT MT.ID
, MT.DIST_NO
, MT.TRANS_ID
, MT.LINE_NO
, MT.PRODUCT_ID
FROM MYTABLE MT
INNER JOIN (
SELECT T.ID, MAX(T.DIST_NO) as DIST_NO FROM MYTABLE T
GROUP BY T.ID
) MAX_MT ON MT.Id = MAX_MT.ID AND MT.DIST_NO = MAX_MT.DIST_NO
The sub query returns each combination of ID and Max value of DIST_NO:
SELECT T.ID, MAX(T.DIST_NO) as DIST_NO FROM MYTABLE T
GROUP BY T.ID
Joining this back to your original table will basically filter your original data-set by only these combinations of values.
Tested on PostgreSQL:
WITH t1 AS (
SELECT id, product_id, MAX(dist_no) AS dist_no
FROM test
GROUP BY 1,2)
SELECT t1.id, t1.dist_no, t2.trans_id, t2.line_no, t1.product_id
FROM test t2, t1
WHERE t1.id=t2.id AND t1.product_id=t2.product_id AND t1.dist_no=t2.dist_no
Use rank() or dense_rank():
select t.*
from (SELECT t.*
RANK() OVER (PARTITION BY ID ORDER BY DIST_NO DESC) as seqnum
FROM Table t
) t
WHERE seqnum = 1;
This is almost a literal translation of your request:
I am trying to pull all records from this table for the max value in
the DIST_NO column for every distinct ID in the left most column.
you can try something like this one :). (But is your result correct? I think there is little mistake in TRANS_ID...)
DECLARE #ExampleTable TABLE
(ID INT,
DIST_NO INT,
TRANS_ID INT,
LINE_NO INT,
PRODUCT_ID INT)
INSERT INTO #ExampleTable
( ID, DIST_NO, TRANS_ID,LINE_NO, PRODUCT_ID )
VALUES ( 102657, 1, 1105365, 1, 109119 ),
( 102657, 1, 1105366, 2, 109114 ),
( 102657, 2, 1105365, 1, 109119 ),
( 102657, 2, 1105366, 2, 109114 ),
( 104371, 1, 1190538, 1, 110981 ),
( 104371, 2, 1190538, 1, 110981 )
;WITH CTE AS ( SELECT DISTINCT ID, LINE_NO
FROM #ExampleTable)
SELECT a.ID,
x.DIST_NO,
x.TRANS_ID,
x.LINE_NO,
x.PRODUCT_ID
FROM CTE a
CROSS APPLY (SELECT TOP 1 *
FROM #ExampleTable f
WHERE a.ID = f.ID AND
a.LINE_NO = f. LINE_NO
ORDER BY DIST_NO DESC) x
I want to join table 1 with table2 twice becuase I need to get the first minimum record and the second minimum. However, I can only think of using a cte to get the second minimum record. Is there a better way to do it?
Here is the table table:
I want to join Member with output table FirstRunID whose Output value is 1 and second RunID whose Output value is 0
current code I am using:
select memid, a.runid as aRunid,b.runid as bRunid
into #temp
from FirstTable m inner join
(select min(RunID), MemID [SecondTable] where ouput=1 group by memid)a on m.memid=a.memid
inner join (select RunID, MemID [SecondTable] where ouput=0 )b on m.memid=a.memid and b.runid>a.runid
with cte as
(
select row_number() over(partition by memid, arunid order by brunid ),* from #temp
)
select * from cte where n=1
You can use outer apply operator for this:
select * from t1
outer apply(select top 1 t2.runid from t2
where t1.memid = t2.memid and t2.output = 1 order by t2.runid) as oa1
outer apply(select top 1 t2.runid from t2
where t1.memid = t2.memid and t2.output = 0 order by t2.runid) as oa2
You can do this with conditional aggregation. Based on your results, you don't need the first table:
select t2.memid,
max(case when output = 1 and seqnum = 1 then runid end) as OutputValue1,
max(case when output = 0 and seqnum = 2 then runid end) as OutputValue2
from (select t2.*,
row_number() over (partition by memid, output order by runid) a seqnum
from t2
) t2
group by t2.memid;
declare #FirstTable table
(memid int, name varchar(20))
insert into #firsttable
values
(1,'John'),
(2,'Victor')
declare #secondtable table
(runid int,memid int,output int)
insert into #secondtable
values
(1,1,0),(1,2,1),(2,1,1),(2,2,1),(3,1,1),(3,2,0),(4,1,0),(4,2,0)
;with cte as
(
SELECT *, row_number() over (partition by memid order by runid) seq --sequence
FROM #SECONDTABLE T
where t.output = 1
union all
SELECT *, row_number() over (partition by memid order by runid) seq --sequence
FROM #SECONDTABLE T
where t.output = 0 and
t.runid > (select min(x.runid) from #secondtable x where x.memid = t.memid and x.output = 1 group by x.memid) --lose any O output record where there is no prior 1 output record
)
select cte1.memid,cte1.runid,cte2.runid from cte cte1
join cte cte2 on cte2.memid = cte1.memid and cte2.seq = cte1.seq
where cte1.seq = 1 --remove this test if you want matched pairs
and cte1.output = 1 and cte2.output = 0
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