I'm trying to identify the gaps in a range of numbers (SQL Server). My scenario is below...
ID Start End
1 1 4
2 1 6
3 2 4
4 8 10
5 13 14
Visual
-------------------------------
1-2-3-4
1-2-3-4-5-6
2-3-4
- -8-9-10
- - -13-14
The result of this could be something along the lines of:
Table
-------------------------------
ID Start End Gap
4 8 10 -1
5 13 14 -2
Ultimately, I want to have the gap ranges, but I should be able to figure that out from above...
Missing
7
11-12
I came up with solutions that are either too slow or don't account for the overlap in ranges (ex ID 2)
CREATE TABLE #Docs (
[Rank] INT, --DENSE_RANK () OVER(ORDER BY BegProd)
ControlNumber BIGINT,
BegProd INT,
EndProd INT
)
SELECT
T1.ControlNumber,
T1.BegProd,
T1.EndProd,
MAX(T2.EndProd) AS [PreviousEndProd],
[Gap] = T1.BegProd - MAX(T2.EndProd) - 1
FROM #Docs T1
INNER JOIN #Docs T2
ON T1.[Rank] = T2.[Rank] + 1
AND T1.EndProd > T2.EndProd
GROUP BY T1.ControlNumber, T1.BegProd, T1.EndProd
HAVING T1.BegProd - MAX(T2.EndProd) > 1
There is over 2 million rows in this table and a range span of 1 to 1 billion
EDIT
Fixed 'Missing' table.
The gap column indicates how much of a gap there is before that start number. (ex missing #7 is 1 number)
Try this:
create table #docs(id int, start int, [end] int)
insert #docs values(1,1,4),(2,1,6),(3,2,4),(4,8,10),(5,13,14)
;with a as
(
select start, dense_rank() over (order by start) rn
from #docs t where not exists (select 1 from #docs where t.start > start and t.start < [end])
group by start
), b as
(
select [end], dense_rank() over (order by [end]) rn
from #docs t where not exists (select 1 from #docs where t.[end] > start and t.[end] < [end])
group by [end]
)
select
case when a.[start]= b.[end]+2 then cast(a.start-1 as varchar(21))
else cast(b.[end]+1 as varchar(10)) +'-' + cast(a.start - 1 as varchar(10)) end missing
from a join b on a.rn - 1 = b.rn
and a.[start] <> b.[end] + 1
Result:
Missing
7
11-12
Related
I have a dataset already sorted by a window function in sql:
ROW_NUMBER() OVER (PARTITION BY LOAN_NUMBER, CAST(CREATED_DATE AS DATE) ORDER BY LOAN_NUMBER, CREATED_DATE) AS ROW_IDX
shown as above. I wonder if there's a way that reset the ROW_IDX when the CREATED_DATE has begun to have a value with over one hour gap to the minimum datetime in a specific day.
For example, the row index for row 3 should be 1 because the time gap between 2016-11-03 15:39:16.000 and 2016-11-03 12:44:11.000 is over one hour.And row index of row 4 will be 2.
I've tried several ways to manipulate the datatime column, since the consideration is about 'gap' instead of moments of the day, no rounding methods worked perfectly.
Are mean ,when the gap more than 60 minutes, will restart at 1?
Which version are you use? If it is SQL Server 2012+, you can try this.
The following query is not satisfying, but wish can give you help.
Calculating the diff minutes between continuous two line.
Check the diff minutes whether greater than one hour
Get row number base on the gap time has same situation continuously.
Sorry if I can not describe clear. My english is not well.
;WITH tb(RptDate,ISSUE_ID,ACCOUNT,CREATED_DATE )AS(
select '2017-01-17','35775','76505156','2016-11-03 12:44:11.000' UNION
select '2017-01-17','35793','76505156','2016-11-03 12:51:43.000' UNION
-- select '2017-01-17','35793','76505156','2016-11-03 13:47:43.000' UNION
-- select '2017-01-17','35793','76505156','2016-11-03 14:45:43.000' UNION
select '2017-01-17','36097','76505156','2016-11-03 15:39:16.000' UNION
select '2017-01-17','36132','76505156','2016-11-03 15:52:51.000' UNION
select '2017-01-17','41391','76505156','2016-11-10 10:49:30.000'
)
SELECT *,ROW_NUMBER()OVER(PARTITION BY tt.ACCOUNT,a ORDER BY tt.ACCOUNT, rn) AS ROW_IDX FROM (
SELECT * ,rn-ROW_NUMBER () OVER (PARTITION BY ACCOUNT, CAST(CREATED_DATE AS DATE),n ORDER BY rn) AS a
FROM (
SELECT *, ROW_NUMBER()OVER(PARTITION BY ACCOUNT ORDER BY CREATED_DATE) AS rn
,CASE WHEN DATEDIFF(MINUTE, LAG(CREATED_DATE)OVER(PARTITION BY ACCOUNT ORDER BY CREATED_DATE),tb.CREATED_DATE)>60 THEN 1 ELSE 0 END AS n
,ISNULL(DATEDIFF(MINUTE, LAG(CREATED_DATE)OVER(PARTITION BY ACCOUNT ORDER BY CREATED_DATE),tb.CREATED_DATE),0) AS DiffMin
FROM tb
) AS t
) AS tt
ORDER BY rn
RptDate ISSUE_ID ACCOUNT CREATED_DATE rn n DiffMin a ROW_IDX
---------- -------- -------- ----------------------- -------------------- ----------- ----------- -------------------- --------------------
2017-01-17 35775 76505156 2016-11-03 12:44:11.000 1 0 0 0 1
2017-01-17 35793 76505156 2016-11-03 12:51:43.000 2 0 7 0 2
2017-01-17 36097 76505156 2016-11-03 15:39:16.000 3 1 168 2 1
2017-01-17 36132 76505156 2016-11-03 15:52:51.000 4 0 13 1 1
2017-01-17 41391 76505156 2016-11-10 10:49:30.000 5 1 9777 4 1
It is another script,Do not use the LAG function, Each step has a statement:
;WITH tb(RptDate,ISSUE_ID,ACCOUNT,CREATED_DATE )AS(
select '2017-01-17','35775','76505156','2016-11-03 12:44:11.000' UNION
select '2017-01-17','35793','76505156','2016-11-03 12:51:43.000' UNION
-- select '2017-01-17','35793','76505156','2016-11-03 13:47:43.000' UNION
-- select '2017-01-17','35793','76505156','2016-11-03 14:45:43.000' UNION
select '2017-01-17','36097','76505156','2016-11-03 15:39:16.000' UNION
select '2017-01-17','36132','76505156','2016-11-03 15:52:51.000' UNION
select '2017-01-17','41391','76505156','2016-11-10 10:49:30.000'
),t1 AS(
SELECT *, ROW_NUMBER()OVER(PARTITION BY ACCOUNT ORDER BY CREATED_DATE) AS rn FROM tb
),t2 AS (
SELECT t1.*,CASE WHEN DATEDIFF(MINUTE,tt.CREATED_DATE,t1.CREATED_DATE)>60 THEN 1 ELSE 0 END AS m
,t1.rn-ROW_NUMBER()OVER(PARTITION BY t1.ACCOUNT,CASE WHEN DATEDIFF(MINUTE,tt.CREATED_DATE,t1.CREATED_DATE)>60 THEN 1 ELSE 0 END ORDER BY t1.CREATED_DATE) AS a
FROM t1 LEFT JOIN t1 AS tt ON tt.ACCOUNT=t1.ACCOUNT AND tt.rn=t1.rn-1
),t3 AS(
SELECT *,ROW_NUMBER()OVER(PARTITION BY ACCOUNT,t2.a ORDER BY CREATED_DATE) AS ROW_IDX
FROM t2
)
SELECT * FROM t3
ORDER BY t3.ACCOUNT,t3.CREATED_DATE
I'm trying to generate the numbers in the "x" column considering the values in field "eq", in a way that it should assign a number for every record until it meets the value "1", and the next row should reset and start counting again. I've tried with row_number, but the problem is that I only have ones and zeros in the column I need to evaluate, and the cases I've seen using row_number were using growing values in a column. Also tried with rank, but I haven't managed to make it work.
nInd Fecha Tipo #Inicio #contador_I #Final #contador_F eq x
1 18/03/2002 I 18/03/2002 1 null null 0 1
2 20/07/2002 F 18/03/2002 1 20/07/2002 1 1 2
3 19/08/2002 I 19/08/2002 2 20/07/2002 1 0 1
4 21/12/2002 F 19/08/2002 2 21/12/2002 2 1 2
5 17/03/2003 I 17/03/2003 3 21/12/2002 2 0 1
6 01/04/2003 I 17/03/2003 4 21/12/2002 2 0 2
7 07/04/2003 I 17/03/2003 5 21/12/2002 2 0 3
8 02/06/2003 F 17/03/2003 5 02/06/2003 3 0 4
9 31/07/2003 F 17/03/2003 5 31/07/2003 4 0 5
10 31/08/2003 F 17/03/2003 5 31/08/2003 5 1 6
11 01/09/2005 I 01/09/2005 6 31/08/2003 5 0 1
12 05/09/2005 I 01/09/2005 7 31/08/2003 5 0 2
13 31/12/2005 F 01/09/2005 7 31/12/2005 6 0 3
14 14/01/2006 F 01/09/2005 7 14/01/2006 7 1 4
There is another solution available:
select
nind, eq, row_number() over (partition by s order by s)
from (
select
nind, eq, coalesce((
select sum(eq) +1 from mytable pre where pre.nInd < mytable.nInd)
,1) s --this is the sum of eq!
from mytable) g
The inner subquery creates groups sequentially for each occurrence of 1 in eq. Then we can use row_number() over partition to get our counter.
Here is an example using Sql Server
I have two answers here. One is based off of the ROW_NUMBER() and the other is based off of what appears to be your index (nInd). I wasn't sure if there would be a gap in your index so I made the ROW_NUMBER() as well.
My table format was as follows -
myIndex int identity(1,1) NOT NULL
number int NOT NULL
First one is ROW_NUMBER()...
WITH rn AS (SELECT *, ROW_NUMBER() OVER (ORDER BY myIndex) AS rn, COUNT(*) AS max
FROM counting c GROUP BY c.myIndex, c.number)
,cte (myIndex, number, level, row) AS (
SELECT r.myIndex, r.number, 1, r.rn + 1 FROM rn r WHERE r.rn = 1
UNION ALL
SELECT r1.myIndex, r1.number,
CASE WHEN r1.number = 0 AND r2.number = 1 THEN 1
ELSE c.level + 1
END,
row + 1
FROM cte c
JOIN rn r1
ON c.row = r1.rn
JOIN rn r2
ON c.row - 1 = r2.rn
)
SELECT c.myIndex, c.number, c.level FROM cte c OPTION (MAXRECURSION 0);
Now the index...
WITH cte (myIndex, number, level) AS (
SELECT c.myIndex + 1, c.number, 1 FROM counting c WHERE c.myIndex = 1
UNION ALL
SELECT c1.myIndex + 1, c1.number,
CASE WHEN c1.number = 0 AND c2.number = 1 THEN 1
ELSE c.level + 1
END
FROM cte c
JOIN counting c1
ON c.myIndex = c1.myIndex
JOIN counting c2
ON c.myIndex - 1 = c2.myIndex
)
SELECT c.myIndex - 1 AS myIndex, c.number, c.level FROM cte c OPTION (MAXRECURSION 0);
The answer that I have now is via using
Cursor
I know if there is another solution without cursor it will be better for performance aspects
here is a quick demo of my solution:
-- Create DBTest
use master
Go
Create Database DBTest
Go
use DBTest
GO
-- Create table
Create table Tabletest
(nInd int , eq int)
Go
-- insert dummy data
insert into Tabletest (nInd,eq)
values (1,0),
(2,1),
(3,0),
(4,1),
(5,0),
(6,0),
(7,0),
(8,0),
(9,1),
(8,0),
(9,1)
Create table #Tabletest (nInd int ,eq int ,x int )
go
DECLARE #nInd int , #eq int , #x int
set #x = 1
DECLARE db_cursor CURSOR FOR
SELECT nInd , eq
FROM Tabletest
order by nInd
OPEN db_cursor
FETCH NEXT FROM db_cursor INTO #nInd , #eq
WHILE ##FETCH_STATUS = 0
BEGIN
if (#eq = 0)
begin
insert into #Tabletest (nInd ,eq ,x) values (#nInd , #eq , #x)
set #x = #x +1
end
else if (#eq = 1)
begin
insert into #Tabletest (nInd ,eq ,x) values (#nInd , #eq , #x)
set #x = 1
end
FETCH NEXT FROM db_cursor INTO #nInd , #eq
END
CLOSE db_cursor
DEALLOCATE db_cursor
select * from #Tabletest
The end result set will be as following:
Hope it helps.
Looking at this a slightly different way (which might not be true, but eliminates the need for cursors of recursive CTEs), it looks like you building ordered groups within your dataset. So, start by finding those groups, then determining the ordering of each of them.
The real key is to determine the rules to find the correcting grouping. Based on your description and comments, I'm guessing the grouping is from the start (ordered by the nInd column) ending at each row with and eq value of 1, so you can do something like:
;with ends(nInd, ord) as (
--Find the ending row for each set
SELECT nInd, row_number() over(order by nInd)
FROM mytable
WHERE eq=1
), ranges(sInd, eInd) as (
--Find the previous ending row for each ending row, forming a range for the group
SELECT coalesce(s.nInd,0), e.nInd
FROM ends s
right join ends e on s.ord=e.ord-1
)
Then, using these group ranges, you can find the final ordering of each:
select t.nInd, t.Fecha, t.eq
,[x] = row_number() over(partition by sInd order by nInd)
from ranges r
join mytable t on r.sInd < t.nInd
and t.nInd <= r.eInd
order by t.nInd
I am using SQL Server 2012 and I know it is quite simple to calculate moving averages.
But what I need is to get the mode and the median for a defined window frame like so (with a window of 2 preceding to current row; month unique):
MONTH | CODE | MEDIAN | MODE
1 0 0 0
2 3 1.5 0
3 2 2 0
4 2 2 2
5 2 2 2
6 5 2 2
7 3 3 2
If several values qualify as mode, than pick the first.
I commented my code thoroughly. Read my comments on my Mode calculations and let me know it needs tweaking. Overall, it's a relatively simple query. It just has a lot of ugly subqueries and it has a lot of comments. Check it out:
DECLARE #Table TABLE ([Month] INT,[Code] INT);
INSERT INTO #Table
VALUES (1,0),
(2,3),
(3,2),
(4,2), --Try commenting this out to test my special mode thingymajig
(5,2),
(6,5),
(7,3);
WITH CTE
AS
(
SELECT ROW_NUMBER() OVER (ORDER BY [Month]) row_num,
[Month],
CAST(Code AS FLOAT) Code
FROM #Table
)
SELECT [Month],
Code,
ISNULL((
SELECT CASE
--When there is only one previous value at row_num = 2, find Mean of first two codes
WHEN A.row_num = 2 THEN (LAG(B.code,1) OVER (ORDER BY [Code]) + B.Code)/2.0
--Else find middle code value of current and previous two rows
ELSE B.Code
END
FROM CTE B
--How subquery relates to outer query
WHERE B.row_num BETWEEN A.row_num - 2 AND A.row_num
ORDER BY B.[Code]
--Order by code and offset by 1 so don't select the lowest value, but fetch the one above the lowest value
OFFSET 1 ROW FETCH NEXT 1 ROW ONLY),
0) AS Median,
--I did mode a little different
--Instead of Avg(D.Code) you could list the values because with mode,
--If there's a tie with more than one of each number, you have multiple modes
--Instead of doing that, I simply return the mean of the tied modes
--When there's one, it doesn't change anything.
--If you were to delete the month 4, then your number of Codes 2 and number of Codes 3 would be the same in the last row.
--Proper mode would be 2,3. I instead average them out to be 2.5.
ISNULL((
SELECT AVG(D.Code)
FROM (
SELECT C.Code,
COUNT(*) cnt,
DENSE_RANK() OVER (ORDER BY COUNT(*) DESC) dnse_rank
FROM CTE C
WHERE C.row_num <= A.row_num
GROUP BY C.Code
HAVING COUNT(*) > 1) D
WHERE D.dnse_rank = 1),
0) AS Mode
FROM CTE A
Results:
Month Code Median Mode
----------- ---------------------- ---------------------- ----------------------
1 0 0 0
2 3 1.5 0
3 2 2 0
4 2 2 2
5 2 2 2
6 5 2 2
7 3 3 2
If I understood your requirements correctly, your source table contains MONTH and CODE columns, and you want to calculate MEDIAN and MODE.
The query below calculates MEDIAN and MODE with moving window <= than 3 month ("2 preceding to current row") and returns the results matching your example.
-----------------------------------------------------
--Demo data
-----------------------------------------------------
CREATE TABLE #Data(
[Month] INT NOT NULL,
[Code] INT NOT NULL,
CONSTRAINT [PK_Data] PRIMARY KEY CLUSTERED
(
[Month] ASC
));
INSERT #Data
([Month],[Code])
VALUES
(1,0),
(2,3),
(3,2),
(4,2),
(5,2),
(6,5),
(7,3);
-----------------------------------------------------
--Query
-----------------------------------------------------
DECLARE #PrecedingRowsLimit INT = 2;
WITH [MPos] AS
(
SELECT [R].[Month]
, [RB].[Month] AS [SubId]
, [RB].[Code]
, ROW_NUMBER() OVER(PARTITION BY [R].[Month] ORDER BY [RB].[Code]) AS [RowNumberInPartition]
, CASE
WHEN [R].[Count] % 2 = 1 THEN ([R].[Count] + 1) / 2
ELSE NULL
END AS [MedianPosition]
, CASE
WHEN [R].[Count] % 2 = 0 THEN [R].[Count] / 2
ELSE NULL
END AS [MedianPosition1]
, CASE
WHEN [R].[Count] % 2 = 0 THEN [R].[Count] / 2 + 1
ELSE NULL
END AS [MedianPosition2]
FROM
(
SELECT [RC].[Month]
, [RC].[RowNumber]
, CASE WHEN [RC].[Count] > #PrecedingRowsLimit + 1 THEN #PrecedingRowsLimit + 1 ELSE [RC].[Count] END AS [Count]
FROM
(
SELECT [Month]
, ROW_NUMBER() OVER(ORDER BY [Month]) AS [RowNumber]
, ROW_NUMBER() OVER(ORDER BY [Month]) AS [Count]
FROM #Data
) [RC]
) [R]
INNER JOIN #Data [RB]
ON [R].[Month] >= [RB].[Month]
AND [RB].[Month] >= [R].[RowNumber] - #PrecedingRowsLimit
)
SELECT DISTINCT [M].[Month]
, [ORIG].[Code]
, COALESCE([ME].[Code],([M1].[Code] + [M2].[Code]) / 2.0) AS [Median]
, [MOD].[Mode]
FROM [MPos] [M]
LEFT JOIN [MPOS] [ME]
ON [M].[Month] = [ME].[Month]
AND [M].[MedianPosition] = [ME].[RowNumberInPartition]
LEFT JOIN [MPOS] [M1]
ON [M].[Month] = [M1].[Month]
AND [M].[MedianPosition1] = [M1].[RowNumberInPartition]
LEFT JOIN [MPOS] [M2]
ON [M].[Month] = [M2].[Month]
AND [M].[MedianPosition2] = [M2].[RowNumberInPartition]
INNER JOIN
(
SELECT [MG].[Month]
, FIRST_VALUE([MG].[Code]) OVER (PARTITION BY [MG].[Month] ORDER BY [MG].[Count] DESC , [MG].[SubId] ASC) AS [Mode]
FROM
(
SELECT [Month] , MIN([SubId]) AS [SubId], [Code] , COUNT(1) AS [Count]
FROM [MPOS]
GROUP BY [Month] , [Code]
) [MG]
) [MOD]
ON [M].[Month] = [MOD].[Month]
INNER JOIN #Data [ORIG]
ON [ORIG].[Month] = [M].[Month]
ORDER BY [M].[Month];
I would like to filter duplicate rows on conditions so that the rows with minimum modified and maximum active and unique rid and did are picked. self join? or any better approach that would be performance wise better?
Example:
id rid modified active did
1 1 2010-09-07 11:37:44.850 1 1
2 1 2010-09-07 11:38:44.000 1 1
3 1 2010-09-07 11:39:44.000 1 1
4 1 2010-09-07 11:40:44.000 0 1
5 2 2010-09-07 11:41:44.000 1 1
6 1 2010-09-07 11:42:44.000 1 2
Output expected is
1 1 2010-09-07 11:37:44.850 1 1
5 2 2010-09-07 11:41:44.000 1 1
6 1 2010-09-07 11:42:44.000 1 2
Commenting on the first answer, the suggestion does not work for the below dataset(when active=0 and modified is the minimum for that row)
id rid modified active did
1 1 2010-09-07 11:37:44.850 1 1
2 1 2010-09-07 11:38:44.000 1 1
3 1 2010-09-07 11:39:44.000 1 1
4 1 2010-09-07 11:36:44.000 0 1
5 2 2010-09-07 11:41:44.000 1 1
6 1 2010-09-07 11:42:44.000 1 2
Assuming SQL Server 2005+. Use RANK() instead of ROW_NUMBER() if you want ties returned.
;WITH YourTable as
(
SELECT 1 id,1 rid,cast('2010-09-07 11:37:44.850' as datetime) modified, 1 active,1 did union all
SELECT 2,1,'2010-09-07 11:38:44.000', 1,1 union all
SELECT 3,1,'2010-09-07 11:39:44.000', 1,1 union all
SELECT 4,1,'2010-09-07 11:36:44.000', 0,1 union all
SELECT 5,2,'2010-09-07 11:41:44.000', 1,1 union all
SELECT 6,1,'2010-09-07 11:42:44.000', 1,2
),cte as
(
SELECT id,rid,modified,active, did,
ROW_NUMBER() OVER (PARTITION BY rid,did ORDER BY active DESC, modified ASC ) RN
FROM YourTable
)
SELECT id,rid,modified,active, did
FROM cte
WHERE rn=1
order by id
select id, rid, min(modified), max(active), did from foo group by rid, did order by id;
You can get good performance with a CROSS APPLY if you have a table that has one row for each combination of rid and did:
SELECT
X.*
FROM
ParentTable P
CROSS APPLY (
SELECT TOP 1 *
FROM YourTable T
WHERE P.rid = T.rid AND P.did = T.did
ORDER BY active DESC, modified
) X
Substituting (SELECT DISTINCT rid, did FROM YourTable) for ParentTable would work but will hurt performance.
Also, here is my crazy, single scan magic query which can often outperform other methods:
SELECT
id = Substring(Packed, 6, 4),
rid,
modified = Convert(datetime, Substring(Packed, 2, 4)),
Active = Convert(bit, 1 - Substring(Packed, 1, 1)),
did,
FROM
(
SELECT
rid,
did,
Packed = Min(Convert(binary(1), 1 - active) + Convert(binary(4), modified) + Convert(binary(4), id)
FROM
YourTable
GROUP BY
rid,
did
) X
This method is not recommended because it's not easy to understand, and it's very easy to make mistakes with it. But it's a fun oddity because it can outperform other methods in some cases.
I want to create a report which aggregates the number of activities per customer per week.
If there has been no activites on that customer for a given week, 0 should be displayed (i.e week 3 and 4 in the sample below)
CUSTOMER | #ACTIVITIES | WEEKNUMBER
A | 4 | 1
A | 2 | 2
A | 0 | 3
A | 0 | 4
A | 1 | 5
B ...
C ...
The problem is that if there are no activities there is no data to report on and therefor week 3 and 4 in the sample below is not in the report.
What is the "best" way to solve this?
Try this:
DECLARE #YourTable table (CUSTOMER char(1), ACTIVITIES int, WEEKNUMBER int)
INSERT #YourTable VALUES ('A' , 4 , 1)
INSERT #YourTable VALUES ('A' , 2 , 2)
INSERT #YourTable VALUES ('A' , 0 , 3)
INSERT #YourTable VALUES ('A' , 0 , 4)
INSERT #YourTable VALUES ('A' , 1 , 5)
INSERT #YourTable VALUES ('B' , 5 , 3)
INSERT #YourTable VALUES ('C' , 2 , 4)
DECLARE #StartNumber int
,#EndNumber int
SELECT #StartNumber=1
,#EndNumber=5
;WITH AllNumbers AS
(
SELECT #StartNumber AS Number
UNION ALL
SELECT Number+1
FROM AllNumbers
WHERE Number<#EndNumber
)
, AllCustomers AS
(
SELECT DISTINCT CUSTOMER FROM #YourTable
)
SELECT
n.Number AS WEEKNUMBER, c.CUSTOMER, CASE WHEN y.Customer IS NULL THEN 0 ELSE y.ACTIVITIES END AS ACTIVITIES
FROM AllNumbers n
CROSS JOIN AllCustomers c
LEFT OUTER JOIN #YourTable y ON n.Number=y.WEEKNUMBER AND c.CUSTOMER=y.CUSTOMER
--OPTION (MAXRECURSION 500)
OUTPUT:
WEEKNUMBER CUSTOMER ACTIVITIES
----------- -------- -----------
1 A 4
1 B 0
1 C 0
2 A 2
2 B 0
2 C 0
3 A 0
3 B 5
3 C 0
4 A 0
4 B 0
4 C 2
5 A 1
5 B 0
5 C 0
(15 row(s) affected)
I use a CTE to build a Numbers table, but you could build a permanent one look at this question: What is the best way to create and populate a numbers table?. You could Write the Query without a CTE (same results as above):
SELECT
n.Number AS WEEKNUMBER, c.CUSTOMER, CASE WHEN y.Customer IS NULL THEN 0 ELSE y.ACTIVITIES END AS ACTIVITIES
FROM Numbers n
CROSS JOIN (SELECT DISTINCT
CUSTOMER
FROM #YourTable
) c
LEFT OUTER JOIN #YourTable y ON n.Number=y.WEEKNUMBER AND c.CUSTOMER=y.CUSTOMER
WHERE n.Number>=1 AND n.Number<=5
ORDER BY n.Number,c.CUSTOMER
Keep a table of time periods separately, and then outer left join the activities to it.
Like:
select *
from ReportingPeriod as p
left join Activities as a on a.ReportingPeriodId = p.ReportingPeriodId;