Cumulative time difference per group - tsql

I have a table structure like below
DECLARE #XTable TABLE
(
ColA Varchar(20),
ColB Varchar(20),
DateCol DATE
)
INSERT INTO #XTable
VALUES
('A', 'X1', '4/1/2015'), ('A', 'X2', '4/10/2015'), ('A', 'X3', '4/12/2015'),
('A', 'X4', '4/16/2015'), ('B', 'X1', '5/18/2015'), ('B', 'X2', '5/20/2015')
Expected output:
/*
ColA ColB DateCol Diff
A X1 4/1/2015 0
A X2 4/10/2015 9
A X3 4/12/2015 2
A X3 4/12/2015 11
A X4 4/16/2015 15
A X4 4/16/2015 5
A X4 4/16/2015 4
B X1 5/18/2015 0
B X2 5/20/2015 12
*/
for example:
A X4 will have a difference of date from A X1, A X2 and A X3
& A X3 will have a difference of date from A X1 & A X2
I am able to get difference from last row via below query
;WITH Dataf
AS (
SELECT
*,
ROW_NUMBER() OVER (ORDER BY ColA,ColB, DateCol) AS RowNum
FROM
#XTable
)
SELECT a.ColA, a.ColB, SUM(DATEDIFF(Dd,b.DateCol,a.DateCol)) as TotalTime
FROM
Dataf AS A
LEFT OUTER JOIN Dataf AS B
ON A.RowNum = B.RowNum + 1 and a.ColA = b.ColA
GROUP BY a.ColA, a.ColB
Thought of applying multiple CTE, here is on what I am working now
;WITH Dataf
AS (
SELECT
*,
ROW_NUMBER() OVER (PARTITION BY ColA ORDER BY DateCol) AS RowNum
FROM
#XTable
),
CTE AS
(
SELECT ColA, ColB, DateCol, RowNum, NULL AS DateDifference
FROM Dataf WHERE RowNum = 1
UNION ALL
SELECT DF.ColA, DF.ColB, DF.DateCol, DF.RowNum ,
DATEDIFF(DD, CT.DateCol, DF.DateCol) AS DateDifference
FROM Dataf DF
JOIN CTE CT ON DF.ColA = CT.ColA AND DF.RowNum = CT.RowNum + 1
)
SELECT *
FROM CTE
ORDER BY ColA

You can instead use LEFT OUTER JOIN to the CTE you prepared. Here is how it can be done
;WITH DataForm
AS (
SELECT
*,
ROW_NUMBER() OVER (PARTITION BY Cola ORDER BY DateCol) AS RowNum
FROM
#XTable
)
SELECT ColA, ColB, DateCol, 0
FROM DataForm WHERE RowNum = 1
UNION
SELECT T1.ColA, T1.ColB, T1.DateCol
, DATEDIFF(dd,T2.DateCol, T1.Datecol)
FROM DataForm T1
LEFT OUTER JOIN DataForm T2 ON T1.ColA = T2.ColA
AND T1.RowNum >= T2.RowNum
WHERE DATEDIFF(dd,T2.DateCol, T1.Datecol) > 0
SQL Fiddler Example

Related

Checking Slowly Changing Dimension 2

I have a table that looks like this:
A slowly changing dimension type 2, according to Kimball.
Key is just a surrogate key, a key to make rows unique.
As you can see there are three rows for product A.
Timelines for this product are ok. During time the description of the product changes.
From 1-1-2020 up until 4-1-2020 the description of this product was ProdA1.
From 5-1-2020 up until 12-2-2020 the description of this product was ProdA2 etc.
If you look at product B, you see there are gaps in the timeline.
We use DB2 V12 z/Os. How can I check if there are gaps in the timelines for each and every product?
Tried this, but doesn't work
with selectie (key, tel) as
(select product, count(*)
from PROD_TAB
group by product
having count(*) > 1)
Select * from
PROD_TAB A
inner join selectie B
on A.product = B.product
Where not exists
(SELECT 1 from PROD_TAB C
WHERE A.product = C.product
AND A.END_DATE + 1 DAY = C.START_DATE
)
Does anyone know the answer?
The following query returns all gaps for all products.
The idea is to enumerate (RN column) all periods inside each product by START_DATE and join each record with its next period record.
WITH
/*
MYTAB (PRODUCT, DESCRIPTION, START_DATE, END_DATE) AS
(
SELECT 'A', 'ProdA1', DATE('2020-01-01'), DATE('2020-01-04') FROM SYSIBM.SYSDUMMY1
UNION ALL SELECT 'A', 'ProdA2', DATE('2020-01-05'), DATE('2020-02-12') FROM SYSIBM.SYSDUMMY1
UNION ALL SELECT 'A', 'ProdA3', DATE('2020-02-13'), DATE('2020-12-31') FROM SYSIBM.SYSDUMMY1
UNION ALL SELECT 'B', 'ProdB1', DATE('2020-01-05'), DATE('2020-01-09') FROM SYSIBM.SYSDUMMY1
UNION ALL SELECT 'B', 'ProdB2', DATE('2020-01-12'), DATE('2020-03-14') FROM SYSIBM.SYSDUMMY1
UNION ALL SELECT 'B', 'ProdB3', DATE('2020-03-15'), DATE('2020-04-18') FROM SYSIBM.SYSDUMMY1
UNION ALL SELECT 'B', 'ProdB4', DATE('2020-04-16'), DATE('2020-05-03') FROM SYSIBM.SYSDUMMY1
)
,
*/
MYTAB_ENUM AS
(
SELECT
T.*
, ROWNUMBER() OVER (PARTITION BY PRODUCT ORDER BY START_DATE) RN
FROM MYTAB T
)
SELECT A.PRODUCT, A.END_DATE + 1 START_DT, B.START_DATE - 1 END_DT
FROM MYTAB_ENUM A
JOIN MYTAB_ENUM B ON B.PRODUCT = A.PRODUCT AND B.RN = A.RN + 1
WHERE A.END_DATE + 1 <> B.START_DATE
AND A.END_DATE < B.START_DATE;
The result is:
|PRODUCT|START_DT |END_DT |
|-------|----------|----------|
|B |2020-01-10|2020-01-11|
May be more efficient way:
WITH MYTAB2 AS
(
SELECT
T.*
, LAG(END_DATE) OVER (PARTITION BY PRODUCT ORDER BY START_DATE) END_DATE_PREV
FROM MYTAB T
)
SELECT PRODUCT, END_DATE_PREV + 1 START_DATE, START_DATE - 1 END_DATE
FROM MYTAB2
WHERE END_DATE_PREV + 1 <> START_DATE
AND END_DATE_PREV < START_DATE;
Thnx Mark, will try this one of these days.
Never heard of LAG in DB2 V12 for z/Os
Will read about it
Thnx

How to PIVOT this query and display only TOP 10 records filtered by SUM(NetWrittenPremium) DESC

In this query I cant understand what would be the proper syntax to PIVOT it by month and also display just top 10 records based on SUM(NetWrittenPremium).
;with cte_TopClasses
AS (
select
b.YearNum,
b.MonthNum,
REPLACE(ClassCode,'+','') + ' - '+ QLL.Description as Description,
SUM( Premium) as NetWrittenPremium
FROM tblCalendar b
LEFT JOIN ProductionReportMetrics prm ON b.MonthNum=Month(prm.EffectiveDate) AND b.YearNum = YEAR(EffectiveDate)
AND prm.EffectiveDate >=DateAdd(yy, -1, DATEADD(d, 1, EOMONTH(GETDATE()))) AND prm.EffectiveDate <= EOMONTH(GETDATE()) AND CompanyLine = 'Ironshore Insurance Company'
LEFT JOIN NetRate_Quote_Insur_Quote Q ON prm.NetRate_QuoteID = Q.QuoteID
LEFT JOIN NetRate_Quote_Insur_Quote_Locat QL ON Q.QuoteID = QL.QuoteID
LEFT JOIN (SELECT * FROM NetRate_Quote_Insur_Quote_Locat_Liabi nqI
JOIN ( SELECT LocationID as LocID, MAX(ClassCode) as ClCode
FROM NetRate_Quote_Insur_Quote_Locat_Liabi GROUP BY LocationID ) nqA
ON nqA.LocID = nqI.LocationID AND nqA.ClCode = nqI.ClassCode ) QLL
ON QLL.LocationID = QL.LocationID
WHERE ( b.YearNum = YEAR(GETDATE())-1 and b.MonthNum >= MONTH(GETDATE())+1 ) OR
( b.YearNum = YEAR(GETDATE()) and b.MonthNum <= MONTH(GETDATE()) )
GROUP BY b.YearNum,b.MonthNum,ClassCode, QLL.Description
)
SELECT
--TOP 10
RANK() OVER (ORDER BY NetWrittenPremium DESC) AS Rank, *
FROM cte_TopClasses
WHERE Description IS NOT NULL
ORDER BY NetWrittenPremium DESC,YearNum,MonthNum
The result should look something like that:
If I use the query below and then using matrics in SSRS to PIVOT it - then after grouping by Description it only displays me 2 Description.
;with cte_TopClasses
AS (
select
b.YearNum,
b.MonthNum,
REPLACE(ClassCode,'+','') + ' - '+ QLL.Description as Description,
SUM( Premium) as NetWrittenPremium
FROM tblCalendar b
LEFT JOIN ProductionReportMetrics prm ON b.MonthNum=Month(prm.EffectiveDate) AND b.YearNum = YEAR(EffectiveDate)
AND prm.EffectiveDate >=DateAdd(yy, -1, DATEADD(d, 1, EOMONTH(GETDATE()))) AND prm.EffectiveDate <= EOMONTH(GETDATE()) AND CompanyLine = 'Ironshore Insurance Company'
LEFT JOIN NetRate_Quote_Insur_Quote Q ON prm.NetRate_QuoteID = Q.QuoteID
LEFT JOIN NetRate_Quote_Insur_Quote_Locat QL ON Q.QuoteID = QL.QuoteID
LEFT JOIN (SELECT * FROM NetRate_Quote_Insur_Quote_Locat_Liabi nqI
JOIN ( SELECT LocationID as LocID, MAX(ClassCode) as ClCode
FROM NetRate_Quote_Insur_Quote_Locat_Liabi GROUP BY LocationID ) nqA
ON nqA.LocID = nqI.LocationID AND nqA.ClCode = nqI.ClassCode ) QLL
ON QLL.LocationID = QL.LocationID
WHERE ( b.YearNum = YEAR(GETDATE())-1 and b.MonthNum >= MONTH(GETDATE())+1 ) OR
( b.YearNum = YEAR(GETDATE()) and b.MonthNum <= MONTH(GETDATE()) )
GROUP BY b.YearNum,b.MonthNum,ClassCode, QLL.Description
)
SELECT *
FROM (SELECT RANK() OVER (ORDER BY NetWrittenPremium DESC) AS Rank, *
FROM cte_TopClasses
WHERE Description IS NOT NULL) AA
WHERE AA.Rank <= 10
ORDER BY AA.NetWrittenPremium DESC, AA.YearNum, AA.MonthNum
And the result of it in SSRS matrics :
You could try something like this at the end of the query, rather than what is there now:
SELECT *
FROM (SELECT RANK() OVER (ORDER BY [Description] DESC) AS Rank, *
FROM cte_TopClasses
WHERE Description IN (SELECT [Description]
FROM (SELECT RANK() OVER (ORDER BY SUM(NetWrittenPremium) DESC) AS [Rank], [Description], SUM(NetWrittenPremium) AS total
FROM cte_TopClasses
WHERE [Description] IS NOT NULL
GROUP BY [Description]) BB
WHERE [Rank] <= 10)) AA
ORDER BY YearNum, MonthNum
This wraps the query in a SELECT, and filters the ranked results to the 10 you want.
Then use a matrix in the report to pivot the results.

how to do dead reckoning on column of table, postgresql

I have a table looks like,
x y
1 2
2 null
3 null
1 null
11 null
I want to fill the null value by conducting a rolling
function to apply y_{i+1}=y_{i}+x_{i+1} with sql as simple as possible (inplace)
so the expected result
x y
1 2
2 4
3 7
1 8
11 19
implement in postgresql. I may encapsulate it in a window function, but the implementation of custom function seems always complex
WITH RECURSIVE t AS (
select x, y, 1 as rank from my_table where y is not null
UNION ALL
SELECT A.x, A.x+ t.y y , t.rank + 1 rank FROM t
inner join
(select row_number() over () rank, x, y from my_table ) A
on t.rank+1 = A.rank
)
SELECT x,y FROM t;
You can iterate over rows using a recursive CTE. But in order to do so, you need a way to jump from row to row. Here's an example using an ID column:
; with recursive cte as
(
select id
, y
from Table1
where id = 1
union all
select cur.id
, prev.y + cur.x
from Table1 cur
join cte prev
on cur.id = prev.id + 1
)
select *
from cte
;
You can see the query at SQL Fiddle. If you don't have an ID column, but you do have another way to order the rows, you can use row_number() to get an ID:
; with recursive sorted as
(
-- Specify your ordering here. This example sorts by the dt column.
select row_number() over (order by dt) as id
, *
from Table1
)
, cte as
(
select id
, y
from sorted
where id = 1
union all
select cur.id
, prev.y + cur.x
from sorted cur
join cte prev
on cur.id = prev.id + 1
)
select *
from cte
;
Here's the SQL Fiddle link.

generate 10000 consecutive integers

Is there a better way to generate [0 ... 9999] than this:
SELECT
(a3.id + a2.id + a1.id + a0.id) id
FROM
(
SELECT 0 id UNION ALL
SELECT 1 UNION ALL
SELECT 2 UNION ALL
SELECT 3 UNION ALL
SELECT 4 UNION ALL
SELECT 5 UNION ALL
SELECT 6 UNION ALL
SELECT 7 UNION ALL
SELECT 8 UNION ALL
SELECT 9
) a0
CROSS JOIN
(
SELECT 0 id UNION ALL
SELECT 10 UNION ALL
SELECT 20 UNION ALL
SELECT 30 UNION ALL
SELECT 40 UNION ALL
SELECT 50 UNION ALL
SELECT 60 UNION ALL
SELECT 70 UNION ALL
SELECT 80 UNION ALL
SELECT 90
) a1
CROSS JOIN
(
SELECT 0 id UNION ALL
SELECT 100 UNION ALL
SELECT 200 UNION ALL
SELECT 300 UNION ALL
SELECT 400 UNION ALL
SELECT 500 UNION ALL
SELECT 600 UNION ALL
SELECT 700 UNION ALL
SELECT 800 UNION ALL
SELECT 900
) a2
CROSS JOIN
(
SELECT 0 id UNION ALL
SELECT 1000 UNION ALL
SELECT 2000 UNION ALL
SELECT 3000 UNION ALL
SELECT 4000 UNION ALL
SELECT 5000 UNION ALL
SELECT 6000 UNION ALL
SELECT 7000 UNION ALL
SELECT 8000 UNION ALL
SELECT 9000
) a3
ORDER BY id
Any feedback appreciated.
You could write it like this:
;WITH x as
(
SELECT 0 id UNION ALL
SELECT 1 UNION ALL
SELECT 2 UNION ALL
SELECT 3 UNION ALL
SELECT 4 UNION ALL
SELECT 5 UNION ALL
SELECT 6 UNION ALL
SELECT 7 UNION ALL
SELECT 8 UNION ALL
SELECT 9
)
SELECT
row_number() over (order by (select 1))-1 id
FROM x a0
CROSS JOIN x a1
CROSS JOIN x a2
CROSS JOIN x a3
By removing the order by you gained a little.
I am not sure why this answer was removed from POST, this also produced desired output
;WITH x as
(
select id from
(values(0),(1),(2),(3),(4),(5),(6),(7),(8),(9)) x(id)
)
SELECT
(a3.id * 1000 +
a2.id * 100 + a1.id * 10 + a0.id) id
FROM x a2
CROSS JOIN x a0
CROSS JOIN x a1
CROSS JOIN x a3
WITH a AS (
SELECT 0 AS a1
UNION ALL
SELECT a1+1 FROM a WHERE a1+1<10000
)
SELECT * FROM a
OPTION (Maxrecursion 10000)

Dealing with periods and dates without using cursors

I would like to solve this issue avoiding to use cursors (FETCH).
Here comes the problem...
1st Table/quantity
------------------
periodid periodstart periodend quantity
1 2010/10/01 2010/10/15 5
2st Table/sold items
-----------------------
periodid periodstart periodend solditems
14343 2010/10/05 2010/10/06 2
Now I would like to get the following view or just query result
Table Table/stock
-----------------------
periodstart periodend itemsinstock
2010/10/01 2010/10/04 5
2010/10/05 2010/10/06 3
2010/10/07 2010/10/15 5
It seems impossible to solve this problem without using cursors, or without using single dates instead of periods.
I would appreciate any help.
Thanks
DECLARE #t1 TABLE (periodid INT,periodstart DATE,periodend DATE,quantity INT)
DECLARE #t2 TABLE (periodid INT,periodstart DATE,periodend DATE,solditems INT)
INSERT INTO #t1 VALUES(1,'2010-10-01T00:00:00.000','2010-10-15T00:00:00.000',5)
INSERT INTO #t2 VALUES(14343,'2010-10-05T00:00:00.000','2010-10-06T00:00:00.000',2)
DECLARE #D1 DATE
SELECT #D1 = MIN(P) FROM (SELECT MIN(periodstart) P FROM #t1
UNION ALL
SELECT MIN(periodstart) FROM #t2) D
DECLARE #D2 DATE
SELECT #D2 = MAX(P) FROM (SELECT MAX(periodend) P FROM #t1
UNION ALL
SELECT MAX(periodend) FROM #t2) D
;WITH
L0 AS (SELECT 1 AS c UNION ALL SELECT 1),
L1 AS (SELECT 1 AS c FROM L0 A CROSS JOIN L0 B),
L2 AS (SELECT 1 AS c FROM L1 A CROSS JOIN L1 B),
L3 AS (SELECT 1 AS c FROM L2 A CROSS JOIN L2 B),
L4 AS (SELECT 1 AS c FROM L3 A CROSS JOIN L3 B),
Nums AS (SELECT ROW_NUMBER() OVER (ORDER BY (SELECT 0)) AS i FROM L4),
Dates AS(SELECT DATEADD(DAY,i-1,#D1) AS D FROM Nums where i <= 1+DATEDIFF(DAY,#D1,#D2)) ,
Stock As (
SELECT D ,t1.quantity - ISNULL(t2.solditems,0) AS itemsinstock
FROM Dates
LEFT OUTER JOIN #t1 t1 ON t1.periodend >= D and t1.periodstart <= D
LEFT OUTER JOIN #t2 t2 ON t2.periodend >= D and t2.periodstart <= D ),
NStock As (
select D,itemsinstock, ROW_NUMBER() over (order by D) - ROW_NUMBER() over (partition by itemsinstock order by D) AS G
from Stock)
SELECT MIN(D) AS periodstart, MAX(D) AS periodend, itemsinstock
FROM NStock
GROUP BY G, itemsinstock
ORDER BY periodstart
Hopefully a little easier to read than Martin's. I used different tables and sample data, hopefully extrapolating the right info:
CREATE TABLE [dbo].[Quantity](
[PeriodStart] [date] NOT NULL,
[PeriodEnd] [date] NOT NULL,
[Quantity] [int] NOT NULL
) ON [PRIMARY]
CREATE TABLE [dbo].[SoldItems](
[PeriodStart] [date] NOT NULL,
[PeriodEnd] [date] NOT NULL,
[SoldItems] [int] NOT NULL
) ON [PRIMARY]
INSERT INTO Quantity (PeriodStart,PeriodEnd,Quantity)
SELECT '20100101','20100115',5
INSERT INTO SoldItems (PeriodStart,PeriodEnd,SoldItems)
SELECT '20100105','20100107',2 union all
SELECT '20100106','20100108',1
The actual query is now:
;WITH Dates as (
select PeriodStart as DateVal from SoldItems union select PeriodEnd from SoldItems union select PeriodStart from Quantity union select PeriodEnd from Quantity
), Periods as (
select d1.DateVal as StartDate, d2.DateVal as EndDate
from Dates d1 inner join Dates d2 on d1.DateVal < d2.DateVal left join Dates d3 on d1.DateVal < d3.DateVal and d3.DateVal < d2.DateVal where d3.DateVal is null
), QuantitiesSold as (
select StartDate,EndDate,COALESCE(SUM(si.SoldItems),0) as Quantity
from Periods p left join SoldItems si on p.StartDate < si.PeriodEnd and si.PeriodStart < p.EndDate
group by StartDate,EndDate
)
select StartDate,EndDate,q.Quantity - qs.Quantity
from QuantitiesSold qs inner join Quantity q on qs.StartDate < q.PeriodEnd and q.PeriodStart < qs.EndDate
And the result is:
StartDate EndDate (No column name)
2010-01-01 2010-01-05 5
2010-01-05 2010-01-06 3
2010-01-06 2010-01-07 2
2010-01-07 2010-01-08 4
2010-01-08 2010-01-15 5
Explanation: I'm using three Common Table Expressions. The first (Dates) is gathering all of the dates that we're talking about, from the two tables involved. The second (Periods) selects consecutive values from the Dates CTE. And the third (QuantitiesSold) then finds items in the SoldItems table that overlap these periods, and adds their totals together. All that remains in the outer select is to subtract these quantities from the total quantity stored in the Quantity Table
John, what you could do is a WHILE loop. Declare and initialise 2 variables before your loop, one being the start date and the other being end date. Your loop would then look like this:
WHILE(#StartEnd <= #EndDate)
BEGIN
--processing goes here
SET #StartEnd = #StartEnd + 1
END
You would need to store your period definitions in another table, so you could retrieve those and output rows when required to a temporary table.
Let me know if you need any more detailed examples, or if I've got the wrong end of the stick!
Damien,
I am trying to fully understand your solution and test it on a large scale of data, but I receive following errors for your code.
Msg 102, Level 15, State 1, Line 20
Incorrect syntax near 'Dates'.
Msg 102, Level 15, State 1, Line 22
Incorrect syntax near ','.
Msg 102, Level 15, State 1, Line 25
Incorrect syntax near ','.
Damien,
Based on your solution I also wanted to get a neat display for StockItems without overlapping dates. How about this solution?
CREATE TABLE [dbo].[SoldItems](
[PeriodStart] [datetime] NOT NULL,
[PeriodEnd] [datetime] NOT NULL,
[SoldItems] [int] NOT NULL
) ON [PRIMARY]
INSERT INTO SoldItems (PeriodStart,PeriodEnd,SoldItems)
SELECT '20100105','20100106',2 union all
SELECT '20100105','20100108',3 union all
SELECT '20100115','20100116',1 union all
SELECT '20100101','20100120',10
;WITH Dates as (
select PeriodStart as DateVal from SoldItems
union
select PeriodEnd from SoldItems
union
select PeriodStart from Quantity
union
select PeriodEnd from Quantity
), Periods as (
select d1.DateVal as StartDate, d2.DateVal as EndDate
from Dates d1
inner join Dates d2 on d1.DateVal < d2.DateVal
left join Dates d3 on d1.DateVal < d3.DateVal and
d3.DateVal < d2.DateVal where d3.DateVal is null
), QuantitiesSold as (
select StartDate,EndDate,SUM(si.SoldItems) as Quantity
from Periods p left join SoldItems si on p.StartDate < si.PeriodEnd and si.PeriodStart < p.EndDate
group by StartDate,EndDate
)
select StartDate,EndDate, qs.Quantity
from QuantitiesSold qs
where qs.quantity is not null