Group by then Sort (SQL Server) - sql

Following the previous question
I have this query:
SELECT Acc.DocTLItem.TLRef ,
Acc.DocTLItem.Debit AS deb,
Acc.DocTLItem.Credit AS cred,
info.MiladiToShamsi(Acc.DocTLItem.StartDocDate) Date,
Acc.TL.TLCode ,
Acc.DocTLItem.DocTLHeaderRef ,
Acc.DocTLHeader.Num
FROM Acc.DocTLItem
INNER JOIN Acc.TL ON Acc.DocTLItem.TLRef = Acc.TL.Id
INNER JOIN Acc.DocTLHeader ON Acc.DocTLItem.DocTLHeaderRef = Acc.DocTLHeader.Id
ORDER BY ( CASE WHEN debit > 0 THEN 0 ELSE 1 END ) ,
Acc.TL.TLCode ,
debit
Result:
TLRef deb cred Date TLCode DocTLHeaderRef Num
--------------------------------------------------------------------------
44 1 0 1396/09/12 111 16 2
44 1 0 1396/09/21 111 18 4
28 13 0 1396/09/11 982 15 1
28 10 0 1396/09/19 982 17 3
44 0 10 1396/09/19 111 17 3
44 0 1 1396/09/21 111 18 4
44 0 9 1396/09/11 111 15 1
44 0 1 1396/09/12 111 16 2
How can I Group by Date then sort by Date?
I need to generate a result set like this that debt comes first and then ordered by TLCode column after all group by date.
Expected result:
TLRef deb cred Date TLCode DocTLHeaderRef Num
--------------------------------------------------------------------------------
44 1 0 1396/09/12 111 16 2
28 13 0 1396/09/11 982 15 1
28 10 0 1396/09/19 982 17 3
44 0 9 1396/09/11 111 15 1
44 0 1 1396/09/12 111 16 2
44 0 10 1396/09/19 111 17 3
Sum 24 20
44 1 0 1396/09/21 111 18 4
44 0 1 1396/09/21 111 18 4
Sum 1 1

May be following query block can help you:
This query will work in 4 steps:
--1. Create a temporary table that we can take as base table (#TMP)
Select *
INTO #TMP
From
(
Select 44 as TLRef, 1 as deb, 0 as cred, '1396/09/12' as Date, 111 as TLCode, 16 as DocTLHeaderRef, 2 as Num Union All
Select 44 as TLRef, 1 as deb, 0 as cred, '1396/09/21' as Date, 111 as TLCode, 18 as DocTLHeaderRef, 4 as Num Union All
Select 28 as TLRef, 13 as deb, 0 as cred, '1396/09/11' as Date, 982 as TLCode, 15 as DocTLHeaderRef, 1 as Num Union All
Select 28 as TLRef, 10 as deb, 0 as cred, '1396/09/19' as Date, 982 as TLCode, 17 as DocTLHeaderRef, 3 as Num Union All
Select 44 as TLRef, 0 as deb, 10 as cred, '1396/09/19' as Date, 111 as TLCode, 17 as DocTLHeaderRef, 3 as Num Union All
Select 44 as TLRef, 0 as deb, 1 as cred, '1396/09/21' as Date, 111 as TLCode, 18 as DocTLHeaderRef, 4 as Num Union All
Select 44 as TLRef, 0 as deb, 9 as cred, '1396/09/11' as Date, 111 as TLCode, 15 as DocTLHeaderRef, 1 as Num Union All
Select 44 as TLRef, 0 as deb, 1 as cred, '1396/09/12' as Date, 111 as TLCode, 16 as DocTLHeaderRef, 2 as Num
) X
--2. Group table by "Date" and select sum of "deb", "cred" columns and insert result in another temporary table (#TMP2)
Select null as TLRef, SUM(deb) as deb, SUM(cred) as cred, Date, null as TLCode, null as DocTLHeaderRef, null as Num
INTO #TMP2
From #TMP
GROUP BY Date
--3. Union both tables to resulting table gets both detail and grouped data.
Select *
From
(
Select *, 0 as IsDetail From #TMP
Union All
Select *, 1 as IsDetail From #TMP2
) X
Order By Date,IsDetail
--4. Drop both temporary table
DROP TABLE #TMP
DROP TABLE #TMP2

You can try this for sorting.
;WITH CTE AS (
SELECT Acc.DocTLItem.TLRef ,
Acc.DocTLItem.Debit AS deb,
Acc.DocTLItem.Credit AS cred,
info.MiladiToShamsi(Acc.DocTLItem.StartDocDate) Date,
Acc.TL.TLCode ,
Acc.DocTLItem.DocTLHeaderRef ,
Acc.DocTLHeader.Num,
ROW_NUMBER() OVER(PARTITION BY Acc.DocTLItem.Debi, Acc.DocTLItem.Credit, Acc.TL.TLCode ORDER BY Acc.DocTLItem.StartDocDate ) AS RN
FROM Acc.DocTLItem
INNER JOIN Acc.TL ON Acc.DocTLItem.TLRef = Acc.TL.Id
INNER JOIN Acc.DocTLHeader ON Acc.DocTLItem.DocTLHeaderRef = Acc.DocTLHeader.Id
)
SELECT * FROM CTE
ORDER BY
RN,
( CASE WHEN deb > 0 THEN 0 ELSE 1 END ) ,
TLCode ,
[Date],
deb

Related

Counts and divide from two different selects with dates

I have a table with this kind of structure (Sample only)
ID | STATUS | DATE |
--- -------- ------
1 OPEN 31-01-2022
2 CLOSE 15-11-2021
3 CLOSE 21-10-2021
4 OPEN 11-10-2021
5 OPEN 28-09-2021
I would like to know the counts of close vs open records by week. So it will be count(close)/count(open) where close.week = open.week
If there are no matching values, need to return 0 of course.
I got to this query below
SELECT *
FROM
(SELECT COUNT(*) AS 'CLOSE', DATEPART(WEEK, DATE) AS 'WEEKSA', DATEPART(YEAR, DATE) AS 'YEARA' FROM TABLE
WHERE STATUS IN ('CLOSE')
GROUP BY DATEPART(WEEK, DATE),DATEPART(YEAR, DATE)) TMPA
FULL OUTER JOIN
(SELECT COUNT(*) AS 'OPEN', DATEPART(WEEK, DATE) AS 'WEEKSB', DATEPART(YEAR, DATE) AS 'YEARB' FROM TABLE
WHERE STATUS IN ('OPEN')
GROUP BY DATEPART(WEEK, DATE),DATEPART(YEAR, DATE)) TMPB
ON TMPA.WEEKSA = TMPB.WEEKSB AND TMPA.YEARA = TMPB.YEARB
My results are as below (sample only)
close | weeksa | yeara | open | weeksb | yearb |
------ -------- ------ ------- ------- ------
3 2 2021
1 3 2021
1 4 2021
2 20 2021 2 20 2021
7 22 2021
2 23 2021
7 26 2021
7 27 2021
2 28 2021 14 28 2021
2 29 2021
10 30
24 31 2021
2 32 2021 5 32
4 33 2021
1 34 2021 13 34 2021
6 35 2021
1 36 2021
1 38 2021
1 39 2021
2 41 2021
4 43 2021
1 45 2021
2 46 2021 25 46 2021
1 47 2021 5 47 2021
4 48 2021
1 49 2021 20 49 2021
1 50 2021 17 50 2021
1 51 2021
How do I do the math now?
If I do another select the query fails. So I guess either syntax is bad or the whole concept is wrong.
The required result should look like this (Sample)
WEEK | YEAR | RATIO |
----- ------ -------
2 2021 0
3 2021 0
4 2021 0
5 2021 0.93
20 2021 0.1
22 2021 0
23 2021 0
26 2021 0
1 2022 0.75
2 2022 0.23
4 2022 0.07
Cheers!
I have added some test data to check the logic, adding the same in the code.
;with cte as(
select 1 ID, 'OPEN' as STATUS, cast('2021 -01-31' as DATE) DATE
union select 10 ID, 'CLOSE' as STATUS, cast('2021 -01-31' as DATE) DATE
union select 11 ID, 'CLOSE' as STATUS, cast('2021 -01-31' as DATE) DATE
union select 12 ID, 'CLOSE' as STATUS, cast('2021 -01-31' as DATE) DATE
union select 22 ID, 'CLOSE' as STATUS, cast('2021 -01-31' as DATE) DATE
union select 32 ID, 'CLOSE' as STATUS, cast('2021 -01-31' as DATE) DATE
union select 2,'CLOSE',cast('2021-11-28' as DATE)
union select 3,'CLOSE',cast('2021-10-21' as DATE)
union select 8,'CLOSE',cast('2021-10-21' as DATE)
union select 9,'CLOSE',cast('2021-10-21' as DATE)
union select 4,'OPEN', cast('2021-10-11' as DATE)
union select 5,'CLOSE', cast('2021-09-28' as DATE)
union select 6,'OPEN', cast('2021-09-27' as DATE)
union select 7,'CLOSE', cast('2021-09-26' as DATE) )
, cte2 as (
select DATEPART(WEEK,date) as week_number,* from cte)
,cte3 as(
select week_number,year(date) yr,count(case when status = 'open' then 1 end)open_count,count(case when status <> 'open' then 1 end) close_count from cte2 group by week_number,year(date))
select week_number as week,yr as year,
cast(case when open_count = 0 then 1.0 else open_count end /
case when close_count = 0 then 1.0 else close_count end as numeric(3,2)) as ratio
from cte3

Count many columns have the same value

How do I write an SQL query to return count the similar values for each column in one row?
I have this:
emp_no
d1
d2
d3
d4
d5
d6
d7
d8
d9
d10
date
1002
2
2
2
26
26
4
4
53
53
53
2021-03-31
1003
4
4
4
26
26
2
26
26
26
26
2021-03-31
1002
2
2
2
26
26
4
4
26
26
26
2021-04-30
I want the result like this:
emp_no
2
4
26
51
53
date
1002
3
2
2
0
3
2021-03-31
1003
1
3
6
0
0
2021-03-31
1002
3
2
2
0
3
2021-04-30
I try UNPIVOT data, but how I can pivot this?
Do I create a view with unpivot data and after that re-pivot the aggregated data?
SELECT EMP_NO, TS_MTH_YR, TSS_D
FROM (
SELECT EMP_NO, TS_MTH_YR, [D1], [D2], [D3], [D4], [D5], [D6], [D7], [D8], [D9], [D10]
FROM TSS_MONTHLY_TS
) AS TSS
UNPIVOT (
TSS_D FOR TSS_DAYS IN ([D1], [D2], [D3], [D4], [D5], [D6], [D7], [D8], [D9], [D10])
) AS TS
As I mentioned in the comments, you'll need to both unpivot and then repivot your data here. One method would therefore be the below:
WITH YourTable AS(
SELECT emp_no ,d1 ,d2 ,d3 ,d4 ,d5 ,d6 ,d7 ,d8 ,d9 ,d10 , CONVERT(date,date) AS date --That's not confusing
FROM (VALUES(1002,2,2,2,26,26,4,4 ,53 ,53 ,53 ,'2021-03-31'),
(1003,4,4,4,26,26,2,26, 26, 26, 26,' 2021-03-31'),
(1002,2,2,2,26,26,4,4 ,26 ,26 ,26 ,'2021-04-30'))V(emp_no ,d1 ,d2 ,d3 ,d4 ,d5 ,d6 ,d7 ,d8 ,d9 ,d10 ,date))
SELECT YT.emp_no,
COUNT(CASE V.Val WHEN 2 THEN 1 END) AS [2],
COUNT(CASE V.Val WHEN 4 THEN 1 END) AS [4],
COUNT(CASE V.Val WHEN 26 THEN 1 END) AS [26],
COUNT(CASE V.Val WHEN 51 THEN 1 END) AS [51],
COUNT(CASE V.Val WHEN 53 THEN 1 END) AS [53],
YT.[date]
FROM YourTable YT
CROSS APPLY (VALUES('d1',YT.d1),
('d2',YT.d2),
('d3',YT.d3),
('d4',YT.d4),
('d5',YT.d5),
('d6',YT.d6),
('d7',YT.d7),
('d8',YT.d8),
('d9',YT.d9),
('d10',YT.d10))V(Col,Val)
GROUP BY YT.emp_no,
YT.[date];

How to split the column values after a certain number

I have a dataset that looks like this:
ID HoursWorked TotalHours
23 1 1
23 1 2
23 1 3
23 0.5 3.5
23 1 4.5
23 1 5.5
23 1 6.5
23 1 7.5
23 1 8.5
61 1 1
61 1 2
What I want to do is if the total hours hits 8 hours, I want to split that row (e.g. 8.5 in the sample data above) so that an employee always has the total hours of 8. If someone works over 8 hours it should continue after hitting 8 in the totalhours column. For example, I want something like this as my final result.
ID HoursWorked TotalHours
23 1 1
23 1 2
23 1 3
23 0.5 3.5
23 1 4.5
23 1 5.5
23 1 6.5
23 1 7.5
23 0.5 8 *
23 0.5 8.5 *
61 1 1
61 1 2
As you can see the row which originally had 8.5 for its totalhours got broken down into two different rows.
I couldn't think of any way to do this in SQL Server. I'd appreciate any help on this.
see if this works.
select ID,HoursWorked,TotalHours from table_name where TotalHours <=8
union
select ID,(HoursWorked-(TotalHours-8) as HoursWorked ,8 as TotalHours from table_name where TotalHours >8
union
select ID,(TotalHours-8) as HoursWorked ,TotalHours from table_name where TotalHours >8
This seems rather complicated. This approach takes all the rows before 8 hours. It then finds the row that first passes 8 hours and splits that one as needed:
select id, hoursworked, totalhours
from t
where totalhours <= 8
union all
select t.id, v.hoursworked, v.totalhours
from (select t.*, row_number() over (partition by id order by totalhours) as seqnum
from t
where totalhours > 8
) t cross apply
(values (case when seqnum = 1 then totalhours - 8 end,
case when seqnum = 1 then 8 end
),
(case when seqnum = 1 and totalhours >= 8 then totalhours - 8 else hoursworked end,
totalhours
)
) v(hoursworked, totalhours)
where v.hoursworked > 0
order by id, totalhours;
Here is a db<>fiddle.

Fill in gaps in year sequence in SQL Server

I have a table with the columns Age, Period and Year. The column Age always starts with 0 and doesn't have a fixed maximum value (I used 'Age' 0 to 30 in this example but the range could also be 0 to 100 etc.), the values Period and Year only appear in certain rows at certain ages.
However at what Age the values for Period and Year appear, changes and the solution should therefore be dynamic. What is the best way to fill in the NULL values with correct Period and Year?
I am using SQL Server.
Age Period Year
-----------------
0 NULL NULL
1 NULL NULL
2 NULL NULL
3 NULL NULL
4 NULL NULL
5 NULL NULL
6 NULL NULL
7 NULL NULL
8 NULL NULL
9 NULL NULL
10 NULL NULL
11 NULL NULL
12 NULL NULL
13 NULL NULL
14 NULL NULL
15 NULL NULL
16 NULL NULL
17 NULL NULL
18 NULL NULL
19 NULL NULL
20 NULL NULL
21 46 2065
22 NULL NULL
23 NULL NULL
24 NULL NULL
25 NULL NULL
26 51 2070
27 NULL NULL
28 NULL NULL
29 NULL NULL
30 NULL NULL
The result should look like this, the numbers for Period and Year should be increased and/or decrease from the last known values for Period and Year.
Age Period Year
-----------------
0 25 2044
1 26 2045
2 27 2046
3 28 2047
4 29 2048
5 30 2049
6 31 2050
7 32 2051
8 33 2052
9 34 2053
10 35 2054
11 36 2055
12 37 2056
13 38 2057
14 39 2058
15 40 2059
16 41 2060
17 42 2061
18 43 2062
19 44 2063
20 45 2064
21 46 2065
22 47 2066
23 48 2067
24 49 2068
25 50 2069
26 51 2070
27 52 2071
28 53 2072
29 54 2073
30 55 2074
Here is an UPDATE to my question as I didn't specify my requirement detailed enough:
The solution should be able to handle different combinations of Age, Period and Year. My start point will always be a known Age, Period and Year combination. However, the combination Age = 21, Period = 46 and Year = 2065 (or 26|51|2070 as the second combination) in my example is not static. The value at Age = 21 could be anything e.g. Period = 2 and Year = 2021. Whatever the combination (Age, Period, Year) is, the solution should fill in the gaps and finish the sequence counting up and down from the known values for Period and Year. If a Period value sequence becomes negative the solutions should return NULL values, if possible.
Seem you have always the same increment for age and year
so
select age, isnull(period,age +25) Period, isnull(year,age+44) year
from yourtable
or the standard function coalesce (as suggested by Gordon Linoff)
select age, coalesce(period,age +25) Period, coalesce(year,age+44) year
from yourtable
Tabel creation code
create table yourtable ( AGE int , Period int, Year int )
insert into yourtable
Select 0 AS AGE , null As Period , null As Year UNION all
Select 1 AS AGE , null As Period , null As Year UNION all
Select 2 AS AGE , null As Period , null As Year UNION all
Select 3 AS AGE , null As Period , null As Year UNION all
Select 4 AS AGE , null As Period , null As Year UNION all
Select 5 AS AGE , null As Period , null As Year UNION all
Select 6 AS AGE , null As Period , null As Year UNION all
Select 7 AS AGE , null As Period , null As Year UNION all
Select 8 AS AGE , null As Period , null As Year UNION all
Select 9 AS AGE , null As Period , null As Year UNION all
Select 10 AS AGE , null As Period , null As Year UNION all
Select 11 AS AGE , null As Period , null As Year UNION all
Select 12 AS AGE , null As Period , null As Year UNION all
Select 13 AS AGE , null As Period , null As Year UNION all
Select 14 AS AGE , null As Period , null As Year UNION all
Select 15 AS AGE , null As Period , null As Year UNION all
Select 16 AS AGE , null As Period , null As Year UNION all
Select 17 AS AGE , null As Period , null As Year UNION all
Select 18 AS AGE , null As Period , null As Year UNION all
Select 19 AS AGE , null As Period , null As Year UNION all
Select 20 AS AGE , null As Period , null As Year UNION all
Select 21 AS AGE ,46 As Period ,2065 As Year UNION all
Select 22 AS AGE , null As Period , null As Year UNION all
Select 23 AS AGE , null As Period , null As Year UNION all
Select 24 AS AGE , null As Period , null As Year UNION all
Select 25 AS AGE , 51 As Period ,2070 As Year UNION all
Select 26 AS AGE , null As Period , null As Year UNION all
Select 27 AS AGE , null As Period , null As Year UNION all
Select 28 AS AGE , null As Period , null As Year UNION all
Select 29 AS AGE , null As Period , null As Year UNION all
Select 30 AS AGE , null As Period , null As Year
**Steps **
We need to get one row with non null value for Period and year.
Using age get first value for both the column .
Now just add respective age column value and fill full table .
Code to fix the serial
;with tmp as
(select top 1 * from yourtable where Period is not null and year is not null)
update yourtable
set Period = (tmp.Period - tmp.age) + yourtable.age
, year = (tmp.year - tmp.age) + yourtable.age
from yourtable , tmp
OR
Declare #age int ,#Year int ,#Period int
select #age = age , #Year = year - (age +1) ,#Period = Period- (AGE +1)
from yourtable where Period is not null and year is not null
update yourtable
set Period =#Period + age
,Year =#year + age
from yourtable
You finally want three sequences with different start values. Then you simply need to calculate an offset and add it to age:
with cte as
(
select age
,max(period - age) over () + age as period -- adjusted period
,max(yr - age) over () + age as yr -- adjusted yr
from #yourtable
)
select age
-- If a Period value sequence becomes negative the solutions should return NULL
,case when period >0 then period end as period
,yr
from cte
See fiddle
-- hope you can manage the syntax error. but some logic like given below should work in this case where we can make period an origin to calculate other missing values. good luck!
declare #knownperiod int;
declare #knownperiodage int;
declare #agetop int;
declare #agebottom int;
#knownperiod = select top 1 period from table1 where period is not null
#knownperiodage = select top 1 age from table1 where period is not null
while(#knownperiodage >= 0)
begin
#knownperiod = #knownperiod -1 ;
#knownperiodage = #knownperiodage -1;
update table1 set period = #knownperiod, year = YEAR(GetDate())+#knownperiod-1 where age = #knownperiodage
end
-- now for bottom age
#knownperiod = select top 1 period from table1 where period is null or year is null
#knownperiodage = select top 1 age from table1 where period is null or year is null
while(#knownperiodage <= (Select max(age) from table1))
begin
#knownperiod = #knownperiod +1 ;
#knownperiodage = #knownperiodage +1;
update table1 set period = #knownperiod, year = YEAR(GetDate())+#knownperiod-1 where age = #knownperiodage
end
Is the process to first calculate the increments (age -> period and age -> year) then simply add those increments to the age values?
This assumes the differences between age and period, and age and year, are consistent across rows (just not filled in sometimes).
As such, you could use the following to first calculate the increments (PeriodInc, YrInc) and then select the values with the increments added (noting that if period goes negative, it gets NULL).
; WITH PeriodInc AS (SELECT TOP 1 Period - Age AS PeriodInc FROM #yourtable WHERE Period IS NOT NULL),
YrInc AS (SELECT TOP 1 Yr - Age AS YrInc FROM #yourtable WHERE Yr IS NOT NULL)
SELECT Age,
CASE WHEN (Age + PeriodInc) >= 0 THEN (Age + PeriodInc) ELSE NULL END AS Period,
Age + YrInc AS Yr
FROM #yourtable
CROSS JOIN PeriodInc
CROSS JOIN YrInc
Here is a DB_Fiddle with the code
This solution takes 4 inputs:
#list_length -- (integer) the number of rows to generate (up to 12^5=248,832)
#start_age -- (integer) beginning age
#start_period -- (integer) beginning period
#start_year -- (integer) beginning year
For any combination of inputs this code generates the requested output. If either the Age or Year is calculated to be negative then it is converted to NULL. The current limit to the list length could be increased to whatever is necessary. The technique of creating a row_number using cross applied rows is known to be very fast when generating large sequences. Above about 500 rows it's always faster than a recursion based CTE. At small row numbers there's little to no performance difference between the two techniques.
Here are the code and output to match the example data.
Inputs
declare
#list_length int=31,
#start_age int=21,
#start_period int=46,
#start_year int=2065;
Code
with
n(n) as (select * from (values (1),(2),(3),(4),(5),(6),(7),(8),(9),(10),(11),(12)) v(n)),
tally_cte(n) as (
select row_number() over (order by (select null))
from n n1 cross join n n2 cross join n n3 cross join n n4 cross join n n5)
select p.Age,
case when p.[Period]<0 then null else p.[Period] end [Period],
case when p.[Year]<0 then null else p.[Year] end [Year]
from tally_cte t
cross apply
(select (t.n-1) [Age], (t.n-1)+(#start_period-#start_age) [Period],
(t.n-1)+(#start_year-#start_age) [Year]) p
where n<=#list_length;
Output
Age Period Year
0 25 2044
1 26 2045
2 27 2046
3 28 2047
4 29 2048
5 30 2049
6 31 2050
7 32 2051
8 33 2052
9 34 2053
10 35 2054
11 36 2055
12 37 2056
13 38 2057
14 39 2058
15 40 2059
16 41 2060
17 42 2061
18 43 2062
19 44 2063
20 45 2064
21 46 2065
22 47 2066
23 48 2067
24 49 2068
25 50 2069
26 51 2070
27 52 2071
28 53 2072
29 54 2073
30 55 2074
Suppose both the Period and the Year are less than the start Age. When the calculated values are negative the value is replaced with a NULL.
Inputs
declare
#list_length int=100,
#start_age int=10,
#start_period int=5,
#start_year int=8;
Output
Age Period Year
0 NULL NULL
1 NULL NULL
2 NULL 0
3 NULL 1
4 NULL 2
5 0 3
6 1 4
7 2 5
8 3 6
9 4 7
10 5 8
11 6 9
12 7 10
...
99 94 97
Imo this is a flexible and efficient way to meet all of the requirements. Please let me know if there are any issues.
This reads like a gaps-and-islands problem, where "empty" rows are the gaps and non-empty rows are the islands.
You want to fill the gaps. Your question is a bit tricky, because you do not clearly describe how to proceed when a gap row has both preceding and following islands - and what to do if they are not consistent.
Let me assume that you want to derive the value from the following island if there is one available, and fall back of the precedng island.
Here is an approach using lateral joins to retrieve the next and preceding non-empty row:
select t.age,
coalesce(t.period, n.period - n.diff, p.period - p.diff) period,
coalesce(t.year, n.year - n.diff, p.year - p.diff) year
from mytable t
outer apply (
select top (1) t1.*, t1.age - t.age diff
from mytable t1
where t1.age > t.age and t1.period is not null and t1.year is not null
order by t1.age
) n
outer apply (
select top (1) t1.*, t1.age - t.age diff
from mytable t1
where t1.age < t.age and t1.period is not null and t1.year is not null
order by t1.age desc
) p
order by t.age
Actually, this would probably be more efficiently performed with window functions. We can implement the very same logic by building groups of records with window counts, then doing the computation within the groups:
select
age,
coalesce(
period,
max(period) over(partition by grp2) - max(age) over(partition by grp2) + age,
max(period) over(partition by grp1) - min(age) over(partition by grp1) + age
) period,
coalesce(
year,
max(year) over(partition by grp2) - max(age) over(partition by grp2) + age,
max(year) over(partition by grp1) - min(age) over(partition by grp1) + age
) year
from (
select t.*,
count(period) over(order by age) grp1,
count(period) over(order by age desc) grp2
from mytable t
) t
order by age
Demo on DB Fiddle - both queries yield:
age | period | year
--: | -----: | ---:
0 | 25 | 2044
1 | 26 | 2045
2 | 27 | 2046
3 | 28 | 2047
4 | 29 | 2048
5 | 30 | 2049
6 | 31 | 2050
7 | 32 | 2051
8 | 33 | 2052
9 | 34 | 2053
10 | 35 | 2054
11 | 36 | 2055
12 | 37 | 2056
13 | 38 | 2057
14 | 39 | 2058
15 | 40 | 2059
16 | 41 | 2060
17 | 42 | 2061
18 | 43 | 2062
19 | 44 | 2063
20 | 45 | 2064
21 | 46 | 2065
22 | 47 | 2066
23 | 48 | 2067
24 | 49 | 2068
25 | 50 | 2069
26 | 51 | 2070
27 | 52 | 2071
28 | 53 | 2072
29 | 54 | 2073
30 | 55 | 2074
Also you can use recursive CTE (it can handle any variation of data in the table except only one that has no populated period and year at all):
WITH cte AS ( -- get any filled period and year
SELECT TOP 1 period - age delta,
[year]-period start_year
FROM tablename
WHERE period is not null and [year] is not null
), seq AS ( --get min and max age values
SELECT MIN(age) as min_age, MAX(age) as max_age
FROM tablename
), go_recursive AS (
SELECT min_age age,
min_age+delta period ,
start_year+min_age+delta year,
max_age
FROM seq
CROSS JOIN cte --That will generate the initial first row
UNION ALL
SELECT age + 1,
period +1,
year + 1,
max_age
FROM go_recursive
WHERE age < max_age --This part increments the data from first row
)
SELECT age,
period,
[year]
FROM go_recursive
OPTION (MAXRECURSION 0)
-- If you know there are some limit of rows in that kind of tables
--use this row count instead 0

Count parts of total value as columns per row (pivot table)

I'm stuck with a seemingly easy query, but couldn't manage to get it working the last hours.
I have a table files that holds file names and some values like records in this file, DATE of creation (create_date), DATE of processing (processing_date) and so on. There can be multiple files for a create date in different hours and it is likely that they will not get processed in the same day of creaton, in fact it can even take up to three days or longer for them to get processed.
So let's assume I have these rows, as an example:
create_date | processing_date
------------------------------
2012-09-10 11:10:55.0 | 2012-09-11 18:00:18.0
2012-09-10 15:20:18.0 | 2012-09-11 13:38:19.0
2012-09-10 19:30:48.0 | 2012-09-12 10:59:00.0
2012-09-11 08:19:11.0 | 2012-09-11 18:14:44.0
2012-09-11 22:31:42.0 | 2012-09-21 03:51:09.0
What I want in a single query is to get a grouped column truncated to the day create_date with 11 additional columns for the differences between the processing_date and the create_date, so that the result should roughly look like this:
create_date | diff0days | diff1days | diff2days | ... | diff10days
------------------------------------------------------------------------
2012-09-10 | 0 2 1 ... 0
2012-09-11 | 1 0 0 ... 1
and so on, I hope you get the point :)
I have tried this and so far it works getting a single aggregated column for a create_date with a difference of - for example - 3:
SELECT TRUNC(f.create_date, 'DD') as created, count(1) FROM files f WHERE TRUNC(f.process_date, 'DD') - trunc(f.create_date, 'DD') = 3 GROUP BY TRUNC(f.create_date, 'DD')
I tried combining the single queries and I tried sub-queries, but that didn't help or at least my knowledge about SQL is not sufficient.
What I need is a hint so that I can include the various differences as columns, like shown above. How could I possibly achieve this?
That's basically the pivoting problem:
SELECT TRUNC(f.create_date, 'DD') as created
, sum(case TRUNC(f.process_date, 'DD') - trunc(f.create_date, 'DD')
when 0 then 1 end) as diff0days
, sum(case TRUNC(f.process_date, 'DD') - trunc(f.create_date, 'DD')
when 1 then 1 end) as diff1days
, sum(case TRUNC(f.process_date, 'DD') - trunc(f.create_date, 'DD')
when 2 then 1 end) as diff2days
, ...
FROM files f
GROUP BY
TRUNC(f.create_date, 'DD')
SELECT CreateDate,
sum(CASE WHEN DateDiff(day, CreateDate, ProcessDate) = 1 THEN 1 ELSE 0 END) AS Diff1,
sum(CASE WHEN DateDiff(day, CreateDate, ProcessDate) = 2 THEN 1 ELSE 0 END) AS Diff2,
...
FROM table
GROUP BY CreateDate
ORDER BY CreateDate
As you are using Oracle 11g you can also get desired result by using pivot query.
Here is an example:
-- sample of data from your question
SQL> create table Your_table(create_date, processing_date) as
2 (
3 select '2012-09-10', '2012-09-11' from dual union all
4 select '2012-09-10', '2012-09-11' from dual union all
5 select '2012-09-10', '2012-09-12' from dual union all
6 select '2012-09-11', '2012-09-11' from dual union all
7 select '2012-09-11', '2012-09-21' from dual
8 )
9 ;
Table created
SQL> with t2 as(
2 select create_date
3 , processing_date
4 , to_date(processing_date, 'YYYY-MM-DD')
- To_Date(create_date, 'YYYY-MM-DD') dif
5 from your_table
6 )
7 select create_date
8 , max(diff0) diff0
9 , max(diff1) diff1
10 , max(diff2) diff2
11 , max(diff3) diff3
12 , max(diff4) diff4
13 , max(diff5) diff5
14 , max(diff6) diff6
15 , max(diff7) diff7
16 , max(diff8) diff8
17 , max(diff9) diff9
18 , max(diff10) diff10
19 from (select *
20 from t2
21 pivot(
22 count(dif)
23 for dif in ( 0 diff0
24 , 1 diff1
25 , 2 diff2
26 , 3 diff3
27 , 4 diff4
28 , 5 diff5
29 , 6 diff6
30 , 7 diff7
31 , 8 diff8
32 , 9 diff9
33 , 10 diff10
34 )
35 ) pd
36 ) res
37 group by create_date
38 ;
Result:
Create_Date Diff0 Diff1 Diff2 Diff3 Diff4 Diff5 Diff6 Diff7 Diff8 Diff9 Diff10
--------------------------------------------------------------------------------
2012-09-10 0 2 1 0 0 0 0 0 0 0 0
2012-09-11 1 0 0 0 0 0 0 0 0 0 1