Cumulative sum with group by and join - tsql

Question

I'm a little struggled with finding a clean way to do this. Assume that I have the following records in my table named Records:
|Name| |InsertDate| |Size|
john 30.06.2015 1
john 10.01.2016 10
john 12.01.2016 100
john 05.03.2016 1000
doe 01.01.2016 1
How do I get the records for year of 2016 and month is equal to or less than 3 grouped by month(even that month does not exists e.g. month 2 in this case) with cumulative sum of Size including that month? I want to get the result as the following:
|Name| |Month| |Size|
john 1 111
john 2 111
john 3 1111
doe 1 1

Answer 1

As other commenters have already stated, you simply need a table with dates in that you can join from to give you the dates that your source table does not have records for:
-- Build the source data table.
declare #t table(Name nvarchar(10)
,InsertDate date
,Size int
);
insert into #t values
('john','20150630',1 )
,('john','20160110',10 )
,('john','20160112',100 )
,('john','20160305',1000)
,('doe' ,'20160101',1 );
-- Specify the year you want to search for by storing the first day here.
declare #year date = '20160101';
-- This derived table builds a set of dates that you can join from.
-- LEFT JOINing from here is what gives you rows for months without records in your source data.
with Dates
as
(
select #year as MonthStart
,dateadd(day,-1,dateadd(month,1,#year)) as MonthEnd
union all
select dateadd(month,1,MonthStart)
,dateadd(day,-1,dateadd(month,2,MonthStart))
from Dates
where dateadd(month,1,MonthStart) < dateadd(yyyy,1,#year)
)
select t.Name
,d.MonthStart
,sum(t.Size) as Size
from Dates d
left join #t t
on(t.InsertDate <= d.MonthEnd)
where d.MonthStart <= '20160301' -- Without knowing what your logic is for specifying values only up to March, I have left this part for you to automate.
group by t.Name
,d.MonthStart
order by t.Name
,d.MonthStart;
If you have a static date reference table in your database, you don't need to do the derived table creation and can just do:
select d.DateValue
,<Other columns>
from DatesReferenceTable d
left join <Other Tables> o
on(d.DateValue = o.AnyDateColumn)
etc

Answer 2

Here's another approach that utilizes a tally table (aka numbers table) to create the date table. Note my comments.
-- Build the source data table.
declare #t table(Name nvarchar(10), InsertDate date, Size int);
insert into #t values
('john','20150630',1 )
,('john','20160110',10 )
,('john','20160112',100 )
,('john','20160305',1000)
,('doe' ,'20160101',1 );
-- A year is fine, don't need a date data type
declare #year smallint = 2016;
WITH -- dummy rows for a tally table:
E AS (SELECT E FROM (VALUES (1),(1),(1),(1),(1),(1),(1),(1),(1),(1)) t(e)),
dateRange(totalDays, mn, mx) AS -- Get the range and number of months to create
(
SELECT DATEDIFF(MONTH, MIN(InsertDate), MAX(InsertDate)), MIN(InsertDate), MAX(InsertDate)
FROM #t
),
iTally(N) AS -- Tally Oh! Create an inline Tally (aka numbers) table starting with 0
(
SELECT ROW_NUMBER() OVER (ORDER BY (SELECT 1))-1
FROM E a CROSS JOIN E b CROSS JOIN E c CROSS JOIN E d
),
RunningTotal AS -- perform a running total by year/month for each person (Name)
(
SELECT
yr = YEAR(DATEADD(MONTH, n, mn)),
mo = MONTH(DATEADD(MONTH, n, mn)),
Name,
Size = SUM(Size) OVER
(PARTITION BY Name ORDER BY YEAR(DATEADD(MONTH, n, mn)), MONTH(DATEADD(MONTH, n, mn)))
FROM iTally
CROSS JOIN dateRange
LEFT JOIN #t ON MONTH(InsertDate) = MONTH(DATEADD(MONTH, n, mn))
WHERE N <= totalDays
) -- Final output will only return rows where the year matches #year:
SELECT
name = ISNULL(name, LAG(Name, 1) OVER (ORDER BY yr, mo)),
yr, mo,
size = ISNULL(Size, LAG(Size, 1) OVER (ORDER BY yr, mo))
FROM RunningTotal
WHERE yr = #year
GROUP BY yr, mo, name, size;
Results:
name yr mo size
---------- ----------- ----------- -----------
doe 2016 1 1
john 2016 1 111
john 2016 2 111
john 2016 3 1111