Cumulative count over dates, discarding some values - sql

Question

I have an Answers table with the following schema:
CREATE TABLE Answers
([id] int, [analyst_id] int, [date] date);
I have to "accumulate-count" how many answers an analyst has per month, discarding any answers given before a period of 3 months after the last answer. Given the following:
INSERT INTO Answers
([id], [analyst_id], [date])
VALUES
(1, 1, '2017/01/01'),
(2, 1, '2017/02/01'), -- should be discarded
(3, 1, '2017/03/01'), -- should be discarded
(4, 1, '2017/05/01'),
(5, 1, '2017/06/01'), -- should be discarded
(6, 1, '2017/07/01'), -- should be discarded
(7, 1, '2017/08/01'),
(8, 2, '2017/01/01'),
(9, 2, '2017/04/01'),
(10, 1, '2018/02/01'),
(11, 2, '2018/03/01');
The expected result is:
analyst_id | month-year | count
-------------------------------
1 | 01/2017 | 1
1 | 02/2017 | 1
1 | 03/2017 | 1
1 | 04/2017 | 1
1 | 05/2017 | 2
1 | 06/2017 | 2
1 | 07/2017 | 2
1 | 08/2017 | 3
1 | 09/2017 | 3
1 | 10/2017 | 3
1 | 11/2017 | 3
1 | 12/2017 | 3
2 | 01/2017 | 1
2 | 02/2017 | 1
2 | 03/2017 | 1
2 | 04/2017 | 2
2 | 05/2017 | 2
2 | 06/2017 | 2
2 | 07/2017 | 2
2 | 08/2017 | 2
2 | 09/2017 | 2
2 | 10/2017 | 2
2 | 11/2017 | 2
2 | 12/2017 | 2
1 | 01/2018 | 0
1 | 02/2018 | 1
1 | 03/2018 | 1
2 | 01/2018 | 0
2 | 02/2018 | 0
2 | 03/2018 | 1
DBMS is a SQL Server 2012.
EDIT
I wrote this fiddle with my current half-solution: http://sqlfiddle.com/#!6/c2e82e/5
Each year, the count need to be reset.

Answer 1

EDIT:
OK, for the updated question, you essentially need to make a "dates" table (here a CTE called "D") that contains all the dates between the minimum and maximum date in your Answers table. Then you can essentially left join your results to that and use a DENSE_RANK() window function to determine the count.
DECLARE #Answers TABLE (ID INT, Analyst_ID INT, [Date] DATE);
INSERT #Answers (ID, Analyst_ID, [Date])
VALUES
(1, 1, '2017/01/01'),
(2, 1, '2017/02/01'),
(3, 1, '2017/03/01'),
(4, 1, '2017/05/01'),
(5, 1, '2017/06/01'),
(6, 1, '2017/07/01'),
(7, 1, '2017/08/01'),
(8, 2, '2017/01/01'),
(9, 2, '2017/04/01'),
(10, 1, '2018/02/01'),
(11, 2, '2018/03/01');
WITH CTE AS
(
SELECT A.Analyst_ID, [Date] = MIN(A.[Date])
FROM #Answers AS A
GROUP BY A.Analyst_ID
UNION ALL
SELECT A.Analyst_ID, A.[Date]
FROM
(
SELECT A.Analyst_ID, A.[Date], RN = ROW_NUMBER() OVER (PARTITION BY A.Analyst_ID ORDER BY A.ID)
FROM #Answers AS A
JOIN CTE
ON CTE.Analyst_ID = A.Analyst_ID
AND DATEADD(MONTH, 3, CTE.[Date]) <= A.[Date]
) AS A
WHERE A.RN = 1
),
D AS -- List of dates between minimum and maximum date in table for each analyst ID.
(
SELECT [Date] = DATEADD(MONTH, RN, (SELECT MIN([Date]) FROM #Answers)),
A.Analyst_ID
FROM (SELECT RN = ROW_NUMBER() OVER (ORDER BY (SELECT NULL)) - 1 FROM sys.objects) AS O
CROSS JOIN (SELECT DISTINCT Analyst_ID FROM #Answers) AS A
WHERE RN <= (SELECT DATEDIFF(MONTH, MIN([Date]), MAX([Date])) FROM #Answers)
)
SELECT D.Analyst_ID,
[Month-Year] = FORMAT(D.[Date], 'MM/yyyy'),
[Count] = CASE WHEN A.[Date] IS NULL THEN 0 ELSE DENSE_RANK() OVER (PARTITION BY D.Analyst_ID, DATEPART(YEAR, A.[Date]) ORDER BY A.[Date]) END
FROM D
OUTER APPLY (SELECT TOP 1 * FROM CTE WHERE CTE.[Date] <= D.[Date] AND DATEDIFF(YEAR, CTE.[Date], D.[Date]) = 0 AND CTE.Analyst_ID = D.Analyst_ID ORDER BY CTE.[Date] DESC) AS A
ORDER BY D.Analyst_ID, D.[Date];