Optimising T-SQL reporting performance - tsql

Question

I have the table bellow, I need to delete opposite rows between two dates by pairs based on PerCode Value,
In fact, we delete rows inside the date range that have the same PerCode and have equal and opposite values.
The problem is that begin date and end date are provided by users as parameters while reporting but the query take too much time if i try to delete these at runtime.
Example:
Begin date = 01/01/2018
End date = 31/12/2018
I should delete rows 3 and 4.
Do u have any idea how to do that while optimising performance (the table have 200 Millions of rows)
+----+------------+---------+---------+-----------+
| Id | Date | PerCode | Value | IsDeleted |
+----+------------+---------+---------+-----------+
| 1 | 01/10/2017 | C1 | 10 | |
| 2 | 01/01/2018 | C1 | -10 | |
| 3 | 15/02/2018 | C2 | 20 | 1 |
| 4 | 10/03/2018 | C2 | -20 | 1 |
| 5 | 01/12/2018 | C3 | 15 | |
| 6 | 01/02/2019 | C3 | -15 | |
+----+------------+---------+---------------------+

Answer 1

I had a quick go at this, using a table variable to allow me to knock together a query using your test data. However, this might not perform well when used over 2 million rows?
DECLARE #table TABLE (id INT, [date] DATE, percode CHAR(2), [value] INT, isdeleted BIT);
INSERT INTO #table
SELECT 1, '20171001', 'C1', 10, NULL
UNION ALL
SELECT 2, '20180101', 'C1', -10, NULL
UNION ALL
SELECT 3, '20180215', 'C2', 20, NULL
UNION ALL
SELECT 4, '20180310', 'C2', -20, NULL
UNION ALL
SELECT 5, '20181201', 'C3', 15, NULL
UNION ALL
SELECT 6, '20190201', 'C3', -15, NULL;
DECLARE #date_from DATE = '20180101';
DECLARE #date_to DATE = '20181231';
WITH ordered AS (
SELECT
id,
percode,
[value],
ROW_NUMBER() OVER (PARTITION BY percode, [value] ORDER BY [value]) AS order_id
FROM
#table
WHERE
[date] BETWEEN #date_from AND #date_to
AND ISNULL(isdeleted, 0) != 1),
matches AS (
SELECT
m1.id AS match_1_id,
m2.id AS match_2_id
FROM
ordered m1
INNER JOIN ordered m2 ON m1.percode = m2.percode AND m1.[value] = m2.[value] * -1 AND m1.order_id = m2.order_id)
UPDATE
t
SET
isdeleted = 1
FROM
#table t
INNER JOIN matches m ON m.match_1_id = t.id OR m.match_2_id = t.id;
SELECT * FROM #table;
Results:
id date percode value isdeleted
1 2017-10-01 C1 10 NULL
2 2018-01-01 C1 -10 NULL
3 2018-02-15 C2 20 1
4 2018-03-10 C2 -20 1
5 2018-12-01 C3 15 NULL
6 2019-02-01 C3 -15 NULL
How does it work? Well I broke the task down into steps:
make a list of all rows in the date period specified, where they aren't already deleted;
for each row of data assign it a running count number, grouped by the percode and the value. So the first C1 10 would be number #1, then the second C1 10 would be number #2, etc.;
to find matches it's simply a case of finding any value that has the same percode, the equal and opposite value to another value group, and the same running count number;
where there's a match set the isdeleted flag to 1.

Answer 2

Here is my code but this is not performant over 200 millions rows in real time.
and in real life Percode is concatenation of 5 columns (date, varchar(13), varchar(2),varchar(1) and varchar(50)) and Value is 4 numeric columns.
I am searching for other ideas.
--DECLARE #table TABLE (id INT, [date] DATE, percode CHAR(2), [value] INT, isdeleted BIT);
Select * INTO #MasterTable FROM
(
SELECT 1 id, '20171001' [date], 'C1' percode, 10 [value], NULL isdeleted
UNION ALL
SELECT 2, '20180101', 'C1', -10, NULL
UNION ALL
SELECT 3, '20180215', 'C2', 20, NULL
UNION ALL
SELECT 4, '20180310', 'C2', -20, NULL
UNION ALL
SELECT 5, '20181201', 'C3', 15, NULL
UNION ALL
SELECT 6, '20190201', 'C3', -15, NULL
) T ;
DECLARE #date_from DATE = '20180101';
DECLARE #date_to DATE = '20181231';
select F.id
Into #TmpTable
from
(
select Id, PerCode, Value
,ROW_NUMBER() over (partition by PerCode, Value order by (select 0)) Rn2
from
#MasterTable ) F
inner join (
select
PerCode
, Rn1
from (
select
PerCode
,Value
,ROW_NUMBER() over (partition by PerCode, Value order by (select 0)) Rn1
FROM #MasterTable
where
[date] BETWEEN #date_from AND #date_to
) A
group by PerCode , Rn1
having sum(Value) = 0 and count(*)>1
) B on F.PerCode = B.PerCode
and F.Rn2 = B.Rn1
update R
set IsDeleted = 1
from #MasterTable R
inner join #TmpTable P
on R.id = P.id
select * from #MasterTable
drop table #MasterTable ;
drop table #TmpTable;