Sql group by latest repeated field - sql

Question

I don't even know what's a good title for this question.
But I'm having a table:
create table trans
(
[transid] INT IDENTITY (1, 1) NOT NULL,
[customerid] int not null,
[points] decimal(10,2) not null,
[date] datetime not null
)
and records:
--cus1
INSERT INTO trans ( customerid , points , date )
VALUES ( 1, 10, '2016-01-01' ) , ( 1, 20, '2017-02-01' ) , ( 1, 22, '2017-03-01' ) ,
( 1, 24, '2018-02-01' ) , ( 1, 50, '2018-02-25' ) , ( 2, 44, '2016-02-01' ) ,
( 2, 20, '2017-02-01' ) , ( 2, 32, '2017-03-01' ) , ( 2, 15, '2018-02-01' ) ,
( 2, 10, '2018-02-25' ) , ( 3, 10, '2018-02-25' ) , ( 4, 44, '2015-02-01' ) ,
( 4, 20, '2015-03-01' ) , ( 4, 32, '2016-04-01' ) , ( 4, 15, '2016-05-01' ) ,
( 4, 10, '2017-02-25' ) , ( 4, 10, '2018-02-27' ) ,( 4, 20, '2018-02-28' ) ,
( 5, 44, '2015-02-01' ) , ( 5, 20, '2015-03-01' ) , ( 5, 32, '2016-04-01' ) ,
( 5, 15, '2016-05-01' ) ,( 5, 10, '2017-02-25' );
-- selecting the data
select * from trans
Produces:
transid customerid points date
----------- ----------- --------------------------------------- -----------------------
1 1 10.00 2016-01-01 00:00:00.000
2 1 20.00 2017-02-01 00:00:00.000
3 1 22.00 2017-03-01 00:00:00.000
4 1 24.00 2018-02-01 00:00:00.000
5 1 50.00 2018-02-25 00:00:00.000
6 2 44.00 2016-02-01 00:00:00.000
7 2 20.00 2017-02-01 00:00:00.000
8 2 32.00 2017-03-01 00:00:00.000
9 2 15.00 2018-02-01 00:00:00.000
10 2 10.00 2018-02-25 00:00:00.000
11 3 10.00 2018-02-25 00:00:00.000
12 4 44.00 2015-02-01 00:00:00.000
13 4 20.00 2015-03-01 00:00:00.000
14 4 32.00 2016-04-01 00:00:00.000
15 4 15.00 2016-05-01 00:00:00.000
16 4 10.00 2017-02-25 00:00:00.000
17 4 10.00 2018-02-27 00:00:00.000
18 4 20.00 2018-02-28 00:00:00.000
19 5 44.00 2015-02-01 00:00:00.000
20 5 20.00 2015-03-01 00:00:00.000
21 5 32.00 2016-04-01 00:00:00.000
22 5 15.00 2016-05-01 00:00:00.000
23 5 10.00 2017-02-25 00:00:00.000
I'm trying to group all the customerid and sum their points. But here's the catch, If the trans is not active for 1 year(the next tran is 1 year and above), the points will be expired.
For this case:
Points for each customers should be:
Customer1 20+22+24+50
Customer2 20+32+15+10
Customer3 10
Customer4 10+20
Customer5 0
Here's what I have so far:
select
t1.transid as transid1,
t1.customerid as customerid1,
t1.date as date1,
t1.points as points1,
t1.rank1 as rank1,
t2.transid as transid2,
t2.customerid as customerid2,
t2.points as points2,
isnull(t2.date,getUTCDate()) as date2,
isnull(t2.rank2,t1.rank1+1) as rank2,
cast(case when(t1.date > dateadd(year,-1,isnull(t2.date,getUTCDate()))) Then 0 ELSE 1 END as bit) as ShouldExpire
from
(
select transid,CustomerID,Date,points,
RANK() OVER(PARTITION BY CustomerID ORDER BY date ASC) AS RANK1
from trans
)t1
left join
(
select transid,CustomerID,Date,points,
RANK() OVER(PARTITION BY CustomerID ORDER BY date ASC) AS RANK2
from trans
)t2 on t1.RANK1=t2.RANK2-1
and t1.customerid=t2.customerid
which gives
from the above table,how do I check for ShouldExpire field having max(rank1) for customer, if it's 1, then totalpoints will be 0, otherwise,sum all the consecutive 0's until there are no more records or a 1 is met?
Or is there a better approach to this problem?

Answer 1

The following query uses LEAD to get the date of the next record withing the same CustomerID slice:
;WITH CTE AS (
SELECT transid, CustomerID, [Date], points,
LEAD([Date]) OVER (PARTITION BY CustomerID
ORDER BY date ASC) AS nextDate,
CASE
WHEN [date] > DATEADD(YEAR,
-1,
-- same LEAD() here as above
ISNULL(LEAD([Date]) OVER (PARTITION BY CustomerID
ORDER BY date ASC),
getUTCDate()))
THEN 0
ELSE 1
END AS ShouldExpire
FROM trans
)
SELECT transid, CustomerID, [Date], points, nextDate, ShouldExpire
FROM CTE
ORDER BY CustomerID, [Date]
Output:
transid CustomerID Date points nextDate ShouldExpire
-------------------------------------------------------------
1 1 2016-01-01 10.00 2017-02-01 1 <-- last exp. for 1
2 1 2017-02-01 20.00 2017-03-01 0
3 1 2017-03-01 22.00 2018-02-01 0
4 1 2018-02-01 24.00 2018-02-25 0
5 1 2018-02-25 50.00 NULL 0
6 2 2016-02-01 44.00 2017-02-01 1 <-- last exp. for 2
7 2 2017-02-01 20.00 2017-03-01 0
8 2 2017-03-01 32.00 2018-02-01 0
9 2 2018-02-01 15.00 2018-02-25 0
10 2 2018-02-25 10.00 NULL 0
11 3 2018-02-25 10.00 NULL 0 <-- no exp. for 3
12 4 2015-02-01 44.00 2015-03-01 0
13 4 2015-03-01 20.00 2016-04-01 1
14 4 2016-04-01 32.00 2016-05-01 0
15 4 2016-05-01 15.00 2017-02-25 0
16 4 2017-02-25 10.00 2018-02-27 1 <-- last exp. for 4
17 4 2018-02-27 10.00 2018-02-28 0
18 4 2018-02-28 20.00 NULL 0
19 5 2015-02-01 44.00 2015-03-01 0
20 5 2015-03-01 20.00 2016-04-01 1
21 5 2016-04-01 32.00 2016-05-01 0
22 5 2016-05-01 15.00 2017-02-25 0
23 5 2017-02-25 10.00 NULL 1 <-- last exp. for 5
Now, you seem to want to calculate the sum of points after the last expiration.
Using the above CTE as a basis you can achieve the required result with:
;WITH CTE AS (
... above query here ...
)
SELECT CustomerID,
SUM(CASE WHEN rnk = 0 THEN points ELSE 0 END) AS sumOfPoints
FROM (
SELECT transid, CustomerID, [Date], points, nextDate, ShouldExpire,
SUM(ShouldExpire) OVER (PARTITION BY CustomerID ORDER BY [Date] DESC) AS rnk
FROM CTE
) AS t
GROUP BY CustomerID
Output:
CustomerID sumOfPoints
-----------------------
1 116.00
2 77.00
3 10.00
4 30.00
5 0.00
Demo here

Answer 2

The tricky part here is to dump all points when they expire, and start accumulating them again. I assumed that if there was only one transaction that we don't expire the points until there's a new transaction, even if that first transaction was over a year ago now?
I also get a different answer for customer #5, as they do appear to have a "transaction chain" that hasn't expired?
Here's my query:
WITH ordered AS (
SELECT
*,
ROW_NUMBER() OVER (PARTITION BY customerid ORDER BY [date]) AS order_id
FROM
trans),
max_transid AS (
SELECT
customerid,
MAX(transid) AS max_transid
FROM
trans
GROUP BY
customerid),
not_expired AS (
SELECT
t1.customerid,
t1.points,
t1.[date] AS t1_date,
CASE
WHEN m.customerid IS NOT NULL THEN GETDATE()
ELSE t2.[date]
END AS t2_date
FROM
ordered t1
LEFT JOIN ordered t2 ON t2.customerid = t1.customerid AND t1.transid != t2.transid AND t2.order_id = t1.order_id + 1 AND t1.[date] > DATEADD(YEAR, -1, t2.[date])
LEFT JOIN max_transid m ON m.customerid = t1.customerid AND m.max_transid = t1.transid
),
max_not_expired AS (
SELECT
customerid,
MAX(t1_date) AS max_expired
FROM
not_expired
WHERE
t2_date IS NULL
GROUP BY
customerid)
SELECT
n.customerid,
SUM(n.points) AS points
FROM
not_expired n
LEFT JOIN max_not_expired m ON m.customerid = n.customerid
WHERE
ISNULL(m.max_expired, '19000101') < n.t1_date
GROUP BY
n.customerid;
It could be refactored to be simpler, but I wanted to show the steps to get to the final answer:
customerid points
1 116.00
2 77.00
3 10.00
4 30.00
5 57.00

Answer 3

can you try this:
SELECT customerid,
Sum(t1.points)
FROM trans t1
WHERE NOT EXISTS (SELECT 1
FROM trans t2
WHERE Datediff(year, t1.date, t2.date) >= 1)
GROUP BY t1.customerid
Hope it helps!

Answer 4

try this:
select customerid,Sum(points)
from trans where Datediff(year, date, GETDATE()) < 1
group by customerid
output:
customerid Points
1 - 74.00
2 - 25.00
3 - 10.00
4 - 30.00