Doing a comparison using the previous row? - sql

Question

I'm trying to work out an efficient way of comparing two rows in SQL Server 2008. I need to write a query which finds all rows in the Movement table which have Speed < 10 N consecutive times.
The structure of the table is:
EventTime
Speed
If the data were:
2012-02-05 13:56:36.980, 2
2012-02-05 13:57:36.980, 11
2012-02-05 13:57:46.980, 2
2012-02-05 13:59:36.980, 2
2012-02-05 14:06:36.980, 22
2012-02-05 15:56:36.980, 2
Then it would return rows 3/4 (13:57:46.980 / 13:59:36.980) if I looked for 2 consecutive rows, and would return nothing if I looked for three consecutive rows. The order of the data is EventTime/DateTime only.
Any help you could give me would be great. I'm considering using cursors but they're usually pretty inefficient. Also, this table is approximately 10m rows in size, so the more efficient the better! :)
Thanks!

Answer 1

DECLARE
#n INT,
#speed_limit INT
SELECT
#n = 5,
#speed_limit = 10
;WITH
partitioned AS
(
SELECT
*,
CASE WHEN speed < #speed_limit THEN 1 ELSE 0 END AS PartitionID
FROM
Movement
)
,
sequenced AS
(
SELECT
ROW_NUMBER() OVER ( ORDER BY EventTime) AS MasterSeqID,
ROW_NUMBER() OVER (PARTITION BY PartitionID ORDER BY EventTime) AS PartIDSeqID,
*
FROM
partitioned
)
,
filter AS
(
SELECT
MasterSeqID - PartIDSeqID AS GroupID,
MIN(MasterSeqID) AS GroupFirstMastSeqID,
MAX(MasterSeqID) AS GroupFinalMastSeqID
FROM
sequenced
WHERE
PartitionID = 1
GROUP BY
MasterSeqID - PartIDSeqID
HAVING
COUNT(*) >= #n
)
SELECT
sequenced.*
FROM
filter
INNER JOIN
sequenced
ON sequenced.MasterSeqID >= filter.GroupFirstMastSeqID
AND sequenced.MasterSeqID <= filter.GroupFinalMastSeqID
Alternative final steps (inspired by #t-clausen-dk), to avoid an additional JOIN. I would test both to see which is more performant.
,
filter AS
(
SELECT
MasterSeqID - PartIDSeqID AS GroupID,
COUNT(*) OVER (PARTITION BY MasterSeqID - PartIDSeqID) AS GroupSize,
*
FROM
sequenced
WHERE
PartitionID = 1
)
SELECT
*
FROM
filter
WHERE
GroupSize >= #n

Answer 2

declare #t table(EventTime datetime, Speed int)
insert #t values('2012-02-05 13:56:36.980', 2)
insert #t values('2012-02-05 13:57:36.980', 11)
insert #t values('2012-02-05 13:57:46.980', 2)
insert #t values('2012-02-05 13:59:36.980', 2)
insert #t values('2012-02-05 14:06:36.980', 22)
insert #t values('2012-02-05 15:56:36.980', 2)
declare #N int = 1
;with a as
(
select EventTime, Speed, row_number() over (order by EventTime) rn from #t
), b as
(
select EventTime, Speed, 1 grp, rn from a where rn = 1
union all
select a.EventTime, a.Speed, case when a.speed < 10 and b.speed < 10 then grp else grp + 1 end, a.rn
from a join b on a.rn = b.rn+1
), c as
(
select EventTime, Speed, count(*) over (partition by grp) cnt from b
)
select * from c
where cnt > #N
OPTION (MAXRECURSION 0) -- Thx Dems

Answer 3

Almost the same ideea as Dems, a little bit different:
select * from (
select eventtime, speed, rnk, new_rnk,
rnk - new_rnk,
max(rnk) over (partition by speed, new_rnk-rnk) -
min(rnk) over (partition by speed, new_rnk-rnk) + 1 as no_consec
from (
select eventtime, rnk, speed,
row_number() over (partition by speed order by eventtime) as new_rnk
from (
select eventtime, speed,
row_number() over (order by eventtime) as rnk
from a
) a
where a.speed < 5
)
order by eventtime
)
where no_consec >= 2;
5 is speed limit and 2 is min number of consecutive events.
I put date as number for simplicity of writing the create database.
SQLFIDDLE
EDIT:
To answer to comments, I've added three columns in the first inner query. To get only the first row you need to add an pos_in_group = 1 to WHERE clause and the distance is at your fingers.
SQLFIDDLE
select eventtime, speed, min_date, max_date, pos_in_group
from (
select eventtime, speed, rnk, new_rnk,
rnk - new_rnk,
row_number() over (partition by speed, new_rnk-rnk order by eventtime) pos_in_group,
min(eventtime) over (partition by speed, new_rnk-rnk) min_date,
max(eventtime) over (partition by speed, new_rnk-rnk) max_date,
max(rnk) over (partition by speed, new_rnk-rnk) -
min(rnk) over (partition by speed, new_rnk-rnk) + 1 as no_consec
from (
select eventtime, rnk, speed,
row_number() over (partition by speed order by eventtime) as new_rnk
from (
select eventtime, speed,
row_number() over (order by eventtime) as rnk
from a
) a
where a.speed < 5
)
order by eventtime
)
where no_consec > 1;