Get time difference between row values grouped by event - sql

Question

I am using Postgres 9.3.3
I have a table with multiple events, two of them are "AVAILABLE" and "UNAVAILABLE". These events are assigned to a specific object. There are also other object ids in this table (removed for clarity):
What I need is the "available" time per day, something like that:

Answer 1

SQL Fiddle
select
object_id, day,
sum(upper(available) - lower(available)) as available
from (
select
g.object_id, date_trunc('day', d) as day,
(
available *
tsrange(date_trunc('day', d), date_trunc('day', d)::date + 1, '[)')
) as available
from
(
select
object_id, event,
tsrange(
timestamp,
lead(timestamp) over(
partition by object_id order by timestamp
),
'[)'
) as available
from events
where event in ('AVAILABLE', 'UNAVAILABLE')
) s
right join
(
generate_series(
(select min(timestamp) from events),
(select max(timestamp) from events),
'1 day'
) g (d)
cross join
(select distinct object_id from events) s
) g on
tsrange(date_trunc('day', d), date_trunc('day', d)::date + 1, '[)') && available and
(event = 'AVAILABLE' or event is null) and
g.object_id = s.object_id
) s
group by 1, 2
order by 1, 2
psql output
object_id | day | available
-----------+---------------------+-----------
1 | 1970-01-02 00:00:00 | 12:00:00
1 | 1970-01-03 00:00:00 | 12:00:00
1 | 1970-01-04 00:00:00 |
1 | 1970-01-05 00:00:00 | 1 day
1 | 1970-01-06 00:00:00 | 1 day
1 | 1970-01-07 00:00:00 | 12:00:00
Table DDL
create table events (
object_id int,
event text,
timestamp timestamp
);
insert into events (object_id, event, timestamp) values
(1, 'AVAILABLE', '1970-01-02 12:00:00'),
(1, 'UNAVAILABLE', '1970-01-03 12:00:00'),
(1, 'AVAILABLE', '1970-01-05 00:00:00'),
(1, 'UNAVAILABLE', '1970-01-07 12:00:00');

Answer 2

Your example output suggests that you want all your objects to be returned, but grouped. If that is the case, this query can do that
select object_id, day, sum(upper(tsrange) - lower(tsrange))
from (
select object_id, date(day) as day, e.tsrange * tsrange(day, day + interval '1' day) tsrange
from generate_series(timestamp '1970-01-01', '1970-01-07', interval '1' day) day
left join (
select object_id,
case event
when 'AVAILABLE' then tsrange(timestamp, lead(timestamp) over (partition by object_id order by timestamp))
else null
end tsrange
from events
where event in ('AVAILABLE', 'UNAVAILABLE')
) e on e.tsrange && tsrange(day, day + interval '1' day)
) d
group by object_id, day
order by day, object_id
But that will output something like that (if you have multiple object_ids):
object_id | day | sum
-----------+--------------+-----------
| '1970-01-01' |
1 | '1970-01-02' | '12:00:00'
1 | '1970-01-03' | '12:00:00'
| '1970-01-04' |
1 | '1970-01-05' | '1 day'
1 | '1970-01-06' | '1 day'
2 | '1970-01-06' | '12:00:00'
1 | '1970-01-07' | '12:00:00'
In my opinion it would make much more sense, if you would query just one object at a time:
select day, sum(upper(tsrange) - lower(tsrange))
from (
select date(day) as day, e.tsrange * tsrange(day, day + interval '1' day) tsrange
from generate_series(timestamp '1970-01-01', '1970-01-07', interval '1' day) day
left join (
select case event
when 'AVAILABLE' then tsrange(timestamp, lead(timestamp) over (partition by object_id order by timestamp))
else null
end tsrange
from events
where event in ('AVAILABLE', 'UNAVAILABLE')
and object_id = 1
) e on e.tsrange && tsrange(day, day + interval '1' day)
) d
group by day
order by day
This will output something, like:
day | sum
--------------+----------
'1970-01-01' |
'1970-01-02' | '12:00:00'
'1970-01-03' | '12:00:00'
'1970-01-04' |
'1970-01-05' | '1 day'
'1970-01-06' | '1 day'
'1970-01-07' | '12:00:00'
I used this schema/data for my outputs:
create table events (
object_id int,
event text,
timestamp timestamp
);
insert into events (object_id, event, timestamp)
values (1, 'AVAILABLE', '1970-01-02 12:00:00'),
(1, 'UNAVAILABLE', '1970-01-03 12:00:00'),
(1, 'AVAILABLE', '1970-01-05 00:00:00'),
(1, 'UNAVAILABLE', '1970-01-07 12:00:00'),
(2, 'AVAILABLE', '1970-01-06 00:00:00'),
(2, 'UNAVAILABLE', '1970-01-06 06:00:00'),
(2, 'AVAILABLE', '1970-01-06 12:00:00'),
(2, 'UNAVAILABLE', '1970-01-06 18:00:00');

Answer 3

This is a partial answer. If we assume that the next event after available is unavailable, then lead() comes to the rescue and the following is a start:
select object_id, to_char(timestamp, 'YYYY-MM-DD') as day,
to_char(nextts - timestamp, 'HH24:MI') as interval
from (select t.*,
lead(timestamp) over (partition by object_id order by timestamp) as nextts
from table t
where event in ('AVAILABLE', 'UNAVAILABLE')
) t
where event = 'AVAILABLE'
group by object_id, to_char(timestamp, 'YYYY-MM-DD');
I suspect, though, that when the interval spans multiple days, you want to split the days into separate parts. This becomes more of a challenge.