SQL - '1' IF hour in month EXISTS, '0' IF NOT EXISTS - sql

Question

I have a table that has aggregations down to the hour level YYYYMMDDHH. The data is aggregated and loaded by an external process (I don't have control over). I want to test the data on a monthly basis.
The question I am looking to answer is: Does every hour in the month exist?
I'm looking to produce output that will return a 1 if the hour exists or 0 if the hour does not exist.
The aggregation table looks something like this...
YYYYMM YYYYMMDD YYYYMMDDHH DATA_AGG
201911 20191101 2019110100 100
201911 20191101 2019110101 125
201911 20191101 2019110103 135
201911 20191101 2019110105 95
… … … …
201911 20191130 2019113020 100
201911 20191130 2019113021 110
201911 20191130 2019113022 125
201911 20191130 2019113023 135
And defined as...
CREATE TABLE YYYYMMDDHH_DATA_AGG AS (
YYYYMM VARCHAR,
YYYYMMDD VARCHAR,
YYYYMMDDHH VARCHAR,
DATA_AGG INT
);
I'm looking to produce the following below...
YYYYMMDDHH HOUR_EXISTS
2019110100 1
2019110101 1
2019110102 0
2019110103 1
2019110104 0
2019110105 1
... ...
In the example above, two hours do not exist, 2019110102 and 2019110104.
I assume I'd have to join the aggregation table against a computed table that contains all the YYYYMMDDHH combos???
The database is Snowflake, but assume most generic ANSI SQL queries will work.

Answer 1

You can get what you want with a recursive CTE
The recursive CTE generates the list of possible Hours. And then a simple left outer join gets you the flag for if you have any records that match that hour.
WITH RECURSIVE CTE (YYYYMMDDHH) as
(
SELECT YYYYMMDDHH
FROM YYYYMMDDHH_DATA_AGG
WHERE YYYYMMDDHH = (SELECT MIN(YYYYMMDDHH) FROM YYYYMMDDHH_DATA_AGG)
UNION ALL
SELECT TO_VARCHAR(DATEADD(HOUR, 1, TO_TIMESTAMP(C.YYYYMMDDHH, 'YYYYMMDDHH')), 'YYYYMMDDHH') YYYYMMDDHH
FROM CTE C
WHERE TO_VARCHAR(DATEADD(HOUR, 1, TO_TIMESTAMP(C.YYYYMMDDHH, 'YYYYMMDDHH')), 'YYYYMMDDHH') <= (SELECT MAX(YYYYMMDDHH) FROM YYYYMMDDHH_DATA_AGG)
)
SELECT
C.YYYYMMDDHH,
IFF(A.YYYYMMDDHH IS NOT NULL, 1, 0) HOUR_EXISTS
FROM CTE C
LEFT OUTER JOIN YYYYMMDDHH_DATA_AGG A
ON C.YYYYMMDDHH = A.YYYYMMDDHH;
If your timerange is too long you'll have issues with the cte recursing too much. You can create a table or temp table with all of the possible hours instead. For example:
CREATE OR REPLACE TEMPORARY TABLE HOURS (YYYYMMDDHH VARCHAR) AS
SELECT TO_VARCHAR(DATEADD(HOUR, SEQ4(), TO_TIMESTAMP((SELECT MIN(YYYYMMDDHH) FROM YYYYMMDDHH_DATA_AGG), 'YYYYMMDDHH')), 'YYYYMMDDHH')
FROM TABLE(GENERATOR(ROWCOUNT => 10000)) V
ORDER BY 1;
SELECT
H.YYYYMMDDHH,
IFF(A.YYYYMMDDHH IS NOT NULL, 1, 0) HOUR_EXISTS
FROM HOURS H
LEFT OUTER JOIN YYYYMMDDHH_DATA_AGG A
ON H.YYYYMMDDHH = A.YYYYMMDDHH
WHERE H.YYYYMMDDHH <= (SELECT MAX(YYYYMMDDHH) FROM YYYYMMDDHH_DATA_AGG);
You can then fiddle with the generator count to make sure you have enough hours.

Answer 2

You can generate a table with every hour of the month and LEFT OUTER JOIN your aggregation to it:
WITH EVERY_HOUR AS (
SELECT TO_CHAR(DATEADD(HOUR, HH, TO_DATE(YYYYMM::TEXT, 'YYYYMM')),
'YYYYMMDDHH')::NUMBER YYYYMMDDHH
FROM (SELECT DISTINCT YYYYMM FROM YYYYMMDDHH_DATA_AGG) t
CROSS JOIN (
SELECT ROW_NUMBER() OVER (ORDER BY NULL) - 1 HH
FROM TABLE(GENERATOR(ROWCOUNT => 745))
) h
QUALIFY YYYYMMDDHH < (YYYYMM + 1) * 10000
)
SELECT h.YYYYMMDDHH, NVL2(a.YYYYMM, 1, 0) HOUR_EXISTS
FROM EVERY_HOUR h
LEFT OUTER JOIN YYYYMMDDHH_DATA_AGG a ON a.YYYYMMDDHH = h.YYYYMMDDHH

Answer 3

Here's something that might help get you started. I'm guessing you want to have 'synthetic' [YYYYMMDD] values? Otherwise, if the value aren't there, then they shouldn't appear in the list
DROP TABLE IF EXISTS #_hours
DROP TABLE IF EXISTS #_temp
--Populate a table with hours ranging from 00 to 23
CREATE TABLE #_hours ([hour_value] VARCHAR(2))
DECLARE #_i INT = 0
WHILE (#_i < 24)
BEGIN
INSERT INTO #_hours
SELECT FORMAT(#_i, '0#')
SET #_i += 1
END
-- Replicate OP's sample data set
CREATE TABLE #_temp (
[YYYYMM] INTEGER
, [YYYYMMDD] INTEGER
, [YYYYMMDDHH] INTEGER
, [DATA_AGG] INTEGER
)
INSERT INTO #_temp
VALUES
(201911, 20191101, 2019110100, 100),
(201911, 20191101, 2019110101, 125),
(201911, 20191101, 2019110103, 135),
(201911, 20191101, 2019110105, 95),
(201911, 20191130, 2019113020, 100),
(201911, 20191130, 2019113021, 110),
(201911, 20191130, 2019113022, 125),
(201911, 20191130, 2019113023, 135)
SELECT X.YYYYMM, X.YYYYMMDD, X.YYYYMMDDHH
-- Case: If 'target_hours' doesn't exist, then 0, else 1
, CASE WHEN X.target_hours IS NULL THEN '0' ELSE '1' END AS [HOUR_EXISTS]
FROM (
-- Select right 2 characters from converted [YYYYMMDDHH] to act as 'target values'
SELECT T.*
, RIGHT(CAST(T.[YYYYMMDDHH] AS VARCHAR(10)), 2) AS [target_hours]
FROM #_temp AS T
) AS X
-- Right join to keep all of our hours and only the target hours that match.
RIGHT JOIN #_hours AS H ON H.hour_value = X.target_hours
Sample output:
YYYYMM YYYYMMDD YYYYMMDDHH HOUR_EXISTS
201911 20191101 2019110100 1
201911 20191101 2019110101 1
NULL NULL NULL 0
201911 20191101 2019110103 1
NULL NULL NULL 0
201911 20191101 2019110105 1
NULL NULL NULL 0

Answer 4

With (almost) standard sql, you can do a cross join of the distinct values of YYYYMMDD to a list of all possible hours and then left join to the table:
select concat(d.YYYYMMDD, h.hour) as YYYYMMDDHH,
case when t.YYYYMMDDHH is null then 0 else 1 end as hour_exists
from (select distinct YYYYMMDD from tablename) as d
cross join (
select '00' as hour union all select '01' union all
select '02' union all select '03' union all
select '04' union all select '05' union all
select '06' union all select '07' union all
select '08' union all select '09' union all
select '10' union all select '11' union all
select '12' union all select '13' union all
select '14' union all select '15' union all
select '16' union all select '17' union all
select '18' union all select '19' union all
select '20' union all select '21' union all
select '22' union all select '23'
) as h
left join tablename as t
on concat(d.YYYYMMDD, h.hour) = t.YYYYMMDDHH
order by concat(d.YYYYMMDD, h.hour)
Maybe in Snowflake you can construct the list of hours with a sequence much easier instead of all those UNION ALLs.

Answer 5

This version accounts for the full range of days, across months and years. It's a simple cross join of the set of possible days with the set of possible hours of the day -- left joined to actual dates.
set first = (select min(yyyymmdd::number) from YYYYMMDDHH_DATA_AGG);
set last = (select max(yyyymmdd::number) from YYYYMMDDHH_DATA_AGG);
with
hours as (select row_number() over (order by null) - 1 h from table(generator(rowcount=>24))),
days as (
select
row_number() over (order by null) - 1 as n,
to_date($first::text, 'YYYYMMDD')::date + n as d,
to_char(d, 'YYYYMMDD') as yyyymmdd
from table(generator(rowcount=>($last-$first+1)))
)
select days.yyyymmdd || lpad(hours.h,2,0) as YYYYMMDDHH, nvl2(t.yyyymmddhh,1,0) as HOUR_EXISTS
from days cross join hours
left join YYYYMMDDHH_DATA_AGG t on t.yyyymmddhh = days.yyyymmdd || lpad(hours.h,2,0)
order by 1
;
$first and $last can be packed in as sub-queries if you prefer.