I have a table1: id int, id_2 int, date timestamp, vec float[]
And table2 : id int, vec float[]
My target is to create trigger on update of table1 which will take last 10 (by date) rows for id_2, take average of vectors by first axis(10 x N -> N) and write it to table2 under id = id_2.
My code:
CREATE OR REPLACE FUNCTION public.foo()
RETURNS trigger
LANGUAGE plpgsql
AS $function$
BEGIN
WITH rows AS (
SELECT DISTINCT t1.id_2, t2.id, t2.vec, t2.date, DENSE_RANK() OVER (PARTITION BY t1.id_2 ORDER BY t2.date desc) AS counter
FROM new_table AS t1
LEFT JOIN table1 t2 ON t1.id_2 = t2.id_2
),
elements_average AS (
SELECT id_2, AVG(unnest::float) AS av
FROM rows,
unnest(vec) with ORDINALITY
WHERE counter < 11
GROUP BY id_2, ORDINALITY
ORDER BY ORDINALITY
),
avr AS (
SELECT id_2, array_agg(av::float) AS averages
FROM elements_average
GROUP BY id_2
)
UPDATE table2 SET vec = averages FROM avr WHERE table2.id = user_av.id_2;
RETURN NULL;
END;
$function$
;
CREATE TRIGGER foo_trigger AFTER
UPDATE
ON
public.table1 REFERENCING NEW TABLE AS new_table FOR EACH STATEMENT EXECUTE FUNCTION foo()
The problem: when I update few rows in table1 with different id_2 in one transactions a value in table2 becomes wrong. Not the average.
What's even more strange is that this code gives correct values in same situation:
...
avr AS (
SELECT id_2, array_agg(av::float) AS averages
FROM elements_average
GROUP BY id_2
),
strange_thing AS (
SELECT * from elements_average
)
UPDATE table2 SET vec = averages FROM avr WHERE table2.id = user_av.id_2;
RETURN NULL;
END;
$function$
;
So, small meaningless and unimportant SELECT changes the behavior of the function. Is it a bug of postgres or my fault?
Related
I didn't find my case on the Internet. Tell me how i can delete duplicates if the values are in different columns.
I have a table with a lot of values, for example:
|Id1|Id2|
|89417980|89417978|
|89417980|89417979|
|89417978|89417980|
|89417979|89417980|
I need to exclude duplicates and leave in the answer only:
|Id1|Id2|
|89417980|89417978|
|89417980|89417979|
min/max does not work here, as the values may be different.
I tried to union/join tables on a table/exclude results with temporary tables, but in the end I come to the beginning.
Assuming id1 and id2 are primary keys columns you could try this
DECLARE #tbl table (id1 int, id2 int )
INSERT INTO #tbl
SELECT 89417980, 89417978
UNION SELECT 89417980, 89417979
UNION SELECT 89417978, 89417980
UNION SELECT 89417979, 89417980
SELECT * FROM #tbl
;WITH CTE AS (--Get comparable value as "cs"
SELECT
IIF(id1 > id2, CHECKSUM(id1, id2), CHECKSUM(id2,id1)) as cs
, id1
, id2
, ROW_NUMBER() OVER (order by id1, id2) as rn
FROM #tbl
)
, CTE2 AS ( --Get rows to keep
SELECT MAX (rn) as rn
FROM CTE
GROUP BY cs
HAVING COUNT(*) > 1
)
DELETE tbl -- Delete all except the rows to keep
FROM #tbl tbl
WHERE NOT EXISTS(SELECT 1
FROM CTE2
JOIN CTE ON CTE.rn = CTE2.rn
WHERE CTE.id1 = tbl.id1
AND CTE.id2 = tbl.id2
)
SELECT * FROM #tbl
In PgSQL I make huge select, and then I want count it's size and apply some extra filters.
execute it twice sound dumm,
so I wrapped it in function
and then "cache" it and return union of filtered table and extra row at the end where in "id" column store size
with q as (select * from myFunc())
select * from q
where q.distance < 400
union all
select count(*) as id, null,null,null
from q
but it also doesn't look like proper solution...
and so the question: is in pg something like "generator function" or any other stuff that can properly solve this ?
postgreSQL 13
myFunc aka "selectItemsByRootTag"
CREATE OR REPLACE FUNCTION selectItemsByRootTag(
in tag_name VARCHAR(50)
)
RETURNS table(
id BIGINT,
name VARCHAR(50),
description TEXT,
/*info JSON,*/
distance INTEGER
)
AS $$
BEGIN
RETURN QUERY(
WITH RECURSIVE prod AS (
SELECT
tags.name, tags.id, tags.parent_tags
FROM
tags
WHERE tags.name = (tags_name)
UNION
SELECT c.name, c.id , c.parent_tags
FROM
tags as c
INNER JOIN prod as p
ON c.parent_tags = p.id
)
SELECT
points.id,
points.name,
points.description,
/*points.info,*/
points.distance
from points
left join tags on points.tag_id = tags.id
where tags.name in (select prod.name from prod)
);
END;
$$ LANGUAGE plpgsql;
as a result i want see maybe set of 2 table or generator function that yield some intermediate result not shure how exacltly it should look
demo
CREATE OR REPLACE FUNCTION pg_temp.selectitemsbyroottag(tag_name text, _distance numeric)
RETURNS TABLE(id bigint, name text, description text, distance numeric, count bigint)
LANGUAGE plpgsql
AS $function$
DECLARE _sql text;
BEGIN
_sql := $p1$WITH RECURSIVE prod AS (
SELECT
tags.name, tags.id, tags.parent_tags
FROM
tags
WHERE tags.name ilike '%$p1$ || tag_name || $p2$%'
UNION
SELECT c.name, c.id , c.parent_tags
FROM
tags as c
INNER JOIN prod as p
ON c.parent_tags = p.id
)
SELECT
points.id,
points.name,
points.description,
points.distance,
count(*) over ()
from points
left join tags on points.tag_id = tags.id
where tags.name in (select prod.name from prod)
and points.distance > $p2$ || _distance
;
raise notice '_sql: %', _sql;
return query execute _sql;
END;
$function$
You can call it throug following way
select * from pg_temp.selectItemsByRootTag('test',20);
select * from pg_temp.selectItemsByRootTag('test_8',20) with ORDINALITY;
The 1 way to call the function, will have a row of total count total number of rows. Second way call have number of rows plus a serial incremental number.
I also make where q.distance < 400 into function input argument.
selectItemsByRootTag('test',20); means that q.distance > 20 and tags.name ilike '%test%'.
I need to write a T-SQL group by query for a table with multiple dates and seq columns:
DROP TABLE #temp
CREATE TABLE #temp(
id char(1),
dt DateTime,
seq int)
Insert into #temp values('A','2015-03-31 10:00:00',1)
Insert into #temp values('A','2015-08-31 10:00:00',2)
Insert into #temp values('A','2015-03-31 10:00:00',5)
Insert into #temp values('B','2015-09-01 10:00:00',1)
Insert into #temp values('B','2015-09-01 10:00:00',2)
I want the results to contains only the items A,B with their latest date and the corresponding seq number, like:
id MaxDate CorrespondentSeq
A 2015-08-31 10:00:00.000 2
B 2015-09-01 10:00:00.000 2
I am trying with (the obviously wrong!):
select id, max(dt) as MaxDate, max(seq) as CorrespondentSeq
from #temp
group by id
which returns:
id MaxDate CorrespondentSeq
A 2015-08-31 10:00:00.000 5 <-- 5 is wrong
B 2015-09-01 10:00:00.000 2
How can I achieve that?
EDIT
The dt datetime column has duplicated values (exactly same date!)
I am using SQL Server 2005
You can use a ranking subselect to get only the highest ranked entries for an id:
select id, dt, seq
from (
select id, dt, seq, rank() over (partition by id order by dt desc, seq desc) as r
from #temp
) ranked
where r=1;
SELECT ID, DT, SEQ
FROM (
SELECT ID, DT, SEQ, Row_Number()
OVER (PARTITION BY id ORDER BY dt DESC, seq DESC) AS row_number
FROM temp
) cte
WHERE row_number = 1;
Demo : http://www.sqlfiddle.com/#!3/3e3d5/5
With trial and errors maybe I have found a solution, but I'm not completely sure this is correct:
select A.id, B.dt, max(B.seq)
from (select id, max(dt) as maxDt
from #temp
group by id) as A
inner join #temp as B on A.id = B.id AND A.maxDt = B.dt
group by A.id, B.dt
Select id, dt, seq
From #temp t
where dt = (Select Max(dt) from #temp
Where id = t.Id)
If there are duplicate rows, then you also need to specify what the query processor should use to determine which of the duplicates to return. Say you want the lowest value of seq,
Then you could write:
Select id, dt, seq
From #temp t
where dt = (Select Max(dt) from #temp
Where id = t.Id)
and seq = (Select Min(Seq) from #temp
where id = t.Id
and dt = t.dt)
table1
id col1 col2 col3...
table2
col_id col_name
3432 col1
5342 col2
6756 col3
Now I want to generate table 3 like this:
id col_name col_value col_id
Please note that col1, col2,col3... are not in order. Therefore I have to query table2 to obtain col_id ( I think pivot does not work here)
How can I do it in SQL?
It appears that you want a select like this:
SELECT t2.id,
CASE
WHEN t2.col_name='col1' THEN t1.col1
WHEN t2.col_name='col2' THEN t1.col2
WHEN t2.col_name='col2' THEN t1.col2
-- ... more columns
ELSE NULL
END
FROM table2 t2 LEFT JOIN table2 t1 ON t2.col_id = t1.id
You could also create a function, though this will be slower in practice:
CREATE OR REPLACE FUNCTION table1_col(id integer, name text) RETURNS text as $$
DECLARE
col_val text;
BEGIN
EXECUTE format('SELECT %s FROM table1 WHERE id=$1', name)
INTO col_val
USING id;
RETURN col_val;
END;
$$ LANGUAGE plpgsql;
SELECT table1_col(col_id,col_name) FROM table2;
I have two tables of records that I need to find all of the matches. The tables are based on different Primary Key identifiers, but the data points are exactly the same. I need a fast query that can show me records that are duplicated from the first table to the second. Here is an example of what I am trying to do:
DECLARE #Table1 TABLE (ID INT, Value INT)
DECLARE #Table2 TABLE (ID INT, Value INT)
INSERT INTO #Table1 VALUES (1, 500)
INSERT INTO #Table1 VALUES (2, 500)
INSERT INTO #Table2 VALUES (3, 500)
INSERT INTO #Table2 VALUES (4, 500)
SELECT MAX(x.T1ID)
,MAX(x.T2ID)
FROM (
SELECT T1ID = t1.ID
,T2ID = 0
,t1.Value
FROM #Table1 t1
UNION ALL
SELECT T1ID = 0
,T2ID = t2.ID
,t2.Value
FROM #Table2 t2
) x
GROUP BY x.Value
HAVING COUNT(*) >= 2
The problem with this code is that it returns record 2 in table 1 correlated to record 4 in table 2. I really need it to return record 1 in table 1 correlated to record 3 in table 2. I tried the following:
SELECT MIN(x.T1ID)
,MIN(x.T2ID)
FROM (
SELECT T1ID = t1.ID
,T2ID = 0
,t1.Value
FROM #Table1 t1
UNION ALL
SELECT T1ID = 0
,T2ID = t2.ID
,t2.Value
FROM #Table2 t2
) x
GROUP BY x.Value
HAVING COUNT(*) >= 2
This code does not work either. It returns 0,0.
Is there a way to return the MIN value greater than 0 for both tables?
Might answer my own question. This seems to work. Are there any reasons why I would not do this?
SELECT MIN(t1.ID)
,MIN(t2.ID)
FROM #Table1 t1
INNER JOIN #Table2 t2 ON t1.Value = t2.Value
GROUP BY t1.Value
If you want to see the records in table1 that have matches in table2 then
select *
from #Table1 T1
where exists (select * from #Table2 T2
where T1.ID=T2.ID
-- you would put the complete join clause that defines a match here
)