Postgresql find by count, joined table - postgresql

Given 3 tables. I need to build SQL query to find two actors who CAST TOGETHER THE MOST and list the titles of those movies. Sort alphabetically
https://www.db-fiddle.com/f/r2Y9CpH8n7MHTeBaqEHe9S/0
The data for reproducing below:
create table film_actor
(
actor_id integer,
film_id integer
)
;
create table film
(
film_id integer,
title varchar
)
;
create table actor
(
actor_id integer,
first_name varchar,
last_name varchar
)
;
INSERT INTO public.film_actor (actor_id, film_id) VALUES (1, 1);
INSERT INTO public.film_actor (actor_id, film_id) VALUES (1, 2);
INSERT INTO public.film_actor (actor_id, film_id) VALUES (1, 3);
INSERT INTO public.film_actor (actor_id, film_id) VALUES (2, 1);
INSERT INTO public.film_actor (actor_id, film_id) VALUES (2, 2);
INSERT INTO public.film_actor (actor_id, film_id) VALUES (2, 3);
INSERT INTO public.film_actor (actor_id, film_id) VALUES (3, 1);
INSERT INTO public.film (film_id, title) VALUES (1, 'First');
INSERT INTO public.film (film_id, title) VALUES (2, 'Second');
INSERT INTO public.film (film_id, title) VALUES (3, 'Third');
INSERT INTO public.film (film_id, title) VALUES (4, 'Fourth');
INSERT INTO public.actor (actor_id, first_name, last_name) VALUES (1, 'John', 'Snow');
INSERT INTO public.actor (actor_id, first_name, last_name) VALUES (2, 'Spider', 'Man');
INSERT INTO public.actor (actor_id, first_name, last_name) VALUES (3, 'Mike', 'Kameron');

Is this what you are looking for?
with acting_pairs as (
select a1.actor_id as a1_id, a2.actor_id as a2_id
from film_actor a1
join film_actor a2 on a1.film_id = a2.film_id
where a1.actor_id < a2.actor_id
)
select a1_id, a2_id, count(*) as total
from acting_pairs
group by (a1_id, a2_id)
order by total desc
limit 1
Giving us expected output for the example input would be nice.

Related

PostgreSQL: Forward fill NULL values with previous NOT NULL value in group

I'm trying fill NULL values in multiple columns (different column types INT, VARCHAR) with previous NOT NULL value in a group ordered by date. Considering following table:
I want to get here:
CREATE TABLE IF NOT EXISTS test (
id VARCHAR,
date DATE,
value_1 INT,
value_2 VARCHAR
);
INSERT INTO test VALUES
(1, '2022-01-01', 5, 'asdf'),
(1, '2022-01-02', NULL, NULL),
(1, '2022-01-03', NULL, 'def'),
(1, '2022-01-04', 4, NULL),
(2, '2022-01-01', 1, 'a'),
(2, '2022-01-02', NULL, NULL),
(2, '2022-01-03', 2, 'b'),
(2, '2022-01-04', NULL, NULL);
One day, PostgreSQL may support the IGNORE NULLS option for LEAD and LAG functions.
In the mean time, you must use window functions to build groups, then select the maximum in each group.
SELECT id, date,
MAX(value_1) OVER (PARTITION BY id, grp_1) AS value_1,
MAX(value_2) OVER (PARTITION BY id, grp_2) AS value_2
FROM(
SELECT *,
COUNT(value_1) OVER (PARTITION BY id ORDER BY Date DESC) as grp_1,
COUNT(value_2) OVER (PARTITION BY id ORDER BY Date DESC) as grp_2
FROM test
) T
ORDER BY ID, date

PostgreSQL WITH RECURSIVE order by in non recursive term

I am trying to create a recursive CTE and I wanted to fetch the row in the non recursive term from the table using ORDER BY but it seems impossible to do. Is there any workaround on this?
Example:
CREATE TABLE mytable (
id BIGSERIAL PRIMARY KEY,
ref_id BIGINT NOT NULL,
previous_id BIGINT REFERENCES mytable(id),
some_name TEXT NOT NULL,
created_at TIMESTAMP DEFAULT NOW()
);
INSERT INTO mytable (id, previous_id, ref_id, some_name) VALUES (1, NULL, 1, 'Barry');
INSERT INTO mytable (id, previous_id, ref_id, some_name) VALUES (2, NULL, 1, 'Nick');
INSERT INTO mytable (id, previous_id, ref_id, some_name) VALUES (3, 1, 2, 'Janet');
INSERT INTO mytable (id, previous_id, ref_id, some_name) VALUES (4, 1, 1, 'John');
INSERT INTO mytable (id, previous_id, ref_id, some_name) VALUES (5, 2, 7, 'Ron');
INSERT INTO mytable (id, previous_id, ref_id, some_name) VALUES (6, 1, 1, 'Aaron');
INSERT INTO mytable (id, previous_id, ref_id, some_name) VALUES (7, 4, 1, 'Anna');
The query I am trying to construct
WITH RECURSIVE my_path AS (
SELECT * FROM mytable
WHERE ref_id = 1 AND some_name = 'Anna'
ORDER BY created_at DESC
LIMIT 1
UNION ALL
SELECT ph.* FROM my_path hp
INNER JOIN mytable ph ON hp.previous_id = ph.id
)
SELECT * FROM my_path;
SQLFIDDLE
Just move it into a starter CTE:
updated fiddle
WITH RECURSIVE base_record as (
SELECT * FROM mytable
WHERE ref_id = 1 AND some_name = 'Anna'
ORDER BY created_at DESC
LIMIT 1
), my_path AS (
SELECT * FROM base_record
UNION ALL
SELECT ph.* FROM my_path hp
INNER JOIN mytable ph ON hp.previous_id = ph.id
)
SELECT * FROM my_path;

triggers and functions trouble

I'm currently going through the growing pains of trying to learn about functions and triggers. I'm trying to do a problem from a book I'm reading , but i dont understand how to do certain parts.
using this table
create table movies (
id integer primary key,
title varchar(255) not null,
year integer
);
insert into movies values (1, 'The Croods', 2013);
insert into movies values (2, 'Now You See Me', 2013);
insert into movies values (3, 'Argo', 2012);
insert into movies values (4, 'Jurassic World', 2015);
create table discs (
id integer primary key,
movie_id integer not null references movies(id),
type_id integer references disc_types(id),
price decimal(10,2),
available boolean
);
insert into discs values (1, 1, 1, 1.59, 't');
insert into discs values (2, 1, 1, 1.59, 'f');
insert into discs values (3, 1, 2, 2.99, 'f');
insert into discs values (4, 2, 1, 1.29, 't');
insert into discs values (5, 2, 1, 1.29, 't');
insert into discs values (6, 2, 2, 2.99, 't');
insert into discs values (7, 3, 2, 2.59, 't');
insert into discs values (8, 3, 2, 2.59, 't');
create table customers (
id integer primary key,
name varchar(255),
email varchar(255)
);
insert into customers values (1, 'John', 'john#hotmail.com');
insert into customers values (2, 'Jane', 'jane#gmail.com');
create table rentals (
id integer primary key,
customer_id integer not null references customers(id),
disc_id integer not null references discs(id),
date_rented date,
date_returned date
);
insert into rentals values (1, 1, 7, '2013-10-01', '2013-10-03');
insert into rentals values (2, 2, 5, '2013-10-05', '2013-10-06');
insert into rentals values (3, 2, 2, '2013-11-02', null);
insert into rentals values (4, 2, 3, '2013-11-02', null);
create table ratings (
customer_id integer not null references customers(id),
movie_id integer not null references movies(id),
rating integer,
primary key (customer_id, movie_id)
);
insert into ratings values (1, 1, 1);
insert into ratings values (1, 2, 4);
insert into ratings values (1, 3, 5);
insert into ratings values (2, 1, 4);
my logic was that i would have the new values of the ratings table that were going to be inserted or updated and use those to compare to whats in the rentals table to see if that customer had rented that movie already, if they did then they could enter a rating. but i cant transfer that logic in this lol. unless there an easier way to do this.
The loop inside the function complicates matters a bit, let's see if we can get rid of it. Your ratings table has a reference to customer and movie so we need a join.
SELECT COUNT(*) INTO rented FROM rentals WHERE disc_id IN
(SELECT id from discs INNER JOIN
rentals ON disc_id = discs.id where movie_id = new.movie_id)
AND customer_id = new.customer_id
Right this should make the logic of your stored procedure a lot easier. I am now leaving you to finish it because this after all is a learning exercise.
You need this sort of a join because it's more efficient and simpler than the loop. The ratings table has a reference to the movie_id but the rentals table only has a disc_id thus to find out if the user has rented a particular movie, you need to join it through the disc table.
You will need to change the return values. ref: http://www.postgresql.org/docs/9.2/static/plpgsql-trigger.html
Row-level triggers fired BEFORE can return null to signal the trigger
manager to skip the rest of the operation for this row (i.e.,
subsequent triggers are not fired, and the INSERT/UPDATE/DELETE does
not occur for this row). If a nonnull value is returned then the
operation proceeds with that row value
And also note that you do not do an INSERT inside your trigger function. You just return a non null value for the insert to proceed.
This is the EXISTS() version. (BTW: the definition for movies is missing)
CREATE OR REPLACE FUNCTION rate_only_rented()
RETURNS TRIGGER AS $func$
BEGIN
IF ( NOT EXISTS (
SELECT *
FROM rentals r
JOIN discs d ON r.disc_id = d.id
WHERE d.movie_id = NEW.movie_id
AND r.customer_id = NEW.customer_id
) ) THEN
RAISE EXCEPTION 'you(%) have not rented this movie(%) before'
, NEW.customer_id ,NEW.movie_id;
RETURN NULL;
ELSE
RETURN NEW;
END IF;
END;
$func$ language plpgsql;
And the trigger:
CREATE TRIGGER rate_only_rented
AFTER INSERT OR UPDATE
ON ratings
FOR EACH ROW
EXECUTE PROCEDURE rate_only_rented()
;

select all rows tagged with a list of tags

I came up with this query to find all people that where tagged with a certain list of tags:
select * from people
where ARRAY[?]::character varying[] <# ARRAY(
select tags.name
from tags
inner join taggings on tags.id = taggings.tag_id
where taggings.taggable_type = 'Person' and
taggings.taggable_id = people.id)
Somehow I feel I'm making things too complicated. Right now we don't have enough data for this not to perform well, but is there really not a better way to do it?
Edit: Minimal table definitions:
create table people (
id integer
);
create table tags (
id integer,
name text
);
create table taggings (
id integer,
tag_id integer,
taggalbe_type text,
taggable_id integer
);
Minimal data:
insert into people values (1);
insert into people values (2);
insert into people values (3);
insert into tags values (1, 'foo');
insert into tags values (2, 'bar');
insert into tags values (3, 'baz');
insert into taggings values (1, 1, 'Person', 1);
insert into taggings values (2, 2, 'Person', 1);
insert into taggings values (3, 1, 'Person', 2);
insert into taggings values (4, 2, 'Person', 2);
insert into taggings values (5, 3, 'Person', 2);
Now I want e.g. everyone that is tagged with foo and bar. That would be the person with id 2 in this example.
select p.id, array_agg(t.name) as tag_name
from
people p
inner join
taggings g on p.id = g.taggable_id
inner join
tags t on g.tag_id = t.id
where g.taggable_type = 'Person'
group by p.id
having array['foo','bar']::text[] <# array_agg(t.name)
;
id | tag_name
----+---------------
1 | {bar,foo}
2 | {baz,bar,foo}

Need help with a SELECT statement

I express the relationship between records and searchtags that can be attached to records like so:
TABLE RECORDS
id
name
TABLE SEARCHTAGS
id
recordid
name
I want to be able to SELECT records based on the searchtags that they have. For example, I want to be able to SELECT all records that have searchtags:
(1 OR 2 OR 5) AND (6 OR 7) AND (10)
Using the above data structure, I am uncertain how to structure the SQL to accomplish this.
Any suggestions?
Thanks!
You may want to try the following:
SELECT r.id, r.name
FROM records r
WHERE EXISTS (SELECT NULL FROM searchtags WHERE recordid = r.id AND id IN (1, 2, 5)) AND
EXISTS (SELECT NULL FROM searchtags WHERE recordid = r.id AND id IN (6, 7)) AND
EXISTS (SELECT NULL FROM searchtags WHERE recordid = r.id AND id IN (10));
Test case: Note that only records 1 and 4 will satisfy the query criteria.
CREATE TABLE records (id int, name varchar(10));
CREATE TABLE searchtags (id int, recordid int);
INSERT INTO records VALUES (1, 'a');
INSERT INTO records VALUES (2, 'b');
INSERT INTO records VALUES (3, 'c');
INSERT INTO records VALUES (4, 'd');
INSERT INTO searchtags VALUES (1, 1);
INSERT INTO searchtags VALUES (2, 1);
INSERT INTO searchtags VALUES (6, 1);
INSERT INTO searchtags VALUES (10, 1);
INSERT INTO searchtags VALUES (1, 2);
INSERT INTO searchtags VALUES (2, 2);
INSERT INTO searchtags VALUES (3, 2);
INSERT INTO searchtags VALUES (1, 3);
INSERT INTO searchtags VALUES (10, 3);
INSERT INTO searchtags VALUES (5, 4);
INSERT INTO searchtags VALUES (7, 4);
INSERT INTO searchtags VALUES (10, 4);
Result:
+------+------+
| id | name |
+------+------+
| 1 | a |
| 4 | d |
+------+------+
2 rows in set (0.01 sec)
SELECT
id, name
FROM
records
WHERE
EXISTS (
SELECT 1 FROM searchtags WHERE recordid = records.id AND id IN (1, 2, 5)
)
AND EXISTS (
SELECT 1 FROM searchtags WHERE recordid = records.id AND id IN (6, 7)
)
AND EXISTS (
SELECT 1 FROM searchtags WHERE recordid = records.id AND id IN (10)
)
not sure how to do it in mysql, but in t-sql, you could do something like:
SELECT id, name FROM RECORDS where id in (SELECT recordid from SEARCHTAGS where id in (1,2,5,6,7,10))
I may not be understanding your question entirely... but I gave it my best.
Try:
SELECT R.*
FROM RECORDS R, SEARCHTAGS S
WHERE R.id == S.recordid
AND S.name in (1,2,5,6,7,10);
Don't know if you need S.name or S.id, but this is an example.
select RECORDS.name
from RECORDS join SEARCHTAGS
on RECORDS.id = SEARCHTAGS.recordid
where RECORDS.id in (1,2,...)
I misread the question first time around, and thought it was asking for
(1 AND 2 AND 5) OR (6 AND 7) OR (10)
instead of the correct
(1 OR 2 OR 5) AND (6 OR 7) AND (10)
All the answers so far have concentrated on answering the specific example, rather than addressing the more general question "and suppose I want a different set of criteria next time".
Actual question
I can't do much better than the selected answer for the actual question (Query 1):
SELECT r.id, r.name
FROM Records AS r
WHERE EXISTS(SELECT * FROM SearchTags AS s
WHERE r.id = s.recordid AND s.id IN (1, 2, 5))
AND EXISTS(SELECT * FROM SearchTags AS s
WHERE r.id = s.recordid AND s.id IN (6, 7))
AND EXISTS(SELECT * FROM SearchTags AS s
WHERE r.id = s.recordid AND s.id IN (10));
This could be written as a join to 3 aliases for the SearchTags table.
Alternative question
There are several ways to answer the alternative - I think this is the most nearly neat and extensible. Clearly, the one item (10) is easy (Query 2):
SELECT r.id, r.name
FROM records AS r JOIN searchtags AS t ON r.id = t.recordid
WHERE t.id IN (10) -- or '= 10' but IN is consistent with what follows
The two items (6 or 7) can be done with (Query 3):
SELECT r.id, r.name
FROM records AS r JOIN searchtags AS t ON r.id = t.recordid
WHERE t.id IN (6, 7)
GROUP BY r.id, r.name
HAVING COUNT(*) = 2
The three items (1, 2, 5) can be done with (Query 4):
SELECT r.id, r.name
FROM records AS r JOIN searchtags AS t ON r.id = t.recordid
WHERE t.id IN (1, 2, 5)
GROUP BY r.id, r.name
HAVING COUNT(*) = 3
And the whole collection can be a UNION of the three terms.
Generalizing the solutions
The downside of this solution is that the SQL must be manually crafted for each set of items.
If you want to automate the 'SQL generation', you need the control data - the sets of interesting search tags - in a table:
CREATE TABLE InterestingTags(GroupID INTEGER, TagID INTEGER);
INSERT INTO InterestingTags(1, 1);
INSERT INTO InterestingTags(1, 2);
INSERT INTO InterestingTags(1, 5);
INSERT INTO InterestingTags(2, 6);
INSERT INTO InterestingTags(2, 7);
INSERT INTO InterestingTags(3, 10);
For the query asking for '(1 OR 2 OR 5) AND (...)' (conjunctive normal form), you can write (Query 5):
SELECT r.id, r.name
FROM records AS r JOIN
searchtags AS s ON r.id = s.recordID JOIN
interestingtags AS t ON s.id = t.tagID
GROUP BY r.id, r.name
HAVING COUNT(DISTINCT t.GroupID) = (SELECT COUNT(DISTINCT GroupID)
FROM InterestingTags);
This checks that the number of distinct 'interesting groups of tags' for a given record is equal to the total number of 'interesting groups of tags'.
For the query asking for '(1 AND 2 AND 5) OR (...)' (disjunctive normal form), you can write a join with InterestingTags and check that the Record has as many entries as the group of tags (Query 6):
SELECT i.id, i.name
FROM (SELECT q.id, q.name, c.GroupSize,
COUNT(DISTINCT t.GroupID) AS GroupCount
FROM records AS q JOIN
searchtags AS s ON q.id = s.recordID JOIN
interestingtags AS t ON s.id = t.tagID JOIN
(SELECT GroupID, COUNT(*) AS GroupSize
FROM InterestingTags
GROUP BY GroupID) AS c ON c.GroupID = t.GroupID
GROUP BY q.id, q.name, c.GroupSize
) AS i
WHERE i.GroupCount = i.GroupSize;
Test Data
I took the test data from Daniel Vassalo's answer and augmented it with some extra values:
CREATE TABLE records (id int, name varchar(10));
CREATE TABLE searchtags (id int, recordid int);
INSERT INTO records VALUES (1, 'a');
INSERT INTO records VALUES (2, 'b');
INSERT INTO records VALUES (3, 'c');
INSERT INTO records VALUES (4, 'd');
INSERT INTO records VALUES (11, 'A11');
INSERT INTO records VALUES (21, 'B12');
INSERT INTO records VALUES (31, 'C13');
INSERT INTO records VALUES (41, 'D14');
INSERT INTO records VALUES (51, 'E15');
INSERT INTO records VALUES (61, 'F16');
INSERT INTO searchtags VALUES (1, 1);
INSERT INTO searchtags VALUES (2, 1);
INSERT INTO searchtags VALUES (6, 1);
INSERT INTO searchtags VALUES (10, 1);
INSERT INTO searchtags VALUES (1, 2);
INSERT INTO searchtags VALUES (2, 2);
INSERT INTO searchtags VALUES (3, 2);
INSERT INTO searchtags VALUES (1, 3);
INSERT INTO searchtags VALUES (10, 3);
INSERT INTO searchtags VALUES (5, 4);
INSERT INTO searchtags VALUES (7, 4);
INSERT INTO searchtags VALUES (10, 4);
INSERT INTO searchtags VALUES (1, 11);
INSERT INTO searchtags VALUES (2, 11);
INSERT INTO searchtags VALUES (5, 11);
INSERT INTO searchtags VALUES (6, 21);
INSERT INTO searchtags VALUES (7, 21);
INSERT INTO searchtags VALUES (10, 31);
INSERT INTO searchtags VALUES (1, 41);
INSERT INTO searchtags VALUES (6, 41);
INSERT INTO searchtags VALUES (10, 41);
INSERT INTO searchtags VALUES (2, 51);
INSERT INTO searchtags VALUES (5, 51);
INSERT INTO searchtags VALUES (10, 51);
INSERT INTO searchtags VALUES (7, 61);
INSERT INTO searchtags VALUES (2, 61);
INSERT INTO searchtags VALUES (1, 61);
CREATE TABLE InterestingTags(GroupID INTEGER, TagID INTEGER);
INSERT INTO InterestingTags VALUES(1, 1);
INSERT INTO InterestingTags VALUES(1, 2);
INSERT INTO InterestingTags VALUES(1, 5);
INSERT INTO InterestingTags VALUES(2, 6);
INSERT INTO InterestingTags VALUES(2, 7);
INSERT INTO InterestingTags VALUES(3, 10);
Test results
The outputs that I got were:
Query 1
1 a
4 d
41 D14
Query 2
1 a
3 c
4 d
31 C13
41 D14
51 E15
Query 3
21 B12
Query 4
11 A11
Query 5
1 a
41 D14
4 d
Query 6
4 d
31 C13
3 c
1 a
41 D14
51 E15
Clearly, if I wanted the output in a specific order, I would add an ORDER BY clause to the queries.