How can this query be optimized? - sql

Question

I need to write this query in postgresql 9.3:
List the most popular movie in each country. The most popular movie/movies is the one that has got the highest average rating
across all the users of that country. In case of a tie, return all
movies order alphabetically. (2 columns)
Tables needed:
CREATE TABLE movie (
id integer,
name varchar(200),
year date
);
CREATE TABLE userProfile (
userid varchar(200),
gender char(1),
age integer,
country varchar(200),
registered date
);
CREATE TABLE ratings (
mid integer,
userid varchar(200),
rating integer
);
CREATE INDEX movie_id_idx ON movie (id);
CREATE INDEX userProfile_userid_idx ON userProfile (userid);
CREATE INDEX ratings_userid_idx ON ratings (userid);
CREATE INDEX ratings_mid_idx ON ratings (mid);
CREATE INDEX ratings_userid_mid_idx ON ratings (userid, mid);
Here is mine query:
CREATE TEMP TABLE tops AS SELECT country, name
FROM ratings AS r INNER JOIN userProfile AS u
ON r.userid=u.userid
INNER JOIN movie AS m ON m.id = r.mid LIMIT 0;
~10 min
CREATE TEMP TABLE avg_country AS
SELECT country, r.mid, AVG(rating) AS rate
FROM ratings AS r INNER JOIN userProfile AS u
ON r.userid=u.userid
GROUP BY country, r.mid;
~8 min
DO $$
DECLARE arrow record;
BEGIN
CREATE TABLE movie_names AS SELECT id, name FROM movie;
FOR arrow IN SELECT DISTINCT country FROM userProfile ORDER BY country
LOOP
CREATE TABLE movies AS SELECT mid FROM (SELECT MAX(rate) AS m_rate FROM avg_country
WHERE country=arrow.country) AS max_val CROSS JOIN LATERAL
(SELECT mid FROM avg_country
WHERE country=arrow.country AND rate=max_val.m_rate) AS a;
WITH names AS (DELETE FROM movie_names AS m
WHERE m.id IN (SELECT mid FROM movies) RETURNING name)
INSERT INTO tops
SELECT arrow.country, name FROM names ORDER BY name;
DROP TABLE movies;
END LOOP;
DROP TABLE movie_names;
END$$;
SELECT * FROM tops;
DROP TABLE tops, avg_country;
Thanks a lot in advance)

Answer 1

This is similar to kordirkos answer, but with one fewer subquery:
select country, movie_name, avg_rating
from (select u.country, m.name as movie_name, avg(r.rating) as avg_rating
rank() over (partition by u.country order by avg(r.rating) desc) as seqnum
from userProfile u join
ratings r
on u.userid = r.userid join
movie m
on r.mid = m.id
group by u.country, m.id -- `name` is not needed here because id is unique
) uc
where seqnum = 1;
Alternatively, if you want to get the list on one row per country:
select country, string_agg(movie_name, '; ') as most_popular_movies
from (select u.country, m.name as movie_name, avg(r.rating) as avg_rating
rank() over (partition by u.country order by avg(r.rating) desc) as seqnum
from userProfile u join
ratings r
on u.userid = r.userid join
movie m
on r.mid = m.id
group by u.country, m.id -- `name` is not needed here because id is unique
) uc
where seqnum = 1
group by country;

Answer 2

Use a plain, old-fashioned SQL - it is old but gold.
WITH q AS (
SELECT *,
dense_rank() over (partition by country order by avg_rating desc ) rank
FROM (
select u.country, m.name movie_name, avg( r.rating ) avg_rating
from userProfile u
join ratings r on u.userid = r.userid
join movie m on r.mid = m.id
group by u.country, m.name
) xx )
SELECT country, movie_name
FROM q WHERE rank <= 1