minstrel/internal/db/queries/genre_mixes.sql

-- Candidate queries for the genre mixes: one daily system playlist per genre
-- the user listens to. Genres live inline on tracks.genre as a delimited
-- string and are split on [;,] the same way the Discover and radio tag arms
-- split them. Matching is case-insensitive, so the ID3 "Post-Punk" and the
-- folksonomy "post-punk" in the taste profile count as one genre.

-- name: ListGenreMixCandidates :many
-- Library genres big enough to carry a mix (>= 25 playable tracks across
-- >= 3 artists), each tagged with how close it is to the user's listening:
--
--   tier 1: a positive taste-profile genre, scored by its taste weight
--   tier 2: a genre of tracks the user has played through or liked, scored
--           by how many — catches a profile that has not been built yet or
--           has decayed past its window
--   tier 3: any other library genre, scored by its size
--
-- track_ids lets the caller tell how much music two genres share: a genre
-- whose songs mostly sit in genres already picked adds no new channel, and a
-- broad genre ("Rock") whose songs mostly carry narrower ones ("Pop Punk",
-- "Ska Punk") gives way to them.
-- $1 user_id.
WITH library_genres AS (
    SELECT lower(trim(g.g))           AS genre_key,
           min(trim(g.g))::text       AS label,
           COUNT(DISTINCT t.id)        AS track_count,
           array_agg(DISTINCT t.id)::uuid[] AS track_ids
      FROM tracks t
      CROSS JOIN LATERAL regexp_split_to_table(coalesce(t.genre, ''), '[;,]') AS g(g)
     WHERE t.missing_since IS NULL
       AND trim(g.g) <> ''
     GROUP BY lower(trim(g.g))
    HAVING COUNT(DISTINCT t.id) >= 25
       AND COUNT(DISTINCT t.artist_id) >= 3
),
taste AS (
    SELECT lower(trim(tpt.tag)) AS genre_key, SUM(tpt.weight) AS weight
      FROM taste_profile_tags tpt
     WHERE tpt.user_id = $1
     GROUP BY lower(trim(tpt.tag))
    HAVING SUM(tpt.weight) > 0
),
listened AS (
    SELECT t.id
      FROM play_events pe
      JOIN tracks t ON t.id = pe.track_id
     WHERE pe.user_id = $1 AND pe.was_skipped = false
    UNION ALL
    SELECT gl.track_id
      FROM general_likes gl
     WHERE gl.user_id = $1
),
history AS (
    SELECT lower(trim(g.g)) AS genre_key, COUNT(*) AS plays
      FROM listened l
      JOIN tracks t ON t.id = l.id
      CROSS JOIN LATERAL regexp_split_to_table(coalesce(t.genre, ''), '[;,]') AS g(g)
     WHERE trim(g.g) <> ''
     GROUP BY lower(trim(g.g))
)
SELECT lg.genre_key::text AS genre_key,
       lg.label           AS label,
       (CASE WHEN ta.genre_key IS NOT NULL THEN 1
             WHEN h.genre_key  IS NOT NULL THEN 2
             ELSE 3 END)::int AS tier,
       (CASE WHEN ta.genre_key IS NOT NULL THEN ta.weight
             WHEN h.genre_key  IS NOT NULL THEN h.plays::float8
             ELSE lg.track_count::float8 END)::float8 AS score,
       lg.track_ids
  FROM library_genres lg
  LEFT JOIN taste   ta ON ta.genre_key = lg.genre_key
  LEFT JOIN history h  ON h.genre_key  = lg.genre_key
 ORDER BY tier, score DESC, lg.genre_key
 LIMIT 60;

-- name: ListGenreMixTracks :many
-- Playable tracks carrying one genre, split into the two halves a genre mix
-- blends: familiar (the user has played it through or liked it) and unheard.
-- Up to 200 of each, drawn by a weighted lottery seeded with the date, so the
-- mix changes day to day, holds still within a day, and leans toward what the
-- user likes without becoming the same 50 songs every day.
--
-- The lottery is the Efraimidis-Spirakis draw: each track gets
-- -ln(u) / weight with u uniform in (0, 1) from md5(track, date), and the
-- smallest keys win. A track of weight 3 is three times as likely as one of
-- weight 1 to come before it, and every track keeps some chance.
--
-- Familiar weight: 1 + ln(1 + plays through) + 1 if liked, times the share of
-- its plays that were not skips. A song played 40 times weighs about 4.7, one
-- played once about 1.7.
--
-- Unheard weight: 1 + ln(1 + the artist's plays through + 2 × its liked
-- tracks) + 2 × how similar the artist is to the user's own artists (the best
-- artist_similarity score from any artist they have played through or liked,
-- 0 to 1), times the share of the artist's plays that were not skips. An
-- artist the user has never met weighs 1, so new artists still come up; an
-- artist they keep skipping weighs well under 1.
--
-- A track the user keeps skipping stays out: twice-skipped and skipped more
-- often than played through. The second half of that test keeps a favourite
-- with a couple of stray skips in.
--
-- exclude_genres keeps each song in one mix: a track carrying a genre that
-- already has a mix today is left to that mix.
WITH play_counts AS (
    SELECT pe.track_id, COUNT(*) AS c
      FROM play_events pe
     WHERE pe.user_id = sqlc.arg(user_id) AND pe.was_skipped = false
     GROUP BY pe.track_id
),
skip_counts AS (
    SELECT pe.track_id, COUNT(*) AS c
      FROM play_events pe
     WHERE pe.user_id = sqlc.arg(user_id) AND pe.was_skipped = true
     GROUP BY pe.track_id
),
artist_plays AS (
    SELECT t.artist_id,
           COUNT(*) FILTER (WHERE NOT pe.was_skipped) AS plays,
           COUNT(*) FILTER (WHERE pe.was_skipped)     AS skips
      FROM play_events pe
      JOIN tracks t ON t.id = pe.track_id
     WHERE pe.user_id = sqlc.arg(user_id)
     GROUP BY t.artist_id
),
artist_likes AS (
    SELECT t.artist_id, COUNT(*) AS likes
      FROM general_likes gl
      JOIN tracks t ON t.id = gl.track_id
     WHERE gl.user_id = sqlc.arg(user_id)
     GROUP BY t.artist_id
),
own_artists AS (
    SELECT ap.artist_id FROM artist_plays ap WHERE ap.plays > 0
    UNION
    SELECT al.artist_id FROM artist_likes al
),
artist_sim AS (
    SELECT asim.artist_b_id AS artist_id,
           MAX(LEAST(GREATEST(asim.score, 0), 1)) AS sim
      FROM artist_similarity asim
      JOIN own_artists oa ON oa.artist_id = asim.artist_a_id
     GROUP BY asim.artist_b_id
),
eligible AS (
    SELECT t.id, t.album_id, t.artist_id,
           (COALESCE(pc.c, 0) > 0 OR gl.track_id IS NOT NULL) AS familiar,
           CASE
             WHEN COALESCE(pc.c, 0) > 0 OR gl.track_id IS NOT NULL THEN
               (1 + ln(1 + COALESCE(pc.c, 0)::float8)
                  + CASE WHEN gl.track_id IS NOT NULL THEN 1 ELSE 0 END)
               * ((COALESCE(pc.c, 0) + 1)::float8 / (COALESCE(pc.c, 0) + COALESCE(sc.c, 0) + 1))
             ELSE
               (1 + ln(1 + COALESCE(ap.plays, 0)::float8 + 2 * COALESCE(al.likes, 0)::float8)
                  + 2 * COALESCE(asm.sim, 0))
               * ((COALESCE(ap.plays, 0) + 1)::float8 / (COALESCE(ap.plays, 0) + COALESCE(ap.skips, 0) + 1))
           END::float8 AS weight,
           -- u in (0, 1): the first 32 bits of md5(track, date), shifted off 0.
           ((('x' || substr(md5(t.id::text || sqlc.arg(date_seed)::text), 1, 8))::bit(32)::bigint)::float8 + 1)
             / 4294967297.0 AS u
      FROM tracks t
      LEFT JOIN play_counts pc ON pc.track_id = t.id
      LEFT JOIN skip_counts sc ON sc.track_id = t.id
      LEFT JOIN general_likes gl ON gl.user_id = sqlc.arg(user_id) AND gl.track_id = t.id
      LEFT JOIN artist_plays ap ON ap.artist_id = t.artist_id
      LEFT JOIN artist_likes al ON al.artist_id = t.artist_id
      LEFT JOIN artist_sim asm ON asm.artist_id = t.artist_id
     WHERE t.missing_since IS NULL   -- never offer a file that is gone
       AND NOT (COALESCE(sc.c, 0) >= 2 AND COALESCE(sc.c, 0) > COALESCE(pc.c, 0))
       AND EXISTS (
           SELECT 1
             FROM regexp_split_to_table(coalesce(t.genre, ''), '[;,]') AS g(g)
            WHERE lower(trim(g.g)) = sqlc.arg(genre_key)::text
       )
       AND NOT EXISTS (
           SELECT 1
             FROM regexp_split_to_table(coalesce(t.genre, ''), '[;,]') AS g(g)
            WHERE lower(trim(g.g)) = ANY(sqlc.arg(exclude_genres)::text[])
       )
       AND NOT EXISTS (
           SELECT 1 FROM quarantine q
            WHERE q.user_id = sqlc.arg(user_id) AND q.track_id = t.id
       )
),
ranked AS (
    SELECT e.id, e.album_id, e.artist_id, e.familiar,
           -ln(e.u) / e.weight AS draw,
           row_number() OVER (PARTITION BY e.familiar ORDER BY -ln(e.u) / e.weight, e.id) AS rn
      FROM eligible e
)
SELECT r.id, r.album_id, r.artist_id, r.familiar::bool AS familiar
  FROM ranked r
 WHERE r.rn <= 200
 ORDER BY r.familiar DESC, r.draw, r.id;