remove comments, prepare for merge

Aerozol · Dec 7, 2023 · 0552478 · 0552478
1 parent 75c9acd
commit 0552478
Show file tree

Hide file tree

Showing 5 changed files with 32 additions and 26 deletions.
diff --git a/listenbrainz/db/playlist.py b/listenbrainz/db/playlist.py
@@ -19,7 +19,15 @@
 LISTENBRAINZ_USER_ID = 23944
 
 # These are the recommendation troi patches that we showcase on the recommendations page for each user
-RECOMMENDATION_PATCHES = ('daily-jams', 'weekly-jams', 'weekly-exploration', 'top-discoveries-for-year', 'top-missed-recordings-for-year')
+RECOMMENDATION_PATCHES = (
+    'daily-jams',
+    'weekly-jams',
+    'weekly-exploration',
+    'top-discoveries-for-year',
+    'top-missed-recordings-for-year',
+    'top-discoveries-of-2023',
+    'top-missed-recordings-of-2023'
+)
 
 
 def get_by_mbid(playlist_id: str, load_recordings: bool = True) -> Optional[model_playlist.Playlist]:

diff --git a/listenbrainz/troi/year_in_music.py b/listenbrainz/troi/year_in_music.py
@@ -26,8 +26,6 @@ def exclude_playlists_from_deleted_users(slug, year, jam_name, description, user
             continue
 
         user = user_details[user_id]
-        if user["username"] not in ["rob", "lucifer", "mr_monkey", "aerozol"]:
-            continue
 
         similar_users = ""
         if slug.startswith("top-missed-recordings"):

diff --git a/listenbrainz_spark/year_in_music/top_discoveries.py b/listenbrainz_spark/year_in_music/top_discoveries.py
@@ -1,8 +1,10 @@
+from datetime import datetime, date, time
+
 from more_itertools import chunked
 
 from listenbrainz_spark.path import RECORDING_ARTIST_DATAFRAME
 from listenbrainz_spark.stats import run_query
-from listenbrainz_spark.year_in_music.utils import create_tracks_of_the_year
+from listenbrainz_spark.utils import get_listens_from_dump
 
 USERS_PER_MESSAGE = 1000
 MAX_ARTIST_OCCURRENCE = 2
@@ -61,3 +63,20 @@ def generate_top_discoveries(year):
         "year": year,
         "type": "year_in_music_playlists_end"
     }
+
+
+def create_tracks_of_the_year(year):
+    end = datetime.combine(date(year, 12, 31), time.max)
+    listens = get_listens_from_dump(end=end)
+    listens.createOrReplaceTempView("listens_for_tracks_of_year")
+    query = f"""
+            SELECT user_id
+                 , recording_mbid
+                 , count(*) AS score
+              FROM listens_for_tracks_of_year
+             WHERE recording_mbid IS NOT NULL
+          GROUP BY user_id
+                 , recording_mbid
+            HAVING date_part('YEAR', min(listened_at)) = {year}
+    """
+    run_query(query).createOrReplaceTempView("tracks_of_year")
diff --git a/listenbrainz_spark/year_in_music/top_missed_recordings.py b/listenbrainz_spark/year_in_music/top_missed_recordings.py
@@ -9,7 +9,6 @@
 from listenbrainz_spark.similarity.user import get_similar_users_df
 from listenbrainz_spark.stats import run_query
 from listenbrainz_spark.utils import get_listens_from_dump
-from listenbrainz_spark.year_in_music.utils import create_tracks_of_the_year
 
 USERS_PER_MESSAGE = 1000
 MAX_ARTIST_OCCURRENCE = 2
@@ -18,9 +17,9 @@
 
 
 def get_similar_users(year):
-    # from_date = datetime(year, 1, 1)
-    # to_date = datetime.combine(date(year, 12, 31), time.max)
-    # calculate_dataframes(from_date, to_date, "similar_users", 50)
+    from_date = datetime(year, 1, 1)
+    to_date = datetime.combine(date(year, 12, 31), time.max)
+    calculate_dataframes(from_date, to_date, "similar_users", 50)
     similar_users_df = get_similar_users_df(3)
 
     users = []

diff --git a/listenbrainz_spark/year_in_music/utils.py b/listenbrainz_spark/year_in_music/utils.py
@@ -1,6 +1,5 @@
 from datetime import datetime, date, time
 
-from listenbrainz_spark.stats import run_query
 from listenbrainz_spark.utils import get_listens_from_dump
 
 
@@ -9,20 +8,3 @@ def setup_listens_for_year(year):
     end = datetime.combine(date(year, 12, 31), time.max)
     listens = get_listens_from_dump(start, end)
     listens.createOrReplaceTempView("listens_of_year")
-
-
-def create_tracks_of_the_year(year):
-    end = datetime.combine(date(year, 12, 31), time.max)
-    listens = get_listens_from_dump(end=end)
-    listens.createOrReplaceTempView("listens_for_tracks_of_year")
-    query = f"""
-            SELECT user_id
-                 , recording_mbid
-                 , count(*) AS score
-              FROM listens_for_tracks_of_year
-             WHERE recording_mbid IS NOT NULL
-          GROUP BY user_id
-                 , recording_mbid
-            HAVING date_part('YEAR', min(listened_at)) = {year}
-    """
-    run_query(query).createOrReplaceTempView("tracks_of_year")