make ratings_df and games_df smaller before merging to main df

threnjen · Dec 17, 2024 · 5bdb4be · 5bdb4be
1 parent bc6d167
commit 5bdb4be
Showing 1 changed file with 6 additions and 3 deletions.
diff --git a/modules/rag_description_generation/main.py b/modules/rag_description_generation/main.py
@@ -85,14 +85,17 @@ def merge_game_df_with_ratings_df(self, game_df_reduced):
             file_name="ratings_data.pkl",
         )
         ratings_df["BGGId"] = ratings_df["BGGId"].astype("string")
+        ratings_df = ratings_df[["username", "BGGId", "rating"]]
+
+        game_df_reduced = game_df_reduced[
+            ["BGGId", "Name", "Description", "AvgRating", "BayesAvgRating"]
+        ]
 
         print(
             f"Reducing user ratings to only include games in the reduced game dataframe\n"
         )
         all_games_df = ratings_df.merge(
-            game_df_reduced[
-                ["BGGId", "Name", "Description", "AvgRating", "BayesAvgRating"]
-            ],
+            game_df_reduced,
             on="BGGId",
             how="inner",
         )