Update docstrings and type hinting

app.py

@@ -9,7 +9,6 @@ from sentence_transformers import SentenceTransformer
 from sklearn.metrics.pairwise import cosine_similarity
 
 
-
 def load_model() -> SentenceTransformer:
     """
     Loads a pre-trained SentenceTransformer model.
@@ -25,7 +24,9 @@ def load_model() -> SentenceTransformer:
     return model
 
 
-def encode_and_calculate_similarity(model: SentenceTransformer, df_merged: pd.DataFrame) -> np.ndarray:
+def encode_and_calculate_similarity(
+    model: SentenceTransformer, df_merged: pd.DataFrame
+) -> np.ndarray:
     """
     Encodes sentences using the provided SentenceTransformer model and calculates cosine similarity.
 
@@ -59,7 +60,7 @@ def svd(df_ratings: pd.DataFrame) -> SVD:
 
 def get_sorted_similar_movies(
     title: str, cos_sim: np.ndarray, df_merged: pd.DataFrame
-) -> list[int]:
+) -> pd.DataFrame:
     """
     Get a sorted DataFrame of movies based on their similarity scores to a given movie.
 
@@ -151,19 +152,25 @@ def predict_user_rating(
     return final_qualified_movies
 
 
-def get_movie_recommendations_hybrid(title: str, user_id: int) -> pd.DataFrame:
+def get_movie_recommendations_hybrid(
+    title: str, user_id: int
+) -> tuple[pd.DataFrame, pd.DataFrame]:
     """
     Get movie recommendations based on a given title and user ID.
 
     :param title: The title of the movie to find similar movies for.
     :param userId: The ID of the user.
-    :return: A Pandas DataFrame containing the recommended movies
+    :return: A tuple of two Pandas DataFrames.
+        The first DataFrame contains the recommended movies.
+        The second DataFrame contains the recommendation criteria (ID, Title, Predicted User Rating, Similarity Score, Weighted Rating).
     """
     # Get recommended movie indices based on the given title
     sorted_similar_movies = get_sorted_similar_movies(title, cos_sim, df_merged)
 
-     # Filter out bad movies and select the top 50 qualified movies
-    qualified_movies = get_qualified_movies(df_qualified, sorted_similar_movies).head(50)
+    # Filter out bad movies and select the top 50 qualified movies
+    qualified_movies = get_qualified_movies(df_qualified, sorted_similar_movies).head(
+        50
+    )
 
     # Predict user ratings for qualified movies and select the top recommended movies
     recommended_movies = predict_user_rating(
@@ -183,8 +190,14 @@ def get_movie_recommendations_hybrid(title: str, user_id: int) -> pd.DataFrame:
         "Predicted User Rating",
     ]
 
-    recommendation_criteria = recommended_movies[["ID", "Title", "Predicted User Rating", "Similarity Score", "Weighted Rating"]]
-    recommended_movies.drop(["Predicted User Rating", "Similarity Score", "Weighted Rating"], axis = 1, inplace=True)
+    recommendation_criteria = recommended_movies[
+        ["ID", "Title", "Predicted User Rating", "Similarity Score", "Weighted Rating"]
+    ]
+    recommended_movies.drop(
+        ["Predicted User Rating", "Similarity Score", "Weighted Rating"],
+        axis=1,
+        inplace=True,
+    )
     return recommended_movies, recommendation_criteria
 
 
@@ -222,7 +235,7 @@ if __name__ == "__main__":
         recommend_button.click(
             get_movie_recommendations_hybrid,
             inputs=[title, user_id],
-            outputs=[recommended_movies, recommendation_criteria]
+            outputs=[recommended_movies, recommendation_criteria],
         )
         examples = gr.Examples(
             examples=[