Update app.py

app.py

@@ -1,3 +1,4 @@
+```python
 import gradio as gr
 import pandas as pd
 from datasets import load_dataset
@@ -8,29 +9,33 @@ ds = load_dataset("bstds/movielens", "small", split="train")
 # 2) Convert to pandas
 df = ds.to_pandas()
 
-# 3) Extract release year from title, e.g. "Movie Title (1999)" → 1999
+# 3) Normalize genres (list -> string) and extract release year from title
+df["genres"] = df["genres"].apply(lambda g: "|".join(g) if isinstance(g, list) else str(g))
 df["release_year"] = (
     df["title"]
-      .str.extract(r"\((\d{4})\)")    # capture 4-digit year
-      .astype(pd.Int64Dtype())         # allow missing values
+      .str.extract(r"\((\d{4})\)")[0]
+      .astype(pd.Int64Dtype(), errors='ignore')
 )
 
 # 4) Deduplicate metadata
 metadata = df[["title", "genres", "release_year"]].drop_duplicates()
 
+
 def recommend_by_genre_year(genre: str, year: int, top_k: int = 5) -> str:
-    # filter genre (case-insensitive substring)
-    mask_genre = metadata["genres"].str.lower().str.contains(genre.lower())
-    # filter release year ≥ input year (drop rows missing year)
-    mask_year  = metadata["release_year"].fillna(0) >= year
+    # filter by genre substring (case-insensitive)
+    mask_genre = metadata["genres"].str.lower().str.contains(genre.lower(), na=False)
+    # filter release year ≥ input year (treat NaN as 0)
+    mask_year = metadata["release_year"].fillna(0) >= year
 
     candidates = metadata[mask_genre & mask_year]
     if candidates.empty:
         return f"No '{genre.title()}' movies found from {year} onward."
 
     picks = candidates.sample(n=min(top_k, len(candidates)))
-    return "\n".join(f"• {row.title} ({int(row.release_year) if pd.notna(row.release_year) else 'Year N/A'})"
-                     for _, row in picks.iterrows())
+    return "\n".join(
+        f"• {row.title} ({int(row.release_year) if pd.notna(row.release_year) else 'Year N/A'})"
+        for _, row in picks.iterrows()
+    )
 
 iface = gr.Interface(
     fn=recommend_by_genre_year,
@@ -43,9 +48,10 @@ iface = gr.Interface(
     title="🎬 Genre & Year-Based Movie Recommender",
     description="""
 Loads MovieLens metadata (small split) from the Hub, extracts release years from titles,
-and filters by genre substring & year. No local files needed.
+normalizes genres, and filters by genre substring & year. No local files needed.
 """,
 )
 
 if __name__ == "__main__":
     iface.launch()
+```