Update app.py

app.py

@@ -1,15 +1,12 @@
-
 import gradio as gr
 import pandas as pd
-from datasets import load_dataset
-
-# 1) Load MovieLens metadata (small split, ~1.5K movies)
-ds = load_dataset("bstds/movielens", "small", split="train")
+import os
 
-# 2) Convert to pandas
-df = ds.to_pandas()
+# 1) Load movies.csv from extracted ml-32m dataset
+csv_path = os.path.join("ml-32m", "movies.csv")  # Adjust path if needed
+df = pd.read_csv(csv_path)
 
-# 3) Normalize genres (list -> string) and extract release year from title
+# 2) Normalize genres (if needed) 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"]
@@ -17,14 +14,12 @@ df["release_year"] = (
       .astype(pd.Int64Dtype(), errors='ignore')
 )
 
-# 4) Deduplicate metadata
+# 3) Deduplicate metadata
 metadata = df[["title", "genres", "release_year"]].drop_duplicates()
 
-
+# 4) Recommendation function
 def recommend_by_genre_year(genre: str, year: int, top_k: int = 5) -> str:
-    # 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]
@@ -37,6 +32,7 @@ def recommend_by_genre_year(genre: str, year: int, top_k: int = 5) -> str:
         for _, row in picks.iterrows()
     )
 
+# 5) Gradio interface
 iface = gr.Interface(
     fn=recommend_by_genre_year,
     inputs=[
@@ -47,11 +43,10 @@ iface = gr.Interface(
     outputs="text",
     title="🎬 Genre & Year-Based Movie Recommender",
     description="""
-Loads MovieLens metadata (small split) from the Hub, extracts release years from titles,
-normalizes genres, and filters by genre substring & year. No local files needed.
+Loads local MovieLens metadata (ml-32m), extracts release years from titles,
+normalizes genres, and filters by genre substring & year. No internet required.
 """,
 )
 
 if __name__ == "__main__":
     iface.launch()
-