Update app.py

app.py

@@ -2,40 +2,60 @@ import gradio as gr
 import pandas as pd
 from datasets import load_dataset
 
-# 1) Load the community MovieLens 100K (small split)
-movies_raw = load_dataset("bstds/movielens", "small", split="train")
+# 1) Load movie metadata and ratings from GroupLens URLs
+movies = load_dataset(
+    "csv",
+    data_files="https://files.grouplens.org/datasets/movielens/ml-latest-small/movies.csv",
+    split="train",
+)
+ratings = load_dataset(
+    "csv",
+    data_files="https://files.grouplens.org/datasets/movielens/ml-latest-small/ratings.csv",
+    split="train",
+)
 
-# 2) Convert to pandas and extract year
-df = movies_raw.to_pandas()
-df["year"] = pd.to_datetime(df["timestamp"], unit="s").dt.year
+# 2) Convert to pandas
+movies_df = movies.to_pandas()
+ratings_df = ratings.to_pandas()
 
-# 3) Deduplicate metadata
-metadata = df[["title", "genres", "year"]].drop_duplicates()
+# 3) Infer a release year per movie by taking the earliest rating timestamp
+#    (assuming users start rating soon after release)
+ratings_df["year"] = pd.to_datetime(ratings_df["timestamp"], unit="s").dt.year
+first_year = ratings_df.groupby("movieId")["year"].min().reset_index()
+
+# 4) Merge metadata + inferred year, drop duplicates
+metadata = (
+    movies_df.merge(first_year, on="movieId", how="inner")
+    .rename(columns={"year": "release_year"})
+    .drop_duplicates(subset=["movieId"])
+)
 
-def recommend_by_genre_year(genre, year, top_k=5):
+def recommend_by_genre_year(genre: str, year: int, top_k: int = 5) -> str:
+    # filter by genre substring (case-insensitive) and release_year ≥ year
     mask_genre = metadata["genres"].str.lower().str.contains(genre.lower())
-    mask_year  = metadata["year"] >= year
+    mask_year = metadata["release_year"] >= 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} ({row.year})" for _, row in picks.iterrows())
+    return "\n".join(f"• {row.title} ({int(row.release_year)})"
+                     for _, row in picks.iterrows())
 
 iface = gr.Interface(
     fn=recommend_by_genre_year,
     inputs=[
         gr.Textbox(label="Genre", placeholder="e.g. Action, Romance"),
-        gr.Number(label="Release Year (≥)", value=2010),
-        gr.Slider(1, 10, step=1, label="Number of Recommendations", value=5)
+        gr.Number(label="Release Year (≥)", value=2010, precision=0),
+        gr.Slider(1, 10, step=1, label="Number of Recommendations", value=5),
     ],
     outputs="text",
     title="🎬 Genre & Year-Based Movie Recommender",
     description="""
-Uses the community MovieLens-100K dataset (via `bstds/movielens` small split) 
-to filter by genre and year (inferred from timestamp).
-"""
+Pulls MovieLens “ml-latest-small” metadata & ratings live from GroupLens  
+to filter by genre and release year (inferred). No local files needed.
+""",
 )
 
 if __name__ == "__main__":