Create app.py

app.py

@@ -0,0 +1,60 @@
+import gradio as gr
+import pandas as pd
+import numpy as np
+import re
+from sklearn.metrics.pairwise import cosine_similarity
+from sentence_transformers import SentenceTransformer
+from datasets import load_dataset
+
+# === Load dataset from Hugging Face ===
+raw_data = load_dataset("MongoDB/embedded_movies") 
+df = pd.DataFrame(raw_data["train"])
+
+# Keep only relevant columns
+df = df[["title", "fullplot"]].dropna().reset_index(drop=True)
+
+# === Load model and compute embeddings ===
+model = SentenceTransformer("all-MiniLM-L6-v2")
+df["fullplot_embedding"] = model.encode(df["fullplot"].tolist(), show_progress_bar=True)
+
+# === Helper Functions ===
+def encode_input_text(text):
+    return model.encode([text])[0]
+
+def extract_keywords(text):
+    words = re.findall(r'\b\w{5,}\b', text.lower())
+    return set(words)
+
+def generate_explanation(user_keywords, movie_text):
+    movie_words = extract_keywords(movie_text)
+    matched = user_keywords & movie_words
+    return ", ".join(sorted(matched)) if matched else "No strong keyword match"
+
+def compute_similar_movies(user_embedding, top_k=5):
+    movie_embeddings = np.stack(df["fullplot_embedding"].values)
+    similarities = cosine_similarity([user_embedding], movie_embeddings)[0]
+    df["similarity"] = similarities
+    top_df = df.sort_values("similarity", ascending=False).head(top_k)
+    return top_df
+
+# === Gradio UI ===
+with gr.Blocks() as demo:
+    gr.Markdown("## 🎬 Movie Recommender Engine with Explanation")
+    input_box = gr.Textbox(label="Enter your plot idea", placeholder="e.g., dreams within dreams")
+    output_box = gr.Textbox(label="Top Recommendations", lines=8)
+    recommend_button = gr.Button("Recommend")
+
+    def recommend(text):
+        user_embedding = encode_input_text(text)
+        user_keywords = extract_keywords(text)
+        top_df = compute_similar_movies(user_embedding)
+
+        results = []
+        for _, row in top_df.iterrows():
+            explanation = generate_explanation(user_keywords, row["fullplot"])
+            results.append(f"🎬 {row['title']} (score={row['similarity']:.2f})\n🔍 {explanation}")
+        return "\n\n".join(results)
+
+    recommend_button.click(fn=recommend, inputs=[input_box], outputs=[output_box])
+
+demo.launch()