Update app.py

app.py

@@ -9,126 +9,139 @@ from sklearn.metrics.pairwise import cosine_similarity
 # ==========================================
 # 1. SETUP & DATA LOADING
 # ==========================================
-csv_path = "cleaned_dataset_10k.csv"
-pkl_path = "final_embeddings_10k.pkl"
+# File paths (Assuming files are in the same root directory as app.py on Hugging Face)
+CSV_PATH = "cleaned_dataset_10k.csv"
+PKL_PATH = "final_embeddings_10k.pkl"
 
-if not os.path.exists(csv_path) or not os.path.exists(pkl_path):
-    raise FileNotFoundError(f"Error: Files not found. I see: {os.listdir('.')}")
+if not os.path.exists(CSV_PATH) or not os.path.exists(PKL_PATH):
+    raise FileNotFoundError("Missing required data files. Please ensure CSV and PKL are uploaded.")
 
-# Load Data
-df = pd.read_csv(csv_path)
+# Load the dataset
+df = pd.read_csv(CSV_PATH)
 df.columns = [c.strip().lower().replace(' ', '_') for c in df.columns]
 
-# Helper to find column names
-def get_col(candidates, default):
-    for c in candidates:
-        if c in df.columns: return c
-    return default
-
-col_name = get_col(['restaurant_name', 'name', 'place'], 'restaurant_name')
-col_rating = get_col(['rating', 'rating_score', 'stars'], 'rating')
-col_review = get_col(['review', 'review_content', 'review_content_clean'], 'review')
-col_persona = get_col(['reviewer_persona', 'persona', 'type'], 'reviewer_persona')
-
-# Load Embeddings
-with open(pkl_path, 'rb') as f:
+# Load pre-computed embeddings
+with open(PKL_PATH, 'rb') as f:
     embedding_data = pickle.load(f)
-    if isinstance(embedding_data, dict) and 'embeddings' in embedding_data:
-        dataset_embeddings = embedding_data['embeddings']
-    else:
-        dataset_embeddings = embedding_data
+    dataset_embeddings = embedding_data['embeddings'] if isinstance(embedding_data, dict) else embedding_data
 
-# Load Model
+# Load the semantic model (MPNet for high accuracy)
 model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
 
-# Calculate Personas
+# Pre-calculate Persona Taste Profiles (Mean vectors)
 persona_profiles = {}
-if col_persona in df.columns:
-    for persona in df[col_persona].unique():
-        if pd.isna(persona): continue
-        indices = df[df[col_persona] == persona].index
-        valid_indices = [i for i in indices if i < len(dataset_embeddings)]
-        if valid_indices:
-            persona_vectors = dataset_embeddings[valid_indices]
-            persona_profiles[persona] = np.mean(persona_vectors, axis=0)
-else:
-    persona_profiles['Default'] = np.mean(dataset_embeddings, axis=0)
+for persona in df['reviewer_persona'].unique():
+    if pd.isna(persona): continue
+    indices = df[df['reviewer_persona'] == persona].index
+    persona_vectors = dataset_embeddings[indices]
+    persona_profiles[persona] = np.mean(persona_vectors, axis=0)
 
 # ==========================================
-# 2. LOGIC ENGINE
+# 2. CORE RECOMMENDATION ENGINE (HYBRID)
 # ==========================================
 def run_ven_engine(budget, dietary, company, purpose, noise):
+    """
+    Finds the best restaurant match using a combination of 
+    Persona Matching and Contextual Semantic Similarity.
+    """
+    # Create the user's context string
     user_context = f"Searching for a {budget} experience, {dietary} friendly. Group: {company}. Occasion: {purpose}. Atmosphere: {noise}."
     query_vec = model.encode([user_context])
     
-    similarities = {p: cosine_similarity(query_vec, v.reshape(1, -1))[0][0] for p, v in persona_profiles.items()}
-    closest_persona = max(similarities, key=similarities.get)
+    # Step A: Identify the closest Persona Profile
+    persona_sims = {p: cosine_similarity(query_vec, v.reshape(1, -1))[0][0] 
+                    for p, v in persona_profiles.items()}
+    closest_persona = max(persona_sims, key=persona_sims.get)
     
-    if col_persona in df.columns:
-        persona_df = df[df[col_persona] == closest_persona]
-        if persona_df.empty: persona_df = df
-    else:
-        persona_df = df
+    # Step B: Filter reviews by that persona
+    persona_indices = df[df['reviewer_persona'] == closest_persona].index
+    persona_embeddings = dataset_embeddings[persona_indices]
     
-    top_match = persona_df.sort_values(by=col_rating, ascending=False).iloc[0]
+    # Step C: Calculate Contextual Similarity for specific reviews within that persona
+    # This prevents getting the same result every time
+    sub_similarities = cosine_similarity(query_vec, persona_embeddings)[0]
     
-    match_pct = int(similarities[closest_persona] * 100)
-    review_text = str(top_match[col_review])[:160] + "..."
+    persona_df = df.loc[persona_indices].copy()
+    persona_df['semantic_fit'] = sub_similarities
+    persona_df['norm_rating'] = persona_df['rating_score'] / 5.0
     
-    # --- VISUAL FIX ---
+    # HYBRID SCORE: 70% Contextual Fit + 30% Rating Quality
+    persona_df['final_score'] = (persona_df['semantic_fit'] * 0.7) + (persona_df['norm_rating'] * 0.3)
+    
+    # Pick the top result after re-ranking
+    top_match = persona_df.sort_values(by='final_score', ascending=False).iloc[0]
+    match_pct = int(top_match['final_score'] * 100)
+    
+    # Format Recommendation Card (HTML)
     return f"""
-    <div style="background: white; border: 1px solid #e2e8f0; border-radius: 20px; padding: 24px; color: #000000 !important;">
-        <div style="display:flex; justify-content:space-between;">
-            <div>
-                <div style="font-size: 22px; font-weight: 800; color: #000000 !important;">{top_match[col_name]}</div>
-                <div style="font-size: 14px; color: #333333 !important; font-weight: 600;">Match for: {closest_persona}</div>
+    <div style="background: white; border-radius: 20px; padding: 25px; color: #0f172a !important; text-align: left; border-left: 10px solid #f97316; box-shadow: 0 10px 25px rgba(0,0,0,0.2);">
+        <div style="display:flex; justify-content:space-between; align-items: flex-start;">
+            <div style="flex: 1;">
+                <h2 style="margin:0; font-size: 24px; font-weight: 900; color: #0f172a !important;">{top_match['restaurant_name']}</h2>
+                <div style="font-size: 14px; color: #475569 !important; font-weight: 700; margin-top: 4px;">Matched for: {closest_persona} profile</div>
             </div>
-            <div style="text-align:right;">
-                <div style="font-size: 28px; font-weight: 900; color: #2563eb !important;">{top_match[col_rating]}</div>
-                <div style="font-size:12px; font-weight:bold; color: #000000 !important;">RATING</div>
+            <div style="text-align:right; background: #f8fafc; padding: 10px; border-radius: 12px; border: 1px solid #e2e8f0;">
+                <div style="font-size: 30px; font-weight: 950; color: #2563eb !important; line-height: 1;">{top_match['rating_score']}</div>
+                <div style="font-size:10px; font-weight:900; color: #64748b !important; letter-spacing: 1px; margin-top: 5px;">RATING</div>
             </div>
         </div>
-        <hr style="border:0; border-top:1px solid #cbd5e1; margin: 15px 0;">
-        
-        <p style="color: #000000 !important; line-height:1.6; font-size: 16px; font-weight: 500; margin-top: 10px;">
-            <i style="color: #000000 !important;">"{review_text}"</i>
+        <hr style="border:0; border-top: 1px solid #e2e8f0; margin: 15px 0;">
+        <p style="color: #1e293b !important; line-height:1.6; font-size: 16px; font-weight: 500;">
+            <i style="color: #334155 !important;">"{top_match['review_content_clean'][:200]}..."</i>
         </p>
-        
-        <div style="margin-top:15px; font-size:13px; font-weight:700; color:#2563eb !important;">Match Confidence: {match_pct}%</div>
+        <div style="margin-top:20px; display: flex; justify-content: space-between; align-items: center;">
+             <span style="font-size: 13px; font-weight: 800; color: #f97316;">VEN Match Confidence: {match_pct}%</span>
+             <span style="font-size: 11px; background: #0f172a; color: white; padding: 4px 10px; border-radius: 6px; font-weight: 700;">AI MATCH</span>
+        </div>
     </div>
     """
 
 # ==========================================
-# 3. APP UI & CSS FIX
+# 3. GRADIO UI SETUP (HF OPTIMIZED)
 # ==========================================
+# CSS Fixes for Visibility and Theme consistency
 ven_css = """
-body { background-color: #0f172a !important; font-family: sans-serif !important; }
-/* Global White Text for Dark Mode */
-h1, h2, h3, h4, h5, h6 { color: white !important; }
-p, span, div, label { color: white; }
-
-/* Override: Force Black Text inside the Results Card */
-.gradio-html div { color: #000000 !important; }
-.gradio-html p { color: #000000 !important; }
-.gradio-html i { color: #000000 !important; }
+.gradio-container { background-color: #0f172a !important; }
+h1 { color: white !important; text-align: center; font-weight: 900 !important; font-size: 2.5rem !important; margin-bottom: 20px !important; }
+
+/* Force input labels to be white and readable */
+label span { color: white !important; font-weight: 700 !important; font-size: 15px !important; margin-bottom: 5px !important; }
+
+/* Force Radio button text options to be white and bold */
+.gr-radio label span { color: white !important; font-weight: 600 !important; }
+
+/* Style the primary orange button */
+.ven-button { 
+    background-color: #f97316 !important; 
+    color: white !important; 
+    border: none !important; 
+    font-weight: 900 !important; 
+    font-size: 18px !important; 
+    height: 50px !important; 
+    border-radius: 12px !important;
+}
+
+/* Fix example table colors */
+.gr-samples-table { background-color: #1e293b !important; color: white !important; }
 """
 
-with gr.Blocks(css=ven_css, title="VEN Project") as demo:
+with gr.Blocks(css=ven_css, title="VEN - AI Restaurant Match") as demo:
     gr.Markdown("# 🍔 VEN: Restaurant Matchmaker")
     
     with gr.Row():
-        with gr.Column():
-            in_budget = gr.Dropdown(["Budget-friendly", "Mid-range", "Premium"], label="Budget", value="Mid-range")
-            in_diet = gr.Dropdown(["Anything", "Vegetarian", "Vegan", "Meat-lover"], label="Diet", value="Anything")
-            in_company = gr.Radio(["Solo", "Date/Couple", "Friends", "Business"], label="With who?", value="Date/Couple")
-            in_purpose = gr.Dropdown(["Casual dinner", "Special occasion", "Quick bite", "Professional meeting"], label="Occasion", value="Casual dinner")
-            in_noise = gr.Radio(["Quiet/Intimate", "Moderate/Social", "Lively/Music"], label="Environment", value="Moderate/Social")
-            btn = gr.Button("Find My Table", variant="primary")
-
-        with gr.Column():
-            output_ui = gr.HTML("<h4>Recommendation will appear here...</h4>")
+        with gr.Column(scale=1):
+            with gr.Group():
+                in_budget = gr.Dropdown(["Budget-friendly", "Mid-range", "Premium"], label="1. Wallet Size", value="Mid-range")
+                in_diet = gr.Dropdown(["Anything", "Vegetarian", "Vegan", "Meat-lover"], label="2. Diet Preference", value="Anything")
+                in_company = gr.Radio(["Solo", "Date/Couple", "Friends", "Business"], label="3. Social Context", value="Date/Couple")
+                in_purpose = gr.Dropdown(["Casual dinner", "Special occasion", "Quick bite", "Professional meeting"], label="4. The Mission", value="Casual dinner")
+                in_noise = gr.Radio(["Quiet/Intimate", "Moderate/Social", "Lively/Music"], label="5. Vibe / Noise", value="Moderate/Social")
+                btn = gr.Button("Find My Table", variant="primary", elem_classes="ven-button")
+        
+        with gr.Column(scale=1):
+            output_ui = gr.HTML("<div style='text-align:center; padding:100px; color:#64748b; font-weight:700; border: 2px dashed #1e293b; border-radius: 20px;'>Your personalized AI match will appear here</div>")
 
-    gr.Markdown("### 🚀 Quick Starters (One-Click)")
+    gr.Markdown("### 🚀 Quick Vibe Starters")
     gr.Examples(
         examples=[
             ["Budget-friendly", "Vegetarian", "Friends", "Quick bite", "Moderate/Social"],
@@ -138,9 +151,9 @@ with gr.Blocks(css=ven_css, title="VEN Project") as demo:
         inputs=[in_budget, in_diet, in_company, in_purpose, in_noise],
         outputs=output_ui,
         fn=run_ven_engine,
-        cache_examples=True,
+        cache_examples=False,
     )
-
+    
     btn.click(run_ven_engine, inputs=[in_budget, in_diet, in_company, in_purpose, in_noise], outputs=output_ui)
 
 if __name__ == "__main__":