Update app.py

app.py

@@ -13,13 +13,15 @@ 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 files are missing, the app will show an error on startup
+    raise FileNotFoundError(f"Error: Required files not found in root directory.")
 
 # Load Data
 df = pd.read_csv(csv_path)
+# Standardize column names (lowercase, no spaces)
 df.columns = [c.strip().lower().replace(' ', '_') for c in df.columns]
 
-# Helper to find column names
+# Helper to identify correct column names automatically
 def get_col(candidates, default):
     for c in candidates:
         if c in df.columns: return c
@@ -30,96 +32,86 @@ 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
+# 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 Semantic Model
 model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
 
-# Calculate Personas
+# 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
+        # Ensure indices are within embedding bounds
         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)
+            persona_profiles[persona] = np.mean(dataset_embeddings[valid_indices], axis=0)
 else:
+    # Fallback if no persona column exists
     persona_profiles['Default'] = np.mean(dataset_embeddings, axis=0)
 
 # ==========================================
-# 2. LOGIC ENGINE
+# 2. RECOMMENDATION LOGIC
 # ==========================================
 def run_ven_engine(budget, dietary, company, purpose, noise):
+    # Construct user context string for embedding
     user_context = f"Searching for a {budget} experience, {dietary} friendly. Group: {company}. Occasion: {purpose}. Atmosphere: {noise}."
     query_vec = model.encode([user_context])
     
+    # Semantic similarity check against persona profiles
     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)
     
-    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
+    # Filter dataset for the matched persona
+    persona_df = df[df[col_persona] == closest_persona] if col_persona in df.columns else df
+    if persona_df.empty: persona_df = df
     
+    # Selection Strategy: Highest rated restaurant for that persona
     top_match = persona_df.sort_values(by=col_rating, ascending=False).iloc[0]
-    
     match_pct = int(similarities[closest_persona] * 100)
-    review_text = str(top_match[col_review])[:160] + "..."
+    review_text = str(top_match[col_review])[:180] + "..."
     
+    # Return HTML Card for display
     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 style="background: white; border-radius: 15px; padding: 20px; color: #1e293b !important; border-left: 8px solid #f97316; box-shadow: 0 10px 15px rgba(0,0,0,0.1);">
+        <div style="display:flex; justify-content:space-between; align-items: flex-start;">
             <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="font-size: 24px; font-weight: 800; color: #0f172a !important; margin-bottom: 2px;">{top_match[col_name]}</div>
+                <div style="font-size: 14px; color: #64748b !important; font-weight: 600;">AI Match: {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: #f1f5f9; padding: 10px; border-radius: 10px;">
+                <div style="font-size: 26px; font-weight: 900; color: #f97316 !important;">{top_match[col_rating]}</div>
+                <div style="font-size:10px; font-weight:800; color: #475569 !important; letter-spacing: 1px;">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>
-        </p>
-        <div style="margin-top:15px; font-size:13px; font-weight:700; color:#2563eb !important;">Match Confidence: {match_pct}%</div>
+        <div style="margin: 15px 0; font-size: 15px; font-style: italic; color: #334155 !important; line-height: 1.5;">
+            "{review_text}"
+        </div>
+        <div style="display: flex; justify-content: space-between; align-items: center; margin-top: 10px;">
+             <span style="font-size: 12px; font-weight: 700; color: #f97316;">Match Confidence: {match_pct}%</span>
+             <span style="font-size: 11px; background: #0f172a; color: white; padding: 3px 8px; border-radius: 5px;">VEN Matchmaker</span>
+        </div>
     </div>
     """
 
 # ==========================================
-# 3. APP UI & CSS FIX (THE NUCLEAR FIX)
+# 3. UI & CSS (OPTIMIZED FOR VISIBILITY)
 # ==========================================
+# Specific CSS to fix visibility of labels and radio buttons in dark mode
 ven_css = """
-/* מכריח את כל הקונטיינרים להיות כהים, גם במצב Light Mode */
-.gradio-container, .gradio-container.light, .gradio-container.dark {
-    background-color: #0f172a !important;
-    color: white !important;
-}
-
-/* מוודא שהרקע תמיד כהה */
-body, .landing, .wrap, .interface-box {
-    background-color: #0f172a !important;
-    color: white !important;
-}
-
-/* טקסטים לבנים לכל הכותרות והתוויות */
-h1, h2, h3, h4, h5, h6, label, span, p {
-    color: white !important;
-}
-
-/* החריג היחיד: כרטיס התוצאה שלנו - שם אנחנו מכריחים שחור */
-.gradio-html div, .gradio-html p, .gradio-html i, .gradio-html span, .gradio-html h1, .gradio-html h2 {
-    color: #000000 !important;
-}
+.gradio-container { background-color: #0f172a !important; }
+/* Force labels above inputs to be white and visible */
+label span { color: white !important; font-weight: 600 !important; font-size: 14px !important; }
+/* Force radio button choice text to be white */
+.gr-radio label span { color: white !important; font-size: 13px !important; }
+/* Style the primary orange button */
+.ven-button { background-color: #f97316 !important; color: white !important; border: none !important; font-weight: 800 !important; }
+/* Ensure headings are white */
+h1 { color: white !important; text-align: center; }
 """
 
 with gr.Blocks(css=ven_css, title="VEN Project") as demo:
@@ -127,16 +119,17 @@ with gr.Blocks(css=ven_css, title="VEN Project") as demo:
     
     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.Group(): # Group keeps labels and inputs contained
+                in_budget = gr.Dropdown(["Budget-friendly", "Mid-range", "Premium"], label="1. Select Budget", value="Mid-range")
+                in_diet = gr.Dropdown(["Anything", "Vegetarian", "Vegan", "Meat-lover"], label="2. Dietary Preference", value="Anything")
+                in_company = gr.Radio(["Solo", "Date/Couple", "Friends", "Business"], label="3. Who are you with?", value="Date/Couple")
+                in_purpose = gr.Dropdown(["Casual dinner", "Special occasion", "Quick bite", "Professional meeting"], label="4. Occasion", value="Casual dinner")
+                in_noise = gr.Radio(["Quiet/Intimate", "Moderate/Social", "Lively/Music"], label="5. Environment vibe", value="Moderate/Social")
+                btn = gr.Button("Find My Table", variant="primary", elem_classes="ven-button")
+        
         with gr.Column():
-            output_ui = gr.HTML("<h4>Recommendation will appear here...</h4>")
-
+            output_ui = gr.HTML("<div style='text-align:center; padding:50px; color:#94a3b8;'>Your personalized recommendation will appear here...</div>")
+    
     gr.Markdown("### 🚀 Quick Starters (One-Click)")
     gr.Examples(
         examples=[
@@ -147,9 +140,9 @@ 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, # Disable cache if you want real-time testing
     )
-
+    
     btn.click(run_ven_engine, inputs=[in_budget, in_diet, in_company, in_purpose, in_noise], outputs=output_ui)
 
 if __name__ == "__main__":