Update app.py

app.py

@@ -330,11 +330,28 @@ elif page== "📊 Tabular Data":
         top_factors = "\n".join([f"- {feat}: {round(value, 2)} impact" for feat, value in top_features])
     
         # 🎭 **Streamlit UI**
-        st.title("🩺 AI-Powered Patient Readmission Analysis")
-    
+        import streamlit as st
+        import time
+        import random
+# Título estilizado
+        st.markdown("""
+            <h1 style='text-align: center; color: #2c3e50;'>🩺 AI-Powered Patient Readmission Analysis</h1>
+            <hr style='border: 2px solid #3498db;'>
+        """, unsafe_allow_html=True)
+        
+        # Função para animar uma aranha
+        placeholder = st.empty()
+        
+        for i in range(40):  # 4 segundos (40 iterações de 0.1s)
+            spider_position = "&nbsp;" * random.randint(1, 20) + "🕷️"
+            placeholder.markdown(f"<h2 style='text-align: center;'>{spider_position}</h2>", unsafe_allow_html=True)
+            time.sleep(0.1)
+        placeholder.empty()
+        
         with st.spinner("🤖 Analyzing..."):
+            time.sleep(2)  # Simular carregamento
             try:
-                ai_output = f"""
+                ai_output = """
                 **Based on the provided feature impacts, here's an interpretation of the model's decision-making process:**
         
                 ### **Most influential factors:**
@@ -361,11 +378,11 @@ elif page== "📊 Tabular Data":
         
                 These characteristics may indicate that the patient has chronic or complex health issues, incomplete recovery, or inadequate post-discharge care, increasing their risk of readmission.
                 """
-
+        
                 # 🎭 **Show AI Response in a Stylish Chat Format**
                 with st.chat_message("assistant"):
                     st.markdown(f"**💡 AI Explanation:**\n\n{ai_output}")
-
+            
             except Exception as e:
                 st.error(f"⚠️ Error retrieving response: {e}")
                 st.stop()