Update app.py

app.py

@@ -1,20 +1,21 @@
 # app.py
 
+import os
 import streamlit as st
 import pandas as pd
 import requests
 from simple_salesforce import Salesforce
 
 # -----------------------------
-# CONFIG — Fill with your creds
+# CONFIG — Use env vars or hardcode for testing
 # -----------------------------
-SF_USERNAME = "[email protected]"
-SF_PASSWORD = "Vedavathi@04"
-SF_SECURITY_TOKEN = "jqe4His8AcuFJucZz5NBHfGU"
-SF_DOMAIN = "login"  # or "test" if you're using a sandbox
+SF_USERNAME = os.getenv("SF_USERNAME", "[email protected]")
+SF_PASSWORD = os.getenv("SF_PASSWORD", "Vedavathi@04")
+SF_SECURITY_TOKEN = os.getenv("SF_SECURITY_TOKEN", "jqe4His8AcuFJucZz5NBHfGU")
+SF_DOMAIN = os.getenv("SF_DOMAIN", "login")  # use "test" for sandbox
 
-HF_API_URL = "https://api-inference.huggingface.co/models/your-model"
-HF_API_TOKEN = "hf_your_token"
+HF_API_URL = os.getenv("HF_API_URL", "https://api-inference.huggingface.co/models/your-model")
+HF_API_TOKEN = os.getenv("HF_API_TOKEN", "hf_your_token")
 
 # -----------------------------
 # Connect to Salesforce
@@ -28,7 +29,7 @@ def connect_salesforce():
 def fetch_pole_data(sf):
     query = """
     SELECT Name, Solar_Generation__c, Wind_Generation__c, Tilt__c, Vibration__c, Camera_Status__c 
-    FROM Smart_Pole__c
+    FROM Vedavathi_Smart_Pole__c
     LIMIT 50
     """
     records = sf.query_all(query)['records']
@@ -36,7 +37,7 @@ def fetch_pole_data(sf):
     return df
 
 # -----------------------------
-# Send data to Hugging Face
+# Predict with Hugging Face
 # -----------------------------
 def predict_with_huggingface(df):
     headers = {"Authorization": f"Bearer {HF_API_TOKEN}"}
@@ -45,51 +46,52 @@ def predict_with_huggingface(df):
     for _, row in df.iterrows():
         payload = {
             "inputs": {
-                "solar": row.get("Solar_Generation__c"),
-                "wind": row.get("Wind_Generation__c"),
-                "tilt": row.get("Tilt__c"),
-                "vibration": row.get("Vibration__c"),
-                "camera": row.get("Camera_Status__c")
+                "solar": row.get("Solar_Generation__c", 0),
+                "wind": row.get("Wind_Generation__c", 0),
+                "tilt": row.get("Tilt__c", 0),
+                "vibration": row.get("Vibration__c", 0),
+                "camera": row.get("Camera_Status__c", "Online")
             }
         }
-        response = requests.post(HF_API_URL, headers=headers, json=payload)
-        if response.status_code == 200:
+        try:
+            response = requests.post(HF_API_URL, headers=headers, json=payload, timeout=10)
+            response.raise_for_status()
             result = response.json()
             label = result[0]['label'] if isinstance(result, list) else result.get("label", "Unknown")
-        else:
-            label = "Error"
+        except Exception as e:
+            label = f"Error: {e}"
         predictions.append(label)
-    
+
     df["Predicted Alert Level"] = predictions
     return df
 
 # -----------------------------
-# Streamlit App UI
+# Streamlit App
 # -----------------------------
 def main():
     st.set_page_config(layout="wide")
-    st.title("📡 Salesforce → Hugging Face Smart Pole Anomaly Detector")
+    st.title("📡 Vedavathi Smart Pole Anomaly Detection")
 
     try:
         sf = connect_salesforce()
         df = fetch_pole_data(sf)
 
         if df.empty:
-            st.warning("No records found.")
+            st.warning("No records found in Salesforce.")
             return
 
-        st.subheader("📋 Raw Pole Data from Salesforce")
+        st.subheader("📋 Raw Pole Data")
         st.dataframe(df)
 
-        st.subheader("🤖 Running Hugging Face Predictions...")
-        df_with_preds = predict_with_huggingface(df)
-        st.success("Predictions complete.")
+        st.subheader("🤖 AI Predictions via Hugging Face")
+        df_pred = predict_with_huggingface(df)
+        st.success("✅ Predictions completed")
 
-        st.subheader("📊 Results with AI-Predicted Alerts")
-        st.dataframe(df_with_preds)
+        st.subheader("📊 Final Table with Alerts")
+        st.dataframe(df_pred)
 
     except Exception as e:
-        st.error(f"Error: {e}")
+        st.error(f"❌ Error: {e}")
 
 if __name__ == "__main__":
     main()