Upload folder using huggingface_hub

backend_files/app.py

@@ -1,3 +1,4 @@
+
 import numpy as np
 import pandas as pd
 import joblib
@@ -5,64 +6,74 @@ from flask import Flask, request, jsonify
 from flask_cors import CORS
 
 # Initialize Flask app
-superkart_api = Flask("Extraa_Learn_api")
-CORS(superkart_api)
+Extraa_Learn_api = Flask("Extraa_Learn_api")
+CORS(Extraa_Learn_api)
 
-# Load the trained model pipeline inside the container
-model = joblib.load("Extraa_Learn_model_v1_0.joblib")
+# Load the trained model pipeline (preprocessing + model)
+model = joblib.load("/content/drive/My Drive/Colab Notebooks/deployment_files/Extraa_Learn_model_v1_0.joblib")
 
 # Health check route
-@superkart_api.get('/')
+@Extraa_Learn_api.get('/')
 def home():
-    return "✅ Extraa_Learn Backend is Running"
+    return "✅ Welcome to the Extraa_Learn_API"
 
 # Prediction route
-@superkart_api.post('/v1/Status')
-def predict_status(): # Renamed function for clarity
+@Extraa_Learn_api.post('/v1/status')
+def predict_status():
     try:
         # Parse JSON payload
         data = request.get_json()
+        print("Raw incoming data:", data)
 
         # Validate expected fields
         required_fields = [
-            'age', 'current_occupation', 'first_interaction',
-            'profile_completed', 'website_visits','time_spent_on_website',
-            'page_views_per_visit', # Added missing field
-            'last_activity', 'print_media_type1','print_media_type2',
-            'digital_media', 'educational_channels', 'referral'
+            'age',
+            'current_occupation',
+            'first_interaction',
+            'profile_completed',
+            'website_visits',
+            'time_spent_on_website',
+            'page_views_per_visit',
+            'last_activity',
+            'print_media_type1',
+            'print_media_type2',
+            'digital_media',
+            'educational_channels',
+            'referral'
         ]
-
-        # Check for missing fields
         missing_fields = [f for f in required_fields if f not in data]
         if missing_fields:
             return jsonify({'error': f"Missing fields: {missing_fields}"}), 400
 
-        # Convert and transform input exactly to match X_train structure
+        # Convert and transform input
         sample = {
-            'age': data['age'], # Removed extra closing parenthesis
+            'age': float(data['age']),
             'current_occupation': data['current_occupation'],
             'first_interaction': data['first_interaction'],
             'profile_completed': data['profile_completed'],
             'website_visits': data['website_visits'],
-            'time_spent_on_website': data['time_spent_on_website'],
-            'page_views_per_visit': data['page_views_per_visit'], # Added missing field
+            'time_spent_on_website': ['time_spent_on_website']),
+            'page_views_per_visit': data['page_views_per_visit'],
             'last_activity': data['last_activity'],
-             'print_media_type1':data['print_media_type1'], # Added missing comma
-             'print_media_type2': data['print_media_type2'],
-            'digital_media':data['digital_media'],
-            'educational_channels':data['educational_channels'], # Added missing comma
-            'referral':data['referral']
+            'print_media_type1': data['print_media_type1'],
+            'print_media_type2': data['print_media_type2']),
+            'digital_media': data['digital_media'],
+            'educational_channels': data['educational_channels'],
+            'referral': data['referral']
         }
 
-        # Create DataFrame and ensure column order doesn't cause issues
         input_df = pd.DataFrame([sample])
+        print("Transformed input for model:
+", input_df)
 
         # Make prediction
         prediction = model.predict(input_df).tolist()[0]
-        return jsonify({'Status': prediction}) # Changed key from 'Predicted_Sales' to 'Status' for consistency with frontend
+        return jsonify({'Status': prediction})
 
     except Exception as e:
+        print("❌ Error during prediction:", str(e))
         return jsonify({'error': f"Prediction failed: {str(e)}"}), 500
 
+# Run the app (for local testing only)
 if __name__ == '__main__':
-    superkart_api.run(debug=True)
+    Extraa_Learn_api.run(debug=True)

frontend_files/app.py

@@ -5,54 +5,65 @@ import requests
 import numpy as np
 
 # App Title
-st.title("Extraa_Learn_Prediction")
+st.title("Extraa Learn Lead Conversion Prediction")
 
-# User Inputs
-Age = st.number_input("age)", min_value=0.0, value=100)
-current_occupation = st.selectbox("current_occupation", ["Professional ", "Unemployed ", "Student "])
-first_interaction = st.selectbox("first_interaction",["Website","Mobile App"])
-profile_completed = st.selectbox("profile_completed)",["High","Medium", "Low"])
-website_visits = st.selectbox("website_visits"),
-time_spent_on_website = st.selectbox("time_spent_on_website"),
-page_views_per_visit = st.selectbox("page_views_per_visit"),
-last_activity = st.selectbox ("last_activity",
-print_media_type1 = st.selectbox("print_media_type1"),
-print_media_type2 = st.selectbox("print_media_type2"),
-digital_media = st._selectbox("digital_media)",
-educational_channels = st.selectbox("educational_channels"),
-referral= st.selectbox("referral")
+# User Inputs                              
+Age = st.number_input("Age", min_value=18, max_value=100, value=35)
+current_occupation = st.selectbox("Current Occupation", ["Professional", "Unemployed", "Student"])
+first_interaction = st.selectbox("First Interaction", ["Website", "Mobile App"])
+profile_completed = st.selectbox("Profile Completed", ["High", "Medium", "Low"])
+website_visits = st.number_input("Website Visits", min_value=0, value=3)
+time_spent_on_website = st.number_input("Time Spent on Website (seconds)", min_value=0, value=500)
+page_views_per_visit = st.number_input("Page Views Per Visit", min_value=0.0, value=3.0)
+last_activity = st.selectbox("Last Activity", ["Email Activity", "Phone Activity", "Website Activity"])
+print_media_type1 = st.selectbox("Seen Ad in Newspaper?", ["Yes", "No"])
+print_media_type2 = st.selectbox("Seen Ad in Magazine?", ["Yes", "No"])
+digital_media = st.selectbox("Seen Ad on Digital Platforms?", ["Yes", "No"])
+educational_channels = st.selectbox("Heard via Educational Channels?", ["Yes", "No"])
+referral = st.selectbox("Heard via Referral?", ["Yes", "No"])
 
 
 # Prepare JSON payload for the backend
-product_data = {
-    "Age": str(Age),
-    "current_occupation ":str( Current_occupation),
-    "first_interaction": str(first_interaction),
-    "profile_completed": str(profile_completed),
-    "website_visits": str(website_visits),
-    "time_spent_on_website": str(time_spent_on_website),
-    "page_views_per_visit": str(page_views_per_visit),
-    "last_activity": str(last_activity),
+leaddata = {
+   "age": int(Age),
+    "current_occupation": current_occupation.strip(),
+    "first_interaction": first_interaction.strip(),
+    "profile_completed": profile_completed.strip(),
+    "website_visits": int(website_visits),
+    "time_spent_on_website": float(time_spent_on_website),
+    "page_views_per_visit": float(page_views_per_visit),
+    "last_activity": last_activity.strip(),
     "print_media_type1": print_media_type1,
     "print_media_type2": print_media_type2,
-    "digital_media": str(digital_media),
+    "digital_media": digital_media,
     "educational_channels": educational_channels,
     "referral": referral
 }
-
-
-# Trigger Prediction
-if st.button("status", type='primary'):
+  
+  # Trigger Prediction API Call
+if st.button("Predict Status", type='primary'):
     try:
+        # This is level 1 indentation (4 spaces)
         response = requests.post(
-            "https://HSSHETTY01-Extraa_Learns-backend2.hf.space/v1/predict",
+            "https://HSSHETTY01-Extraa_Learn-backend2.hf.space/v1/Status",
             json=product_data
         )
+        
+        # This must stay at level 1 indentation (4 spaces)
         if response.status_code == 200:
+            # This is level 2 indentation (8 spaces)
             result = response.json()
-            predicted_sales = result["Status"]
-            st.success(f"📈 Ststus: **${status:,.2f} USD**")
+            status_pred = result.get("Status", result.get("prediction", 0))
+            
+            if status_pred == 1:
+                st.success("📈 **Status:** Lead is likely to convert!")
+            else:
+                st.warning("📉 **Status:** Lead is not likely to convert.")
         else:
-            st.error("❌ API Error: Please verify input values or try again later.")
+            st.error(f"❌ API Error {response.status_code}: {response.text}")
+            
     except Exception as e:
+        # Aligns perfectly with the 'try:' statement
         st.error(f"⚠️ Connection error: {e}")
+
+