Upload app.py

app.py

@@ -0,0 +1,280 @@
+import gradio as gr
+import joblib
+import pandas as pd
+import numpy as np
+import os
+from PIL import Image
+
+# Load models and encoders
+def load_models():
+    try:
+        model = joblib.load('models/churn_model.pkl')
+        encoders = joblib.load('models/label_encoders.pkl')
+        try:
+            scaler = joblib.load('models/scaler.pkl')
+        except:
+            scaler = None
+        return model, encoders, scaler
+    except Exception as e:
+        print(f"Error loading models: {e}")
+        return None, None, None
+
+model, encoders, scaler = load_models()
+
+# Define feature options based on the training data
+REGIONS = ['North', 'South', 'East', 'West', 'Central']
+PLAN_TYPES = ['Prepaid', 'Postpaid']
+CONTRACT_TYPES = ['Month-to-month', 'One year', 'Two year']
+COMPLAINT_STATUS = ['Open', 'Closed', 'Not Applicable']
+
+def predict_churn(customer_id, region, plan_type, monthly_charges, total_charges, 
+                 tenure_months, contract_type, paperless_billing, payment_method,
+                 data_usage_gb, call_minutes, sms_count, complaint_status, complaint_count):
+    
+    if model is None:
+        return "Model not loaded properly", 0.0
+    
+    try:
+        # Create input dataframe
+        input_data = pd.DataFrame({
+            'customer_id': [customer_id],
+            'region': [region],
+            'plan_type': [plan_type],
+            'monthly_charges': [monthly_charges],
+            'total_charges': [total_charges],
+            'tenure_months': [tenure_months],
+            'contract_type': [contract_type],
+            'paperless_billing': [1 if paperless_billing else 0],
+            'payment_method': [payment_method],
+            'data_usage_gb': [data_usage_gb],
+            'call_minutes': [call_minutes],
+            'sms_count': [sms_count],
+            'complaint_status': [complaint_status],
+            'complaint_count': [complaint_count]
+        })
+        
+        # Encode categorical variables
+        categorical_columns = ['region', 'plan_type', 'contract_type', 'payment_method', 'complaint_status']
+        
+        for col in categorical_columns:
+            if col in encoders:
+                try:
+                    input_data[col] = encoders[col].transform(input_data[col])
+                except ValueError:
+                    # Handle unseen labels by using the most frequent class
+                    input_data[col] = 0
+        
+        # Drop customer_id for prediction
+        prediction_data = input_data.drop(['customer_id'], axis=1)
+        
+        # Scale features if scaler exists
+        if scaler is not None:
+            prediction_data = scaler.transform(prediction_data)
+        
+        # Make prediction
+        churn_probability = model.predict_proba(prediction_data)[0][1]
+        churn_prediction = "HIGH RISK" if churn_probability > 0.5 else "LOW RISK"
+        
+        # Create detailed result
+        risk_level = "🔴 HIGH RISK" if churn_probability > 0.7 else "🟡 MEDIUM RISK" if churn_probability > 0.4 else "🟢 LOW RISK"
+        
+        result = f"""
+        **Prediction Result for Customer {customer_id}**
+        
+        **Churn Risk:** {risk_level}
+        **Churn Probability:** {churn_probability:.1%}
+        **Recommendation:** {'Immediate retention action required' if churn_probability > 0.7 else 'Monitor and engage' if churn_probability > 0.4 else 'Standard service maintenance'}
+        """
+        
+        return result, churn_probability
+        
+    except Exception as e:
+        return f"Error in prediction: {str(e)}", 0.0
+
+def load_image(image_name):
+    """Load and return image from the images folder"""
+    try:
+        img_path = f"images/{image_name}"
+        if os.path.exists(img_path):
+            return Image.open(img_path)
+        else:
+            return None
+    except Exception as e:
+        print(f"Error loading image {image_name}: {e}")
+        return None
+
+# Create Gradio interface
+with gr.Blocks(title="Telecom Churn Prediction - BRBRAITT Group 5", theme=gr.themes.Soft()) as app:
+    
+    # Header
+    gr.Markdown("""
+    # 🔮 Telecom Churn Prediction System
+    
+    **TIRTC Course: Advance AI/ML Training - Telecom Data Analytics (Nokia)**  
+    **Institution:** BRBRAITT, Jabalpur
+    
+    **Group 5 Members:**
+    - Abhay Gupta
+    - Jay Kumar  
+    - Kripanshu Gupta
+    - Ruhy Namdeo
+    
+    ---
+    
+    This AI-powered system predicts customer churn with **90% accuracy** using Random Forest ML model.
+    """)
+    
+    with gr.Tabs():
+        
+        # Tab 1: Prediction Interface
+        with gr.TabItem("🎯 Churn Prediction"):
+            gr.Markdown("### Enter Customer Details for Churn Prediction")
+            
+            with gr.Row():
+                with gr.Column():
+                    customer_id = gr.Textbox(label="Customer ID", placeholder="e.g., CUST001", value="CUST001")
+                    region = gr.Dropdown(choices=REGIONS, label="Region", value="North")
+                    plan_type = gr.Dropdown(choices=PLAN_TYPES, label="Plan Type", value="Postpaid")
+                    contract_type = gr.Dropdown(choices=CONTRACT_TYPES, label="Contract Type", value="Month-to-month")
+                    
+                with gr.Column():
+                    monthly_charges = gr.Number(label="Monthly Charges (₹)", value=1000, minimum=0)
+                    total_charges = gr.Number(label="Total Charges (₹)", value=12000, minimum=0)
+                    tenure_months = gr.Number(label="Tenure (Months)", value=12, minimum=0, maximum=120)
+                    paperless_billing = gr.Checkbox(label="Paperless Billing", value=True)
+                    
+                with gr.Column():
+                    payment_method = gr.Dropdown(choices=['Electronic check', 'Mailed check', 'Bank transfer', 'Credit card'], 
+                                               label="Payment Method", value="Electronic check")
+                    data_usage_gb = gr.Number(label="Data Usage (GB)", value=15, minimum=0)
+                    call_minutes = gr.Number(label="Call Minutes", value=500, minimum=0)
+                    sms_count = gr.Number(label="SMS Count", value=100, minimum=0)
+                    
+            with gr.Row():
+                complaint_status = gr.Dropdown(choices=COMPLAINT_STATUS, label="Complaint Status", value="Not Applicable")
+                complaint_count = gr.Number(label="Complaint Count", value=0, minimum=0)
+            
+            predict_btn = gr.Button("🔮 Predict Churn Risk", variant="primary", size="lg")
+            
+            with gr.Row():
+                prediction_output = gr.Markdown()
+                probability_gauge = gr.Number(label="Churn Probability", interactive=False)
+            
+            predict_btn.click(
+                fn=predict_churn,
+                inputs=[customer_id, region, plan_type, monthly_charges, total_charges, 
+                       tenure_months, contract_type, paperless_billing, payment_method,
+                       data_usage_gb, call_minutes, sms_count, complaint_status, complaint_count],
+                outputs=[prediction_output, probability_gauge]
+            )
+        
+        # Tab 2: Business Insights
+        with gr.TabItem("📊 Business Insights"):
+            gr.Markdown("### Key Findings from Analysis")
+            
+            insights = gr.Markdown("""
+            ## 🎯 Model Performance
+            - **Accuracy:** 90%
+            - **AUC Score:** 0.95
+            - **Best Algorithm:** Random Forest Classifier
+            
+            ## 💼 Business Impact
+            - **Current Churn Rate:** 50%
+            - **Revenue at Risk:** ₹12,250+ monthly
+            - **Annual Loss:** ₹147,000+ potential
+            - **Savings Opportunity:** ₹36,750+ with 25% churn reduction
+            
+            ## 🔴 Top Risk Factors
+            1. **Contract Type:** Month-to-month customers (100% churn rate)
+            2. **Tenure:** New customers (0-12 months) at highest risk
+            3. **Complaints:** Open complaints double churn likelihood
+            4. **Plan Type:** Significant differences between Prepaid/Postpaid
+            
+            ## 📈 Recommendations
+            ### Immediate Actions
+            - Target month-to-month customers for contract upgrades
+            - Implement 90-day new customer check-in program
+            - Prioritize complaint resolution within 48 hours
+            
+            ### Long-term Strategy
+            - Deploy real-time churn scoring system
+            - Implement tiered retention programs
+            - A/B test retention campaigns
+            """)
+        
+        # Tab 3: Visualizations
+        with gr.TabItem("📈 Data Visualizations"):
+            gr.Markdown("### Comprehensive Analysis Dashboard")
+            
+            # Load and display images
+            image_files = [
+                ("churn_distribution.png", "Overall Churn Distribution"),
+                ("churn_by_contract.png", "Churn by Contract Type"),
+                ("churn_by_plan.png", "Churn by Plan Type"),
+                ("churn_by_region.png", "Regional Churn Analysis"),
+                ("tenure_vs_churn.png", "Tenure vs Churn Pattern"),
+                ("revenue_vs_churn.png", "Revenue Impact Analysis"),
+                ("complaints_analysis.png", "Complaints Impact on Churn"),
+                ("correlation_matrix.png", "Feature Correlation Matrix"),
+                ("feature_coefficients.png", "Model Feature Importance")
+            ]
+            
+            for img_file, title in image_files:
+                img = load_image(img_file)
+                if img is not None:
+                    with gr.Row():
+                        gr.Markdown(f"#### {title}")
+                    with gr.Row():
+                        gr.Image(img, label=title, show_label=False)
+                else:
+                    gr.Markdown(f"*{title} - Image not available*")
+        
+        # Tab 4: About Project
+        with gr.TabItem("ℹ️ About Project"):
+            gr.Markdown("""
+            ## 🎓 Academic Project Details
+            
+            **Course:** TIRTC - Advance AI/ML Training - Telecom Data Analytics (Nokia)  
+            **Institution:** BRBRAITT (Bharat Ratna Bhimrao Ambedkar Institute of Technology and Training), Jabalpur  
+            **Project Type:** Capstone Project 1
+            
+            ### 👥 Team Members (Group 5)
+            - **Abhay Gupta**
+            - **Jay Kumar**
+            - **Kripanshu Gupta**
+            - **Ruhy Namdeo**
+            
+            ### 🛠️ Technical Stack
+            - **Machine Learning:** scikit-learn, Random Forest Classifier
+            - **Data Processing:** pandas, numpy
+            - **Visualization:** matplotlib, seaborn
+            - **Interface:** Gradio
+            - **Deployment:** Hugging Face Spaces
+            
+            ### 📈 Project Scope
+            This end-to-end machine learning project demonstrates:
+            - Data engineering and ETL pipeline
+            - Advanced ML model development
+            - Business intelligence and insights generation
+            - Production deployment capabilities
+            
+            ### 🎯 Learning Outcomes
+            - Real-world problem solving in telecom domain
+            - Complete ML pipeline implementation
+            - Business value creation through AI/ML
+            - Model deployment and productionization
+            
+            ---
+            
+            **🏆 Project Status:** Complete | **📅 Last Updated:** October 2024 | **🔢 Version:** 1.0.0
+            """)
+    
+    # Footer
+    gr.Markdown("""
+    ---
+    **© 2024 BRBRAITT Group 5 | TIRTC Advance AI/ML Training | Telecom Data Analytics**
+    """)
+
+# Launch the app
+if __name__ == "__main__":
+    app.launch(share=True, server_name="0.0.0.0", server_port=7860)