Update app.py

app.py

@@ -1,45 +1,40 @@
 import gradio as gr
 import pandas as pd
 from joblib import load
-import os
 
-# Load the model once when the app starts
+# Load the model at startup
 rf_model = load('churn_prediction_model.joblib')
 
 def predict_churn(file):
-    """
-    Process the uploaded file and return churn predictions
-    """
     try:
-        # Read the uploaded file
+        # Load the uploaded file
         if file.name.endswith('.csv'):
             test_data = pd.read_csv(file.name)
         else:
             test_data = pd.read_excel(file.name)
 
-        # Ensure 'major_issue' is one-hot encoded
+        # Ensure 'major_issue' is one-hot encoded if needed
         if 'major_issue_Technical Issue' not in test_data.columns:
             test_data = pd.get_dummies(test_data, columns=['major_issue'], drop_first=True)
 
-        # Ensure all required columns are present
+        # Ensure all training-time columns are present
         required_columns = [
             'late_payments_last_year', 'missed_payments_last_year', 'plan_tenure',
             'num_employees', 'avg_monthly_contribution', 'annual_revenue',
             'support_calls_last_year', 'support_engagement_per_year',
             'major_issue_Technical Issue'
         ]
-        
         for col in required_columns:
             if col not in test_data.columns:
                 test_data[col] = 0
 
         # Extract features
         test_data_features = test_data[required_columns]
-        
+
         # Make predictions
         test_data['predicted_churn'] = rf_model.predict(test_data_features)
 
-        # Prepare output
+        # Select output columns
         output_columns = [
             'customer_id', 'late_payments_last_year', 'missed_payments_last_year',
             'plan_tenure', 'num_employees', 'avg_monthly_contribution',
@@ -49,7 +44,7 @@ def predict_churn(file):
         output_data = test_data[output_columns]
 
         # Save to temporary file
-        temp_output = "temp_output.csv"
+        temp_output = "output.csv"
         output_data.to_csv(temp_output, index=False)
         
         return temp_output
@@ -67,13 +62,7 @@ iface = gr.Interface(
     ),
     outputs=gr.File(label="Download Predictions"),
     title="Customer Churn Prediction",
-    description="""Upload a file with customer data to predict churn probability. 
-                  Required columns: customer_id, late_payments_last_year, missed_payments_last_year, 
-                  plan_tenure, num_employees, avg_monthly_contribution, annual_revenue, 
-                  support_calls_last_year, support_engagement_per_year, major_issue""",
-    examples=[
-        ["sample_input.csv"]  # Add a sample file if you have one
-    ],
+    description="Upload your customer data file to predict churn probability",
     cache_examples=False
 )