Upload app.py

app.py

@@ -28,8 +28,8 @@ if uploaded_file is not None:
     # One-hot encode categorical features for the predictive model
     data_encoded = pd.get_dummies(data, columns=['Gender', 'Purchase_Category'], drop_first=True)
 
-    # Assuming 'Return' variable can be derived from a condition, like Purchase_Frequency > 1
-    data_encoded['Return'] = (data['Purchase_Frequency'] > 1).astype(int)  # Example condition for return status
+    # Assuming 'Return' variable can be derived from a condition, like Purchase_Frequency > 2
+    data_encoded['Return'] = (data['Purchase_Frequency'] > 2).astype(int)  # Example condition for return status
 
     X = data_encoded.drop(columns=['Customer_ID', 'Return'])  # Features
     y = data_encoded['Return']  # Return as the target variable
@@ -81,6 +81,7 @@ if uploaded_file is not None:
             st.write("No associations found for the selected product.")
     
     elif model_choice == 'Customers Who Will Return':
+
         st.header("Customers Predicted to Return")
         
         # Make predictions for all customers
@@ -92,5 +93,13 @@ if uploaded_file is not None:
         # Filter customers who will return
         customers_will_return = data[data['Predicted_Return'] == 1]
         
+        # Group by Customer_ID and aggregate other fields (you can customize this as needed)
+        customers_will_return = customers_will_return.groupby('Customer_ID').agg({
+            'Age': 'first',  # or 'mean', depending on your preference
+            'Gender': 'first',
+            'Income': 'first',
+            'Purchase_Frequency': 'sum'  # Aggregate if there are multiple entries
+        }).reset_index()
+        
         # Display the customers who will return
-        st.dataframe(customers_will_return[['Customer_ID', 'Age', 'Gender', 'Income', 'Purchase_Frequency']])
+        st.dataframe(customers_will_return)