bugfix: added import lgbm

app.py

@@ -144,30 +144,35 @@ elif page == "Customer Analysis":
                 X_predict_cluster = pd.read_csv(f'predicts/X_predict_cluster_{cluster}.csv')
 
                 # Filter for the specific customer and drop the 'cliente_id' column
-                X_cliente = X_predict_cluster[X_predict_cluster['cliente_id'] == customer_code].drop(columns=['cliente_id'])
+                X_cliente = X_predict_cluster[X_predict_cluster['cliente_id'] == customer_code]
 
                 if not X_cliente.empty:
                     # Make Prediction for the selected customer
-                    y_pred = gbm.predict(X_cliente, num_iteration=gbm.best_iteration)
-                    st.write(f"Predicted sales for Customer {customer_code}: {y_pred.sum():.2f}")
+                    y_pred = gbm.predict(X_cliente.drop(columns=['cliente_id', 'fecha_mes']), num_iteration=gbm.best_iteration)
+                    
+                    # Reassemble the results
+                    results = X_cliente[['cliente_id', 'marca_id_encoded', 'fecha_mes']].copy()
+                    results['ventas_predichas'] = y_pred
+                    
+                    st.write(f"Predicted total sales for Customer {customer_code}: {results['ventas_predichas'].sum():.2f}")
 
                     # Merge with actual data from df_agg_2024
                     df_agg_2024 = pd.read_csv('predicts/df_agg_2024.csv')
-                    actual_sales = df_agg_2024[(df_agg_2024['cliente_id'] == customer_code) & (df_agg_2024['marca_id_encoded'].isin(X_cliente['marca_id_encoded']))]
+                    actual_sales = df_agg_2024[df_agg_2024['cliente_id'] == customer_code]
+                    
                     if not actual_sales.empty:
-                        merged_data = pd.DataFrame({
-                            'cliente_id': [customer_code],
-                            'ventas_predichas': [y_pred.sum()],
-                            'ventas_reales': [actual_sales['precio_total'].sum()]
-                        })
-
+                        results = results.merge(actual_sales[['cliente_id', 'marca_id_encoded', 'fecha_mes', 'precio_total']], 
+                                                on=['cliente_id', 'marca_id_encoded', 'fecha_mes'], 
+                                                how='left')
+                        results.rename(columns={'precio_total': 'ventas_reales'}, inplace=True)
+                        
                         # Calculate metrics
-                        mae = mean_absolute_error(merged_data['ventas_reales'], merged_data['ventas_predichas'])
-                        mape = np.mean(np.abs((merged_data['ventas_reales'] - merged_data['ventas_predichas']) / merged_data['ventas_reales'])) * 100
-                        rmse = np.sqrt(mean_squared_error(merged_data['ventas_reales'], merged_data['ventas_predichas']))
-                        smape_value = smape(merged_data['ventas_reales'], merged_data['ventas_predichas'])
+                        mae = mean_absolute_error(results['ventas_reales'], results['ventas_predichas'])
+                        mape = np.mean(np.abs((results['ventas_reales'] - results['ventas_predichas']) / results['ventas_reales'])) * 100
+                        rmse = np.sqrt(mean_squared_error(results['ventas_reales'], results['ventas_predichas']))
+                        smape_value = smape(results['ventas_reales'], results['ventas_predichas'])
 
-                        st.write(f"Actual sales for Customer {customer_code}: {merged_data['ventas_reales'].values[0]:.2f}")
+                        st.write(f"Actual total sales for Customer {customer_code}: {results['ventas_reales'].sum():.2f}")
                         st.write(f"MAE: {mae:.2f}")
                         st.write(f"MAPE: {mape:.2f}%")
                         st.write(f"RMSE: {rmse:.2f}")