feat: updated app.py

app.py

@@ -6,16 +6,18 @@ import numpy as np
 import lightgbm as lgb
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
+from sklearn.metrics import mean_absolute_error, mean_squared_error
 
 # Page configuration
 st.set_page_config(page_title="Customer Insights App", page_icon=":bar_chart:")
 
-# Load CSV files at the top, only once
+# Load CSV files at the top
 df = pd.read_csv("df_clean.csv")
 nombres_proveedores = pd.read_csv("nombres_proveedores.csv", sep=';')
 euros_proveedor = pd.read_csv("euros_proveedor.csv", sep=',')
 ventas_clientes = pd.read_csv("ventas_clientes.csv", sep=',')
 customer_clusters = pd.read_csv('predicts/customer_clusters.csv')  # Load the customer clusters here
+df_agg_2024 = pd.read_csv('predicts/df_agg_2024.csv') 
 
 # Ensure customer codes are strings
 df['CLIENTE'] = df['CLIENTE'].astype(str)
@@ -25,6 +27,7 @@ customer_clusters['cliente_id'] = customer_clusters['cliente_id'].astype(str)  #
 fieles_df = pd.read_csv("clientes_relevantes.csv")
 cestas = pd.read_csv("cestas.csv")
 productos = pd.read_csv("productos.csv")
+df_agg_2024['cliente_id'] = df_agg_2024['cliente_id'].astype(str)
 
 # Convert all columns except 'CLIENTE' to float in euros_proveedor
 for col in euros_proveedor.columns:
@@ -103,144 +106,6 @@ if page == "":
     st.markdown("## Welcome to the Customer Insights App")
     st.write("Use the dropdown menu to navigate between the different sections.")
 
-# Customer Analysis Page
-# elif page == "Customer Analysis":
-#     st.title("Customer Analysis")
-#     st.markdown("Use the tools below to explore your customer data.")
-
-#     partial_code = st.text_input("Enter part of Customer Code (or leave empty to see all)")
-#     if partial_code:
-#         filtered_customers = df[df['CLIENTE'].str.contains(partial_code)]
-#     else:
-#         filtered_customers = df
-#     customer_list = filtered_customers['CLIENTE'].unique()
-#     customer_code = st.selectbox("Select Customer Code", customer_list)
-
-#     if st.button("Calcular"):
-#         if customer_code:
-#             # Find Customer's Cluster
-#             customer_match = customer_clusters[customer_clusters['cliente_id'] == customer_code]
-
-#             if not customer_match.empty:
-#                 cluster = customer_match['cluster_id'].values[0]
-#                 st.write(f"Customer {customer_code} belongs to cluster {cluster}")
-
-#                 # Load the Corresponding Model
-#                 model_path = f'models/modelo_cluster_{cluster}.txt'
-#                 gbm = lgb.Booster(model_file=model_path)
-#                 st.write(f"Loaded model for cluster {cluster}")
-
-#                 # Load X_predict for that cluster
-#                 X_predict_cluster = pd.read_csv(f'predicts/X_predict_cluster_{cluster}.csv')
-
-#                 # Filter for the specific customer
-#                 X_cliente = X_predict_cluster[X_predict_cluster['cliente_id'] == customer_code]
-
-#                 if not X_cliente.empty:
-#                     # Prepare data for prediction
-#                     features_for_prediction = X_cliente.drop(columns=['cliente_id', 'fecha_mes'])
-                    
-#                     # Make Prediction for the selected customer
-#                     y_pred = gbm.predict(features_for_prediction, 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}")
-
-#                     # Load actual data
-#                     df_agg_2024 = pd.read_csv('predicts/df_agg_2024.csv')
-#                     actual_sales = df_agg_2024[df_agg_2024['cliente_id'] == customer_code]
-                    
-#                     if not actual_sales.empty:
-#                         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 only for non-null actual sales
-#                         valid_results = results.dropna(subset=['ventas_reales'])
-#                         if not valid_results.empty:
-#                             mae = mean_absolute_error(valid_results['ventas_reales'], valid_results['ventas_predichas'])
-#                             mape = np.mean(np.abs((valid_results['ventas_reales'] - valid_results['ventas_predichas']) / valid_results['ventas_reales'])) * 100
-#                             rmse = np.sqrt(mean_squared_error(valid_results['ventas_reales'], valid_results['ventas_predichas']))
-
-#                             st.write(f"Actual total sales for Customer {customer_code}: {valid_results['ventas_reales'].sum():.2f}")
-#                             st.write(f"MAE: {mae:.2f}")
-#                             st.write(f"MAPE: {mape:.2f}%")
-#                             st.write(f"RMSE: {rmse:.2f}")
-
-#                         # Analysis of results
-#                         threshold_good = 100  # You may want to adjust this threshold
-#                         if mae < threshold_good:
-#                             st.success(f"Customer {customer_code} is performing well based on the predictions.")
-#                         else:
-#                             st.warning(f"Customer {customer_code} is not performing well based on the predictions.")
-#                     else:
-#                         st.warning(f"No actual sales data found for customer {customer_code} in df_agg_2024.")
-
-#                     # Show the radar chart
-#                     all_manufacturers = customer_data.iloc[:, 1:].T  # Exclude CLIENTE column
-#                     all_manufacturers.index = all_manufacturers.index.astype(str)
-
-#                     sales_data = customer_euros.iloc[:, 1:].T  # Exclude CLIENTE column
-#                     sales_data.index = sales_data.index.astype(str)
-
-#                     sales_data_filtered = sales_data.drop(index='CLIENTE', errors='ignore')
-#                     sales_data_filtered = sales_data_filtered.apply(pd.to_numeric, errors='coerce')
-
-#                     top_units = all_manufacturers.sort_values(by=all_manufacturers.columns[0], ascending=False).head(10)
-#                     top_sales = sales_data_filtered.sort_values(by=sales_data_filtered.columns[0], ascending=False).head(10)
-#                     combined_top = pd.concat([top_units, top_sales]).index.unique()[:20]
-#                     combined_top = [m for m in combined_top if m in all_manufacturers.index and m in sales_data_filtered.index]
-
-#                     combined_data = pd.DataFrame({
-#                         'units': all_manufacturers.loc[combined_top, all_manufacturers.columns[0]],
-#                         'sales': sales_data_filtered.loc[combined_top, sales_data_filtered.columns[0]]
-#                     }).fillna(0)
-
-#                     combined_data_sorted = combined_data.sort_values(by=['units', 'sales'], ascending=False)
-#                     non_zero_manufacturers = combined_data_sorted[combined_data_sorted['units'] > 0]
-
-#                     if len(non_zero_manufacturers) < 3:
-#                         zero_manufacturers = combined_data_sorted[combined_data_sorted['units'] == 0].head(3 - len(non_zero_manufacturers))
-#                         manufacturers_to_show = pd.concat([non_zero_manufacturers, zero_manufacturers])
-#                     else:
-#                         manufacturers_to_show = non_zero_manufacturers
-
-#                     values = manufacturers_to_show['units'].tolist()
-#                     amounts = manufacturers_to_show['sales'].tolist()
-#                     manufacturers = [get_supplier_name(m) for m in manufacturers_to_show.index]
-
-#                     st.write(f"### Results for top {len(manufacturers)} manufacturers:")
-#                     for manufacturer, value, amount in zip(manufacturers, values, amounts):
-#                         st.write(f"{manufacturer} = {value:.2f}% of units, €{amount:.2f} total sales")
-
-#                     if manufacturers:
-#                         fig = radar_chart(manufacturers, values, amounts, f'Radar Chart for Top {len(manufacturers)} Manufacturers of Customer {customer_code}')
-#                         st.pyplot(fig)
-#                     else:
-#                         st.warning("No data available to create the radar chart.")
-
-#                     # Show sales over the years graph
-#                     sales_columns = ['VENTA_2021', 'VENTA_2022', 'VENTA_2023']
-#                     if all(col in ventas_clientes.columns for col in sales_columns):
-#                         years = ['2021', '2022', '2023']
-#                         customer_sales = ventas_clientes[ventas_clientes['codigo_cliente'] == customer_code][sales_columns].values[0]
-
-#                         fig_sales = px.line(x=years, y=customer_sales, markers=True, title=f'Sales Over the Years for Customer {customer_code}')
-#                         fig_sales.update_layout(xaxis_title="Year", yaxis_title="Sales")
-#                         st.plotly_chart(fig_sales)
-#                     else:
-#                         st.warning("Sales data for 2021-2023 not available.")
-#                 else:
-#                     st.warning(f"No prediction data found for customer {customer_code}.")
-#             else:
-#                 st.warning(f"No data found for customer {customer_code}. Please check the code.")
-#         else:
-#             st.warning("Please select a customer.")
-
 elif page == "Customer Analysis":
     st.title("Customer Analysis")
     st.markdown("Use the tools below to explore your customer data.")
@@ -333,8 +198,7 @@ elif page == "Customer Analysis":
                     st.write(f"Predicted total sales for Customer {customer_code}: {results['ventas_predichas'].sum():.2f}")
 
                     # Load actual data
-                    df_agg_2024 = pd.read_csv('predicts/df_agg_2024.csv')
-                    actual_sales = df_agg_2024[df_agg_2024['cliente_id'] == customer_code]
+                    actual_sales = df_agg_2024[df_agg_2024['cliente_id'] == customer_code_str]
                     st.write("### Actual Sales DataFrame:")
                     st.write(actual_sales.head())
                     st.write(f"Shape: {actual_sales.shape}")
@@ -574,3 +438,142 @@ elif page == "Articles Recommendations":
                         st.warning("No recommendations found for the provided basket.")
                 else:
                     st.warning("Please select at least one article and set its quantity.")
+
+
+# Customer Analysis Page
+# elif page == "Customer Analysis":
+#     st.title("Customer Analysis")
+#     st.markdown("Use the tools below to explore your customer data.")
+
+#     partial_code = st.text_input("Enter part of Customer Code (or leave empty to see all)")
+#     if partial_code:
+#         filtered_customers = df[df['CLIENTE'].str.contains(partial_code)]
+#     else:
+#         filtered_customers = df
+#     customer_list = filtered_customers['CLIENTE'].unique()
+#     customer_code = st.selectbox("Select Customer Code", customer_list)
+
+#     if st.button("Calcular"):
+#         if customer_code:
+#             # Find Customer's Cluster
+#             customer_match = customer_clusters[customer_clusters['cliente_id'] == customer_code]
+
+#             if not customer_match.empty:
+#                 cluster = customer_match['cluster_id'].values[0]
+#                 st.write(f"Customer {customer_code} belongs to cluster {cluster}")
+
+#                 # Load the Corresponding Model
+#                 model_path = f'models/modelo_cluster_{cluster}.txt'
+#                 gbm = lgb.Booster(model_file=model_path)
+#                 st.write(f"Loaded model for cluster {cluster}")
+
+#                 # Load X_predict for that cluster
+#                 X_predict_cluster = pd.read_csv(f'predicts/X_predict_cluster_{cluster}.csv')
+
+#                 # Filter for the specific customer
+#                 X_cliente = X_predict_cluster[X_predict_cluster['cliente_id'] == customer_code]
+
+#                 if not X_cliente.empty:
+#                     # Prepare data for prediction
+#                     features_for_prediction = X_cliente.drop(columns=['cliente_id', 'fecha_mes'])
+                    
+#                     # Make Prediction for the selected customer
+#                     y_pred = gbm.predict(features_for_prediction, 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}")
+
+#                     # Load actual data
+#                     df_agg_2024 = pd.read_csv('predicts/df_agg_2024.csv')
+#                     actual_sales = df_agg_2024[df_agg_2024['cliente_id'] == customer_code]
+                    
+#                     if not actual_sales.empty:
+#                         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 only for non-null actual sales
+#                         valid_results = results.dropna(subset=['ventas_reales'])
+#                         if not valid_results.empty:
+#                             mae = mean_absolute_error(valid_results['ventas_reales'], valid_results['ventas_predichas'])
+#                             mape = np.mean(np.abs((valid_results['ventas_reales'] - valid_results['ventas_predichas']) / valid_results['ventas_reales'])) * 100
+#                             rmse = np.sqrt(mean_squared_error(valid_results['ventas_reales'], valid_results['ventas_predichas']))
+
+#                             st.write(f"Actual total sales for Customer {customer_code}: {valid_results['ventas_reales'].sum():.2f}")
+#                             st.write(f"MAE: {mae:.2f}")
+#                             st.write(f"MAPE: {mape:.2f}%")
+#                             st.write(f"RMSE: {rmse:.2f}")
+
+#                         # Analysis of results
+#                         threshold_good = 100  # You may want to adjust this threshold
+#                         if mae < threshold_good:
+#                             st.success(f"Customer {customer_code} is performing well based on the predictions.")
+#                         else:
+#                             st.warning(f"Customer {customer_code} is not performing well based on the predictions.")
+#                     else:
+#                         st.warning(f"No actual sales data found for customer {customer_code} in df_agg_2024.")
+
+#                     # Show the radar chart
+#                     all_manufacturers = customer_data.iloc[:, 1:].T  # Exclude CLIENTE column
+#                     all_manufacturers.index = all_manufacturers.index.astype(str)
+
+#                     sales_data = customer_euros.iloc[:, 1:].T  # Exclude CLIENTE column
+#                     sales_data.index = sales_data.index.astype(str)
+
+#                     sales_data_filtered = sales_data.drop(index='CLIENTE', errors='ignore')
+#                     sales_data_filtered = sales_data_filtered.apply(pd.to_numeric, errors='coerce')
+
+#                     top_units = all_manufacturers.sort_values(by=all_manufacturers.columns[0], ascending=False).head(10)
+#                     top_sales = sales_data_filtered.sort_values(by=sales_data_filtered.columns[0], ascending=False).head(10)
+#                     combined_top = pd.concat([top_units, top_sales]).index.unique()[:20]
+#                     combined_top = [m for m in combined_top if m in all_manufacturers.index and m in sales_data_filtered.index]
+
+#                     combined_data = pd.DataFrame({
+#                         'units': all_manufacturers.loc[combined_top, all_manufacturers.columns[0]],
+#                         'sales': sales_data_filtered.loc[combined_top, sales_data_filtered.columns[0]]
+#                     }).fillna(0)
+
+#                     combined_data_sorted = combined_data.sort_values(by=['units', 'sales'], ascending=False)
+#                     non_zero_manufacturers = combined_data_sorted[combined_data_sorted['units'] > 0]
+
+#                     if len(non_zero_manufacturers) < 3:
+#                         zero_manufacturers = combined_data_sorted[combined_data_sorted['units'] == 0].head(3 - len(non_zero_manufacturers))
+#                         manufacturers_to_show = pd.concat([non_zero_manufacturers, zero_manufacturers])
+#                     else:
+#                         manufacturers_to_show = non_zero_manufacturers
+
+#                     values = manufacturers_to_show['units'].tolist()
+#                     amounts = manufacturers_to_show['sales'].tolist()
+#                     manufacturers = [get_supplier_name(m) for m in manufacturers_to_show.index]
+
+#                     st.write(f"### Results for top {len(manufacturers)} manufacturers:")
+#                     for manufacturer, value, amount in zip(manufacturers, values, amounts):
+#                         st.write(f"{manufacturer} = {value:.2f}% of units, €{amount:.2f} total sales")
+
+#                     if manufacturers:
+#                         fig = radar_chart(manufacturers, values, amounts, f'Radar Chart for Top {len(manufacturers)} Manufacturers of Customer {customer_code}')
+#                         st.pyplot(fig)
+#                     else:
+#                         st.warning("No data available to create the radar chart.")
+
+#                     # Show sales over the years graph
+#                     sales_columns = ['VENTA_2021', 'VENTA_2022', 'VENTA_2023']
+#                     if all(col in ventas_clientes.columns for col in sales_columns):
+#                         years = ['2021', '2022', '2023']
+#                         customer_sales = ventas_clientes[ventas_clientes['codigo_cliente'] == customer_code][sales_columns].values[0]
+
+#                         fig_sales = px.line(x=years, y=customer_sales, markers=True, title=f'Sales Over the Years for Customer {customer_code}')
+#                         fig_sales.update_layout(xaxis_title="Year", yaxis_title="Sales")
+#                         st.plotly_chart(fig_sales)
+#                     else:
+#                         st.warning("Sales data for 2021-2023 not available.")
+#                 else:
+#                     st.warning(f"No prediction data found for customer {customer_code}.")
+#             else:
+#                 st.warning(f"No data found for customer {customer_code}. Please check the code.")
+#         else:
+#             st.warning("Please select a customer.")