feat: updated app.py

app.py

@@ -234,79 +234,89 @@ elif page == "Customer Analysis":
                     else:
                         st.warning(f"No actual sales data found for customer {customer_code} in df_agg_2024.")
 
-                    # Show the radar chart
+                    st.write("### Debug Information for Radar Chart:")
+                    st.write(f"Shape of customer_data: {customer_data.shape}")
+                    st.write(f"Shape of euros_proveedor: {euros_proveedor.shape}")
+
+                    # Get percentage of units sold for each manufacturer
                     all_manufacturers = customer_data.iloc[:, 1:].T  # Exclude CLIENTE column
                     all_manufacturers.index = all_manufacturers.index.astype(str)
 
-                    sales_data = euros_proveedor.iloc[:, 1:].T  # Exclude CLIENTE column
+                    # Get total sales for each manufacturer
+                    customer_euros = euros_proveedor[euros_proveedor["CLIENTE"] == str(customer_code)]
+                    sales_data = customer_euros.iloc[:, 1:].T  # Exclude CLIENTE column
                     sales_data.index = sales_data.index.astype(str)
 
+                    # Remove the 'CLIENTE' row from sales_data to avoid issues with mixed types
                     sales_data_filtered = sales_data.drop(index='CLIENTE', errors='ignore')
+
+                    # Ensure all values are numeric
                     sales_data_filtered = sales_data_filtered.apply(pd.to_numeric, errors='coerce')
 
-                    # Ensure the values in all_manufacturers are numeric before sorting
-                    all_manufacturers_numeric = pd.to_numeric(all_manufacturers.iloc[:, 0], errors='coerce')
+                    # Sort manufacturers by percentage of units and get top 10
+                    top_units = all_manufacturers.sort_values(by=all_manufacturers.columns[0], ascending=False).head(10)
 
-                    # Sort the manufacturers based on numeric values
-                    top_units = all_manufacturers.assign(numeric_values=all_manufacturers_numeric).sort_values(by='numeric_values', ascending=False).head(10)
+                    # Sort manufacturers by total sales and get top 10
+                    top_sales = sales_data_filtered.sort_values(by=sales_data_filtered.columns[0], ascending=False).head(10)
 
-                    # Drop the temporary numeric column after sorting
-                    top_units = top_units.drop(columns=['numeric_values'])
+                    # Combine top manufacturers from both lists and get up to 20 unique manufacturers
+                    combined_top = pd.concat([top_units, top_sales]).index.unique()[:20]
 
-                    # Ensure the values in sales_data_filtered are numeric before sorting
-                    sales_data_filtered_numeric = pd.to_numeric(sales_data_filtered.iloc[:, 0], errors='coerce')
+                    # Filter out manufacturers that are not present in both datasets
+                    combined_top = [m for m in combined_top if m in all_manufacturers.index and m in sales_data_filtered.index]
 
-                    # Sort the sales data based on numeric values
-                    top_sales = sales_data_filtered.assign(numeric_values=sales_data_filtered_numeric).sort_values(by='numeric_values', ascending=False).head(10)
+                    st.write(f"Number of combined top manufacturers: {len(combined_top)}")
 
-                    # Drop the temporary numeric column after sorting
-                    top_sales = top_sales.drop(columns=['numeric_values'])
-                    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]
+                    if combined_top:
+                        # Create a DataFrame with combined data for these top manufacturers
+                        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 = 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)
+                        # Sort by units, then by sales
+                        combined_data_sorted = combined_data.sort_values(by=['units', 'sales'], ascending=False)
 
-                    combined_data_sorted = combined_data.sort_values(by=['units', 'sales'], ascending=False)
-                    non_zero_manufacturers = combined_data_sorted[combined_data_sorted['units'] > 0]
+                        # Filter out manufacturers with 0 units
+                        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
+                        # If we have less than 3 non-zero manufacturers, add some zero-value ones
+                        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]
+                        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")
+                        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:  # Only create the chart if we have data
+                            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.")
 
-                    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.")
+                        st.warning("No combined top manufacturers found.")
 
-                    # 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]
+                    # Customer sales 2021-2024 (if data exists)
+                    sales_columns = ['VENTA_2021', 'VENTA_2022', 'VENTA_2023', 'VENTA_2024']
+                    if all(col in df.columns for col in sales_columns):
+                        years = ['2021', '2022', '2023', '2024']
+                        customer_sales = customer_data[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.")
+                        st.warning("Sales data for 2021-2024 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.")
+                    st.warning(f"No data found for customer {customer_code}. Please check the code.")
         else:
             st.warning("Please select a customer.")