feat: generated files

app.py

@@ -12,26 +12,26 @@ 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=',')
 
+# Ensure customer codes are strings
+df['CLIENTE'] = df['CLIENTE'].astype(str)
 nombres_proveedores['codigo'] = nombres_proveedores['codigo'].astype(str)
 euros_proveedor['CLIENTE'] = euros_proveedor['CLIENTE'].astype(str)
 
-# Convertir todas las columnas excepto 'CLIENTE' a float en euros_proveedor
+# Convert all columns except 'CLIENTE' to float in euros_proveedor
 for col in euros_proveedor.columns:
     if col != 'CLIENTE':
         euros_proveedor[col] = pd.to_numeric(euros_proveedor[col], errors='coerce')
 
-# Verificar si hay valores NaN después de la conversión
+# Check for NaN values after conversion
 if euros_proveedor.isna().any().any():
-    st.warning("Algunos valores en euros_proveedor no pudieron ser convertidos a números. Por favor, revise los datos de entrada.")
+    st.warning("Some values in euros_proveedor couldn't be converted to numbers. Please review the input data.")
 
-# Ignore the last two columns
+# Ignore the last two columns of df
 df = df.iloc[:, :-2]
 
-# Ensure customer code is a string
-df['CLIENTE'] = df['CLIENTE'].astype(str)
-
 # Function to get supplier name
 def get_supplier_name(code):
+    code = str(code)  # Ensure code is a string
     name = nombres_proveedores[nombres_proveedores['codigo'] == code]['nombre'].values
     return name[0] if len(name) > 0 else code
 
@@ -105,8 +105,8 @@ elif page == "Customer Analysis":
     customer_code = st.selectbox("Select Customer Code", customer_list)
 
     if customer_code:
-        customer_data = df[df["CLIENTE"] == customer_code]
-        customer_euros = euros_proveedor[euros_proveedor["CLIENTE"] == customer_code]
+        customer_data = df[df["CLIENTE"] == str(customer_code)]
+        customer_euros = euros_proveedor[euros_proveedor["CLIENTE"] == str(customer_code)]
 
         if not customer_data.empty and not customer_euros.empty:
             st.write(f"### Analysis for Customer {customer_code}")
@@ -120,10 +120,10 @@ elif page == "Customer Analysis":
             sales_data.index = sales_data.index.astype(str)
 
             # Sort manufacturers by percentage of units and get top 10
-            top_units = all_manufacturers.sort_values(by=customer_data.index[0], ascending=False).head(10)
+            top_units = all_manufacturers.sort_values(by=all_manufacturers.columns[0], ascending=False).head(10)
             
             # Sort manufacturers by total sales and get top 10
-            top_sales = sales_data.sort_values(by=customer_euros.index[0], ascending=False).head(10)
+            top_sales = sales_data.sort_values(by=sales_data.columns[0], ascending=False).head(10)
 
             # Combine top manufacturers from both lists
             combined_top = pd.concat([top_units, top_sales]).index.unique()
@@ -134,9 +134,9 @@ elif page == "Customer Analysis":
 
             for m in combined_top:
                 if m in all_manufacturers.index and m in sales_data.index:
-                    values.append(float(all_manufacturers.loc[m, customer_data.index[0]]))
+                    values.append(float(all_manufacturers.loc[m, all_manufacturers.columns[0]]))
                     manufacturers.append(get_supplier_name(m))
-                    amounts.append(float(sales_data.loc[m, customer_euros.index[0]]))
+                    amounts.append(float(sales_data.loc[m, sales_data.columns[0]]))
 
             st.write(f"### Results for top {len(manufacturers)} manufacturers (balanced by units % and total sales):")
             for manufacturer, value, amount in zip(manufacturers, values, amounts):
@@ -149,9 +149,9 @@ elif page == "Customer Analysis":
                 st.warning("No data available to create the radar chart.")
 
             # Customer sales 2021-2024 (if data exists)
-            if 'VENTA_2021' in df.columns and 'VENTA_2022' in df.columns and 'VENTA_2023' in df.columns and 'VENTA_2024' in df.columns:
+            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']
-                sales_columns = ['VENTA_2021', 'VENTA_2022', 'VENTA_2023', 'VENTA_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}')
@@ -178,7 +178,7 @@ elif page == "Customer Recommendations":
     customer_code = st.selectbox("Select Customer Code for Recommendations", customer_list)
 
     if customer_code:
-        customer_data = df[df["CLIENTE"] == customer_code]
+        customer_data = df[df["CLIENTE"] == str(customer_code)]
 
         if not customer_data.empty:
             st.write(f"### Purchase History for Customer {customer_code}")