Update app.py

app.py

@@ -117,11 +117,14 @@ if st.session_state['active_card'] == 'card1':
 # Card 2: Sales Volume & Unit Price Correlation plot for Item Category and Container Code
 if st.session_state['active_card'] == 'card2':
     # Dropdown to select item type (using session_state)
-    st.session_state['selected_item_type'] = st.selectbox('Select Item Type', 
-                                                                df['Itemtype'].unique(),
-                                                                index=list(df['Itemtype'].unique()).index(st.session_state['selected_item_type']))
+    st.session_state['selected_item_type'] = st.selectbox(
+        'Select Item Type', df['Itemtype'].unique(),
+        index=list(df['Itemtype'].unique()).index(st.session_state['selected_item_type']))
 
-    st.subheader("Sales Volume & Unit Price Correlation for Container Codes")
+    # Dropdown to select the grouping category (container code, chain code, or state)
+    group_by_option = st.selectbox('Group by', ['Containercode', 'Chaincode', 'State'])
+
+    st.subheader(f"Sales Volume & Unit Price Correlation for {group_by_option}")
 
     # Group the dataframe and prepare for plotting
     df = df.groupby(['FyWeek', 'Fy', 'Chaincode', 'Store', 'Address', 'Zipcode', 'City', 'State', 'Containercode', 'Itemtype'], observed=True).agg({
@@ -149,42 +152,42 @@ if st.session_state['active_card'] == 'card2':
     # Filter the dataframe based on the selected item type
     filtered_df = df[df['Itemtype'] == st.session_state['selected_item_type']]
 
-    # Find the top 3 container codes based on total SalesVolume
-    top_3_containers = filtered_df.groupby('Containercode', observed=True)['SalesVolume'].sum().nlargest(3).index
+    # Find the top 3 values based on total SalesVolume in the selected grouping category
+    top_3_values = filtered_df.groupby(group_by_option, observed=True)['SalesVolume'].sum().nlargest(3).index
 
-    # Filter the data for only the top 3 container codes
-    top_container_data = filtered_df[filtered_df['Containercode'].isin(top_3_containers)]
+    # Filter the data for only the top 3 values
+    top_group_data = filtered_df[filtered_df[group_by_option].isin(top_3_values)]
 
-    # Group by Year, Week, Dt, and Containercode and aggregate SalesVolume and UnitPrice
-    agg_df = top_container_data.groupby(['Containercode', 'Year', 'Week', 'Dt'], observed=True).agg({
+    # Group by Year, Week, Dt, and the selected category and aggregate SalesVolume and UnitPrice
+    agg_df = top_group_data.groupby([group_by_option, 'Year', 'Week', 'Dt'], observed=True).agg({
         'SalesVolume': 'sum',
         'UnitPrice': 'mean'
     }).reset_index()
 
-    # Loop through the top 3 container codes and create separate plots
-    for container in top_3_containers:
-        container_data = agg_df[agg_df['Containercode'] == container]
+    # Loop through the top 3 values and create separate plots
+    for value in top_3_values:
+        value_data = agg_df[agg_df[group_by_option] == value]
 
-        # Create a new figure for each container code
+        # Create a new figure for each group
         fig, (axd, axp) = plt.subplots(2, 1, figsize=(10, 6))
 
         # Plot SalesVolume
-        sns.lineplot(data=container_data, x='Dt', y='SalesVolume', ax=axd)
-        axd.set_title(f"SalesVolume - {container}")
+        sns.lineplot(data=value_data, x='Dt', y='SalesVolume', ax=axd)
+        axd.set_title(f"SalesVolume - {value} ({group_by_option})")
         axd.grid(True, linestyle='--', color='gray', alpha=0.7)
 
         # Plot mean line for SalesVolume
-        axd.axhline(container_data['SalesVolume'].mean(), ls="--", color="r")
+        axd.axhline(value_data['SalesVolume'].mean(), ls="--", color="r")
         axd.xaxis.set_major_locator(mdates.MonthLocator(interval=2))
         axd.set_xticklabels([])
 
         # Plot UnitPrice
-        sns.lineplot(data=container_data, x='Dt', y='UnitPrice', ax=axp, color='green', errorbar='sd')
-        axp.set_title(f"UnitPrice - {container}")
+        sns.lineplot(data=value_data, x='Dt', y='UnitPrice', ax=axp, color='green', errorbar='sd')
+        axp.set_title(f"UnitPrice - {value} ({group_by_option})")
         axp.grid(True, linestyle='--', color='gray', alpha=0.7)
 
         # Plot mean line for UnitPrice
-        axp.axhline(container_data['UnitPrice'].mean(), ls="--", color="r")
+        axp.axhline(value_data['UnitPrice'].mean(), ls="--", color="r")
         axp.xaxis.set_major_locator(mdates.MonthLocator(interval=2))
         axp.tick_params(axis='x', rotation=90)
 
@@ -193,7 +196,6 @@ if st.session_state['active_card'] == 'card2':
 
         # Display the plot in Streamlit
         st.pyplot(fig)
-
 ###############################################################################################
 
 ########################################### CARD #3 ####################################################