Update app.py

app.py

@@ -50,7 +50,7 @@ def load_data(active_card):
 
     # Columns specific to cards
     card_specific_cols = {
-        'card1': ['FyWeek', 'State', 'Itemtype', 'Chaincode', 'SalesVolume'],
+        'card1': ['FyWeek', 'Fy', 'State','Store','Address','Zipcode','City','Itemtype', 'Chaincode', 'Containercode', 'SalesVolume', 'UnitPrice', 'Sales'],
         'card2': ['FyWeek', 'Fy', 'State','Store','Address','Zipcode','City','Itemtype', 'Chaincode', 'Containercode', 'SalesVolume', 'UnitPrice', 'Sales'],
         'card3': ['FyWeek', 'Fy', 'State','Store','Address','Zipcode','City','Itemtype', 'Chaincode', 'Containercode', 'SalesVolume', 'UnitPrice', 'Sales'] # Added for PE calculation card
     }
@@ -82,7 +82,7 @@ def load_data(active_card):
 
     # st.write("+++++++++++++++++++++++")
 
-    if active_card in ['card2', 'card3', 'card4']:
+    if active_card in ['card1','card2', 'card3',]:
         df = df.groupby(['FyWeek', 'Fy', 'Chaincode', 'Store', 'Address', 'Zipcode', 'City', 'State', 'Containercode', 'Itemtype'], observed=True).agg({
         'SalesVolume': 'sum',
         'UnitPrice': 'mean',
@@ -96,19 +96,13 @@ def load_data(active_card):
     df['Region'] = df['State'].map(state_to_region)
 
     return df
-
-# st.image("bonnie.png", width=200) 
-# # Main interactive section
-# st.title('Bonnnie Plants Price vs Sales Volume Trcaker')
-
+    
 # Display logo
 st.image("bonnie.png", width=150)  # Adjust width as needed
 
 # Display title
 st.title("Bonnie Plants Pricing & Sales Analytics Dashboard")
 
-# Close the div for logo and title
-# st.markdown('</div>', unsafe_allow_html=True)
 
 #  Initialize session state for storing which card was clicked and item type
 if 'active_card' not in st.session_state:
@@ -119,60 +113,221 @@ if 'selected_item_type' not in st.session_state:
 if 'selected_feature' not in st.session_state:
     st.session_state['selected_feature'] = 'Chaincode'  # Default to 'Chain Code'
 
-# Card selection buttons
-col1, col2, col3= st.columns(3)
-# Define buttons for plot categories, update session state when clicked
+# Card selection buttons with logic to reset session state on switch
+col1, col2, col3 = st.columns(3)
 with col1:
     if st.button("Sales Volume Trend for Item Category"):
         st.session_state['active_card'] = 'card1'
+        # Reset other selections when switching cards
+        st.session_state['selected_state'] = None
+        st.session_state['selected_chaincode'] = None
+        st.session_state['selected_itemtype'] = None
+        st.session_state['selected_containercode'] = None
 
 with col2:
     if st.button("Sales Volume & Unit Price Correlation for Item Category and Container Code"):
         st.session_state['active_card'] = 'card2'
+        # Reset selections when switching cards
+        st.session_state['selected_state'] = None
+        st.session_state['selected_chaincode'] = None
+        st.session_state['selected_itemtype'] = None
+        st.session_state['selected_containercode'] = None
+
 with col3:
     if st.button("PE Coefficient Calculation for Regions & Item Categories"):
         st.session_state['active_card'] = 'card3'
-
-
-start_time=time.time()
-# st.write(st.session_state['active_card'])
+        # Reset selections when switching cards
+        st.session_state['selected_state'] = None
+        st.session_state['selected_chaincode'] = None
+        st.session_state['selected_itemtype'] = None
+        st.session_state['selected_containercode'] = None
+
+# Load data for the current card
+start_time = time.time()
 df = load_data(st.session_state['active_card'])
 time_taken = time.time() - start_time
 st.write(f"Data loaded in {time_taken:.2f} seconds")
 
 
-# Initialize session state for storing the selected state and feature
-if 'selected_state' not in st.session_state:
-    st.session_state['selected_state'] = df['State'].unique()[0]  # Default to the first state
-
 ############################################ CARD #1 ####################################################
 if st.session_state['active_card'] == 'card1':
-    # st.write("Processing card1...")
-    # Dropdown for selecting the state
-    selected_state = st.selectbox('Select State', df['State'].unique())
-    # Dropdown for selecting the feature for grouping
-    selected_feature = st.selectbox('Select Feature for Grouping', ['Chaincode', 'Itemtype',])
-    
-    # Filter the dataframe based on selected state
-    filtered_df = df[df['State'] == selected_state]
-    
-    # Time the grouping operation
-    start_time = time.time()
-    group_data = filtered_df.groupby(['FyWeek', selected_feature],observed=True)['SalesVolume'].sum().reset_index()
-    time_taken = time.time() - start_time
-    # st.write(f"Data grouped in {time_taken:.2f} seconds")
-
-    # Plotting
-    fig = px.bar(group_data, x='FyWeek', y='SalesVolume', color=selected_feature,
-                 title=f'Sales Volume over Fiscal Week in {selected_state} by {selected_feature}',
-                 labels={'SalesVolume': 'Sales Volume', 'Fiscal Week Short': 'Fiscal Week'})
-    st.plotly_chart(fig)
-
+    # Step 1: Sales Volume vs FyWeek for the whole dataset (no filter)
+    st.subheader("Total Sales Volume vs Fiscal Week")
+    df['FY_Week'] = df['FY'].astype(str) + '_' + df['Week'].astype(str)
+    # Split FY_Week again for correct sorting
+    if not df.empty and 'FY_Week' in df.columns:
+        total_sales_df = df.groupby('FY_Week', observed=True)['SalesVolume'].sum().reset_index()
+        total_sales_df[['FY', 'Week']] = total_sales_df['FY_Week'].str.split('_', expand=True)
+        total_sales_df['Week'] = total_sales_df['Week'].astype(int)
+        total_sales_df = total_sales_df.sort_values(by=['FY', 'Week'])
+        
+        # Create a line chart using Plotly
+        fig = px.line(total_sales_df, x='FY_Week', y='SalesVolume',
+                      title='Total Sales Volume vs Fiscal Week',
+                      labels={'SalesVolume': 'Sales Volume', 'FY_Week': 'Fiscal Week'})
+        st.plotly_chart(fig)
+
+    # Step 2: Top 3 states based on sales volume as buttons/cards
+    top_states = df.groupby('State', observed=True)['SalesVolume'].sum().nlargest(3).index
+    st.write("### Top 3 Selling States :")
+    col1, col2, col3 = st.columns(3)
+    if len(top_states) > 0 and col1.button(top_states[0]):
+        st.session_state['selected_state'] = top_states[0]
+    if len(top_states) > 1 and col2.button(top_states[1]):
+        st.session_state['selected_state'] = top_states[1]
+    if len(top_states) > 2 and col3.button(top_states[2]):
+        st.session_state['selected_state'] = top_states[2]
+
+    # If a state is selected, show the corresponding plot
+    if 'selected_state' in st.session_state and st.session_state['selected_state']:
+        selected_state = st.session_state['selected_state']
+
+        # Step 3: Sales volume vs FyWeek for the selected state
+        st.subheader(f"Sales Volume vs Fiscal Week for {selected_state}")
+        state_sales_df = df[df['State'] == selected_state].groupby('FY_Week', observed=True)['SalesVolume'].sum().reset_index()
+
+        if not state_sales_df.empty and 'FY_Week' in state_sales_df.columns:
+            state_sales_df[['FY', 'Week']] = state_sales_df['FY_Week'].str.split('_', expand=True)
+            state_sales_df['Week'] = state_sales_df['Week'].astype(int)
+            state_sales_df = state_sales_df.sort_values(by=['FY', 'Week'])
+
+            fig = px.line(state_sales_df, x='FY_Week', y='SalesVolume',
+                          title=f'Sales Volume vs Fiscal Week in {selected_state}',
+                          labels={'SalesVolume': 'Sales Volume', 'FY_Week': 'Fiscal Week'})
+            st.plotly_chart(fig)
+
+        # Step 4: Top 3 chaincodes based on sales volume as buttons/cards
+        top_chaincodes = df[df['State'] == selected_state].groupby('Chaincode', observed=True)['SalesVolume'].sum().nlargest(3).index
+        st.write(f"### Top 3 selling Chaincode in {selected_state}:")
+
+        # Add a check to ensure top_chaincodes has values before accessing
+        col1, col2, col3 = st.columns(3)
+        if len(top_chaincodes) > 0 and col1.button(top_chaincodes[0]):
+            st.session_state['selected_chaincode'] = top_chaincodes[0]
+        if len(top_chaincodes) > 1 and col2.button(top_chaincodes[1]):
+            st.session_state['selected_chaincode'] = top_chaincodes[1]
+        if len(top_chaincodes) > 2 and col3.button(top_chaincodes[2]):
+            st.session_state['selected_chaincode'] = top_chaincodes[2]
+
+        # If a chaincode is selected, show the corresponding plot
+        if 'selected_chaincode' in st.session_state:
+            selected_chaincode = st.session_state['selected_chaincode']
+
+            # Step 5: Sales volume vs FyWeek for the selected chaincode in the selected state
+            st.subheader(f"Sales Volume vs Fiscal Week for {selected_chaincode} in {selected_state}")
+            chain_sales_df = df[(df['State'] == selected_state) & (df['Chaincode'] == selected_chaincode)].groupby('FY_Week', observed=True)['SalesVolume'].sum().reset_index()
+
+            if not chain_sales_df.empty and 'FY_Week' in chain_sales_df.columns:
+                chain_sales_df[['FY', 'Week']] = chain_sales_df['FY_Week'].str.split('_', expand=True)
+                chain_sales_df['Week'] = chain_sales_df['Week'].astype(int)
+                chain_sales_df = chain_sales_df.sort_values(by=['FY', 'Week'])
+
+                fig = px.line(chain_sales_df, x='FY_Week', y='SalesVolume',
+                              title=f'Sales Volume vs Fiscal Week in {selected_chaincode}, {selected_state}',
+                              labels={'SalesVolume': 'Sales Volume', 'FY_Week': 'Fiscal Week'})
+                st.plotly_chart(fig)
+
+            # Step 6: Top 3 itemtypes based on sales volume as buttons/cards
+            top_itemtypes = df[(df['State'] == selected_state) & (df['Chaincode'] == selected_chaincode)].groupby('Itemtype', observed=True)['SalesVolume'].sum().nlargest(3).index
+            st.write(f"### Top Itemtype in {selected_chaincode}, {selected_state}:")
+
+            col1, col2, col3 = st.columns(3)
+            if len(top_itemtypes) > 0 and col1.button(top_itemtypes[0]):
+                st.session_state['selected_itemtype'] = top_itemtypes[0]
+            if len(top_itemtypes) > 1 and col2.button(top_itemtypes[1]):
+                st.session_state['selected_itemtype'] = top_itemtypes[1]
+            if len(top_itemtypes) > 2 and col3.button(top_itemtypes[2]):
+                st.session_state['selected_itemtype'] = top_itemtypes[2]
+
+            # If an itemtype is selected, show the corresponding dual-axis plot for Sales Volume & Unit Price
+            if 'selected_itemtype' in st.session_state:
+                selected_itemtype = st.session_state['selected_itemtype']
+
+                # Step 7: Dual-axis plot for Sales volume and UnitPrice vs FyWeek for the selected itemtype
+                st.subheader(f"Sales Volume & Unit Price vs Fiscal Week for {selected_itemtype} in {selected_chaincode}, {selected_state}")
+                item_sales_df = df[(df['State'] == selected_state) & (df['Chaincode'] == selected_chaincode) & (df['Itemtype'] == selected_itemtype)].groupby('FY_Week', observed=True).agg({
+                    'SalesVolume': 'sum',
+                    'UnitPrice': 'mean'
+                }).reset_index()
+                if not item_sales_df.empty and 'FY_Week' in item_sales_df.columns:
+                    item_sales_df[['FY', 'Week']] = item_sales_df['FY_Week'].str.split('_', expand=True)
+                    item_sales_df['Week'] = item_sales_df['Week'].astype(int)
+                    item_sales_df = item_sales_df.sort_values(by=['FY', 'Week'])
+
+                    # Dual-axis plot using Plotly Graph Objects
+                    fig = go.Figure()
+
+                    # Add SalesVolume trace
+                    fig.add_trace(go.Scatter(
+                        x=item_sales_df['FY_Week'],
+                        y=item_sales_df['SalesVolume'],
+                        mode='lines+markers',
+                        name='SalesVolume',
+                        line=dict(color='blue'),
+                        hovertemplate='SalesVolume: %{y}<br>Week-Year: %{x}'
+                    ))
+
+                    # Add UnitPrice trace with secondary Y-axis
+                    fig.add_trace(go.Scatter(
+                        x=item_sales_df['FY_Week'],
+                        y=item_sales_df['UnitPrice'],
+                        mode='lines+markers',
+                        name='UnitPrice',
+                        line=dict(color='green'),
+                        yaxis='y2',
+                        hovertemplate='UnitPrice: %{y}<br>Week-Year: %{x}'
+                    ))
+
+                    # Update layout for dual axes
+                    fig.update_layout(
+                        title=f"Sales Volume & Unit Price vs Fiscal Week in {selected_itemtype}, {selected_chaincode}, {selected_state}",
+                        xaxis_title='Fiscal Week',
+                        yaxis_title='Sales Volume',
+                        yaxis2=dict(title='Unit Price', overlaying='y', side='right'),
+                        legend=dict(x=0.9, y=1.15),
+                        hovermode="x unified",  # Show both values in a tooltip
+                        height=600,
+                        margin=dict(l=50, r=50, t=50, b=50)
+                    )
+
+                    # Rotate X-axis labels
+                    fig.update_xaxes(tickangle=90)
+
+                    # Display the Plotly figure in Streamlit
+                    st.plotly_chart(fig, use_container_width=True)
+                    # Step 8: Display Top/Bottom Container Codes and Stores
+                    st.subheader("Top & Bottom 3 Container Codes and Stores")
+
+                    # Get top and bottom 3 container codes based on SalesVolume
+                    top_containercodes = df[(df['State'] == selected_state) & (df['Chaincode'] == selected_chaincode) & (df['Itemtype'] == selected_itemtype)].groupby('Containercode', observed=True)['SalesVolume'].sum().nlargest(3).reset_index()
+                    bottom_containercodes = df[(df['State'] == selected_state) & (df['Chaincode'] == selected_chaincode) & (df['Itemtype'] == selected_itemtype)].groupby('Containercode', observed=True)['SalesVolume'].sum().nsmallest(3).reset_index()
+
+                    # Get top and bottom 3 stores based on SalesVolume
+                    top_stores = df[(df['State'] == selected_state) & (df['Chaincode'] == selected_chaincode) & (df['Itemtype'] == selected_itemtype)].groupby('Store', observed=True)['SalesVolume'].sum().nlargest(3).reset_index()
+                    bottom_stores = df[(df['State'] == selected_state) & (df['Chaincode'] == selected_chaincode) & (df['Itemtype'] == selected_itemtype)].groupby('Store', observed=True)['SalesVolume'].sum().nsmallest(3).reset_index()
+
+                    # Create a table with the top and bottom container codes and stores
+                    st.write("### Top 3 Container Codes:")
+                    st.dataframe(top_containercodes)
+
+                    st.write("### Bottom 3 Container Codes:")
+                    st.dataframe(bottom_containercodes)
+
+                    st.write("### Top 3 Stores:")
+                    st.dataframe(top_stores)
+
+                    st.write("### Bottom 3 Stores:")
+                    st.dataframe(bottom_stores)
 ##########################################################################################################
 
-##########################################################################################################
 
+########################################### CARD #2 ####################################################
 if st.session_state['active_card'] == 'card2':
+    # Identify the top 10 Itemtypes based on total SalesVolume
+    top_10_itemtypes = df.groupby('Itemtype')['SalesVolume'].sum().nlargest(10).index
+
+    # Filter the DataFrame to include only the top 10 Itemtypes
+    df = df[df['Itemtype'].isin(top_10_itemtypes)]
     # Dropdown to select item type (using session_state)
     st.session_state['selected_item_type'] = st.selectbox(
         'Select Item Type', df['Itemtype'].unique(),
@@ -279,7 +434,7 @@ if st.session_state['active_card'] == 'card3':
     selected_item_type = st.selectbox("Select Item Type", item_type_options)
 
     # Dropdown for selecting the region (multiple selection allowed)
-    region_options = df['Region'].unique()
+    region_options = df['Region'].dropna().unique()
     selected_regions = st.multiselect("Select Region(s)", region_options, default=region_options)
 
     # Filter data based on selected item type and selected regions