Update app.py

app.py

@@ -11,7 +11,30 @@ from datetime import datetime, timedelta
 import warnings
 import time
 import dask.dataframe as dd
-
+state_to_region = {
+    # WEST
+    'AK': 'WEST', 'CA': 'WEST', 'CO': 'WEST', 'HI': 'WEST', 'ID': 'WEST', 
+    'MT': 'WEST', 'NV': 'WEST', 'OR': 'WEST', 'UT': 'WEST', 'WA': 'WEST', 'WY': 'WEST',
+    
+    # SOUTHWEST
+    'AZ': 'SOUTHWEST', 'NM': 'SOUTHWEST', 'OK': 'SOUTHWEST', 'TX': 'SOUTHWEST',
+    
+    # MIDWEST
+    'IL': 'MIDWEST', 'IN': 'MIDWEST', 'IA': 'MIDWEST', 'KS': 'MIDWEST', 'MI': 'MIDWEST',
+    'MN': 'MIDWEST', 'MO': 'MIDWEST', 'NE': 'MIDWEST', 'ND': 'MIDWEST', 'OH': 'MIDWEST', 
+    'SD': 'MIDWEST', 'WI': 'MIDWEST',
+    
+    # SOUTHEAST
+    'AL': 'SOUTHEAST', 'AR': 'SOUTHEAST', 'DE': 'SOUTHEAST', 'FL': 'SOUTHEAST', 
+    'GA': 'SOUTHEAST', 'KY': 'SOUTHEAST', 'LA': 'SOUTHEAST', 'MD': 'SOUTHEAST', 
+    'MS': 'SOUTHEAST', 'NC': 'SOUTHEAST', 'SC': 'SOUTHEAST', 'TN': 'SOUTHEAST', 
+    'VA': 'SOUTHEAST', 'WV': 'SOUTHEAST',
+    
+    # NORTHEAST
+    'CT': 'NORTHEAST', 'ME': 'NORTHEAST', 'MA': 'NORTHEAST', 'NH': 'NORTHEAST', 
+    'NJ': 'NORTHEAST', 'NY': 'NORTHEAST', 'PA': 'NORTHEAST', 'RI': 'NORTHEAST', 
+    'VT': 'NORTHEAST'
+}
 @st.cache_data
 def date_from_week(year, week):
     # Assuming the fiscal year starts in August and the week starts from August 1st
@@ -29,6 +52,7 @@ def load_data(active_card):
     card_specific_cols = {
         'card1': ['FyWeek', 'State', 'Itemtype', 'Chaincode', 'SalesVolume'],
         'card2': ['FyWeek', 'Fy', 'State','Store','Address','Zipcode','City','Itemtype', 'Chaincode', 'Containercode', 'SalesVolume', 'UnitPrice', 'Sales'],
+        'card3': ['FyWeek', 'Fy', 'State', 'Store', 'Itemtype', 'Chaincode', 'SalesVolume', 'UnitPrice', 'Sales']  # Added for PE calculation card
     }
 
     # Choose columns based on the active card
@@ -57,7 +81,7 @@ def load_data(active_card):
     df = ddf.compute()
 
 
-    if active_card in ['card2']:
+    if active_card in ['card2','card3']:
         df = df.groupby(['FyWeek', 'Fy', 'Chaincode', 'Store', 'Address', 'Zipcode', 'City', 'State', 'Containercode', 'Itemtype'], observed=True).agg({
         'SalesVolume': 'sum',
         'UnitPrice': 'mean',
@@ -68,6 +92,9 @@ def load_data(active_card):
         df['Year'] = df['FY'].str[2:].astype(int)  # Extract year part and convert to int
         df['Dt'] = date_from_week(df['Year'], df['Week'])
 
+    # Add the region column based on state
+    df['Region'] = df['State'].map(state_to_region)
+
     # st.write(df.columns)
     return df
 
@@ -75,10 +102,9 @@ def load_data(active_card):
 st.image("bonnie.png", width=150)  # Adjust width as needed
 
 # Display title
-st.title("Bonnie Plants Pricing & Sales Analytics Dashboard")
+# st.title("Bonnie Plants Pricing & Sales Analytics Dashboard")
+st.title("Price vs. Sales Volume Tracker 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:
@@ -90,7 +116,7 @@ if 'selected_feature' not in st.session_state:
     st.session_state['selected_feature'] = 'Chaincode'  # Default to 'Chain Code'
 
 # Card selection buttons
-col1, col2 = st.columns(2)
+col1, col2 ,col3= st.columns(3)
 # Define buttons for plot categories, update session state when clicked
 with col1:
     if st.button("Sales Volume Trend for Item Category"):
@@ -99,7 +125,10 @@ with col1:
 with col2:
     if st.button("Sales Volume & Unit Price Correlation for Item Category and Container Code"):
         st.session_state['active_card'] = 'card2'
-
+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'])
 df = load_data(st.session_state['active_card'])
@@ -246,3 +275,58 @@ if st.session_state['active_card'] == 'card2':
 
 
 ##########################################################################################################
+
+if st.session_state['active_card'] == 'card3':
+    # Dropdown for selecting the item type
+    item_type_options = df['Itemtype'].unique()
+    selected_item_type = st.selectbox("Select Item Type", item_type_options)
+
+    # Dropdown for selecting the region (multiple selection allowed)
+    region_options = df['Region'].unique()
+    selected_regions = st.multiselect("Select Region(s)", region_options, default=region_options)
+
+    # Filter data based on selected item type and selected regions
+    filtered_df = df[(df['Itemtype'] == selected_item_type) & (df['Region'].isin(selected_regions))]
+
+    # Group by Year, Region, Itemtype and Promo, and aggregate SalesVolume and UnitPrice
+    agg_df = filtered_df.groupby(['Fy', 'Region', 'Itemtype',]).agg({
+        'SalesVolume': 'sum',
+        'UnitPrice': 'mean'
+    }).reset_index()
+
+    # Sort values by Region, Itemtype, Fy, and Promo for YOY calculation
+    agg_df = agg_df.sort_values(by=['Region', 'Itemtype', 'Fy',])
+
+    # Calculate YOY percentage changes in Sales Volume and Unit Price
+    agg_df['SalesVolume_pct_change'] = agg_df.groupby(['Region', 'Itemtype',])['SalesVolume'].pct_change().round(3) * 100
+    agg_df['UnitPrice_pct_change'] = agg_df.groupby(['Region', 'Itemtype', ])['UnitPrice'].pct_change().round(3) * 100
+
+    # Calculate Price Elasticity Coefficient (PE)
+    agg_df['PE_Coeff'] = (agg_df['SalesVolume_pct_change'] / agg_df['UnitPrice_pct_change']).round(2)
+
+    # Exclude FY 2025 but keep FY 2021 even with NaN values
+    agg_df_filtered = agg_df[agg_df['Fy'] != 'FY 2025']
+
+    # Drop rows where PE_Coeff is NaN (optional)
+    agg_df_filtered = agg_df_filtered.dropna(subset=['PE_Coeff'])
+    st.dataframe(agg_df_filtered)
+    st.write(agg_df_filtered.shape)
+    # Plot the PE Coefficient with Plotly
+    fig = px.line(
+        agg_df_filtered, 
+        x='Fy', 
+        y='PE_Coeff',  # Differentiate between Promo and NoPromo
+        line_dash='Region',  # Differentiate lines by Region
+        title=f"Price Elasticity Coefficient (PE) by Year for {selected_item_type}",
+        labels={'Fy': 'Fiscal Year', 'PE_Coeff': 'Price Elasticity Coefficient'},
+        markers=True
+    )
+
+    # Customize layout and show plot
+    fig.update_layout(
+        height=600,
+        width=1000,
+    )
+
+    st.plotly_chart(fig, use_container_width=True)
+    ###################################################################################################################