Update app.py

app.py

@@ -12,39 +12,64 @@ if uploaded_file:
     # Load Data
     df = pd.read_excel(uploaded_file, sheet_name=0)
 
+    # Display the first few rows of the dataframe to understand its structure
+    st.write("Preview of the uploaded data:")
+    st.dataframe(df.head())
+
     # Data Preprocessing
-    df['INVOICE_DATE'] = pd.to_datetime(df['INVOICE_DATE'])
-    df['YEAR'] = df['INVOICE_DATE'].dt.year
-    df['MONTH'] = df['INVOICE_DATE'].dt.month
+    # Convert 'Date' to datetime
+    df['Date'] = pd.to_datetime(df['Date'])
+
+    # Extract year and month for further analysis
+    df['Year'] = df['Date'].dt.year
+    df['Month'] = df['Date'].dt.month
 
-    # Clean whitespace and ensure consistent case in 'CUSTOMER_NAME' and 'DESCRIPTION'
-    df['CUSTOMER_NAME'] = df['CUSTOMER_NAME'].str.strip().str.lower()
-    df['DESCRIPTION'] = df['DESCRIPTION'].str.strip().str.lower()
+    # Clean whitespace and ensure consistent case in 'Customer Name' and 'Product Name'
+    df['Customer Name'] = df['Customer Name'].str.strip().str.lower()
+    df['Product Name'] = df['Product Name'].str.strip().str.lower()
+    df['City'] = df['City'].str.strip().str.lower()
+    df['Country'] = df['Country'].str.strip().str.lower()
+    df['State'] = df['State'].str.strip().str.lower()
 
     # Sidebar Filters
     st.sidebar.header("Filter Options")
 
-    # Text Input for Customer and Product
+    # Text Input for Customer, Product, City, Country, and State
     customer_query = st.sidebar.text_input('Enter Customer Name (partial or full):').strip().lower()
     product_query = st.sidebar.text_input('Enter Product Name (partial or full):').strip().lower()
+    city_query = st.sidebar.text_input('Enter City (partial or full):').strip().lower()
+    country_query = st.sidebar.text_input('Enter Country (partial or full):').strip().lower()
+    state_query = st.sidebar.text_input('Enter State (partial or full):').strip().lower()
 
     # Date Range Selection
-    start_date = st.sidebar.date_input('Start Date:', df['INVOICE_DATE'].min())
-    end_date = st.sidebar.date_input('End Date:', df['INVOICE_DATE'].max())
+    start_date = st.sidebar.date_input('Start Date:', df['Date'].min())
+    end_date = st.sidebar.date_input('End Date:', df['Date'].max())
 
     # Filter Data by Date Range
     filtered_df = df[
-        (df['INVOICE_DATE'] >= pd.to_datetime(start_date)) &
-        (df['INVOICE_DATE'] <= pd.to_datetime(end_date))
+        (df['Date'] >= pd.to_datetime(start_date)) &
+        (df['Date'] <= pd.to_datetime(end_date))
     ]
 
     # Filter Data by Customer Name
     if customer_query:
-        filtered_df = filtered_df[filtered_df['CUSTOMER_NAME'].str.contains(customer_query, case=False, na=False)]
+        filtered_df = filtered_df[filtered_df['Customer Name'].str.contains(customer_query, case=False, na=False)]
 
     # Filter Data by Product Name
     if product_query:
-        filtered_df = filtered_df[filtered_df['DESCRIPTION'].str.contains(product_query, case=False, na=False)]
+        filtered_df = filtered_df[filtered_df['Product Name'].str.contains(product_query, case=False, na=False)]
+
+    # Filter Data by City
+    if city_query:
+        filtered_df = filtered_df[filtered_df['City'].str.contains(city_query, case=False, na=False)]
+
+    # Filter Data by Country
+    if country_query:
+        filtered_df = filtered_df[filtered_df['Country'].str.contains(country_query, case=False, na=False)]
+
+    # Filter Data by State
+    if state_query:
+        filtered_df = filtered_df[filtered_df['State'].str.contains(state_query, case=False, na=False)]
 
     # Display Filtered Data
     st.write(f"Filtered Data: {len(filtered_df)} records found.")
@@ -53,24 +78,34 @@ if uploaded_file:
     # Visualizations
     if not filtered_df.empty:
         st.subheader("Sales Trend Over Time")
-        trend = filtered_df.groupby('INVOICE_DATE')['NSV'].sum().reset_index()
-        fig_trend = px.line(trend, x='INVOICE_DATE', y='NSV', title='Sales Over Time')
+        trend = filtered_df.groupby('Date')['Net Sales Value'].sum().reset_index()
+        fig_trend = px.line(trend, x='Date', y='Net Sales Value', title='Sales Over Time')
         st.plotly_chart(fig_trend)
 
         st.subheader("Top 10 Products by Sales")
-        top_products = filtered_df.groupby('DESCRIPTION')['NSV'].sum().nlargest(10).reset_index()
-        fig_top_products = px.bar(top_products, x='DESCRIPTION', y='NSV', title='Top 10 Products')
+        top_products = filtered_df.groupby('Product Name')['Net Sales Value'].sum().nlargest(10).reset_index()
+        fig_top_products = px.bar(top_products, x='Product Name', y='Net Sales Value', title='Top 10 Products')
         st.plotly_chart(fig_top_products)
 
-        st.subheader("Sales Distribution by Region")
-        region_sales = filtered_df.groupby('REIGON')['NSV'].sum().reset_index()
-        fig_region = px.pie(region_sales, names='REIGON', values='NSV', title='Sales by Region')
-        st.plotly_chart(fig_region)
+        st.subheader("Sales Distribution by Country")
+        country_sales = filtered_df.groupby('Country')['Net Sales Value'].sum().reset_index()
+        fig_country = px.pie(country_sales, names='Country', values='Net Sales Value', title='Sales by Country')
+        st.plotly_chart(fig_country)
+
+        st.subheader("Sales by City")
+        city_sales = filtered_df.groupby('City')['Net Sales Value'].sum().reset_index()
+        fig_city = px.bar(city_sales, x='City', y='Net Sales Value', title='Sales by City')
+        st.plotly_chart(fig_city)
 
         st.subheader("Monthly Sales Heatmap")
-        heatmap_data = filtered_df.pivot_table(values='NSV', index='MONTH', columns='YEAR', aggfunc='sum')
+        heatmap_data = filtered_df.pivot_table(values='Net Sales Value', index='Month', columns='Year', aggfunc='sum')
         fig_heatmap = px.imshow(heatmap_data, labels=dict(x="Year", y="Month", color="Sales"))
         st.plotly_chart(fig_heatmap)
+
+        st.subheader("Margin vs. Cost")
+        margin_cost = filtered_df.groupby('Product Name')[['Margin Amount', 'Cost']].sum().reset_index()
+        fig_margin_cost = px.scatter(margin_cost, x='Cost', y='Margin Amount', color='Product Name', title='Margin vs. Cost')
+        st.plotly_chart(fig_margin_cost)
     else:
         st.write("No data available for the selected filters.")
 else: