Update app.py

app.py

@@ -10,58 +10,56 @@ uploaded_file = st.file_uploader("Upload your Excel file", type=["xlsx"])
 
 if uploaded_file:
     # Load Data
-    data = pd.ExcelFile(uploaded_file)
-    df = pd.read_excel(data, sheet_name=0)
+    df = pd.read_excel(uploaded_file, sheet_name=0)
 
     # 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
 
-    # Filters
-    year = st.sidebar.selectbox('Select Year:', sorted(df['YEAR'].unique()))
-    month = st.sidebar.multiselect('Select Month(s):', sorted(df['MONTH'].unique()))
-    region = st.sidebar.multiselect('Select Region(s):', df['REIGON'].unique())
-    category = st.sidebar.multiselect('Select Category:', df['PRODUCT_CATEGORY'].dropna().unique())
+    # User Inputs
+    st.sidebar.header("Filter Options")
+    product_query = st.sidebar.text_input('Product Name:')
+    customer_query = st.sidebar.text_input('Customer Name:')
+    start_date = st.sidebar.date_input('Start Date:', df['INVOICE_DATE'].min())
+    end_date = st.sidebar.date_input('End Date:', df['INVOICE_DATE'].max())
 
     # Filter Data
-    filtered_df = df[(df['YEAR'] == year)]
-    if month:
-        filtered_df = filtered_df[filtered_df['MONTH'].isin(month)]
-    if region:
-        filtered_df = filtered_df[filtered_df['REIGON'].isin(region)]
-    if category:
-        filtered_df = filtered_df[filtered_df['PRODUCT_CATEGORY'].isin(category)]
+    filtered_df = df[
+        (df['INVOICE_DATE'] >= pd.to_datetime(start_date)) &
+        (df['INVOICE_DATE'] <= pd.to_datetime(end_date))
+    ]
+    if product_query:
+        filtered_df = filtered_df[filtered_df['DESCRIPTION'].str.contains(product_query, case=False, na=False)]
+    if customer_query:
+        filtered_df = filtered_df[filtered_df['CUSTOMER_NAME'].str.contains(customer_query, case=False, na=False)]
 
-    # KPIs
-    total_sales = filtered_df['NSV'].sum()
-    total_quantity = filtered_df['QTY'].sum()
-    top_product = filtered_df.groupby('DESCRIPTION')['NSV'].sum().idxmax()
-
-    st.metric("Total Sales (NSV)", f"${total_sales:,.2f}")
-    st.metric("Total Quantity Sold", f"{total_quantity:,}")
-    st.metric("Top-Selling Product", top_product)
+    # Display Filtered Data
+    st.write(f"Filtered Data: {len(filtered_df)} records found.")
+    st.dataframe(filtered_df)
 
     # Visualizations
-    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')
-    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')
-    st.plotly_chart(fig_top_products)
+    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')
+        st.plotly_chart(fig_trend)
 
-    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("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')
+        st.plotly_chart(fig_top_products)
 
-    st.subheader("Monthly Sales Heatmap")
-    heatmap_data = filtered_df.pivot_table(values='NSV', 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("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("Monthly Sales Heatmap")
+        heatmap_data = filtered_df.pivot_table(values='NSV', 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)
+    else:
+        st.write("No data available for the selected filters.")
 else:
     st.write("Upload a file to begin.")