Create app.py

app.py

@@ -0,0 +1,67 @@
+import streamlit as st
+import pandas as pd
+import plotly.express as px
+
+# Title of the App
+st.title('Sales Data Visualization App')
+
+# Upload File
+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)
+
+    # 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())
+
+    # 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)]
+
+    # 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)
+
+    # 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)
+
+    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("Upload a file to begin.")