Update app.py

app.py

@@ -1,120 +1,122 @@
 import streamlit as st
 import pandas as pd
 import plotly.express as px
+import plotly.graph_objects as go
 import random
 from datetime import datetime, timedelta
 
-# Sample Data Generation (You can remove this part when uploading your own file)
-def generate_sample_data():
-    customers = ['Customer A', 'Customer B', 'Customer C', 'Customer D']
-    products = ['Product 1', 'Product 2', 'Product 3', 'Product 4']
-    cities = ['City 1', 'City 2', 'City 3', 'City 4']
-    states = ['State 1', 'State 2', 'State 3', 'State 4']
-    countries = ['Country 1', 'Country 2', 'Country 3', 'Country 4']
-    
-    # Generate sample sales data for 100 records
-    data = []
-    for i in range(100):
-        customer = random.choice(customers)
-        product = random.choice(products)
-        city = random.choice(cities)
-        state = random.choice(states)
-        country = random.choice(countries)
-        date = datetime.today() - timedelta(days=random.randint(1, 365))
-        nsv = random.randint(1000, 10000)  # Net Sales Value
-        cost = random.randint(500, 7000)  # Cost
-        data.append([customer, product, city, state, country, date, nsv, cost])
-    
-    columns = ['Customer Name', 'Product Name', 'City', 'State', 'Country', 'Date', 'Net Sales Value', 'Cost']
-    return pd.DataFrame(data, columns=columns)
-
-# Load sample data
-df = generate_sample_data()
-
-# Data Preprocessing
-df['Date'] = pd.to_datetime(df['Date'])
-df['Year'] = df['Date'].dt.year
-df['Month'] = df['Date'].dt.month
-
-# Sidebar Filters
-st.sidebar.header("Filter Options")
-
-# Text Input for Customer and Product
-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()
-state_query = st.sidebar.text_input('Enter State (partial or full):').strip().lower()
-country_query = st.sidebar.text_input('Enter Country (partial or full):').strip().lower()
-
-# Date Range Selection
-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['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)]
-
-# Filter Data by Product Name
-if product_query:
-    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 State
-if state_query:
-    filtered_df = filtered_df[filtered_df['State'].str.contains(state_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)]
-
-# Add 'Net Sales Value - Cost' as a new column
-filtered_df['Net Sales Value - Cost'] = filtered_df['Net Sales Value'] - filtered_df['Cost']
-
-# Display Filtered Data
-st.write(f"Filtered Data: {len(filtered_df)} records found.")
-st.dataframe(filtered_df)
-
-if not filtered_df.empty:
-    # KPI Metrics
-    st.subheader("Key Financial Metrics")
-
-    # Profit for the Year (Calculated as Net Sales Value - Cost)
-    profit_for_the_year = filtered_df['Net Sales Value'] - filtered_df['Cost']
-    st.metric("Profit for the Year", f"${profit_for_the_year.sum():,.2f}")
-
-    # Gross Margin (Net Sales Value - Cost)
-    gross_margin = filtered_df['Net Sales Value'] - filtered_df['Cost']
-    st.metric("Gross Margin", f"${gross_margin.sum():,.2f}")
-
-    # Total Sales
-    total_sales = filtered_df['Net Sales Value'].sum()
-    st.metric("Total Sales", f"${total_sales:,.2f}")
-
-    # Matrix View (like Power BI Matrix)
-    st.subheader("Matrix View of Financial Data")
-    matrix_data = filtered_df.pivot_table(
-        values='Net Sales Value', 
-        index=['Year', 'Customer Name'], 
-        columns=['Product Name'], 
-        aggfunc='sum', 
-        fill_value=0
-    )
-    st.dataframe(matrix_data)
-
-    # Visualization 4: Profit and Loss Overview (Simple Table)
-    st.subheader("Profit and Loss Overview")
-    pnl_data = filtered_df[['Customer Name', 'Product Name', 'Net Sales Value', 'Cost', 'Net Sales Value - Cost']]
-    pnl_data.columns = ['Customer', 'Product', 'Sales', 'Cost', 'Profit']
-    st.dataframe(pnl_data)
+# File upload functionality
+st.sidebar.header("Upload Data")
+uploaded_file = st.sidebar.file_uploader("Choose a CSV file", type=["csv"])
 
+# Check if file is uploaded
+if uploaded_file is not None:
+    # Load the data
+    df = pd.read_csv(uploaded_file)
+
+    # Convert Date to datetime format if it's in string format
+    if 'Date' in df.columns:
+        df['Date'] = pd.to_datetime(df['Date'])
+    
+    # Add 'Year' and 'Month' columns for easy filtering and analysis
+    df['Year'] = df['Date'].dt.year
+    df['Month'] = df['Date'].dt.month
+
+    # Sidebar Filters
+    st.sidebar.header("Filter Options")
+
+    # Text Input for Customer and Product
+    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()
+    state_query = st.sidebar.text_input('Enter State (partial or full):').strip().lower()
+    country_query = st.sidebar.text_input('Enter Country (partial or full):').strip().lower()
+
+    # Date Range Selection
+    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['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)]
+
+    # Filter Data by Product Name
+    if product_query:
+        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 State
+    if state_query:
+        filtered_df = filtered_df[filtered_df['State'].str.contains(state_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)]
+
+    # Add 'Net Sales Value - Cost' as a new column
+    filtered_df['Net Sales Value - Cost'] = filtered_df['Net Sales Value'] - filtered_df['Cost']
+
+    # Display Filtered Data
+    st.write(f"Filtered Data: {len(filtered_df)} records found.")
+    st.dataframe(filtered_df)
+
+    if not filtered_df.empty:
+        # KPI Metrics
+        st.subheader("Key Financial Metrics")
+
+        # Profit for the Year (Calculated as Net Sales Value - Cost)
+        profit_for_the_year = filtered_df['Net Sales Value'] - filtered_df['Cost']
+        st.metric("Profit for the Year", f"${profit_for_the_year.sum():,.2f}")
+
+        # Gross Margin (Net Sales Value - Cost)
+        gross_margin = filtered_df['Net Sales Value'] - filtered_df['Cost']
+        st.metric("Gross Margin", f"${gross_margin.sum():,.2f}")
+
+        # Total Sales
+        total_sales = filtered_df['Net Sales Value'].sum()
+        st.metric("Total Sales", f"${total_sales:,.2f}")
+
+        # Visualization 1: Profit and Loss Overview (Table)
+        st.subheader("Profit and Loss Overview")
+        pnl_data = filtered_df[['Customer Name', 'Product Name', 'Net Sales Value', 'Cost', 'Net Sales Value - Cost']]
+        pnl_data.columns = ['Customer', 'Product', 'Sales', 'Cost', 'Profit']
+        st.dataframe(pnl_data)
+
+        # Visualization 2: Matrix View (like Power BI Matrix)
+        st.subheader("Matrix View of Financial Data")
+        matrix_data = filtered_df.pivot_table(
+            values='Net Sales Value', 
+            index=['Year', 'Customer Name'], 
+            columns=['Product Name'], 
+            aggfunc='sum', 
+            fill_value=0
+        )
+        st.dataframe(matrix_data)
+
+        # Visualization 3: Sales Trend over Time
+        st.subheader("Sales Trend over Time")
+        sales_trend = filtered_df.groupby(['Year', 'Month'])['Net Sales Value'].sum().reset_index()
+        fig = px.line(sales_trend, x='Month', y='Net Sales Value', color='Year', title="Sales Trend over Time")
+        st.plotly_chart(fig)
+
+        # Visualization 4: Profit Margin Visualization (Bar Chart)
+        st.subheader("Profit Margin per Product")
+        profit_margin_data = filtered_df.groupby('Product Name').apply(
+            lambda x: (x['Net Sales Value'] - x['Cost']).sum() / x['Net Sales Value'].sum()
+        ).reset_index(name="Profit Margin")
+        fig = px.bar(profit_margin_data, x='Product Name', y='Profit Margin', title="Profit Margin per Product")
+        st.plotly_chart(fig)
+
+    else:
+        st.write("No data available for the selected filters.")
 else:
-    st.write("No data available for the selected filters.")
+    st.write("Please upload a CSV file to get started.")