2024 Dec 30 : version app updated

Signed-off-by: Milind Kamat <36366961+milindkamat0507@users.noreply.github.com>

app.py

@@ -1,7 +1,6 @@
 import streamlit as st
 import pandas as pd
 import numpy as np
-import plotly.express as px
 import plotly.graph_objects as go
 from datetime import datetime, timedelta
 
@@ -25,243 +24,138 @@ def generate_sales_data():
 # Main Navigation
 st.title("📊 Business Analytics & Data Analysis Tutorial")
 
-tabs = st.tabs([
-    "Business Dashboard",
-    "Data Analysis",
-    "Financial Metrics",
-    "Practice Zone"
-])
+# Generate sample data
+df_sales = generate_sales_data()
 
-# Tab 1: Business Dashboard
-with tabs[0]:
-    st.header("Creating Business Dashboards")
-    st.write("Learn how to build interactive business dashboards with Streamlit")
-    
-    # Generate sample data
-    df_sales = generate_sales_data()
-    
-    # Dashboard filters
-    col1, col2, col3 = st.columns(3)
-    with col1:
-        selected_region = st.multiselect(
-            "Select Region",
-            df_sales['Region'].unique(),
-            default=df_sales['Region'].unique()[0]
-        )
-    with col2:
-        date_range = st.date_input(
-            "Select Date Range",
-            value=(df_sales['Date'].min(), df_sales['Date'].max())
-        )
-    with col3:
-        product_type = st.selectbox(
-            "Select Product",
-            ['All'] + list(df_sales['Product'].unique())
-        )
-    
-    # Filter data based on selections
-    mask = (df_sales['Region'].isin(selected_region)) & \
-           (df_sales['Date'] >= pd.Timestamp(date_range[0])) & \
-           (df_sales['Date'] <= pd.Timestamp(date_range[1]))
-    
-    if product_type != 'All':
-        mask &= (df_sales['Product'] == product_type)
-    
-    filtered_df = df_sales[mask]
-    
-    # KPI Metrics
-    st.subheader("Key Performance Indicators")
-    kpi1, kpi2, kpi3, kpi4 = st.columns(4)
-    
-    with kpi1:
-        st.metric(
-            "Total Sales",
-            f"${filtered_df['Sales'].sum():,.0f}",
-            f"{((filtered_df['Sales'].sum() / df_sales['Sales'].sum()) - 1) * 100:.1f}%"
-        )
-    with kpi2:
-        st.metric(
-            "Average Daily Sales",
-            f"${filtered_df['Sales'].mean():,.0f}",
-            f"{((filtered_df['Sales'].mean() / df_sales['Sales'].mean()) - 1) * 100:.1f}%"
-        )
-    with kpi3:
-        st.metric(
-            "Total Profit",
-            f"${filtered_df['Profit'].sum():,.0f}",
-            f"{((filtered_df['Profit'].sum() / df_sales['Profit'].sum()) - 1) * 100:.1f}%"
-        )
-    with kpi4:
-        st.metric(
-            "Profit Margin",
-            f"{(filtered_df['Profit'].sum() / filtered_df['Sales'].sum() * 100):.1f}%"
-        )
+# Dashboard filters
+col1, col2, col3 = st.columns(3)
+with col1:
+    selected_region = st.multiselect(
+        "Select Region",
+        df_sales['Region'].unique(),
+        default=df_sales['Region'].unique()[0]
+    )
+with col2:
+    date_range = st.date_input(
+        "Select Date Range",
+        value=(df_sales['Date'].min(), df_sales['Date'].max())
+    )
+with col3:
+    product_type = st.selectbox(
+        "Select Product",
+        ['All'] + list(df_sales['Product'].unique())
+    )
 
-    # Sales Trends
-    st.subheader("Sales Trends Analysis")
-    daily_sales = filtered_df.groupby('Date')[['Sales', 'Profit']].sum().reset_index()
-    
-    fig = go.Figure()
-    fig.add_trace(go.Scatter(
-        x=daily_sales['Date'],
-        y=daily_sales['Sales'],
-        name='Sales',
-        line=dict(color='blue')
-    ))
-    fig.add_trace(go.Scatter(
-        x=daily_sales['Date'],
-        y=daily_sales['Profit'],
-        name='Profit',
-        line=dict(color='green')
-    ))
-    fig.update_layout(title='Daily Sales and Profit Trends')
-    st.plotly_chart(fig, use_container_width=True)
+# Filter data based on selections
+mask = (df_sales['Region'].isin(selected_region)) & \
+       (df_sales['Date'] >= pd.Timestamp(date_range[0])) & \
+       (df_sales['Date'] <= pd.Timestamp(date_range[1]))
 
-# Tab 2: Data Analysis
-with tabs[1]:
-    st.header("Advanced Data Analysis")
-    
-    analysis_type = st.selectbox(
-        "Choose Analysis Type",
-        ["Time Series Analysis", "Regional Performance", "Product Analysis"]
+if product_type != 'All':
+    mask &= (df_sales['Product'] == product_type)
+
+filtered_df = df_sales[mask]
+
+# KPI Metrics
+st.subheader("Key Performance Indicators")
+kpi1, kpi2, kpi3, kpi4 = st.columns(4)
+
+with kpi1:
+    st.metric(
+        "Total Sales",
+        f"${filtered_df['Sales'].sum():,.0f}",
+        f"{((filtered_df['Sales'].sum() / df_sales['Sales'].sum()) - 1) * 100:.1f}%"
+    )
+with kpi2:
+    st.metric(
+        "Average Daily Sales",
+        f"${filtered_df['Sales'].mean():,.0f}",
+        f"{((filtered_df['Sales'].mean() / df_sales['Sales'].mean()) - 1) * 100:.1f}%"
+    )
+with kpi3:
+    st.metric(
+        "Total Profit",
+        f"${filtered_df['Profit'].sum():,.0f}",
+        f"{((filtered_df['Profit'].sum() / df_sales['Profit'].sum()) - 1) * 100:.1f}%"
+    )
+with kpi4:
+    st.metric(
+        "Profit Margin",
+        f"{(filtered_df['Profit'].sum() / filtered_df['Sales'].sum() * 100):.1f}%"
     )
-    
-    if analysis_type == "Time Series Analysis":
-        st.subheader("Time Series Decomposition")
-        # Monthly aggregation
-        monthly_sales = df_sales.groupby(df_sales['Date'].dt.to_period('M')).agg({
-            'Sales': 'sum',
-            'Profit': 'sum'
-        }).reset_index()
-        
-        # Rolling averages
-        window_size = st.slider("Moving Average Window (months)", 1, 12, 3)
-        monthly_sales['Sales_MA'] = monthly_sales['Sales'].rolling(window=window_size).mean()
-        
-        fig = px.line(monthly_sales, 
-                     x='Date', 
-                     y=['Sales', 'Sales_MA'],
-                     title=f'Monthly Sales with {window_size}-Month Moving Average')
-        st.plotly_chart(fig, use_container_width=True)
 
-    elif analysis_type == "Regional Performance":
-        st.subheader("Regional Sales Distribution")
-        
-        regional_sales = df_sales.groupby('Region').agg({
-            'Sales': 'sum',
-            'Profit': 'sum'
-        }).reset_index()
-        
-        fig = px.scatter(regional_sales, 
-                        x='Sales', 
-                        y='Profit',
-                        size='Sales',
-                        color='Region',
-                        title='Regional Sales vs Profit')
-        st.plotly_chart(fig, use_container_width=True)
+# Sales Trends
+st.subheader("Sales Trends Analysis")
+daily_sales = filtered_df.groupby('Date')[['Sales', 'Profit']].sum().reset_index()
 
-# Tab 3: Financial Metrics
-with tabs[2]:
-    st.header("Financial Analysis Tools")
-    
-    # ROI Calculator
-    st.subheader("ROI Calculator")
-    col1, col2 = st.columns(2)
-    with col1:
-        investment = st.number_input("Initial Investment ($)", min_value=0, value=10000)
-        revenue = st.number_input("Expected Revenue ($)", min_value=0, value=15000)
-    with col2:
-        costs = st.number_input("Operating Costs ($)", min_value=0, value=5000)
-        time_period = st.number_input("Time Period (years)", min_value=1, value=1)
-    
-    roi = ((revenue - costs - investment) / investment) * 100
-    st.metric("ROI (%)", f"{roi:.1f}%")
-    
-    # Break-even Analysis
-    st.subheader("Break-even Analysis")
-    fixed_costs = st.number_input("Fixed Costs ($)", min_value=0, value=50000)
-    unit_price = st.number_input("Unit Price ($)", min_value=0, value=100)
-    unit_cost = st.number_input("Unit Variable Cost ($)", min_value=0, value=60)
-    
-    break_even_units = fixed_costs / (unit_price - unit_cost)
-    st.metric("Break-even Point (units)", f"{break_even_units:,.0f}")
+# Create the figure ensuring dates are in datetime format
+fig = go.Figure()
 
-# Tab 4: Practice Zone
-with tabs[3]:
-    st.header("Practice Exercises")
-    
-    exercise = st.selectbox(
-        "Select Exercise",
-        ["Sales Dashboard", "Financial Analysis", "Customer Segmentation"]
+fig.add_trace(go.Scatter(
+    x=daily_sales['Date'].dt.strftime('%Y-%m-%d'),  # Convert to string format
+    y=daily_sales['Sales'],
+    name='Sales',
+    line=dict(color='blue')
+))
+
+fig.add_trace(go.Scatter(
+    x=daily_sales['Date'].dt.strftime('%Y-%m-%d'),  # Convert to string format
+    y=daily_sales['Profit'],
+    name='Profit',
+    line=dict(color='green')
+))
+
+fig.update_layout(
+    title='Daily Sales and Profit Trends',
+    xaxis_title='Date',
+    yaxis_title='Amount ($)',
+    xaxis=dict(
+        type='category',  # Use category type for x-axis
+        tickangle=45
     )
-    
-    if exercise == "Sales Dashboard":
-        st.markdown("""
-        ### Exercise: Create a Sales Dashboard
-        
-        Create a dashboard that shows:
-        1. Total sales by region
-        2. Monthly sales trend
-        3. Top-selling products
-        
-        ```python
-        # Sample code to get started
-        import streamlit as st
-        import pandas as pd
-        
-        # Load your data
-        df = pd.DataFrame({
-            'Date': dates,
-            'Sales': values,
-            'Region': regions
-        })
-        
-        # Create visualizations
-        st.line_chart(df.set_index('Date')['Sales'])
-        ```
-        """)
-    
-    # Code input and execution area
-    st.subheader("Your Code")
-    user_code = st.text_area("Write your code here:", height=200)
-    if st.button("Run Analysis"):
-        try:
-            with st.container(border=True):
-                exec(user_code)
-        except Exception as e:
-            st.error(f"Error: {str(e)}")
+)
 
-# Documentation
-with st.expander("📚 Documentation & Tips"):
-    st.markdown("""
-    ### Business Analytics Best Practices
-    
-    1. **Data Preparation**
-    - Always clean and validate your data
-    - Handle missing values appropriately
-    - Consider seasonality in time series data
-    
-    2. **Visualization Guidelines**
-    - Choose appropriate chart types
-    - Use consistent color schemes
-    - Include clear labels and titles
-    
-    3. **Financial Analysis**
-    - Document all assumptions
-    - Include sensitivity analysis
-    - Provide context for metrics
-    
-    4. **Dashboard Design**
-    - Keep it simple and focused
-    - Provide interactive filters
-    - Update in real-time
-    """)
+st.plotly_chart(fig, use_container_width=True)
+
+# Regional Analysis
+st.subheader("Regional Performance")
+regional_data = filtered_df.groupby('Region').agg({
+    'Sales': 'sum',
+    'Profit': 'sum'
+}).reset_index()
+
+fig_region = go.Figure(data=[
+    go.Bar(name='Sales', x=regional_data['Region'], y=regional_data['Sales']),
+    go.Bar(name='Profit', x=regional_data['Region'], y=regional_data['Profit'])
+])
+
+fig_region.update_layout(
+    barmode='group',
+    title='Sales and Profit by Region'
+)
+
+st.plotly_chart(fig_region, use_container_width=True)
+
+# Product Analysis
+if product_type == 'All':
+    st.subheader("Product Performance")
+    product_data = filtered_df.groupby('Product').agg({
+        'Sales': 'sum',
+        'Profit': 'sum'
+    }).reset_index()
+
+    fig_product = go.Figure(data=[
+        go.Bar(name='Sales', x=product_data['Product'], y=product_data['Sales']),
+        go.Bar(name='Profit', x=product_data['Product'], y=product_data['Profit'])
+    ])
+
+    fig_product.update_layout(
+        barmode='group',
+        title='Sales and Profit by Product'
+    )
+
+    st.plotly_chart(fig_product, use_container_width=True)
 
-# Footer with additional resources
+# Footer
 st.markdown("---")
-st.markdown("""
-<div style='text-align: center'>
-    <p>📈 For more business analytics resources, visit our documentation</p>
-    <p>Last updated: {}</p>
-</div>
-""".format(datetime.now().strftime("%Y-%m-%d")), unsafe_allow_html=True)
+st.markdown(f"Dashboard last updated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")