datanalysis.py

import streamlit as st
import pandas as pd
import numpy as np
import plotly.graph_objects as go
from datetime import datetime, timedelta

st.set_page_config(layout="wide", page_title="Business Analytics Dashboard Tutorial")

# Sample business data generation
def generate_sales_data():
    dates = pd.date_range(start='2024-01-01', end='2024-12-31', freq='D')
    np.random.seed(42)
    
    df = pd.DataFrame({
        'Date': dates,
        'Sales': np.random.normal(1000, 200, len(dates)),
        'Region': np.random.choice(['North', 'South', 'East', 'West'], len(dates)),
        'Product': np.random.choice(['Electronics', 'Clothing', 'Food', 'Books'], len(dates)),
        'Customer_Type': np.random.choice(['Retail', 'Wholesale'], len(dates)),
    })
    df['Profit'] = df['Sales'] * np.random.uniform(0.15, 0.25, len(df))
    return df

# Main Navigation
st.title("📊 Business Analytics & Data Analysis Tutorial")

# 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}%"
    )

# Sales Trends
st.subheader("Sales Trends Analysis")
daily_sales = filtered_df.groupby('Date')[['Sales', 'Profit']].sum().reset_index()

# Create the figure ensuring dates are in datetime format
fig = go.Figure()

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
    )
)

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
st.markdown("---")
st.markdown(f"Dashboard last updated: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")