app.py

import streamlit as st
import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px
import plotly.graph_objects as go
from datetime import datetime, timedelta
import data_service
import os

st.set_page_config(
    page_title="COVID-19 Data Dashboard",
    page_icon="🦠",
    layout="wide",
    initial_sidebar_state="expanded"
)

st.title("🦠 COVID-19 Data Analysis Dashboard")
st.markdown("Real-time COVID-19 data from disease.sh API (Johns Hopkins CSSE)")

@st.cache_data(ttl=3600)
def load_and_process_data(countries, days):
    """Load and process data with caching."""
    df, errors = data_service.load_data(countries, days)
    if not df.empty:
        df = data_service.clean_data(df)
        df, regional_summary = data_service.analyze_data(df)
        return df, regional_summary, errors
    return pd.DataFrame(), pd.DataFrame(), errors

with st.sidebar:
    st.header("⚙️ Settings")
    
    all_countries = ['USA', 'India', 'Brazil', 'UK', 'France', 'Germany', 
                     'Italy', 'Spain', 'Canada', 'Australia', 'Mexico', 
                     'Russia', 'Japan', 'South Korea', 'Indonesia']
    
    selected_countries = st.multiselect(
        "Select Countries",
        all_countries,
        default=['USA', 'India', 'Brazil', 'UK', 'France', 'Germany', 'Italy', 'Spain', 'Canada', 'Australia']
    )
    
    days = st.slider("Days of Historical Data", 30, 365, 90)
    
    if st.button("🔄 Refresh Data", type="primary"):
        st.cache_data.clear()
        st.rerun()
    
    st.markdown("---")
    st.markdown("### 📊 Data Source")
    st.markdown("**API:** disease.sh")
    st.markdown("**Source:** Johns Hopkins CSSE")
    st.markdown("**Update:** Hourly")

if not selected_countries:
    st.warning("⚠️ Please select at least one country from the sidebar.")
    st.stop()

with st.spinner("Loading COVID-19 data..."):
    df, regional_summary, errors = load_and_process_data(tuple(selected_countries), days)

if errors:
    with st.expander("⚠️ Data Loading Warnings", expanded=False):
        for error in errors:
            st.warning(error)

if df.empty:
    st.error("❌ No data available. Please check your selections and try again.")
    st.stop()

global_stats = data_service.calculate_global_stats(regional_summary)
min_date, max_date = data_service.get_date_range(df)

st.markdown("### 📈 Global Statistics")
col1, col2, col3, col4 = st.columns(4)

with col1:
    st.metric(
        label="Total Cases",
        value=f"{global_stats['total_cases']:,}",
        delta=None
    )

with col2:
    st.metric(
        label="Total Deaths",
        value=f"{global_stats['total_deaths']:,}",
        delta=None
    )

with col3:
    st.metric(
        label="Death Rate",
        value=f"{global_stats['death_rate']:.2f}%",
        delta=None
    )

with col4:
    st.metric(
        label="Countries",
        value=len(selected_countries),
        delta=None
    )

st.markdown(f"**Data Range:** {min_date.strftime('%Y-%m-%d') if min_date else 'N/A'} to {max_date.strftime('%Y-%m-%d') if max_date else 'N/A'}")

st.markdown("---")

tab1, tab2, tab3 = st.tabs(["📊 Visualizations", "📋 Data Tables", "📥 Export"])

with tab1:
    st.markdown("### 📈 Cases Trend Over Time")
    
    fig = go.Figure()
    
    for country in selected_countries:
        country_data = data_service.get_country_data(df, country)
        if not country_data.empty:
            fig.add_trace(go.Scatter(
                x=country_data['date'],
                y=country_data['cases'],
                mode='lines',
                name=country,
                line=dict(width=2)
            ))
    
    fig.update_layout(
        xaxis_title="Date",
        yaxis_title="Total Cases",
        hovermode='x unified',
        height=500,
        legend=dict(
            orientation="h",
            yanchor="bottom",
            y=1.02,
            xanchor="right",
            x=1
        )
    )
    
    st.plotly_chart(fig, width='stretch')
    
    st.markdown("### 📊 Total Cases by Country")
    
    fig2 = px.bar(
        regional_summary.head(10),
        x='region',
        y='cases',
        title='Top 10 Countries by Total Cases',
        labels={'region': 'Country', 'cases': 'Total Cases'},
        color='cases',
        color_continuous_scale='Reds'
    )
    
    fig2.update_layout(height=500)
    st.plotly_chart(fig2, width='stretch')
    
    col1, col2 = st.columns(2)
    
    with col1:
        st.markdown("### 💀 Deaths by Country")
        fig3 = px.pie(
            regional_summary.head(10),
            values='deaths',
            names='region',
            title='Death Distribution (Top 10 Countries)'
        )
        fig3.update_traces(textposition='inside', textinfo='percent+label')
        st.plotly_chart(fig3, width='stretch')
    
    with col2:
        st.markdown("### 📉 Death Rate by Country")
        regional_summary_copy = regional_summary.copy()
        regional_summary_copy['death_rate_pct'] = (
            regional_summary_copy['deaths'] / regional_summary_copy['cases'] * 100
        )
        fig4 = px.bar(
            regional_summary_copy.head(10),
            x='region',
            y='death_rate_pct',
            title='Death Rate by Country (%)',
            labels={'region': 'Country', 'death_rate_pct': 'Death Rate (%)'},
            color='death_rate_pct',
            color_continuous_scale='OrRd'
        )
        st.plotly_chart(fig4, width='stretch')

with tab2:
    st.markdown("### 📋 Regional Summary")
    
    display_df = regional_summary.copy()
    display_df['Death Rate (%)'] = (display_df['deaths'] / display_df['cases'] * 100).round(2)
    display_df['Recovery Rate (%)'] = (display_df['recoveries'] / display_df['cases'] * 100).round(2)
    
    display_df = display_df.rename(columns={
        'region': 'Country',
        'cases': 'Total Cases',
        'deaths': 'Total Deaths',
        'recoveries': 'Total Recoveries'
    })
    
    st.dataframe(
        display_df,
        width='stretch',
        hide_index=True,
        column_config={
            "Total Cases": st.column_config.NumberColumn(format="%d"),
            "Total Deaths": st.column_config.NumberColumn(format="%d"),
            "Total Recoveries": st.column_config.NumberColumn(format="%d"),
            "Death Rate (%)": st.column_config.NumberColumn(format="%.2f%%"),
            "Recovery Rate (%)": st.column_config.NumberColumn(format="%.2f%%"),
        }
    )
    
    st.markdown("### 📊 Detailed Timeline Data")
    
    search_country = st.selectbox("Select country to view detailed timeline:", selected_countries)
    
    if search_country:
        country_detail = data_service.get_country_data(df, search_country)
        
        if not country_detail.empty:
            detail_display = country_detail[['date', 'cases', 'deaths', 'recoveries', 'death_rate']].copy()
            detail_display['death_rate'] = (detail_display['death_rate'] * 100).round(2)
            detail_display = detail_display.rename(columns={
                'date': 'Date',
                'cases': 'Cases',
                'deaths': 'Deaths',
                'recoveries': 'Recoveries',
                'death_rate': 'Death Rate (%)'
            })
            
            st.dataframe(
                detail_display,
                width='stretch',
                hide_index=True,
                height=400
            )

with tab3:
    st.markdown("### 📥 Export Data")
    
    col1, col2 = st.columns(2)
    
    with col1:
        st.markdown("#### Regional Summary")
        csv_regional = regional_summary.to_csv(index=False)
        st.download_button(
            label="📥 Download Regional Summary (CSV)",
            data=csv_regional,
            file_name=f"covid_regional_summary_{datetime.now().strftime('%Y%m%d')}.csv",
            mime="text/csv"
        )
    
    with col2:
        st.markdown("#### Full Dataset")
        csv_full = df.to_csv(index=False)
        st.download_button(
            label="📥 Download Full Dataset (CSV)",
            data=csv_full,
            file_name=f"covid_full_data_{datetime.now().strftime('%Y%m%d')}.csv",
            mime="text/csv"
        )
    
    st.markdown("#### Excel Export")
    
    if st.button("📊 Generate Excel Report"):
        with st.spinner("Generating Excel report..."):
            try:
                output_file = f"outputs/covid_summary_{datetime.now().strftime('%Y%m%d_%H%M%S')}.xlsx"
                os.makedirs("outputs", exist_ok=True)
                
                with pd.ExcelWriter(output_file, engine='openpyxl') as writer:
                    regional_summary.to_excel(writer, sheet_name='Regional Summary', index=False)
                    df.to_excel(writer, sheet_name='Full Data', index=False)
                    
                    for worksheet in writer.sheets.values():
                        for column in worksheet.columns:
                            max_length = 0
                            column_letter = column[0].column_letter
                            for cell in column:
                                try:
                                    if len(str(cell.value)) > max_length:
                                        max_length = len(str(cell.value))
                                except:
                                    pass
                            adjusted_width = min(max_length + 2, 50)
                            worksheet.column_dimensions[column_letter].width = adjusted_width
                
                st.success(f"✅ Excel report generated: {output_file}")
                
                with open(output_file, 'rb') as f:
                    st.download_button(
                        label="📥 Download Excel Report",
                        data=f,
                        file_name=f"covid_report_{datetime.now().strftime('%Y%m%d')}.xlsx",
                        mime="application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
                    )
            except Exception as e:
                st.error(f"❌ Error generating Excel: {str(e)}")

st.markdown("---")
st.markdown(
    """
    <div style='text-align: center; color: gray;'>
        <p>Data provided by disease.sh API | Updated hourly</p>
        <p>Note: Recovery data may not be available for all regions</p>
    </div>
    """,
    unsafe_allow_html=True
)