main.py

import pandas as pd
import matplotlib.pyplot as plt
import requests
from datetime import datetime, timedelta
import numpy as np

def load_data():
    """
    Fetch COVID-19 data from disease.sh API (Johns Hopkins CSSE data).
    Returns a pandas DataFrame with historical data.
    
    Note: Recent data may not include recovery figures as disease.sh API
    no longer tracks recoveries for most regions.
    """
    print("=" * 60)
    print("LOADING COVID-19 DATA FROM API")
    print("=" * 60)
    
    countries = ['USA', 'India', 'Brazil', 'UK', 'France', 'Germany', 'Italy', 'Spain', 'Canada', 'Australia']
    all_data = []
    
    for country in countries:
        try:
            url = f"https://disease.sh/v3/covid-19/historical/{country}?lastdays=90"
            response = requests.get(url)
            
            if response.status_code == 200:
                data = response.json()
                
                if 'timeline' not in data:
                    print(f"✗ No timeline data for {country}")
                    continue
                    
                timeline = data['timeline']
                
                if 'cases' not in timeline or 'deaths' not in timeline:
                    print(f"✗ Incomplete timeline data for {country}")
                    continue
                
                for date_str in timeline['cases'].keys():
                    all_data.append({
                        'date': date_str,
                        'region': country,
                        'cases': timeline['cases'].get(date_str, 0),
                        'deaths': timeline['deaths'].get(date_str, 0),
                        'recoveries': timeline.get('recovered', {}).get(date_str, 0)
                    })
                print(f"✓ Loaded data for {country}")
            else:
                print(f"✗ Failed to load data for {country} (HTTP {response.status_code})")
        except Exception as e:
            print(f"✗ Error loading {country}: {str(e)}")
    
    df = pd.DataFrame(all_data)
    print(f"\n✓ Successfully loaded {len(df)} records from {len(countries)} countries")
    return df

def clean_data(df):
    """
    Clean the COVID-19 data: handle missing values and convert dates.
    """
    print("\n" + "=" * 60)
    print("DATA CLEANING")
    print("=" * 60)
    
    print("\nMissing values before cleaning:")
    missing_values = df.isnull().sum()
    print(missing_values)
    
    df['recoveries'] = df['recoveries'].fillna(0)
    
    df['date'] = pd.to_datetime(df['date'], format='%m/%d/%y', errors='coerce')
    
    df = df.sort_values(['region', 'date']).reset_index(drop=True)
    
    print("\nMissing values after cleaning:")
    print(df.isnull().sum())
    
    print(f"\n✓ Data cleaned successfully")
    print(f"  - Date range: {df['date'].min().strftime('%Y-%m-%d')} to {df['date'].max().strftime('%Y-%m-%d')}")
    print(f"  - Regions: {df['region'].nunique()}")
    
    return df

def analyze_data(df):
    """
    Perform data analysis: calculate ratios, group by region, and compute correlations.
    """
    print("\n" + "=" * 60)
    print("DATA ANALYSIS")
    print("=" * 60)
    
    df['recovery_ratio'] = df.apply(lambda row: row['recoveries'] / row['cases'] if row['cases'] > 0 else 0, axis=1)
    df['death_rate'] = df.apply(lambda row: row['deaths'] / row['cases'] if row['cases'] > 0 else 0, axis=1)
    
    df_grouped = df.groupby('region').last().reset_index()
    regional_summary = df_grouped[['region', 'cases', 'deaths', 'recoveries']].copy()
    regional_summary = regional_summary.sort_values('cases', ascending=False)
    
    print("\nREGIONAL SUMMARY (Latest Data):")
    print("-" * 60)
    print(regional_summary.to_string(index=False))
    
    valid_data = df[(df['cases'] > 0) & (df['recovery_ratio'] > 0) & (df['death_rate'] > 0)]
    if len(valid_data) > 0:
        correlation = valid_data['recovery_ratio'].corr(valid_data['death_rate'])
        print(f"\n✓ Correlation between recovery ratio and death rate: {correlation:.4f}")
    else:
        print("\n⚠ Not enough valid data to calculate correlation")
        correlation = 0
    
    total_cases = regional_summary['cases'].sum()
    total_deaths = regional_summary['deaths'].sum()
    total_recoveries = regional_summary['recoveries'].sum()
    
    print(f"\nGLOBAL SUMMARY:")
    print(f"  - Total Cases: {total_cases:,}")
    print(f"  - Total Deaths: {total_deaths:,}")
    print(f"  - Total Recoveries: {total_recoveries:,}")
    print(f"  - Global Death Rate: {(total_deaths/total_cases*100):.2f}%")
    
    return df, regional_summary

def visualize_data(df, regional_summary):
    """
    Create visualizations: line plot for cases trend and bar chart for regional cases.
    """
    print("\n" + "=" * 60)
    print("DATA VISUALIZATION")
    print("=" * 60)
    
    plt.style.use('seaborn-v0_8-darkgrid')
    
    fig, ax = plt.subplots(figsize=(12, 6))
    for region in df['region'].unique():
        region_data = df[df['region'] == region].sort_values('date')
        ax.plot(region_data['date'], region_data['cases'], label=region, linewidth=2)
    
    ax.set_xlabel('Date', fontsize=12, fontweight='bold')
    ax.set_ylabel('Total Cases', fontsize=12, fontweight='bold')
    ax.set_title('COVID-19 Cases Trend Over Time by Country', fontsize=14, fontweight='bold')
    ax.legend(loc='upper left', framealpha=0.9)
    ax.grid(True, alpha=0.3)
    plt.xticks(rotation=45)
    plt.tight_layout()
    plt.savefig('cases_trend.png', dpi=300, bbox_inches='tight')
    plt.close()
    print("✓ Saved cases_trend.png")
    
    fig, ax = plt.subplots(figsize=(12, 6))
    top_regions = regional_summary.head(10)
    bars = ax.bar(range(len(top_regions)), top_regions['cases'], color='steelblue', edgecolor='navy', linewidth=1.5)
    ax.set_xlabel('Country', fontsize=12, fontweight='bold')
    ax.set_ylabel('Total Cases', fontsize=12, fontweight='bold')
    ax.set_title('COVID-19 Total Cases by Country (Top 10)', fontsize=14, fontweight='bold')
    ax.set_xticks(range(len(top_regions)))
    ax.set_xticklabels(top_regions['region'], rotation=45, ha='right')
    ax.grid(True, alpha=0.3, axis='y')
    
    for i, bar in enumerate(bars):
        height = bar.get_height()
        ax.text(bar.get_x() + bar.get_width()/2., height,
                f'{int(height):,}',
                ha='center', va='bottom', fontsize=9)
    
    plt.tight_layout()
    plt.savefig('regional_cases.png', dpi=300, bbox_inches='tight')
    plt.close()
    print("✓ Saved regional_cases.png")
    
    print("\n✓ Visualizations created successfully")

def save_to_excel(regional_summary):
    """
    Save the regional summary to an Excel file.
    """
    print("\n" + "=" * 60)
    print("EXCEL EXPORT")
    print("=" * 60)
    
    with pd.ExcelWriter('covid_summary.xlsx', engine='openpyxl') as writer:
        regional_summary.to_excel(writer, sheet_name='Regional Summary', index=False)
        
        workbook = writer.book
        worksheet = writer.sheets['Regional Summary']
        
        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
    
    print("✓ Saved covid_summary.xlsx")
    print("\n✓ Excel export completed successfully")

def main():
    """
    Main function to orchestrate the entire data analysis workflow.
    """
    print("\n" + "=" * 60)
    print("COVID-19 DATA ANALYSIS PROJECT")
    print("Data Source: disease.sh API (Johns Hopkins CSSE)")
    print("=" * 60)
    
    df = load_data()
    
    df = clean_data(df)
    
    df, regional_summary = analyze_data(df)
    
    visualize_data(df, regional_summary)
    
    save_to_excel(regional_summary)
    
    print("\n" + "=" * 60)
    print("ANALYSIS COMPLETE!")
    print("=" * 60)
    print("\nGenerated Files:")
    print("  1. cases_trend.png - Line chart showing cases over time")
    print("  2. regional_cases.png - Bar chart showing cases by country")
    print("  3. covid_summary.xlsx - Excel file with regional summary")
    print("\n" + "=" * 60)

if __name__ == "__main__":
    main()