data_service.py

import pandas as pd
import requests
from datetime import datetime, timedelta

def load_data(countries=None, days=90):
    """
    Fetch COVID-19 data from disease.sh API (Johns Hopkins CSSE data).
    Returns a pandas DataFrame with historical data.
    
    Args:
        countries: List of country names. Defaults to top 10 countries.
        days: Number of days of historical data to fetch. Defaults to 90.
    
    Note: Recent data may not include recovery figures as disease.sh API
    no longer tracks recoveries for most regions.
    """
    if countries is None:
        countries = ['USA', 'India', 'Brazil', 'UK', 'France', 'Germany', 'Italy', 'Spain', 'Canada', 'Australia']
    
    all_data = []
    errors = []
    
    for country in countries:
        try:
            url = f"https://disease.sh/v3/covid-19/historical/{country}?lastdays={days}"
            response = requests.get(url, timeout=10)
            
            if response.status_code == 200:
                data = response.json()
                
                if 'timeline' not in data:
                    errors.append(f"No timeline data for {country}")
                    continue
                    
                timeline = data['timeline']
                
                if 'cases' not in timeline or 'deaths' not in timeline:
                    errors.append(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)
                    })
            else:
                errors.append(f"Failed to load {country} (HTTP {response.status_code})")
        except Exception as e:
            errors.append(f"Error loading {country}: {str(e)}")
    
    df = pd.DataFrame(all_data)
    return df, errors

def clean_data(df):
    """
    Clean the COVID-19 data: handle missing values and convert dates.
    """
    if df.empty:
        return df
    
    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)
    
    return df

def analyze_data(df):
    """
    Perform data analysis: calculate ratios, group by region, and compute correlations.
    Returns analyzed DataFrame and regional summary.
    """
    if df.empty:
        return df, pd.DataFrame()
    
    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)
    
    return df, regional_summary

def calculate_global_stats(regional_summary):
    """
    Calculate global statistics from regional summary.
    """
    if regional_summary.empty:
        return {
            'total_cases': 0,
            'total_deaths': 0,
            'total_recoveries': 0,
            'death_rate': 0.0
        }
    
    total_cases = regional_summary['cases'].sum()
    total_deaths = regional_summary['deaths'].sum()
    total_recoveries = regional_summary['recoveries'].sum()
    death_rate = (total_deaths / total_cases * 100) if total_cases > 0 else 0
    
    return {
        'total_cases': int(total_cases),
        'total_deaths': int(total_deaths),
        'total_recoveries': int(total_recoveries),
        'death_rate': death_rate
    }

def get_country_data(df, country):
    """
    Get data for a specific country.
    """
    return df[df['region'] == country].copy()

def get_date_range(df):
    """
    Get the date range of the data.
    """
    if df.empty or 'date' not in df.columns:
        return None, None
    
    return df['date'].min(), df['date'].max()

def filter_by_date_range(df, start_date, end_date):
    """
    Filter data by date range.
    """
    if df.empty:
        return df
    
    mask = (df['date'] >= pd.to_datetime(start_date)) & (df['date'] <= pd.to_datetime(end_date))
    return df[mask].copy()

def filter_by_countries(df, countries):
    """
    Filter data by list of countries.
    """
    if df.empty or not countries:
        return df
    
    return df[df['region'].isin(countries)].copy()