"""
Export Healthcare Patient Dataset to JSON
==========================================
This script exports the healthcare patient dataset to JSON format
with nested structure and metadata.

Author: RSK World
Website: https://rskworld.in
Email: help@rskworld.in
Phone: +91 93305 39277
"""

import pandas as pd
import json
from datetime import datetime

def export_to_json(csv_file='healthcare_patients.csv', json_file='healthcare_patients.json'):
    """
    Export CSV dataset to JSON format.
    
    Parameters:
    csv_file (str): Path to input CSV file
    json_file (str): Path to output JSON file
    """
    try:
        print(f"Reading CSV file: {csv_file}")
        df = pd.read_csv(csv_file)
        
        # Convert dates to strings
        df['admission_date'] = pd.to_datetime(df['admission_date']).dt.strftime('%Y-%m-%d')
        df['discharge_date'] = pd.to_datetime(df['discharge_date']).dt.strftime('%Y-%m-%d')
        
        # Create structured JSON with metadata
        json_data = {
            'metadata': {
                'dataset_name': 'Healthcare Patient Dataset',
                'description': 'Medical patient dataset with health records, diagnostic information, and treatment outcomes',
                'total_patients': len(df),
                'total_features': len(df.columns),
                'export_date': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
                'author': {
                    'name': 'RSK World',
                    'website': 'https://rskworld.in',
                    'email': 'help@rskworld.in',
                    'phone': '+91 93305 39277'
                }
            },
            'statistics': {
                'mean_age': float(df['age'].mean()),
                'mean_length_of_stay': float(df['length_of_stay'].mean()),
                'total_charges': float(df['charges'].sum()),
                'mean_charges': float(df['charges'].mean()),
                'readmission_rate': float((df['readmission_30_days'] == 'Yes').sum() / len(df) * 100)
            },
            'patients': df.to_dict('records')
        }
        
        # Export to JSON
        print(f"Creating JSON file: {json_file}")
        with open(json_file, 'w', encoding='utf-8') as f:
            json.dump(json_data, f, indent=2, ensure_ascii=False)
        
        print(f"[OK] JSON file created successfully: {json_file}")
        print(f"  - Total patients: {len(df)}")
        print(f"  - File size: {len(json.dumps(json_data)) / 1024:.2f} KB")
        return True
        
    except FileNotFoundError:
        print(f"[ERROR] File '{csv_file}' not found")
        return False
    except Exception as e:
        print(f"[ERROR] Error creating JSON file: {str(e)}")
        return False

def main():
    """
    Main function to export dataset to JSON.
    """
    print("\n" + "="*60)
    print("HEALTHCARE PATIENT DATASET - JSON EXPORT")
    print("="*60)
    print("Author: RSK World")
    print("Website: https://rskworld.in")
    print("Email: help@rskworld.in")
    print("Phone: +91 93305 39277")
    print("="*60 + "\n")
    
    success = export_to_json()
    
    if success:
        print("\n" + "="*60)
        print("EXPORT COMPLETE!")
        print("="*60)
        print("\nThe JSON file contains:")
        print("  - Metadata (dataset information)")
        print("  - Statistics (key metrics)")
        print("  - Patients (complete patient records)")
        print("\n")

if __name__ == "__main__":
    main()