"""
Healthcare Patient Dataset - Data Validation Script
===================================================
This script validates the healthcare patient dataset for data quality,
completeness, and consistency.

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

import pandas as pd
import numpy as np

def validate_dataset(csv_file='healthcare_patients.csv'):
    """
    Validate the healthcare patient dataset.
    
    Parameters:
    csv_file (str): Path to the CSV file
    
    Returns:
    dict: Validation results
    """
    print("\n" + "="*60)
    print("DATASET VALIDATION")
    print("="*60)
    print("Author: RSK World")
    print("Website: https://rskworld.in")
    print("Email: help@rskworld.in")
    print("Phone: +91 93305 39277")
    print("="*60 + "\n")
    
    try:
        df = pd.read_csv(csv_file)
        print(f"✓ Dataset loaded: {len(df)} records, {len(df.columns)} columns\n")
        
        validation_results = {
            'total_records': len(df),
            'total_columns': len(df.columns),
            'missing_values': {},
            'data_types': {},
            'validation_passed': True,
            'issues': []
        }
        
        # Check for missing values
        print("--- Missing Values Check ---")
        missing = df.isnull().sum()
        for col, count in missing.items():
            if count > 0:
                validation_results['missing_values'][col] = count
                validation_results['issues'].append(f"Missing values in {col}: {count}")
                print(f"⚠ {col}: {count} missing values")
            else:
                print(f"✓ {col}: No missing values")
        
        # Check data types
        print("\n--- Data Type Check ---")
        for col, dtype in df.dtypes.items():
            validation_results['data_types'][col] = str(dtype)
            print(f"✓ {col}: {dtype}")
        
        # Validate specific fields
        print("\n--- Field Validation ---")
        
        # Patient ID uniqueness
        if df['patient_id'].is_unique:
            print("✓ Patient IDs are unique")
        else:
            print("✗ Duplicate patient IDs found")
            validation_results['validation_passed'] = False
            validation_results['issues'].append("Duplicate patient IDs")
        
        # Age validation
        if (df['age'] >= 0).all() and (df['age'] <= 120).all():
            print("✓ Age values are valid (0-120)")
        else:
            print("✗ Invalid age values found")
            validation_results['validation_passed'] = False
            validation_results['issues'].append("Invalid age values")
        
        # Length of stay validation
        if (df['length_of_stay'] > 0).all():
            print("✓ Length of stay values are positive")
        else:
            print("✗ Invalid length of stay values")
            validation_results['validation_passed'] = False
            validation_results['issues'].append("Invalid length of stay")
        
        # Charges validation
        if (df['charges'] >= 0).all():
            print("✓ Charges values are non-negative")
        else:
            print("✗ Negative charges found")
            validation_results['validation_passed'] = False
            validation_results['issues'].append("Negative charges")
        
        # Date validation
        try:
            df['admission_date'] = pd.to_datetime(df['admission_date'])
            df['discharge_date'] = pd.to_datetime(df['discharge_date'])
            if (df['discharge_date'] >= df['admission_date']).all():
                print("✓ Discharge dates are after admission dates")
            else:
                print("✗ Some discharge dates are before admission dates")
                validation_results['validation_passed'] = False
                validation_results['issues'].append("Invalid date ranges")
        except Exception as e:
            print(f"✗ Date validation error: {str(e)}")
            validation_results['validation_passed'] = False
            validation_results['issues'].append(f"Date validation error: {str(e)}")
        
        # Outcome values validation
        valid_outcomes = ['Recovered', 'Improved', 'Stable']
        if df['outcome'].isin(valid_outcomes).all():
            print("✓ Outcome values are valid")
        else:
            print("✗ Invalid outcome values found")
            validation_results['validation_passed'] = False
            validation_results['issues'].append("Invalid outcome values")
        
        # Summary
        print("\n" + "="*60)
        print("VALIDATION SUMMARY")
        print("="*60)
        
        if validation_results['validation_passed'] and len(validation_results['issues']) == 0:
            print("✓ All validations passed!")
        else:
            print("⚠ Validation completed with issues:")
            for issue in validation_results['issues']:
                print(f"  - {issue}")
        
        print(f"\nTotal Records: {validation_results['total_records']}")
        print(f"Total Columns: {validation_results['total_columns']}")
        print(f"Missing Value Fields: {len(validation_results['missing_values'])}")
        print(f"Issues Found: {len(validation_results['issues'])}")
        print("="*60 + "\n")
        
        return validation_results
        
    except FileNotFoundError:
        print(f"✗ Error: File '{csv_file}' not found")
        return None
    except Exception as e:
        print(f"✗ Error during validation: {str(e)}")
        return None

def main():
    """
    Main function to run validation.
    """
    results = validate_dataset()
    
    if results and results['validation_passed']:
        print("Dataset is ready for use! ✓\n")
    else:
        print("Please review the issues above before using the dataset.\n")

if __name__ == "__main__":
    main()