"""
Run all Deepchecks validation suites

This script executes all data validation checks:
1. Data Integrity Suite - validates training data quality
2. Train-Test Validation Suite - ensures proper train/test split

Usage:
    python tests/run_all_deepchecks.py
"""

import sys
from pathlib import Path

# Add project root to path
project_root = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(project_root))

from tests.test_data_integrity import (
    run_data_integrity_suite,
    run_custom_integrity_checks,
    analyze_data_statistics
)
from tests.test_train_test_validation import (
    run_train_test_validation_suite,
    run_custom_train_test_checks,
    compare_distributions,
    validate_split_quality
)


def main():
    """
    Run all Deepchecks validation suites and generate reports.
    """
    import argparse
    
    parser = argparse.ArgumentParser(description='Run Deepchecks validation suites')
    parser.add_argument('--original', action='store_true', 
                       help='Use original data instead of cleaned data')
    args = parser.parse_args()
    
    use_cleaned = not args.original
    
    print("="*80)
    print(" DEEPCHECKS VALIDATION - COMPLETE SUITE")
    print("="*80)
    print(f"\nUsing {'CLEANED' if use_cleaned else 'ORIGINAL'} data")
    print("Reports will be saved in: reports/deepchecks/")
    print("\n" + "="*80)
    
    # Phase 1: Data Integrity Checks
    print("\nPHASE 1: DATA INTEGRITY VALIDATION")
    print("="*80)
    
    try:
        # Dataset statistics
        analyze_data_statistics(use_cleaned=use_cleaned)
        
        # Run full integrity suite
        print("\n")
        integrity_result = run_data_integrity_suite(save_output=True, use_cleaned=use_cleaned)
        
        # Run custom integrity checks
        print("\n")
        custom_integrity_results = run_custom_integrity_checks(save_output=True, use_cleaned=use_cleaned)
        
        print("\nPhase 1 completed successfully!")
        
    except Exception as e:
        print(f"\nError in Phase 1: {str(e)}")
        return False
    
    # Phase 2: Train-Test Validation
    print("\n\nPHASE 2: TRAIN-TEST VALIDATION")
    print("="*80)
    
    try:
        # Distribution comparison
        compare_distributions(use_cleaned=use_cleaned)
        
        # Split quality validation
        print("\n")
        validate_split_quality(use_cleaned=use_cleaned)
        
        # Run full train-test suite
        print("\n")
        train_test_suite_result = run_train_test_validation_suite(save_output=True, use_cleaned=use_cleaned)
        
        # Run custom train-test checks
        print("\n")
        custom_train_test_results = run_custom_train_test_checks(save_output=True, use_cleaned=use_cleaned)
        
        print("\nPhase 2 completed successfully!")
        
    except Exception as e:
        print(f"\nError in Phase 2: {str(e)}")
        return False
    
    # Summary
    print("\n\n" + "="*80)
    print(" VALIDATION SUMMARY")
    print("="*80)
    
    print("\nAll Deepchecks validation suites completed successfully!")
    print("\nGenerated Reports:")
    print("   - reports/deepchecks/data_integrity_suite_results.json")
    print("   - reports/deepchecks/train_test_validation_suite_results.json")
    print("   - reports/deepchecks/validation_summary.json")
    
    print("\nNext Steps:")
    print("   1. Review the JSON reports for check results")
    print("   2. Examine any warnings or failed checks")
    print("   3. Address data quality issues if found")
    print("   4. Document findings in your project documentation")
    
    print("\n" + "="*80)
    
    return True


if __name__ == "__main__":
    success = main()
    sys.exit(0 if success else 1)