run.py

import argparse
import sys
from CW1.src.main import recreate_results, build_and_evaluate_decision_tree, cross_validate_decision_tree

def print_help():
    """Print detailed help information about available commands."""
    help_text = """
DECISION TREE ANALYSIS - COMMAND LINE INTERFACE
===============================================

USAGE:
    python run.py [COMMAND] [OPTIONS]

COMMANDS:
    (no command)    Run complete analysis pipeline (recreate_results)
    build_tree      Build and evaluate a single decision tree
    cross_validate  Perform k-fold cross-validation
    --help, -h      Show this help message

OPTIONS FOR build_tree:
    --data_path PATH        Path to dataset (default: wifi_db/clean_dataset.txt)
    --train_split FLOAT     Training split ratio (default: 0.8)
    --random_seed INT       Random seed for reproducibility (default: -1)

OPTIONS FOR cross_validate:
    --k INT                Number of folds (default: 10)
    --data_path PATH       Path to dataset (default: None)
    --random_seed INT      Random seed for reproducibility (default: -1)

OPTIONS FOR recreate_results (default):
    --random_seed INT      Random seed for reproducibility (default: -1)

EXAMPLES:
    python3 run.py
    python3 run.py --random_seed 42
    
    python3 run.py build_tree --data_path wifi_db/noisy_dataset.txt
    python3 run.py build_tree --train_split 0.7 --random_seed 123
    
    python3 run.py cross_validate --k 5 --data_path wifi_db/noisy_dataset.txt

===============================================
"""
    print(help_text)

def main():
    parser = argparse.ArgumentParser(description='Decision Tree Analysis Tool', add_help=False)
    
    # Add custom help flag
    parser.add_argument('--help', '-h', action='store_true', help='Show help message')
    
    # Command selection
    parser.add_argument('command', nargs='?', choices=['build_tree', 'cross_validate'], 
                       help='Command to execute')
    
    # Common arguments
    parser.add_argument('--random_seed', type=int, default=-1,
                       help='Random seed for reproducibility (default: -1)')
    
    # build_tree specific arguments
    parser.add_argument('--data_path', type=str, default='wifi_db/clean_dataset.txt',
                       help='Path to dataset (default: wifi_db/clean_dataset.txt)')
    parser.add_argument('--train_split', type=float, default=0.8,
                       help='Training split ratio (default: 0.8)')
    
    # cross_validate specific arguments
    parser.add_argument('--k', type=int, default=10,
                       help='Number of folds for cross-validation (default: 10)')
    
    args = parser.parse_args()
    
    # Handle help
    if args.help:
        print_help()
        return
    
    # Handle different commands
    if args.command is None:
        # Default: recreate_results
        print("🔄 Running complete analysis pipeline...")
        print(f"⚙️  Random seed: {args.random_seed}")
        recreate_results(random_seed=args.random_seed)
        
    elif args.command == 'build_tree':
        # Validate arguments for build_tree
        if not (0.1 <= args.train_split <= 0.9):
            print("❌ Error: --train_split must be between 0.1 and 0.9")
            print("💡 Suggestion: Use --train_split 0.8 for 80% training data")
            return
        
        if not args.data_path.endswith('.txt'):
            print("❌ Error: --data_path must point to a .txt file")
            print("💡 Suggestion: Use a valid dataset path like wifi_db/clean_dataset.txt")
            return
        
        print("🌳 Building and evaluating decision tree...")
        print(f"📁 Data path: {args.data_path}")
        print(f"📊 Train split: {args.train_split}")
        print(f"⚙️  Random seed: {args.random_seed}")

        # Call with only the parameters the function accepts
        build_and_evaluate_decision_tree(
            data_path=args.data_path,
            train_test_split=args.train_split,  # Changed from train_split to train_test_split
            prune=False,  # Pruning option removed
            random_seed=args.random_seed
        )
        
    elif args.command == 'cross_validate':
        # Validate arguments for cross_validate
        if args.k < 2:
            print("❌ Error: --k must be at least 2 for cross-validation")
            print("💡 Suggestion: Use --k 10 for 10-fold cross-validation")
            return
        
        if args.k > 20:
            print("⚠️  Warning: Large k values (>20) may be computationally expensive")
            response = input("Continue? (y/n): ")
            if response.lower() != 'y':
                return
        
        print("📊 Performing k-fold cross-validation...")
        print(f"🔢 K-folds: {args.k}")
        if not args.data_path.endswith('.txt'):
            print("❌ Error: --data_path must point to a .txt file")
            print("💡 Suggestion: Use a valid dataset path like wifi_db/clean_dataset.txt")
            return
        print(f"📁 Data path: {args.data_path}")
        print(f"⚙️  Random seed: {args.random_seed}")
        
        # Call with only the parameters the function accepts
        cross_validate_decision_tree(
                k=args.k,
                data_path=args.data_path,
                random_seed=args.random_seed
        )

if __name__ == "__main__":
    try:
        main()
    except KeyboardInterrupt:
        print("\n⚠️  Operation cancelled by user")
        sys.exit(1)
    except Exception as e:
        print(f"❌ Error: {e}")
        print("💡 Use 'python run.py --help' for usage information")
        sys.exit(1)