sales-data-analysis/run_all_analyses.py

"""
Batch runner for all analysis scripts
Runs all analyses in sequence and generates a summary report

To use:
1. Add your analysis scripts to the ANALYSIS_SCRIPTS list below
2. Run: python run_all_analyses.py
"""
import subprocess
import sys
from pathlib import Path
from datetime import datetime
import time

# ============================================================================
# CONFIGURATION
# ============================================================================

# List of analysis scripts to run
# TODO: Add your analysis scripts here
ANALYSIS_SCRIPTS = [
    # Example structure - customize for your analyses:
    # 'check_annual_revenue.py',
    # 'revenue_analysis.py',
    # 'geographic_analysis.py',
    # 'customer_segmentation.py',
    # 'product_analysis.py',
    # Add your analysis scripts here...
]

# Timeout per script (in seconds)
SCRIPT_TIMEOUT = 600  # 10 minutes

# ============================================================================
# HELPER FUNCTIONS
# ============================================================================

def run_script(script_path):
    """Run a single analysis script"""
    script_name = Path(script_path).name
    print(f"\n{'='*60}")
    print(f"Running: {script_name}")
    print(f"{'='*60}")
    
    start_time = time.time()
    
    try:
        result = subprocess.run(
            [sys.executable, script_path],
            capture_output=True,
            text=True,
            timeout=SCRIPT_TIMEOUT
        )
        
        elapsed = time.time() - start_time
        
        if result.returncode == 0:
            print(f"✅ {script_name} completed successfully ({elapsed:.1f}s)")
            if result.stdout:
                # Print last 10 lines of output
                lines = result.stdout.strip().split('\n')
                if len(lines) > 10:
                    print("  ... (output truncated)")
                    for line in lines[-10:]:
                        print(f"  {line}")
                else:
                    for line in lines:
                        print(f"  {line}")
            return True, elapsed, None
        else:
            print(f"❌ {script_name} failed ({elapsed:.1f}s)")
            if result.stderr:
                print(f"  Error: {result.stderr[:500]}")
            return False, elapsed, result.stderr
            
    except subprocess.TimeoutExpired:
        elapsed = time.time() - start_time
        print(f"⏱️  {script_name} timed out after {elapsed:.1f}s")
        return False, elapsed, "Timeout"
    except Exception as e:
        elapsed = time.time() - start_time
        print(f"❌ {script_name} error: {str(e)}")
        return False, elapsed, str(e)

# ============================================================================
# MAIN FUNCTION
# ============================================================================

def main():
    """Run all analysis scripts"""
    from config import COMPANY_NAME
    
    print(f"\n{'='*60}")
    print(f"{COMPANY_NAME} Sales Analysis - Batch Runner")
    print(f"Started: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
    print(f"{'='*60}\n")
    
    # Check which scripts exist
    existing_scripts = []
    missing_scripts = []
    
    for script in ANALYSIS_SCRIPTS:
        script_path = Path(script)
        if script_path.exists():
            existing_scripts.append(script)
        else:
            missing_scripts.append(script)
    
    if missing_scripts:
        print(f"⚠️  Warning: {len(missing_scripts)} scripts not found:")
        for script in missing_scripts:
            print(f"   - {script}")
        print()
    
    if not existing_scripts:
        print("❌ No analysis scripts found!")
        print("   Please add analysis scripts to ANALYSIS_SCRIPTS list in run_all_analyses.py")
        return
    
    print(f"Found {len(existing_scripts)} analysis scripts to run\n")
    
    # Run scripts
    results = []
    total_start = time.time()
    
    for script in existing_scripts:
        success, elapsed, error = run_script(script)
        results.append({
            'script': script,
            'success': success,
            'elapsed': elapsed,
            'error': error
        })
    
    total_elapsed = time.time() - total_start
    
    # Print summary
    print(f"\n{'='*60}")
    print("Batch Run Summary")
    print(f"{'='*60}\n")
    
    successful = [r for r in results if r['success']]
    failed = [r for r in results if not r['success']]
    
    print(f"Total scripts: {len(results)}")
    print(f"✅ Successful: {len(successful)}")
    print(f"❌ Failed: {len(failed)}")
    print(f"⏱️  Total time: {total_elapsed/60:.1f} minutes\n")
    
    if failed:
        print("Failed scripts:")
        for r in failed:
            print(f"  ❌ {r['script']} ({r['elapsed']:.1f}s)")
            if r['error']:
                print(f"     Error: {r['error'][:100]}")
        print()
    
    # Save summary to file
    summary_file = Path('analysis_run_summary.txt')
    with open(summary_file, 'w') as f:
        f.write(f"{COMPANY_NAME} Sales Analysis - Batch Run Summary\n")
        f.write(f"Date: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}\n")
        f.write(f"{'='*60}\n\n")
        f.write(f"Total scripts: {len(results)}\n")
        f.write(f"Successful: {len(successful)}\n")
        f.write(f"Failed: {len(failed)}\n")
        f.write(f"Total time: {total_elapsed/60:.1f} minutes\n\n")
        
        if successful:
            f.write("Successful scripts:\n")
            for r in successful:
                f.write(f"  ✅ {r['script']} ({r['elapsed']:.1f}s)\n")
            f.write("\n")
        
        if failed:
            f.write("Failed scripts:\n")
            for r in failed:
                f.write(f"  ❌ {r['script']} ({r['elapsed']:.1f}s)\n")
                if r['error']:
                    f.write(f"     Error: {r['error']}\n")
    
    print(f"Summary saved to: {summary_file}")

if __name__ == "__main__":
    main()