sales-data-analysis/logger_config.py

"""
Logging configuration for analysis scripts
Provides structured logging with file and console output

Usage:
    from logger_config import get_logger
    
    logger = get_logger('my_analysis')
    logger.info("Analysis started")
    logger.warning("Low data quality detected")
    logger.error("Failed to load data")
"""
import logging
import sys
from pathlib import Path
from datetime import datetime
from config import COMPANY_NAME, OUTPUT_DIR

# Global logger instance
_logger = None

def setup_logging(log_level=logging.INFO, log_file=None, analysis_name=None):
    """
    Setup logging configuration
    
    Args:
        log_level: Logging level (DEBUG, INFO, WARNING, ERROR)
        log_file: Path to log file (defaults to logs/analysis_YYYYMMDD_HHMMSS.log)
        analysis_name: Name of analysis for log file naming
    
    Returns:
        logging.Logger: Configured logger instance
    """
    global _logger
    
    # Create logs directory
    logs_dir = Path('logs')
    logs_dir.mkdir(exist_ok=True)
    
    # Default log file name
    if log_file is None:
        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
        if analysis_name:
            safe_name = analysis_name.lower().replace(' ', '_').replace('/', '_')
            log_file = logs_dir / f"{safe_name}_{timestamp}.log"
        else:
            log_file = logs_dir / f"analysis_{timestamp}.log"
    else:
        log_file = Path(log_file)
        log_file.parent.mkdir(parents=True, exist_ok=True)
    
    # Create logger
    logger = logging.getLogger(analysis_name or 'analysis')
    logger.setLevel(log_level)
    
    # Remove existing handlers to avoid duplicates
    logger.handlers = []
    
    # Create formatters
    detailed_formatter = logging.Formatter(
        '%(asctime)s - %(name)s - %(levelname)s - %(message)s',
        datefmt='%Y-%m-%d %H:%M:%S'
    )
    
    console_formatter = logging.Formatter(
        '%(levelname)s - %(message)s'
    )
    
    # File handler (detailed)
    file_handler = logging.FileHandler(log_file, encoding='utf-8')
    file_handler.setLevel(log_level)
    file_handler.setFormatter(detailed_formatter)
    logger.addHandler(file_handler)
    
    # Console handler (simpler)
    console_handler = logging.StreamHandler(sys.stdout)
    console_handler.setLevel(log_level)
    console_handler.setFormatter(console_formatter)
    logger.addHandler(console_handler)
    
    # Log startup message
    logger.info(f"="*60)
    logger.info(f"Analysis: {analysis_name or 'Unknown'}")
    logger.info(f"Company: {COMPANY_NAME}")
    logger.info(f"Log File: {log_file}")
    logger.info(f"="*60)
    
    _logger = logger
    return logger

def get_logger(analysis_name=None, log_level=logging.INFO):
    """
    Get or create logger instance
    
    Args:
        analysis_name: Name of analysis
        log_level: Logging level (default: INFO)
    
    Returns:
        logging.Logger: Logger instance
    """
    global _logger
    
    if _logger is None:
        _logger = setup_logging(log_level=log_level, analysis_name=analysis_name)
    
    return _logger

def log_analysis_start(analysis_name, logger=None):
    """
    Log analysis start
    
    Args:
        analysis_name: Name of analysis
        logger: Logger instance (creates one if None)
    """
    if logger is None:
        logger = get_logger(analysis_name)
    
    logger.info(f"Starting analysis: {analysis_name}")
    logger.info(f"Timestamp: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")

def log_analysis_end(analysis_name, success=True, logger=None):
    """
    Log analysis completion
    
    Args:
        analysis_name: Name of analysis
        success: Whether analysis completed successfully
        logger: Logger instance (creates one if None)
    """
    if logger is None:
        logger = get_logger(analysis_name)
    
    if success:
        logger.info(f"Analysis completed successfully: {analysis_name}")
    else:
        logger.error(f"Analysis failed: {analysis_name}")
    
    logger.info(f"Timestamp: {datetime.now().strftime('%Y-%m-%d %H:%M:%S')}")
    logger.info("="*60)

def log_data_loading(df, logger=None):
    """
    Log data loading summary
    
    Args:
        df: Loaded DataFrame
        logger: Logger instance (creates one if None)
    """
    if logger is None:
        logger = get_logger()
    
    logger.info(f"Data loaded: {len(df):,} rows, {len(df.columns)} columns")
    
    from config import REVENUE_COLUMN, DATE_COLUMN
    if REVENUE_COLUMN in df.columns:
        revenue = df[REVENUE_COLUMN].sum()
        logger.info(f"Total revenue: ${revenue / 1e6:.2f}m")
    
    if DATE_COLUMN in df.columns:
        date_coverage = df[DATE_COLUMN].notna().sum() / len(df) * 100
        logger.info(f"Date coverage: {date_coverage:.1f}%")

def log_error(error, logger=None, context=None):
    """
    Log error with context
    
    Args:
        error: Exception or error message
        logger: Logger instance (creates one if None)
        context: Additional context string
    """
    if logger is None:
        logger = get_logger()
    
    error_msg = str(error)
    if context:
        error_msg = f"{context}: {error_msg}"
    
    logger.error(error_msg, exc_info=True)

# ============================================================================
# EXAMPLE USAGE
# ============================================================================

if __name__ == "__main__":
    """Example usage"""
    logger = setup_logging(log_level=logging.DEBUG, analysis_name="Example Analysis")
    
    logger.debug("This is a debug message")
    logger.info("This is an info message")
    logger.warning("This is a warning message")
    logger.error("This is an error message")
    
    log_analysis_start("Example Analysis", logger)
    log_analysis_end("Example Analysis", success=True, logger)