Data science productionization: maintenance - example 1

ds_prod_maintenance1.py

import logging

logger = logging.getLogger(__name__)
logger.setLevel(logging.INFO)

# create a file handler
handler = logging.FileHandler('error.log')
handler.setLevel(logging.ERROR)

# create a logging format
formatter = logging.Formatter(
'%(asctime)s - %(name)s - %(levelname)s - %(message)s')
handler.setFormatter(formatter)

# add the handlers to the logger
logger.addHandler(handler)


def normalize_word(word, stops=None):

    '''
    Processes a string by stripping whitespace, lowercasing, and 
    optionally removing stop characters.

    Args:
        word (str): The word to be processed.
        stops (list): A list of characters to remove from the string.
    Returns:
            str: The processed string. May be zero length.

    '''
    
    assert isinstance(word, str)

    try:
        word = word.strip().lower()

        if stops:
            word = ''.join([char for char in word if char not in stops]) 

        return word
    except (SystemExit, KeyboardInterrupt):
        raise
    except Exception, e:
        logger.error('Failed to process string', exc_info=True)