Function designed to strip out all numbers (alphabetic - English only - and numeric) from a string as part of a text normalisation process.

remove_numbers.py

# Function designed to strip out all numbers (alphabetic - English only - and numeric) from a string as part of a
# text normalisation process.

# Based on the text2num package (https://github.com/ghewgill/text2num) and using code from 
# here (http://stackoverflow.com/questions/25346058/removing-list-of-words-from-a-string)

from string import digits

# List of number terms
nums = ['zero', 'one', 'two', 'three', 'four', 'five', 'six', 'seven', 'eight', 'nine', 'ten', 'eleven',
        'twelve', 'thirteen', 'fourteen', 'fifteen', 'sixteen', 'seventeen', 'eighteen', 'nineteen', 
        'twenty', 'thirty', 'forty', 'fifty', 'sixty', 'seventy', 'eighty', 'ninety', 'hundred', 
        'thousand', 'million', 'billion', 'trillion', 'quadrillion', 'quintillion', 'sextillion',
        'septillion', 'octillion', 'nonillion', 'decillion']


def remove_numbers(s):
    """
    Removes all numbers from strings, both alphabetic (in English) and numeric. Intended to be
    part of a text normalisation process. If the number contains 'and' or commas, these are 
    left behind on the assumption the text will be cleaned further to remove punctuation 
    and stop-words.
    """
    
    query = s.replace('-', ' ').lower().split(' ')
    resultwords = [word for word in query if word not in nums]
    noText = ' '.join(resultwords).encode('utf-8')
    noNums = noText.translate(None, digits).replace('  ', ' ')
    
    return noNums