Clean up numbers for MfA

from pathlib import Path
BASEPATH = Path("/home/joregan/hsi_mfa")

%pip install num2words

Requirement already satisfied: num2words in /home/joregan/miniconda3/envs/mfa/lib/python3.10/site-packages (0.5.13)
Requirement already satisfied: docopt>=0.6.2 in /home/joregan/miniconda3/envs/mfa/lib/python3.10/site-packages (from num2words) (0.6.2)
Note: you may need to restart the kernel to use updated packages.

from num2words import num2words

import re

def get_words(word):
    if re.match("^[2-9]0s$", word):
        oword = num2words(int(word[0:-1]), lang="en")
        return oword[:-1] + "ies"
    if re.match("^[0-9]+(?:th|st|nd|rd)$", word):
        return num2words(int(word[0:-2]), lang="en", to="ordinal")
    if re.match("^[0-9]+(?:,[0-9][0-9][0-9])+$", word):
        return num2words(int(word.replace(",", "")), lang="en")
    if re.match("^\$[0-9]+(?:,[0-9][0-9][0-9])*$", word):
        return num2words(int(word[1:].replace(",", "")), lang="en") + " dollars"
    if re.match("^20[1-9][0-9]$", word):
        return "twenty " + num2words(int(word[2:]), lang="en")
    if re.match("^[0-9]+$"):
        return num2words(int(word))
    return word

get_words("$2019")

'two thousand and nineteen dollars'