Yule's K and Yule's I for lexical diversity in Python 3 (quick & dirty)

lexical_diversity_yule.py

import collections
import re

def tokenize(s):
    tokens = re.split(r"[^0-9A-Za-z\-'_]+", s)
    return tokens

def get_yules(s):
    """ 
    Returns a tuple with Yule's K and Yule's I.
    (cf. Oakes, M.P. 1998. Statistics for Corpus Linguistics.
    International Journal of Applied Linguistics, Vol 10 Issue 2)

    In production this needs exception handling.
    """
    tokens = tokenize(s)
    token_counter = collections.Counter(tok.upper() for tok in tokens)
    m1 = sum(token_counter.values())
    m2 = sum([freq ** 2 for freq in token_counter.values()])
    i = (m1*m1) / (m2-m1)
    k = 1/i * 10000
    return (k, i)

Also, k = 10000/i 👍

Thanks for pointing it out, forgot to remove the self after excerpting it from a class.