Divide Overflow when subdividing groups

A division overflow can occur when subdividing groups multiple times.

Example:

from sklearn.datasets import fetch_20newsgroups
from sklearn.feature_extraction.text import CountVectorizer
from turftopic import KeyNMF


def split_groups(groups, n):
    if n == 0:
        return

    for group in groups:
        group.divide(5)
        split_groups(group, n - 1)


if __name__ == '__main__':
    corpus = fetch_20newsgroups(subset='all', remove=('headers', 'footers', 'quotes')).data

    corpus = corpus[0:250]

    vectorizer = CountVectorizer(min_df=5, max_df=0.8, stop_words='english')

    model = KeyNMF(n_components=5, vectorizer=vectorizer)

    topic_data = model.prepare_topic_data(corpus)

    split_groups(topic_data.hierarchy, 3)

Error:

/.venv1/lib/python3.10/site-packages/turftopic/models/wnmf.py:40: RuntimeWarning:

overflow encountered in divide

Reproduce the provided recursive subdivision example with the 20 Newsgroups corpus and inspect turftopic/models/wnmf.py at line 40, where the RuntimeWarning is reported. Trace the repeated group divisions and verify that the example completes without a division-overflow warning.