string_treatment is a library for cleaning and adjusting words with inconsistency.
This library uses string similarity from rapidfuzz to group words with similar spelling into clusters, mapping each word to the most frequent (canonical) form within its cluster.
Since the clustering process may not always be perfectly accurate, the library can generate an interactive graph to help visualize the groupings.
Install the latest stable version from PyPI:
pip install string-treatment
See the testing script in the root: test_standardize.py.