fastdatascience/faststylometry

Implements forensic authorship attribution by computing z-score normalized feature vectors from most-frequent words, then measuring cosine distances between texts to quantify stylistic similarity. Provides utilities for tokenization, corpus management, and batch Delta calculations across training and test document sets, with built-in support for English text preprocessing including pronoun removal.

47 stars and 3,209 monthly downloads. No commits in the last 6 months. Available on PyPI.