PsychiatryNLPKit.analysis.stop_words_ratio

PsychiatryNLPKit.analysis.stop_words_ratio(pos_tags, sections=None, lang='en', averaging_method='macro')[source]

Stop word-to-total-word ratio per section.

Notes:

Theoretical basis - Baseline measure of function-word usage. Matches against lemmas (not surface forms). Function word patterns are sensitive to thought disorder and language impairment.

Args:

pos_tags: Dict mapping section names to lists of POS-tagged sentences. sections: Sections to process. None processes all sections in

pos_tags.

lang: Language code (“en” or “fr”). averaging_method: "macro" averages per-sentence ratios; "micro"

computes total stopwords / total words across the section.

Returns:

Dict mapping section names to a dict with keys "stop_words_ratio" and "stop_words_count". Empty sections receive float("nan") for both.