def extract_synonyms_and_derivation(word): lemma_names = set() derivationally_related_forms = set() for synset in wn.synsets(word): for lemma in synset.lemmas(): lemma_name = lemma.name().replace("_", " ") if not StringUtils.is_stop(lemma_name.lower()): lemma_names.add(lemma_name) derivationally_related_forms.update([ l.name().replace("_", " ") for l in lemma.derivationally_related_forms() if not StringUtils.is_stop(l.name().lower()) ]) return lemma_names, derivationally_related_forms
def all_clean_words_synonyms(clean_phrase): words = clean_phrase.split() return [ set([ lemma.lower().replace("_", " ") for synset in wn.synsets(w) for lemma in synset.lemma_names() if not StringUtils.is_stop(lemma.lower()) ]) for w in words ]
def test_is_stopword(): assert StringUtils.is_stop('always') assert StringUtils.is_stop('sunday') is False
def test_is_stopword(): assert StringUtils.is_stop("always") assert StringUtils.is_stop("sunday") is False