def test_default(spacy_doc):
result = ke.scake(spacy_doc)
assert isinstance(result, list) and len(result) > 0
assert all(isinstance(ts, tuple) and len(ts) == 2 for ts in result)
assert all(
isinstance(ts[0], compat.unicode_) and isinstance(ts[1], float)
for ts in result)
def test_single_sentence_doc():
doc = textacy.make_spacy_doc("This is a document with a single sentence.",
lang="en")
result = ke.scake(doc)
assert isinstance(result, list)
assert len(result) > 0
def test_empty_doc(empty_spacy_doc):
result = ke.scake(empty_spacy_doc)
assert isinstance(result, list)
assert len(result) == 0
def test_topn_float(spacy_doc):
result = ke.scake(spacy_doc, topn=0.2)
assert len(result) > 0
with pytest.raises(ValueError):
_ = ke.scake(spacy_doc, topn=2.0)
def test_n_topn(spacy_doc):
for n in (5, 25):
result = ke.scake(spacy_doc, topn=n)
assert 0 < len(result) <= n
def test_include_pos(spacy_doc):
result1 = ke.scake(spacy_doc, include_pos={"NOUN", "PROPN", "ADJ"})
result2 = ke.scake(spacy_doc, include_pos={"NOUN", "PROPN"})
assert len(result1) > 0 and len(result2) > 0
assert result1 != result2
#open data from .txt file
with open('news_article.txt', 'r') as file:
data = file.read().replace('\n', '')
article = data.replace(u'\xa0', u' ')
#create doc object
doc = textacy.make_spacy_doc(article, lang='en_core_web_sm')
#KEYTERM EXTRACTION
#Each algorithm returns a list of tuples, containg the keyterm and a score
textrank = ke.textrank(doc,normalize="lemma")
yake = ke.yake(doc,normalize="lemma")
scake = ke.scake(doc,normalize="lemma")
sgrank = ke.sgrank(doc,normalize="lemma")
#separate terms and relevany scores
terms_textrank, scores_textrank = decompose_keyterms(textrank)
terms_yake, scores_yake = decompose_keyterms(yake)
terms_scake, scores_scake = decompose_keyterms(scake)
terms_sgrank, scores_sgrank = decompose_keyterms(sgrank)
#save results to dataframe
df = keyterm_dataframe(scake,'scake')
print(df)
#Make plot
