def test_own_terminology():
nlp = spacy.load("en_core_web_sm")
negex = Negex(nlp, termination=["whatever"])
nlp.add_pipe(negex, last=True)
doc = nlp(
"He does not like Steve Jobs whatever he says about Barack Obama.")
assert doc.ents[1]._.negex == False
def test_issue7():
nlp = spacy.load("en_core_web_sm")
negex = Negex(nlp)
nlp.add_pipe(negex, last=True)
ruler = EntityRuler(nlp)
patterns = [{"label": "SOFTWARE", "pattern": "spacy"}]
doc = nlp("fgfgdghgdh")
def test_own_terminology():
nlp = spacy.load("pt_core_news_sm")
negex = Negex(nlp, language="pt", termination=["por causa do que"])
nlp.add_pipe(negex, last=True)
doc = nlp(
"Ele não gosta do que Steve Jobs por causa do que diz sobre Barack Obama."
)
assert doc.ents[1]._.negex == False
def test_umls():
nlp = spacy.load("en_core_sci_sm")
negex = Negex(nlp, ent_types=["ENTITY"])
nlp.add_pipe(negex, last=True)
docs = build_med_docs()
for d in docs:
doc = nlp(d[0])
for i, e in enumerate(doc.ents):
assert (e.text, e._.negex) == d[1][i]
def test():
nlp = spacy.load("en_core_web_sm")
negex = Negex(nlp)
nlp.add_pipe(negex, last=True)
docs = build_docs()
for d in docs:
doc = nlp(d[0])
for i, e in enumerate(doc.ents):
assert (e.text, e._.negex) == d[1][i]
def test_pt():
nlp = spacy.load("pt_core_news_sm")
negex = Negex(nlp, language="en")
nlp.add_pipe(negex, last=True)
docs = build_docs()
for d in docs:
doc = nlp(d[0])
for i, e in enumerate(doc.ents):
print(e.text, e._.negex)
assert (e.text, e._.negex) == d[1][i]
def test_umls2():
nlp = spacy.load("en_core_sci_sm")
negex = Negex(
nlp, language="en_clinical_sensitive", ent_types=["ENTITY"], chunk_prefix=["no"]
)
nlp.add_pipe(negex, last=True)
docs = build_med_docs()
for d in docs:
doc = nlp(d[0])
for i, e in enumerate(doc.ents):
print(e.text, e._.negex)
assert (e.text, e._.negex) == d[1][i]
def test_issue_14():
nlp = spacy.load("en_core_sci_sm")
negex = Negex(nlp,
language="en_clinical",
chunk_prefix=["no", "cancer free"])
negex.remove_patterns(following_negations="free")
nlp.add_pipe(negex, last=True)
print(negex.get_patterns())
doc = nlp("The patient has a cancer free diagnosis")
expected = [False, True]
for i, e in enumerate(doc.ents):
print(e.text, e._.negex)
assert e._.negex == expected[i]
nlp.remove_pipe("Negex")
negex = Negex(nlp, language="en_clinical", chunk_prefix=["no", "free"])
nlp.add_pipe(negex, last=True)
doc = nlp("The patient has a cancer free diagnosis")
expected = [False, False]
for i, e in enumerate(doc.ents):
print(e.text, e._.negex)
assert e._.negex == expected[i]
def test_get_patterns():
nlp = spacy.load("en_core_web_sm")
negex = Negex(nlp)
patterns = negex.get_patterns()
assert type(patterns) == dict
assert len(patterns) == 4
def test_add_remove_patterns():
nlp = spacy.load("en_core_web_sm")
negex = Negex(nlp)
patterns = negex.get_patterns()
negex.add_patterns(
pseudo_negations=["my favorite pattern"],
termination=["these are", "great patterns"],
preceding_negations=["wow a negation"],
following_negations=["extra negation"],
)
patterns_after = negex.get_patterns()
print(patterns_after)
print(len(patterns_after["pseudo_patterns"]))
assert len(patterns_after["pseudo_patterns"]) - 1 == len(
patterns["pseudo_patterns"])
assert len(patterns_after["termination_patterns"]) - 2 == len(
patterns["termination_patterns"])
assert len(patterns_after["preceding_patterns"]) - 1 == len(
patterns["preceding_patterns"])
assert len(patterns_after["following_patterns"]) - 1 == len(
patterns["following_patterns"])
negex.remove_patterns(
termination=["these are", "great patterns"],
pseudo_negations=["my favorite pattern"],
preceding_negations="denied",
following_negations=["unlikely"],
)
negex.remove_patterns(termination="but")
negex.remove_patterns(preceding_negations="wow a negation",
following_negations="extra negation")
patterns_after = negex.get_patterns()
assert (len(patterns_after["termination_patterns"]) == len(
patterns["termination_patterns"]) - 1)
assert (len(patterns_after["following_patterns"]) == len(
patterns["following_patterns"]) - 1)
assert (len(patterns_after["preceding_patterns"]) == len(
patterns["preceding_patterns"]) - 1)
assert len(patterns_after["pseudo_patterns"]) == len(
patterns["pseudo_patterns"])
def test_get_patterns():
nlp = spacy.load("pt_core_news_sm")
negex = Negex(nlp, language="pt")
patterns = negex.get_patterns()
assert type(patterns) == dict
assert len(patterns) == 4
