explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-04 20:30:24 +03:00
Code Issues Packages Projects Releases Wiki Activity

Fix redundant test. 2 failures

Browse Source
This commit is contained in:
Matthew Honnibal 2021-10-31 01:56:28 +02:00 committed by svlandeg
parent dea702b4b7
commit 604ceb1da1
1 changed files with 37 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
spacy/tests/parser/test_ner.py
View File

@ -131,6 +131,41 @@ def test_negative_sample_key_is_in_config(vocab, entity_types):
assert tsys.cfg["neg_key"] == "non_entities"
@pytest.mark.filterwarnings("ignore::UserWarning")
def test_get_oracle_moves_negative_entities(tsys, doc, entity_annots):
entity_annots = [(s, e, "!" + label) for s, e, label in entity_annots]
example = Example.from_dict(doc, {"entities": entity_annots})
ex_dict = example.to_dict()
for i, tag in enumerate(ex_dict["doc_annotation"]["entities"]):
if tag == "L-!GPE":
ex_dict["doc_annotation"]["entities"][i] = "-"
example = Example.from_dict(doc, ex_dict)
act_classes = tsys.get_oracle_sequence(example)
names = [tsys.get_class_name(act) for act in act_classes]
assert names
def test_get_oracle_moves_negative_entities2(tsys, vocab):
doc = Doc(vocab, words=["A", "B", "C", "D"])
entity_annots = ["B-!PERSON", "L-!PERSON", "B-!PERSON", "L-!PERSON"]
example = Example.from_dict(doc, {"entities": entity_annots})
act_classes = tsys.get_oracle_sequence(example)
names = [tsys.get_class_name(act) for act in act_classes]
assert names
@pytest.mark.skip(reason="Maybe outdated? Unsure")
def test_get_oracle_moves_negative_O(tsys, vocab):
doc = Doc(vocab, words=["A", "B", "C", "D"])
entity_annots = ["O", "!O", "O", "!O"]
example = Example.from_dict(doc, {"entities": entity_annots})
act_classes = tsys.get_oracle_sequence(example)
names = [tsys.get_class_name(act) for act in act_classes]
assert names
# We can't easily represent this on a Doc object. Not sure what the best solution
# would be, but I don't think it's an important use case?
@pytest.mark.skip(reason="No longer supported")
@ -242,7 +277,7 @@ def test_train_empty():
train_examples.append(Example.from_dict(nlp.make_doc(t[0]), t[1]))
ner = nlp.add_pipe("ner", last=True)
ner.add_label("PERSON")
nlp.initialize()
nlp.initialize(get_examples=lambda: train_examples)
for itn in range(2):
losses = {}
batches = util.minibatch(train_examples, size=8)
@ -372,7 +407,7 @@ def test_block_ner():
def test_overfitting_IO():
# Simple test to try and quickly overfit the NER component
nlp = English()
ner = nlp.add_pipe("ner")
ner = nlp.add_pipe("ner", config={"model": {}})
train_examples = []
for text, annotations in TRAIN_DATA:
train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))