Rooba
/
spaCy
mirror of https://github.com/explosion/spaCy.git
1
1
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Fix tests

This commit is contained in:
Matthew Honnibal 2017-06-04 16:00:44 -05:00
parent 55d0621532
commit bb98d45a63
2 changed files with 9 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
spacy/tests/regression/test_issue910.py
View File

@ -55,19 +55,13 @@ def additional_entity_types():
@contextlib.contextmanager @contextlib.contextmanager
def temp_save_model(model): def temp_save_model(model):
model_dir = Path(tempfile.mkdtemp()) model_dir = tempfile.mkdtemp()
# store the fine tuned model model.to_disk(model_dir)
with (model_dir / "config.json").open('w') as file_:
data = json.dumps(model.cfg)
if not isinstance(data, unicode):
data = data.decode('utf8')
file_.write(data)
model.model.dump((model_dir / 'model').as_posix())
yield model_dir yield model_dir
shutil.rmtree(model_dir.as_posix()) shutil.rmtree(model_dir.as_posix())
@pytest.mark.xfail
@pytest.mark.models('en') @pytest.mark.models('en')
def test_issue910(EN, train_data, additional_entity_types): def test_issue910(EN, train_data, additional_entity_types):
'''Test that adding entities and resuming training works passably OK. '''Test that adding entities and resuming training works passably OK.
@ -84,18 +78,20 @@ def test_issue910(EN, train_data, additional_entity_types):
for entity_type in additional_entity_types: for entity_type in additional_entity_types:
nlp.entity.add_label(entity_type) nlp.entity.add_label(entity_type)
nlp.entity.model.learn_rate = 0.001 sgd = Adam(nlp.entity.model[0].ops, 0.001)
for itn in range(10): for itn in range(10):
random.shuffle(train_data) random.shuffle(train_data)
for raw_text, entity_offsets in train_data: for raw_text, entity_offsets in train_data:
doc = nlp.make_doc(raw_text) doc = nlp.make_doc(raw_text)
nlp.tagger(doc) nlp.tagger(doc)
nlp.tensorizer(doc)
gold = GoldParse(doc, entities=entity_offsets) gold = GoldParse(doc, entities=entity_offsets)
loss = nlp.entity.update(doc, gold) loss = nlp.entity.update(doc, gold, sgd=sgd, drop=0.5)
with temp_save_model(nlp.entity) as model_dir: with temp_save_model(nlp.entity) as model_dir:
# Load the fine tuned model # Load the fine tuned model
loaded_ner = EntityRecognizer.load(model_dir, nlp.vocab) loaded_ner = EntityRecognizer(nlp.vocab)
loaded_ner.from_disk(model_dir)
for raw_text, entity_offsets in train_data: for raw_text, entity_offsets in train_data:
doc = nlp.make_doc(raw_text) doc = nlp.make_doc(raw_text)

2
spacy/tests/regression/test_issue995.py
View File

@ -4,7 +4,7 @@ import pytest
@pytest.mark.models('en') @pytest.mark.models('en')
def test_issue955(EN, doc): def test_issue955(EN):
'''Test that we don't have any nested noun chunks''' '''Test that we don't have any nested noun chunks'''
doc = EN('Does flight number three fifty-four require a connecting flight' doc = EN('Does flight number three fifty-four require a connecting flight'
' to get to Boston?') ' to get to Boston?')