explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2024-12-26 01:46:28 +03:00
Code Issues Packages Projects Releases Wiki Activity

adjusted tests to Travis Setup

Browse Source
This commit is contained in:
Wolfgang Seeker 2016-04-21 17:15:10 +02:00
parent 736ffcb9a2
commit b6477fc4f4
1 changed files with 15 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

21
spacy/tests/parser/test_sbd.py
View File

@ -123,24 +123,21 @@ def test_sentence_breaks_with_space(EN):
@pytest.fixture
@pytest.mark.models
def example(EN):
def apply_transition_sequence(model, doc, sequence):
def apply_transition_sequence(model, doc, sequence):
with model.parser.step_through(doc) as stepwise:
for transition in sequence:
stepwise.transition(transition)
doc = EN.tokenizer.tokens_from_list(u"I bought a couch from IKEA. It was n't very comfortable .".split(' '))
EN.tagger(doc)
apply_transition_sequence(EN, doc, ['L-nsubj','S','L-det','R-dobj','D','R-prep','R-pobj','D','D','S','L-nsubj','R-ROOT','R-neg','D','S','L-advmod','R-acomp','D','R-punct'])
return doc
def test_sbd_for_root_label_dependents(example):
@pytest.mark.models
def test_sbd_for_root_label_dependents(EN):
"""
make sure that the parser properly introduces a sentence boundary without
the break transition by checking for dependents with the root label
"""
example = EN.tokenizer.tokens_from_list(u"I bought a couch from IKEA. It was n't very comfortable .".split(' '))
EN.tagger(example)
apply_transition_sequence(EN, example, ['L-nsubj','S','L-det','R-dobj','D','R-prep','R-pobj','D','D','S','L-nsubj','R-ROOT','R-neg','D','S','L-advmod','R-acomp','D','R-punct'])
assert example[1].head.i == 1
assert example[7].head.i == 7
@ -152,7 +149,7 @@ def test_sbd_for_root_label_dependents(example):
@pytest.mark.models
def test_sbd_serialization(EN, example):
def test_sbd_serialization(EN):
"""
test that before and after serialization, the sentence boundaries are the same even
if the parser predicted two roots for the sentence that were made into two sentences
@ -168,6 +165,10 @@ def test_sbd_serialization(EN, example):
it introduced the second root node.
"""
example = EN.tokenizer.tokens_from_list(u"I bought a couch from IKEA. It was n't very comfortable .".split(' '))
EN.tagger(example)
apply_transition_sequence(EN, example, ['L-nsubj','S','L-det','R-dobj','D','R-prep','R-pobj','D','D','S','L-nsubj','R-ROOT','R-neg','D','S','L-advmod','R-acomp','D','R-punct'])
example_serialized = Doc(EN.vocab).from_bytes(example.to_bytes())
assert example.to_bytes() == example_serialized.to_bytes()