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

Merge remote-tracking branch 'refs/remotes/honnibal/master'

This commit is contained in:
maxirmx 2015-10-13 10:55:58 +03:00
parent 653ed854cd 7673e3a32c
commit 90c6c5fabf
2 changed files with 20 additions and 13 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
spacy/syntax/arc_eager.pyx
View File

@ -384,16 +384,16 @@ cdef class ArcEager(TransitionSystem):
for i in range(st.length): for i in range(st.length):
# Always attach spaces to the previous word # Always attach spaces to the previous word
if Lexeme.c_check_flag(st._sent[i].lex, IS_SPACE): if Lexeme.c_check_flag(st._sent[i].lex, IS_SPACE):
if i >= 1:
st.add_arc(i-1, i, st._sent[i].dep)
else:
st.add_arc(i+1, i, st._sent[i].dep)
if st._sent[i].sent_start and st._sent[i].head == -1: if st._sent[i].sent_start and st._sent[i].head == -1:
st._sent[i].sent_start = False st._sent[i].sent_start = False
# If we had this space token as the start of a sentence, # If we had this space token as the start of a sentence,
# move that sentence start forward one # move that sentence start forward one
if (i + 1) < st.length and not st._sent[i+1].sent_start: if (i + 1) < st.length and not st._sent[i+1].sent_start:
st._sent[i+1].sent_start = True st._sent[i+1].sent_start = True
if i >= 1:
st.add_arc(i-1, i, st._sent[i].dep)
else:
st.add_arc(i+1, i, st._sent[i].dep)
elif st._sent[i].head == 0 and st._sent[i].dep == 0: elif st._sent[i].head == 0 and st._sent[i].dep == 0:
st._sent[i].dep = self.root_label st._sent[i].dep = self.root_label
# If we're not using the Break transition, we segment via root-labelled # If we're not using the Break transition, we segment via root-labelled

25
tests/test_basic_load.py
View File

@ -25,28 +25,34 @@ from thinc.learner import LinearModel
class TestLoadVocab(unittest.TestCase): class TestLoadVocab(unittest.TestCase):
def test_load(self): def test_load(self):
vocab = Vocab.from_dir(path.join(English.default_data_dir(), 'vocab')) if path.exists(path.join(English.default_data_dir(), 'vocab')):
vocab = Vocab.from_dir(path.join(English.default_data_dir(), 'vocab'))
class TestLoadTokenizer(unittest.TestCase): class TestLoadTokenizer(unittest.TestCase):
def test_load(self): def test_load(self):
data_dir = English.default_data_dir() data_dir = English.default_data_dir()
vocab = Vocab.from_dir(path.join(data_dir, 'vocab')) if path.exists(path.join(data_dir, 'vocab')):
tokenizer = Tokenizer.from_dir(vocab, path.join(data_dir, 'tokenizer')) vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
tokenizer = Tokenizer.from_dir(vocab, path.join(data_dir, 'tokenizer'))
class TestLoadTagger(unittest.TestCase): class TestLoadTagger(unittest.TestCase):
def test_load(self): def test_load(self):
data_dir = English.default_data_dir() data_dir = English.default_data_dir()
vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
tagger = Tagger.from_dir(path.join(data_dir, 'tagger'), vocab) if path.exists(path.join(data_dir, 'vocab')):
vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
tagger = Tagger.from_dir(path.join(data_dir, 'tagger'), vocab)
class TestLoadParser(unittest.TestCase): class TestLoadParser(unittest.TestCase):
def test_load(self): def test_load(self):
data_dir = English.default_data_dir() data_dir = English.default_data_dir()
vocab = Vocab.from_dir(path.join(data_dir, 'vocab')) if path.exists(path.join(data_dir, 'vocab')):
parser = Parser.from_dir(path.join(data_dir, 'deps'), vocab.strings, ArcEager) vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
if path.exists(path.join(data_dir, 'deps')):
parser = Parser.from_dir(path.join(data_dir, 'deps'), vocab.strings, ArcEager)
def test_load_careful(self): def test_load_careful(self):
config_data = {"labels": {"0": {"": True}, "1": {"": True}, "2": {"cc": True, "agent": True, "ccomp": True, "prt": True, "meta": True, "nsubjpass": True, "csubj": True, "conj": True, "dobj": True, "neg": True, "csubjpass": True, "mark": True, "auxpass": True, "advcl": True, "aux": True, "ROOT": True, "prep": True, "parataxis": True, "xcomp": True, "nsubj": True, "nummod": True, "advmod": True, "punct": True, "relcl": True, "quantmod": True, "acomp": True, "compound": True, "pcomp": True, "intj": True, "poss": True, "npadvmod": True, "case": True, "attr": True, "dep": True, "appos": True, "det": True, "nmod": True, "amod": True, "dative": True, "pobj": True, "expl": True, "predet": True, "preconj": True, "oprd": True, "acl": True}, "3": {"cc": True, "agent": True, "ccomp": True, "prt": True, "meta": True, "nsubjpass": True, "csubj": True, "conj": True, "acl": True, "poss": True, "neg": True, "mark": True, "auxpass": True, "advcl": True, "aux": True, "amod": True, "ROOT": True, "prep": True, "parataxis": True, "xcomp": True, "nsubj": True, "nummod": True, "advmod": True, "punct": True, "quantmod": True, "acomp": True, "pcomp": True, "intj": True, "relcl": True, "npadvmod": True, "case": True, "attr": True, "dep": True, "appos": True, "det": True, "nmod": True, "dobj": True, "dative": True, "pobj": True, "iobj": True, "expl": True, "predet": True, "preconj": True, "oprd": True}, "4": {"ROOT": True}}, "seed": 0, "features": "basic", "beam_width": 1} config_data = {"labels": {"0": {"": True}, "1": {"": True}, "2": {"cc": True, "agent": True, "ccomp": True, "prt": True, "meta": True, "nsubjpass": True, "csubj": True, "conj": True, "dobj": True, "neg": True, "csubjpass": True, "mark": True, "auxpass": True, "advcl": True, "aux": True, "ROOT": True, "prep": True, "parataxis": True, "xcomp": True, "nsubj": True, "nummod": True, "advmod": True, "punct": True, "relcl": True, "quantmod": True, "acomp": True, "compound": True, "pcomp": True, "intj": True, "poss": True, "npadvmod": True, "case": True, "attr": True, "dep": True, "appos": True, "det": True, "nmod": True, "amod": True, "dative": True, "pobj": True, "expl": True, "predet": True, "preconj": True, "oprd": True, "acl": True}, "3": {"cc": True, "agent": True, "ccomp": True, "prt": True, "meta": True, "nsubjpass": True, "csubj": True, "conj": True, "acl": True, "poss": True, "neg": True, "mark": True, "auxpass": True, "advcl": True, "aux": True, "amod": True, "ROOT": True, "prep": True, "parataxis": True, "xcomp": True, "nsubj": True, "nummod": True, "advmod": True, "punct": True, "quantmod": True, "acomp": True, "pcomp": True, "intj": True, "relcl": True, "npadvmod": True, "case": True, "attr": True, "dep": True, "appos": True, "det": True, "nmod": True, "dobj": True, "dative": True, "pobj": True, "iobj": True, "expl": True, "predet": True, "preconj": True, "oprd": True}, "4": {"ROOT": True}}, "seed": 0, "features": "basic", "beam_width": 1}
@ -67,8 +73,9 @@ class TestLoadParser(unittest.TestCase):
# n classes. moves.n_moves above # n classes. moves.n_moves above
# n features. len(templates) + 1 above # n features. len(templates) + 1 above
model = LinearModel(92, 116) if path.exists(model_loc):
model.load(model_loc) model = LinearModel(92, 116)
model.load(model_loc)
if __name__ == '__main__': if __name__ == '__main__':