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 2015-10-11 16:47:49 +03:00
parent 356181944a afec8cac20
commit aab71668cd
1 changed files with 25 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
tests/test_basic_load.py
View File

@ -16,9 +16,12 @@ from spacy._ml import Model
from spacy.tagger import Tagger
from spacy.syntax.parser import Parser
from spacy.matcher import Matcher
from spacy.syntax.parser import get_templates
from spacy.en import English
from thinc.learner import LinearModel
class TestLoadVocab(unittest.TestCase):
def test_load(self):
@ -45,6 +48,28 @@ class TestLoadParser(unittest.TestCase):
vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
parser = Parser.from_dir(path.join(data_dir, 'deps'), vocab.strings, ArcEager)
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}
data_dir = English.default_data_dir()
vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
moves = ArcEager(vocab.strings, config_data['labels'])
templates = get_templates(config_data['features'])
model = Model(moves.n_moves, templates, path.join(data_dir, 'deps'))
parser = Parser(vocab.strings, moves, model)
def test_thinc_load(self):
data_dir = English.default_data_dir()
model_loc = path.join(data_dir, 'deps', 'model')
# n classes. moves.n_moves above
# n features. len(templates) + 1 above
model = LinearModel(92, 116)
model.load(model_loc)
if __name__ == '__main__':
unittest.main()