mirror of https://github.com/explosion/spaCy.git
* Remove extraneous test files
This commit is contained in:
Matthew Honnibal
parent
6f47074214
commit
15eab7354f
|
|
@ -1,88 +0,0 @@
|
||||||
"""Some quick tests that don't depend on data files or on pytest, for debugging the
|
|
||||||
MS windows build issues."""
|
|
||||||
from __future__ import print_function, unicode_literals
|
|
||||||
|
|
||||||
import unittest
|
|
||||||
import re
|
|
||||||
|
|
||||||
from spacy.lemmatizer import Lemmatizer
|
|
||||||
from spacy.morphology import Morphology
|
|
||||||
from spacy.strings import StringStore
|
|
||||||
from spacy.vocab import Vocab
|
|
||||||
from spacy.tokenizer import Tokenizer
|
|
||||||
from spacy.syntax.arc_eager import ArcEager
|
|
||||||
from spacy.tagger import Tagger, TaggerModel
|
|
||||||
from spacy.syntax.parser import Parser, ParserModel
|
|
||||||
from spacy.matcher import Matcher
|
|
||||||
|
|
||||||
|
|
||||||
class TestStringStore(unittest.TestCase):
|
|
||||||
def test_encode_decode(self):
|
|
||||||
strings = StringStore()
|
|
||||||
hello_id = strings[u'Hello']
|
|
||||||
world_id = strings[u'World']
|
|
||||||
|
|
||||||
self.assertNotEqual(hello_id, world_id)
|
|
||||||
|
|
||||||
self.assertEqual(strings[hello_id], u'Hello')
|
|
||||||
self.assertEqual(strings[world_id], u'World')
|
|
||||||
|
|
||||||
self.assertEqual(strings[u'Hello'], hello_id)
|
|
||||||
self.assertEqual(strings[u'World'], world_id)
|
|
||||||
|
|
||||||
|
|
||||||
class TestMorphology(unittest.TestCase):
|
|
||||||
def test_create(self):
|
|
||||||
lemmatizer = Lemmatizer({}, {}, {})
|
|
||||||
strings = StringStore()
|
|
||||||
lemmatizer = Lemmatizer({}, {}, {})
|
|
||||||
morphology = Morphology(strings, {}, lemmatizer)
|
|
||||||
|
|
||||||
|
|
||||||
class TestVocab(unittest.TestCase):
|
|
||||||
def test_create(self):
|
|
||||||
vocab = Vocab()
|
|
||||||
|
|
||||||
def test_get_lexeme(self):
|
|
||||||
vocab = Vocab()
|
|
||||||
lexeme = vocab[u'Hello']
|
|
||||||
self.assertEqual(lexeme.orth_, u'Hello')
|
|
||||||
|
|
||||||
|
|
||||||
class TestTokenizer(unittest.TestCase):
|
|
||||||
def test_create(self):
|
|
||||||
vocab = Vocab()
|
|
||||||
dummy_re = re.compile(r'sklfb;s')
|
|
||||||
tokenizer = Tokenizer(vocab, {}, dummy_re, dummy_re, dummy_re)
|
|
||||||
doc = tokenizer(u'I am a document.')
|
|
||||||
|
|
||||||
self.assertEqual(len(doc), 4)
|
|
||||||
|
|
||||||
|
|
||||||
class TestTagger(unittest.TestCase):
|
|
||||||
def test_create(self):
|
|
||||||
vocab = Vocab()
|
|
||||||
templates = ((1,),)
|
|
||||||
model = TaggerModel(vocab.morphology.n_tags, templates)
|
|
||||||
tagger = Tagger(vocab, model)
|
|
||||||
|
|
||||||
|
|
||||||
class TestParser(unittest.TestCase):
|
|
||||||
def test_create(self):
|
|
||||||
vocab = Vocab()
|
|
||||||
templates = ((1,),)
|
|
||||||
labels_by_action = {0: ['One', 'Two'], 1: ['Two', 'Three']}
|
|
||||||
transition_system = ArcEager(vocab.strings, labels_by_action)
|
|
||||||
model = ParserModel(transition_system.n_moves, templates)
|
|
||||||
|
|
||||||
parser = Parser(vocab.strings, transition_system, model)
|
|
||||||
|
|
||||||
|
|
||||||
class TestMatcher(unittest.TestCase):
|
|
||||||
def test_create(self):
|
|
||||||
vocab = Vocab()
|
|
||||||
matcher = Matcher(vocab, {})
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
|
||||||
unittest.main()
|
|
||||||
|
|
@ -1,69 +0,0 @@
|
||||||
"""Some quick tests that don't depend on data files or on pytest, for debugging the
|
|
||||||
MS windows build issues."""
|
|
||||||
from __future__ import print_function, unicode_literals
|
|
||||||
|
|
||||||
import unittest
|
|
||||||
import re
|
|
||||||
from os import path
|
|
||||||
|
|
||||||
from spacy.lemmatizer import Lemmatizer
|
|
||||||
from spacy.morphology import Morphology
|
|
||||||
from spacy.strings import StringStore
|
|
||||||
from spacy.vocab import Vocab
|
|
||||||
from spacy.tokenizer import Tokenizer
|
|
||||||
from spacy.syntax.arc_eager import ArcEager
|
|
||||||
from spacy.tagger import Tagger
|
|
||||||
from spacy.syntax.parser import Parser, ParserModel
|
|
||||||
from spacy.matcher import Matcher
|
|
||||||
from spacy.syntax.parser import get_templates
|
|
||||||
|
|
||||||
from spacy.en import English
|
|
||||||
|
|
||||||
|
|
||||||
class TestLoadVocab(unittest.TestCase):
|
|
||||||
def test_load(self):
|
|
||||||
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):
|
|
||||||
def test_load(self):
|
|
||||||
data_dir = English.default_data_dir()
|
|
||||||
if path.exists(path.join(data_dir, 'vocab')):
|
|
||||||
vocab = Vocab.from_dir(path.join(data_dir, 'vocab'))
|
|
||||||
tokenizer = Tokenizer.from_dir(vocab, path.join(data_dir, 'tokenizer'))
|
|
||||||
|
|
||||||
|
|
||||||
class TestLoadTagger(unittest.TestCase):
|
|
||||||
def test_load(self):
|
|
||||||
data_dir = English.default_data_dir()
|
|
||||||
|
|
||||||
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):
|
|
||||||
def test_load(self):
|
|
||||||
data_dir = English.default_data_dir()
|
|
||||||
if path.exists(path.join(data_dir, 'vocab')):
|
|
||||||
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)
|
|
||||||
|
|
||||||
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 = ParserModel(moves.n_moves, templates)
|
|
||||||
model.load(path.join(data_dir, 'deps', 'model'))
|
|
||||||
|
|
||||||
parser = Parser(vocab.strings, moves, model)
|
|
||||||
|
|
||||||
|
|
||||||
if __name__ == '__main__':
|
|
||||||
unittest.main()
|
|
||||||
Loading…
Reference in New Issue