mirror of
https://github.com/explosion/spaCy.git
synced 2024-09-21 19:39:13 +03:00
8661218fe8
* Work on refactoring greedy parser * Compile updated parser * Fix refactored parser * Update test * Fix refactored parser * Fix refactored parser * Readd beam search after refactor * Fix beam search after refactor * Fix parser * Fix beam parsing * Support oracle segmentation in ud-train CLI command * Avoid relying on final gold check in beam search * Add a keyword argument sink to GoldParse * Bug fixes to beam search after refactor * Avoid importing fused token symbol in ud-run-test, untl that's added * Avoid importing fused token symbol in ud-run-test, untl that's added * Don't modify Token in global scope * Fix error in beam gradient calculation * Default to beam_update_prob 1 * Set a more aggressive threshold on the max violn update * Disable some tests to figure out why CI fails * Disable some tests to figure out why CI fails * Add some diagnostics to travis.yml to try to figure out why build fails * Tell Thinc to link against system blas on Travis * Point thinc to libblas on Travis * Try running sudo=true for travis * Unhack travis.sh * Restore beam_density argument for parser beam * Require thinc 6.11.1.dev16 * Revert hacks to tests * Revert hacks to travis.yml * Update thinc requirement * Fix parser model loading * Fix size limits in training data * Add missing name attribute for parser * Fix appveyor for Windows
85 lines
1.9 KiB
Python
85 lines
1.9 KiB
Python
# coding: utf8
|
|
from __future__ import unicode_literals
|
|
from thinc.neural import Model
|
|
import pytest
|
|
import numpy
|
|
|
|
from ..._ml import chain, Tok2Vec, doc2feats
|
|
from ...vocab import Vocab
|
|
from ...pipeline import Tensorizer
|
|
from ...syntax.arc_eager import ArcEager
|
|
from ...syntax.nn_parser import Parser
|
|
from ...tokens.doc import Doc
|
|
from ...gold import GoldParse
|
|
|
|
|
|
@pytest.fixture
|
|
def vocab():
|
|
return Vocab()
|
|
|
|
|
|
@pytest.fixture
|
|
def arc_eager(vocab):
|
|
actions = ArcEager.get_actions(left_labels=['L'], right_labels=['R'])
|
|
return ArcEager(vocab.strings, actions)
|
|
|
|
|
|
@pytest.fixture
|
|
def tok2vec():
|
|
return Tok2Vec(8, 100)
|
|
|
|
|
|
@pytest.fixture
|
|
def parser(vocab, arc_eager):
|
|
return Parser(vocab, moves=arc_eager, model=None)
|
|
|
|
@pytest.fixture
|
|
def model(arc_eager, tok2vec):
|
|
return Parser.Model(arc_eager.n_moves, token_vector_width=tok2vec.nO)[0]
|
|
|
|
@pytest.fixture
|
|
def doc(vocab):
|
|
return Doc(vocab, words=['a', 'b', 'c'])
|
|
|
|
@pytest.fixture
|
|
def gold(doc):
|
|
return GoldParse(doc, heads=[1, 1, 1], deps=['L', 'ROOT', 'R'])
|
|
|
|
|
|
def test_can_init_nn_parser(parser):
|
|
assert parser.model is None
|
|
|
|
|
|
def test_build_model(parser):
|
|
parser.model = Parser.Model(parser.moves.n_moves, hist_size=0)[0]
|
|
assert parser.model is not None
|
|
|
|
|
|
def test_predict_doc(parser, tok2vec, model, doc):
|
|
doc.tensor = tok2vec([doc])[0]
|
|
parser.model = model
|
|
parser(doc)
|
|
|
|
|
|
def test_update_doc(parser, model, doc, gold):
|
|
parser.model = model
|
|
def optimize(weights, gradient, key=None):
|
|
weights -= 0.001 * gradient
|
|
parser.update([doc], [gold], sgd=optimize)
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_predict_doc_beam(parser, model, doc):
|
|
parser.model = model
|
|
parser(doc, beam_width=32, beam_density=0.001)
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_update_doc_beam(parser, model, doc, gold):
|
|
parser.model = model
|
|
def optimize(weights, gradient, key=None):
|
|
weights -= 0.001 * gradient
|
|
parser.update_beam([doc], [gold], sgd=optimize)
|
|
|
|
|