mirror of
https://github.com/explosion/spaCy.git
synced 2024-11-11 04:08:09 +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
94 lines
3.3 KiB
Python
94 lines
3.3 KiB
Python
# coding: utf-8
|
|
from __future__ import unicode_literals
|
|
|
|
from ..util import ensure_path
|
|
from .. import util
|
|
from ..displacy import parse_deps, parse_ents
|
|
from ..tokens import Span
|
|
from .util import get_doc
|
|
from .._ml import PrecomputableAffine
|
|
|
|
from pathlib import Path
|
|
import pytest
|
|
from thinc.neural._classes.maxout import Maxout
|
|
from thinc.neural._classes.softmax import Softmax
|
|
from thinc.api import chain
|
|
|
|
|
|
@pytest.mark.parametrize('text', ['hello/world', 'hello world'])
|
|
def test_util_ensure_path_succeeds(text):
|
|
path = util.ensure_path(text)
|
|
assert isinstance(path, Path)
|
|
|
|
|
|
@pytest.mark.parametrize('package', ['numpy'])
|
|
def test_util_is_package(package):
|
|
"""Test that an installed package via pip is recognised by util.is_package."""
|
|
assert util.is_package(package)
|
|
|
|
|
|
@pytest.mark.parametrize('package', ['thinc'])
|
|
def test_util_get_package_path(package):
|
|
"""Test that a Path object is returned for a package name."""
|
|
path = util.get_package_path(package)
|
|
assert isinstance(path, Path)
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_displacy_parse_ents(en_vocab):
|
|
"""Test that named entities on a Doc are converted into displaCy's format."""
|
|
doc = get_doc(en_vocab, words=["But", "Google", "is", "starting", "from", "behind"])
|
|
doc.ents = [Span(doc, 1, 2, label=doc.vocab.strings[u'ORG'])]
|
|
ents = parse_ents(doc)
|
|
assert isinstance(ents, dict)
|
|
assert ents['text'] == 'But Google is starting from behind '
|
|
assert ents['ents'] == [{'start': 4, 'end': 10, 'label': 'ORG'}]
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_displacy_parse_deps(en_vocab):
|
|
"""Test that deps and tags on a Doc are converted into displaCy's format."""
|
|
words = ["This", "is", "a", "sentence"]
|
|
heads = [1, 0, 1, -2]
|
|
pos = ['DET', 'VERB', 'DET', 'NOUN']
|
|
tags = ['DT', 'VBZ', 'DT', 'NN']
|
|
deps = ['nsubj', 'ROOT', 'det', 'attr']
|
|
doc = get_doc(en_vocab, words=words, heads=heads, pos=pos, tags=tags,
|
|
deps=deps)
|
|
deps = parse_deps(doc)
|
|
assert isinstance(deps, dict)
|
|
assert deps['words'] == [{'text': 'This', 'tag': 'DET'},
|
|
{'text': 'is', 'tag': 'VERB'},
|
|
{'text': 'a', 'tag': 'DET'},
|
|
{'text': 'sentence', 'tag': 'NOUN'}]
|
|
assert deps['arcs'] == [{'start': 0, 'end': 1, 'label': 'nsubj', 'dir': 'left'},
|
|
{'start': 2, 'end': 3, 'label': 'det', 'dir': 'left'},
|
|
{'start': 1, 'end': 3, 'label': 'attr', 'dir': 'right'}]
|
|
|
|
|
|
@pytest.mark.xfail
|
|
def test_PrecomputableAffine(nO=4, nI=5, nF=3, nP=2):
|
|
model = PrecomputableAffine(nO=nO, nI=nI, nF=nF, nP=nP)
|
|
assert model.W.shape == (nF, nO, nP, nI)
|
|
tensor = model.ops.allocate((10, nI))
|
|
Y, get_dX = model.begin_update(tensor)
|
|
assert Y.shape == (tensor.shape[0]+1, nF, nO, nP)
|
|
assert model.d_pad.shape == (1, nF, nO, nP)
|
|
dY = model.ops.allocate((15, nO, nP))
|
|
ids = model.ops.allocate((15, nF))
|
|
ids[1,2] = -1
|
|
dY[1] = 1
|
|
assert model.d_pad[0, 2, 0, 0] == 0.
|
|
model._backprop_padding(dY, ids)
|
|
assert model.d_pad[0, 2, 0, 0] == 1.
|
|
model.d_pad.fill(0.)
|
|
ids.fill(0.)
|
|
dY.fill(0.)
|
|
ids[1,2] = -1
|
|
ids[1,1] = -1
|
|
ids[1,0] = -1
|
|
dY[1] = 1
|
|
assert model.d_pad[0, 2, 0, 0] == 0.
|
|
model._backprop_padding(dY, ids)
|
|
assert model.d_pad[0, 2, 0, 0] == 3.
|