mirror of
https://github.com/explosion/spaCy.git
synced 2025-01-24 08:14:15 +03:00
569cc98982
* Add load_from_config function * Add train_from_config script * Merge configs and expose via spacy.config * Fix script * Suggest create_evaluation_callback * Hard-code for NER * Fix errors * Register command * Add TODO * Update train-from-config todos * Fix imports * Allow delayed setting of parser model nr_class * Get train-from-config working * Tidy up and fix scores and printing * Hide traceback if cancelled * Fix weighted score formatting * Fix score formatting * Make output_path optional * Add Tok2Vec component * Tidy up and add tok2vec_tensors * Add option to copy docs in nlp.update * Copy docs in nlp.update * Adjust nlp.update() for set_annotations * Don't shuffle pipes in nlp.update, decruft * Support set_annotations arg in component update * Support set_annotations in parser update * Add get_gradients method * Add get_gradients to parser * Update errors.py * Fix problems caused by merge * Add _link_components method in nlp * Add concept of 'listeners' and ControlledModel * Support optional attributes arg in ControlledModel * Try having tok2vec component in pipeline * Fix tok2vec component * Fix config * Fix tok2vec * Update for Example * Update for Example * Update config * Add eg2doc util * Update and add schemas/types * Update schemas * Fix nlp.update * Fix tagger * Remove hacks from train-from-config * Remove hard-coded config str * Calculate loss in tok2vec component * Tidy up and use function signatures instead of models * Support union types for registry models * Minor cleaning in Language.update * Make ControlledModel specifically Tok2VecListener * Fix train_from_config * Fix tok2vec * Tidy up * Add function for bilstm tok2vec * Fix type * Fix syntax * Fix pytorch optimizer * Add example configs * Update for thinc describe changes * Update for Thinc changes * Update for dropout/sgd changes * Update for dropout/sgd changes * Unhack gradient update * Work on refactoring _ml * Remove _ml.py module * WIP upgrade cli scripts for thinc * Move some _ml stuff to util * Import link_vectors from util * Update train_from_config * Import from util * Import from util * Temporarily add ml.component_models module * Move ml methods * Move typedefs * Update load vectors * Update gitignore * Move imports * Add PrecomputableAffine * Fix imports * Fix imports * Fix imports * Fix missing imports * Update CLI scripts * Update spacy.language * Add stubs for building the models * Update model definition * Update create_default_optimizer * Fix import * Fix comment * Update imports in tests * Update imports in spacy.cli * Fix import * fix obsolete thinc imports * update srsly pin * from thinc to ml_datasets for example data such as imdb * update ml_datasets pin * using STATE.vectors * small fix * fix Sentencizer.pipe * black formatting * rename Affine to Linear as in thinc * set validate explicitely to True * rename with_square_sequences to with_list2padded * rename with_flatten to with_list2array * chaining layernorm * small fixes * revert Optimizer import * build_nel_encoder with new thinc style * fixes using model's get and set methods * Tok2Vec in component models, various fixes * fix up legacy tok2vec code * add model initialize calls * add in build_tagger_model * small fixes * setting model dims * fixes for ParserModel * various small fixes * initialize thinc Models * fixes * consistent naming of window_size * fixes, removing set_dropout * work around Iterable issue * remove legacy tok2vec * util fix * fix forward function of tok2vec listener * more fixes * trying to fix PrecomputableAffine (not succesful yet) * alloc instead of allocate * add morphologizer * rename residual * rename fixes * Fix predict function * Update parser and parser model * fixing few more tests * Fix precomputable affine * Update component model * Update parser model * Move backprop padding to own function, for test * Update test * Fix p. affine * Update NEL * build_bow_text_classifier and extract_ngrams * Fix parser init * Fix test add label * add build_simple_cnn_text_classifier * Fix parser init * Set gpu off by default in example * Fix tok2vec listener * Fix parser model * Small fixes * small fix for PyTorchLSTM parameters * revert my_compounding hack (iterable fixed now) * fix biLSTM * Fix uniqued * PyTorchRNNWrapper fix * small fixes * use helper function to calculate cosine loss * small fixes for build_simple_cnn_text_classifier * putting dropout default at 0.0 to ensure the layer gets built * using thinc util's set_dropout_rate * moving layer normalization inside of maxout definition to optimize dropout * temp debugging in NEL * fixed NEL model by using init defaults ! * fixing after set_dropout_rate refactor * proper fix * fix test_update_doc after refactoring optimizers in thinc * Add CharacterEmbed layer * Construct tagger Model * Add missing import * Remove unused stuff * Work on textcat * fix test (again :)) after optimizer refactor * fixes to allow reading Tagger from_disk without overwriting dimensions * don't build the tok2vec prematuraly * fix CharachterEmbed init * CharacterEmbed fixes * Fix CharacterEmbed architecture * fix imports * renames from latest thinc update * one more rename * add initialize calls where appropriate * fix parser initialization * Update Thinc version * Fix errors, auto-format and tidy up imports * Fix validation * fix if bias is cupy array * revert for now * ensure it's a numpy array before running bp in ParserStepModel * no reason to call require_gpu twice * use CupyOps.to_numpy instead of cupy directly * fix initialize of ParserModel * remove unnecessary import * fixes for CosineDistance * fix device renaming * use refactored loss functions (Thinc PR 251) * overfitting test for tagger * experimental settings for the tagger: avoid zero-init and subword normalization * clean up tagger overfitting test * use previous default value for nP * remove toy config * bringing layernorm back (had a bug - fixed in thinc) * revert setting nP explicitly * remove setting default in constructor * restore values as they used to be * add overfitting test for NER * add overfitting test for dep parser * add overfitting test for textcat * fixing init for linear (previously affine) * larger eps window for textcat * ensure doc is not None * Require newer thinc * Make float check vaguer * Slop the textcat overfit test more * Fix textcat test * Fix exclusive classes for textcat * fix after renaming of alloc methods * fixing renames and mandatory arguments (staticvectors WIP) * upgrade to thinc==8.0.0.dev3 * refer to vocab.vectors directly instead of its name * rename alpha to learn_rate * adding hashembed and staticvectors dropout * upgrade to thinc 8.0.0.dev4 * add name back to avoid warning W020 * thinc dev4 * update srsly * using thinc 8.0.0a0 ! Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com> Co-authored-by: Ines Montani <ines@ines.io>
138 lines
3.9 KiB
Python
138 lines
3.9 KiB
Python
import pytest
|
|
import os
|
|
import ctypes
|
|
from pathlib import Path
|
|
from spacy import util
|
|
from spacy import prefer_gpu, require_gpu
|
|
from spacy.compat import symlink_to, symlink_remove, is_windows
|
|
from spacy.ml._layers import PrecomputableAffine
|
|
from spacy.ml._layers import _backprop_precomputable_affine_padding
|
|
from subprocess import CalledProcessError
|
|
|
|
|
|
@pytest.fixture
|
|
def symlink_target():
|
|
return Path("./foo-target")
|
|
|
|
|
|
@pytest.fixture
|
|
def symlink():
|
|
return Path("./foo-symlink")
|
|
|
|
|
|
@pytest.fixture(scope="function")
|
|
def symlink_setup_target(request, symlink_target, symlink):
|
|
if not symlink_target.exists():
|
|
os.mkdir(str(symlink_target))
|
|
# yield -- need to cleanup even if assertion fails
|
|
# https://github.com/pytest-dev/pytest/issues/2508#issuecomment-309934240
|
|
|
|
def cleanup():
|
|
# Remove symlink only if it was created
|
|
if symlink.exists():
|
|
symlink_remove(symlink)
|
|
os.rmdir(str(symlink_target))
|
|
|
|
request.addfinalizer(cleanup)
|
|
|
|
|
|
@pytest.fixture
|
|
def is_admin():
|
|
"""Determine if the tests are run as admin or not."""
|
|
try:
|
|
admin = os.getuid() == 0
|
|
except AttributeError:
|
|
admin = ctypes.windll.shell32.IsUserAnAdmin() != 0
|
|
|
|
return admin
|
|
|
|
|
|
@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)
|
|
|
|
|
|
def test_PrecomputableAffine(nO=4, nI=5, nF=3, nP=2):
|
|
model = PrecomputableAffine(nO=nO, nI=nI, nF=nF, nP=nP)
|
|
assert model.get_param("W").shape == (nF, nO, nP, nI)
|
|
tensor = model.ops.alloc((10, nI))
|
|
Y, get_dX = model.begin_update(tensor)
|
|
assert Y.shape == (tensor.shape[0] + 1, nF, nO, nP)
|
|
dY = model.ops.alloc((15, nO, nP))
|
|
ids = model.ops.alloc((15, nF))
|
|
ids[1, 2] = -1
|
|
dY[1] = 1
|
|
assert not model.has_grad("pad")
|
|
d_pad = _backprop_precomputable_affine_padding(model, dY, ids)
|
|
assert d_pad[0, 2, 0, 0] == 1.0
|
|
ids.fill(0.0)
|
|
dY.fill(0.0)
|
|
dY[0] = 0
|
|
ids[1, 2] = 0
|
|
ids[1, 1] = -1
|
|
ids[1, 0] = -1
|
|
dY[1] = 1
|
|
ids[2, 0] = -1
|
|
dY[2] = 5
|
|
d_pad = _backprop_precomputable_affine_padding(model, dY, ids)
|
|
assert d_pad[0, 0, 0, 0] == 6
|
|
assert d_pad[0, 1, 0, 0] == 1
|
|
assert d_pad[0, 2, 0, 0] == 0
|
|
|
|
|
|
def test_prefer_gpu():
|
|
try:
|
|
import cupy # noqa: F401
|
|
except ImportError:
|
|
assert not prefer_gpu()
|
|
|
|
|
|
def test_require_gpu():
|
|
try:
|
|
import cupy # noqa: F401
|
|
except ImportError:
|
|
with pytest.raises(ValueError):
|
|
require_gpu()
|
|
|
|
|
|
def test_create_symlink_windows(
|
|
symlink_setup_target, symlink_target, symlink, is_admin
|
|
):
|
|
"""Test the creation of symlinks on windows. If run as admin or not on windows it should succeed, otherwise a CalledProcessError should be raised."""
|
|
assert symlink_target.exists()
|
|
|
|
if is_admin or not is_windows:
|
|
try:
|
|
symlink_to(symlink, symlink_target)
|
|
assert symlink.exists()
|
|
except CalledProcessError as e:
|
|
pytest.fail(e)
|
|
else:
|
|
with pytest.raises(CalledProcessError):
|
|
symlink_to(symlink, symlink_target)
|
|
|
|
assert not symlink.exists()
|
|
|
|
|
|
def test_ascii_filenames():
|
|
"""Test that all filenames in the project are ASCII.
|
|
See: https://twitter.com/_inesmontani/status/1177941471632211968
|
|
"""
|
|
root = Path(__file__).parent.parent
|
|
for path in root.glob("**/*"):
|
|
assert all(ord(c) < 128 for c in path.name), path.name
|