spaCy/spacy/tests/test_misc.py
Ines Montani 43b960c01b
Refactor pipeline components, config and language data (#5759)
* Update with WIP

* Update with WIP

* Update with pipeline serialization

* Update types and pipe factories

* Add deep merge, tidy up and add tests

* Fix pipe creation from config

* Don't validate default configs on load

* Update spacy/language.py

Co-authored-by: Ines Montani <ines@ines.io>

* Adjust factory/component meta error

* Clean up factory args and remove defaults

* Add test for failing empty dict defaults

* Update pipeline handling and methods

* provide KB as registry function instead of as object

* small change in test to make functionality more clear

* update example script for EL configuration

* Fix typo

* Simplify test

* Simplify test

* splitting pipes.pyx into separate files

* moving default configs to each component file

* fix batch_size type

* removing default values from component constructors where possible (TODO: test 4725)

* skip instead of xfail

* Add test for config -> nlp with multiple instances

* pipeline.pipes -> pipeline.pipe

* Tidy up, document, remove kwargs

* small cleanup/generalization for Tok2VecListener

* use DEFAULT_UPSTREAM field

* revert to avoid circular imports

* Fix tests

* Replace deprecated arg

* Make model dirs require config

* fix pickling of keyword-only arguments in constructor

* WIP: clean up and integrate full config

* Add helper to handle function args more reliably

Now also includes keyword-only args

* Fix config composition and serialization

* Improve config debugging and add visual diff

* Remove unused defaults and fix type

* Remove pipeline and factories from meta

* Update spacy/default_config.cfg

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>

* Update spacy/default_config.cfg

* small UX edits

* avoid printing stack trace for debug CLI commands

* Add support for language-specific factories

* specify the section of the config which holds the model to debug

* WIP: add Language.from_config

* Update with language data refactor WIP

* Auto-format

* Add backwards-compat handling for Language.factories

* Update morphologizer.pyx

* Fix morphologizer

* Update and simplify lemmatizers

* Fix Japanese tests

* Port over tagger changes

* Fix Chinese and tests

* Update to latest Thinc

* WIP: xfail first Russian lemmatizer test

* Fix component-specific overrides

* fix nO for output layers in debug_model

* Fix default value

* Fix tests and don't pass objects in config

* Fix deep merging

* Fix lemma lookup data registry

Only load the lookups if an entry is available in the registry (and if spacy-lookups-data is installed)

* Add types

* Add Vocab.from_config

* Fix typo

* Fix tests

* Make config copying more elegant

* Fix pipe analysis

* Fix lemmatizers and is_base_form

* WIP: move language defaults to config

* Fix morphology type

* Fix vocab

* Remove comment

* Update to latest Thinc

* Add morph rules to config

* Tidy up

* Remove set_morphology option from tagger factory

* Hack use_gpu

* Move [pipeline] to top-level block and make [nlp.pipeline] list

Allows separating component blocks from component order – otherwise, ordering the config would mean a changed component order, which is bad. Also allows initial config to define more components and not use all of them

* Fix use_gpu and resume in CLI

* Auto-format

* Remove resume from config

* Fix formatting and error

* [pipeline] -> [components]

* Fix types

* Fix tagger test: requires set_morphology?

Co-authored-by: Sofie Van Landeghem <svlandeg@users.noreply.github.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: Matthew Honnibal <honnibal+gh@gmail.com>
2020-07-22 13:42:59 +02:00

160 lines
4.5 KiB
Python

import pytest
import os
import ctypes
from pathlib import Path
from spacy.about import __version__ as spacy_version
from spacy import util
from spacy import prefer_gpu, require_gpu
from spacy.ml._precomputable_affine import PrecomputableAffine
from spacy.ml._precomputable_affine import _backprop_precomputable_affine_padding
@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,result", [("numpy", True), ("sfkodskfosdkfpsdpofkspdof", False)]
)
def test_util_is_package(package, result):
"""Test that an installed package via pip is recognised by util.is_package."""
assert util.is_package(package) is result
@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).initialize()
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_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
def test_load_model_blank_shortcut():
"""Test that using a model name like "blank:en" works as a shortcut for
spacy.blank("en").
"""
nlp = util.load_model("blank:en")
assert nlp.lang == "en"
assert nlp.pipeline == []
with pytest.raises(ImportError):
util.load_model("blank:fjsfijsdof")
@pytest.mark.parametrize(
"version,constraint,compatible",
[
(spacy_version, spacy_version, True),
(spacy_version, f">={spacy_version}", True),
("3.0.0", "2.0.0", False),
("3.2.1", ">=2.0.0", True),
("2.2.10a1", ">=1.0.0,<2.1.1", False),
("3.0.0.dev3", ">=1.2.3,<4.5.6", True),
("n/a", ">=1.2.3,<4.5.6", None),
("1.2.3", "n/a", None),
("n/a", "n/a", None),
],
)
def test_is_compatible_version(version, constraint, compatible):
assert util.is_compatible_version(version, constraint) is compatible
@pytest.mark.parametrize(
"constraint,expected",
[
("3.0.0", False),
("==3.0.0", False),
(">=2.3.0", True),
(">2.0.0", True),
("<=2.0.0", True),
(">2.0.0,<3.0.0", False),
(">=2.0.0,<3.0.0", False),
("!=1.1,>=1.0,~=1.0", True),
("n/a", None),
],
)
def test_is_unconstrained_version(constraint, expected):
assert util.is_unconstrained_version(constraint) is expected
@pytest.mark.parametrize(
"dot_notation,expected",
[
(
{"token.pos": True, "token._.xyz": True},
{"token": {"pos": True, "_": {"xyz": True}}},
),
(
{"training.batch_size": 128, "training.optimizer.learn_rate": 0.01},
{"training": {"batch_size": 128, "optimizer": {"learn_rate": 0.01}}},
),
],
)
def test_dot_to_dict(dot_notation, expected):
result = util.dot_to_dict(dot_notation)
assert result == expected
assert util.dict_to_dot(result) == dot_notation