2018-07-24 21:38:44 +00:00
|
|
|
import numpy
|
2021-12-04 19:34:48 +00:00
|
|
|
import pytest
|
|
|
|
from numpy.testing import assert_allclose, assert_almost_equal, assert_equal
|
|
|
|
from thinc.api import NumpyOps, get_current_ops
|
|
|
|
|
2021-10-27 12:08:31 +00:00
|
|
|
from spacy.lang.en import English
|
🏷 Add Mypy check to CI and ignore all existing Mypy errors (#9167)
* 🚨 Ignore all existing Mypy errors
* 🏗 Add Mypy check to CI
* Add types-mock and types-requests as dev requirements
* Add additional type ignore directives
* Add types packages to dev-only list in reqs test
* Add types-dataclasses for python 3.6
* Add ignore to pretrain
* 🏷 Improve type annotation on `run_command` helper
The `run_command` helper previously declared that it returned an
`Optional[subprocess.CompletedProcess]`, but it isn't actually possible
for the function to return `None`. These changes modify the type
annotation of the `run_command` helper and remove all now-unnecessary
`# type: ignore` directives.
* 🔧 Allow variable type redefinition in limited contexts
These changes modify how Mypy is configured to allow variables to have
their type automatically redefined under certain conditions. The Mypy
documentation contains the following example:
```python
def process(items: List[str]) -> None:
# 'items' has type List[str]
items = [item.split() for item in items]
# 'items' now has type List[List[str]]
...
```
This configuration change is especially helpful in reducing the number
of `# type: ignore` directives needed to handle the common pattern of:
* Accepting a filepath as a string
* Overwriting the variable using `filepath = ensure_path(filepath)`
These changes enable redefinition and remove all `# type: ignore`
directives rendered redundant by this change.
* 🏷 Add type annotation to converters mapping
* 🚨 Fix Mypy error in convert CLI argument verification
* 🏷 Improve type annotation on `resolve_dot_names` helper
* 🏷 Add type annotations for `Vocab` attributes `strings` and `vectors`
* 🏷 Add type annotations for more `Vocab` attributes
* 🏷 Add loose type annotation for gold data compilation
* 🏷 Improve `_format_labels` type annotation
* 🏷 Fix `get_lang_class` type annotation
* 🏷 Loosen return type of `Language.evaluate`
* 🏷 Don't accept `Scorer` in `handle_scores_per_type`
* 🏷 Add `string_to_list` overloads
* 🏷 Fix non-Optional command-line options
* 🙈 Ignore redefinition of `wandb_logger` in `loggers.py`
* ➕ Install `typing_extensions` in Python 3.8+
The `typing_extensions` package states that it should be used when
"writing code that must be compatible with multiple Python versions".
Since SpaCy needs to support multiple Python versions, it should be used
when newer `typing` module members are required. One example of this is
`Literal`, which is available starting with Python 3.8.
Previously SpaCy tried to import `Literal` from `typing`, falling back
to `typing_extensions` if the import failed. However, Mypy doesn't seem
to be able to understand what `Literal` means when the initial import
means. Therefore, these changes modify how `compat` imports `Literal` by
always importing it from `typing_extensions`.
These changes also modify how `typing_extensions` is installed, so that
it is a requirement for all Python versions, including those greater
than or equal to 3.8.
* 🏷 Improve type annotation for `Language.pipe`
These changes add a missing overload variant to the type signature of
`Language.pipe`. Additionally, the type signature is enhanced to allow
type checkers to differentiate between the two overload variants based
on the `as_tuple` parameter.
Fixes #8772
* ➖ Don't install `typing-extensions` in Python 3.8+
After more detailed analysis of how to implement Python version-specific
type annotations using SpaCy, it has been determined that by branching
on a comparison against `sys.version_info` can be statically analyzed by
Mypy well enough to enable us to conditionally use
`typing_extensions.Literal`. This means that we no longer need to
install `typing_extensions` for Python versions greater than or equal to
3.8! 🎉
These changes revert previous changes installing `typing-extensions`
regardless of Python version and modify how we import the `Literal` type
to ensure that Mypy treats it properly.
* resolve mypy errors for Strict pydantic types
* refactor code to avoid missing return statement
* fix types of convert CLI command
* avoid list-set confustion in debug_data
* fix typo and formatting
* small fixes to avoid type ignores
* fix types in profile CLI command and make it more efficient
* type fixes in projects CLI
* put one ignore back
* type fixes for render
* fix render types - the sequel
* fix BaseDefault in language definitions
* fix type of noun_chunks iterator - yields tuple instead of span
* fix types in language-specific modules
* 🏷 Expand accepted inputs of `get_string_id`
`get_string_id` accepts either a string (in which case it returns its
ID) or an ID (in which case it immediately returns the ID). These
changes extend the type annotation of `get_string_id` to indicate that
it can accept either strings or IDs.
* 🏷 Handle override types in `combine_score_weights`
The `combine_score_weights` function allows users to pass an `overrides`
mapping to override data extracted from the `weights` argument. Since it
allows `Optional` dictionary values, the return value may also include
`Optional` dictionary values.
These changes update the type annotations for `combine_score_weights` to
reflect this fact.
* 🏷 Fix tokenizer serialization method signatures in `DummyTokenizer`
* 🏷 Fix redefinition of `wandb_logger`
These changes fix the redefinition of `wandb_logger` by giving a
separate name to each `WandbLogger` version. For
backwards-compatibility, `spacy.train` still exports `wandb_logger_v3`
as `wandb_logger` for now.
* more fixes for typing in language
* type fixes in model definitions
* 🏷 Annotate `_RandomWords.probs` as `NDArray`
* 🏷 Annotate `tok2vec` layers to help Mypy
* 🐛 Fix `_RandomWords.probs` type annotations for Python 3.6
Also remove an import that I forgot to move to the top of the module 😅
* more fixes for matchers and other pipeline components
* quick fix for entity linker
* fixing types for spancat, textcat, etc
* bugfix for tok2vec
* type annotations for scorer
* add runtime_checkable for Protocol
* type and import fixes in tests
* mypy fixes for training utilities
* few fixes in util
* fix import
* 🐵 Remove unused `# type: ignore` directives
* 🏷 Annotate `Language._components`
* 🏷 Annotate `spacy.pipeline.Pipe`
* add doc as property to span.pyi
* small fixes and cleanup
* explicit type annotations instead of via comment
Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>
Co-authored-by: svlandeg <sofie.vanlandeghem@gmail.com>
Co-authored-by: svlandeg <svlandeg@github.com>
2021-10-14 13:21:40 +00:00
|
|
|
from spacy.strings import hash_string # type: ignore
|
2021-12-04 19:34:48 +00:00
|
|
|
from spacy.tokenizer import Tokenizer
|
2018-07-24 21:38:44 +00:00
|
|
|
from spacy.tokens import Doc
|
2021-10-27 12:08:31 +00:00
|
|
|
from spacy.training.initialize import convert_vectors
|
2021-12-04 19:34:48 +00:00
|
|
|
from spacy.vectors import Vectors
|
|
|
|
from spacy.vocab import Vocab
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2020-05-21 16:39:06 +00:00
|
|
|
from ..util import add_vecs_to_vocab, get_cosine, make_tempdir
|
2015-09-14 07:48:13 +00:00
|
|
|
|
2021-04-22 12:58:29 +00:00
|
|
|
OPS = get_current_ops()
|
2017-01-13 13:29:54 +00:00
|
|
|
|
2021-06-28 09:48:00 +00:00
|
|
|
|
2017-01-13 13:29:54 +00:00
|
|
|
@pytest.fixture
|
2017-06-05 10:32:49 +00:00
|
|
|
def strings():
|
|
|
|
return ["apple", "orange"]
|
2017-01-13 13:29:54 +00:00
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2017-08-19 18:34:58 +00:00
|
|
|
@pytest.fixture
|
|
|
|
def vectors():
|
|
|
|
return [
|
2021-04-22 12:58:29 +00:00
|
|
|
("apple", OPS.asarray([1, 2, 3])),
|
|
|
|
("orange", OPS.asarray([-1, -2, -3])),
|
|
|
|
("and", OPS.asarray([-1, -1, -1])),
|
|
|
|
("juice", OPS.asarray([5, 5, 10])),
|
|
|
|
("pie", OPS.asarray([7, 6.3, 8.9])),
|
2018-11-27 00:09:36 +00:00
|
|
|
]
|
2017-08-19 18:34:58 +00:00
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2017-06-05 10:32:49 +00:00
|
|
|
@pytest.fixture
|
|
|
|
def data():
|
2018-11-27 00:09:36 +00:00
|
|
|
return numpy.asarray([[0.0, 1.0, 2.0], [3.0, -2.0, 4.0]], dtype="f")
|
2017-06-05 10:32:49 +00:00
|
|
|
|
2019-10-18 09:27:38 +00:00
|
|
|
|
2019-10-16 21:18:55 +00:00
|
|
|
@pytest.fixture
|
|
|
|
def most_similar_vectors_data():
|
2019-10-18 09:27:38 +00:00
|
|
|
return numpy.asarray(
|
|
|
|
[[0.0, 1.0, 2.0], [1.0, -2.0, 4.0], [1.0, 1.0, -1.0], [2.0, 3.0, 1.0]],
|
|
|
|
dtype="f",
|
|
|
|
)
|
2019-10-16 21:18:55 +00:00
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2020-05-19 14:41:26 +00:00
|
|
|
@pytest.fixture
|
|
|
|
def most_similar_vectors_keys():
|
|
|
|
return ["a", "b", "c", "d"]
|
|
|
|
|
|
|
|
|
2018-03-31 11:28:25 +00:00
|
|
|
@pytest.fixture
|
|
|
|
def resize_data():
|
2018-11-27 00:09:36 +00:00
|
|
|
return numpy.asarray([[0.0, 1.0], [2.0, 3.0]], dtype="f")
|
2017-06-05 10:32:49 +00:00
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2017-08-19 18:34:58 +00:00
|
|
|
@pytest.fixture()
|
|
|
|
def vocab(en_vocab, vectors):
|
|
|
|
add_vecs_to_vocab(en_vocab, vectors)
|
|
|
|
return en_vocab
|
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
|
|
|
@pytest.fixture()
|
|
|
|
def tokenizer_v(vocab):
|
|
|
|
return Tokenizer(vocab, {}, None, None, None)
|
|
|
|
|
|
|
|
|
2021-12-04 19:34:48 +00:00
|
|
|
@pytest.mark.issue(1518)
|
|
|
|
def test_issue1518():
|
|
|
|
"""Test vectors.resize() works."""
|
|
|
|
vectors = Vectors(shape=(10, 10))
|
|
|
|
vectors.add("hello", row=2)
|
|
|
|
vectors.resize((5, 9))
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.mark.issue(1539)
|
|
|
|
def test_issue1539():
|
|
|
|
"""Ensure vectors.resize() doesn't try to modify dictionary during iteration."""
|
|
|
|
v = Vectors(shape=(10, 10), keys=[5, 3, 98, 100])
|
|
|
|
v.resize((100, 100))
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.mark.issue(1807)
|
|
|
|
def test_issue1807():
|
|
|
|
"""Test vocab.set_vector also adds the word to the vocab."""
|
|
|
|
vocab = Vocab(vectors_name="test_issue1807")
|
|
|
|
assert "hello" not in vocab
|
|
|
|
vocab.set_vector("hello", numpy.ones((50,), dtype="f"))
|
|
|
|
assert "hello" in vocab
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.mark.issue(2871)
|
|
|
|
def test_issue2871():
|
|
|
|
"""Test that vectors recover the correct key for spaCy reserved words."""
|
|
|
|
words = ["dog", "cat", "SUFFIX"]
|
|
|
|
vocab = Vocab(vectors_name="test_issue2871")
|
|
|
|
vocab.vectors.resize(shape=(3, 10))
|
|
|
|
vector_data = numpy.zeros((3, 10), dtype="f")
|
|
|
|
for word in words:
|
|
|
|
_ = vocab[word] # noqa: F841
|
|
|
|
vocab.set_vector(word, vector_data[0])
|
|
|
|
vocab.vectors.name = "dummy_vectors"
|
|
|
|
assert vocab["dog"].rank == 0
|
|
|
|
assert vocab["cat"].rank == 1
|
|
|
|
assert vocab["SUFFIX"].rank == 2
|
|
|
|
assert vocab.vectors.find(key="dog") == 0
|
|
|
|
assert vocab.vectors.find(key="cat") == 1
|
|
|
|
assert vocab.vectors.find(key="SUFFIX") == 2
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.mark.issue(3412)
|
|
|
|
def test_issue3412():
|
|
|
|
data = numpy.asarray([[0, 0, 0], [1, 2, 3], [9, 8, 7]], dtype="f")
|
|
|
|
vectors = Vectors(data=data, keys=["A", "B", "C"])
|
|
|
|
keys, best_rows, scores = vectors.most_similar(
|
|
|
|
numpy.asarray([[9, 8, 7], [0, 0, 0]], dtype="f")
|
|
|
|
)
|
|
|
|
assert best_rows[0] == 2
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.mark.issue(4725)
|
|
|
|
def test_issue4725_2():
|
|
|
|
if isinstance(get_current_ops, NumpyOps):
|
|
|
|
# ensures that this runs correctly and doesn't hang or crash because of the global vectors
|
|
|
|
# if it does crash, it's usually because of calling 'spawn' for multiprocessing (e.g. on Windows),
|
|
|
|
# or because of issues with pickling the NER (cf test_issue4725_1)
|
|
|
|
vocab = Vocab(vectors_name="test_vocab_add_vector")
|
|
|
|
data = numpy.ndarray((5, 3), dtype="f")
|
|
|
|
data[0] = 1.0
|
|
|
|
data[1] = 2.0
|
|
|
|
vocab.set_vector("cat", data[0])
|
|
|
|
vocab.set_vector("dog", data[1])
|
|
|
|
nlp = English(vocab=vocab)
|
|
|
|
nlp.add_pipe("ner")
|
|
|
|
nlp.initialize()
|
|
|
|
docs = ["Kurt is in London."] * 10
|
|
|
|
for _ in nlp.pipe(docs, batch_size=2, n_process=2):
|
|
|
|
pass
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
def test_init_vectors_with_resize_shape(strings, resize_data):
|
2018-03-31 11:28:25 +00:00
|
|
|
v = Vectors(shape=(len(strings), 3))
|
|
|
|
v.resize(shape=resize_data.shape)
|
|
|
|
assert v.shape == resize_data.shape
|
|
|
|
assert v.shape != (len(strings), 3)
|
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
def test_init_vectors_with_resize_data(data, resize_data):
|
2018-03-31 11:28:25 +00:00
|
|
|
v = Vectors(data=data)
|
|
|
|
v.resize(shape=resize_data.shape)
|
|
|
|
assert v.shape == resize_data.shape
|
|
|
|
assert v.shape != data.shape
|
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2020-03-29 11:51:20 +00:00
|
|
|
def test_get_vector_resize(strings, data):
|
2018-03-31 11:28:25 +00:00
|
|
|
strings = [hash_string(s) for s in strings]
|
2020-03-29 11:51:20 +00:00
|
|
|
|
|
|
|
# decrease vector dimension (truncate)
|
|
|
|
v = Vectors(data=data)
|
|
|
|
resized_dim = v.shape[1] - 1
|
|
|
|
v.resize(shape=(v.shape[0], resized_dim))
|
|
|
|
for i, string in enumerate(strings):
|
|
|
|
v.add(string, row=i)
|
|
|
|
|
|
|
|
assert list(v[strings[0]]) == list(data[0, :resized_dim])
|
|
|
|
assert list(v[strings[1]]) == list(data[1, :resized_dim])
|
|
|
|
|
|
|
|
# increase vector dimension (pad with zeros)
|
|
|
|
v = Vectors(data=data)
|
|
|
|
resized_dim = v.shape[1] + 1
|
|
|
|
v.resize(shape=(v.shape[0], resized_dim))
|
2018-03-31 11:28:25 +00:00
|
|
|
for i, string in enumerate(strings):
|
|
|
|
v.add(string, row=i)
|
|
|
|
|
2020-03-29 11:51:20 +00:00
|
|
|
assert list(v[strings[0]]) == list(data[0]) + [0]
|
|
|
|
assert list(v[strings[1]]) == list(data[1]) + [0]
|
2017-08-19 18:34:58 +00:00
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2017-06-05 10:32:49 +00:00
|
|
|
def test_init_vectors_with_data(strings, data):
|
2017-10-31 17:25:08 +00:00
|
|
|
v = Vectors(data=data)
|
2017-06-05 10:32:49 +00:00
|
|
|
assert v.shape == data.shape
|
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2017-10-31 17:25:08 +00:00
|
|
|
def test_init_vectors_with_shape(strings):
|
|
|
|
v = Vectors(shape=(len(strings), 3))
|
2017-06-05 10:32:49 +00:00
|
|
|
assert v.shape == (len(strings), 3)
|
2021-10-27 12:08:31 +00:00
|
|
|
assert v.is_full is False
|
2017-06-05 10:32:49 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_get_vector(strings, data):
|
2017-10-31 17:25:08 +00:00
|
|
|
v = Vectors(data=data)
|
2017-11-01 12:24:47 +00:00
|
|
|
strings = [hash_string(s) for s in strings]
|
2017-10-31 17:25:08 +00:00
|
|
|
for i, string in enumerate(strings):
|
|
|
|
v.add(string, row=i)
|
2017-06-05 10:32:49 +00:00
|
|
|
assert list(v[strings[0]]) == list(data[0])
|
|
|
|
assert list(v[strings[0]]) != list(data[1])
|
|
|
|
assert list(v[strings[1]]) != list(data[0])
|
|
|
|
|
|
|
|
|
|
|
|
def test_set_vector(strings, data):
|
|
|
|
orig = data.copy()
|
2017-10-31 17:25:08 +00:00
|
|
|
v = Vectors(data=data)
|
2017-11-01 12:24:47 +00:00
|
|
|
strings = [hash_string(s) for s in strings]
|
2017-10-31 17:25:08 +00:00
|
|
|
for i, string in enumerate(strings):
|
|
|
|
v.add(string, row=i)
|
2017-06-05 10:32:49 +00:00
|
|
|
assert list(v[strings[0]]) == list(orig[0])
|
|
|
|
assert list(v[strings[0]]) != list(orig[1])
|
|
|
|
v[strings[0]] = data[1]
|
|
|
|
assert list(v[strings[0]]) == list(orig[1])
|
|
|
|
assert list(v[strings[0]]) != list(orig[0])
|
|
|
|
|
|
|
|
|
2020-05-19 14:41:26 +00:00
|
|
|
def test_vectors_most_similar(most_similar_vectors_data, most_similar_vectors_keys):
|
|
|
|
v = Vectors(data=most_similar_vectors_data, keys=most_similar_vectors_keys)
|
2019-10-16 21:18:55 +00:00
|
|
|
_, best_rows, _ = v.most_similar(v.data, batch_size=2, n=2, sort=True)
|
|
|
|
assert all(row[0] == i for i, row in enumerate(best_rows))
|
|
|
|
|
2020-05-19 14:41:26 +00:00
|
|
|
with pytest.raises(ValueError):
|
|
|
|
v.most_similar(v.data, batch_size=2, n=10, sort=True)
|
|
|
|
|
2019-10-16 21:18:55 +00:00
|
|
|
|
2019-10-22 16:18:43 +00:00
|
|
|
def test_vectors_most_similar_identical():
|
|
|
|
"""Test that most similar identical vectors are assigned a score of 1.0."""
|
|
|
|
data = numpy.asarray([[4, 2, 2, 2], [4, 2, 2, 2], [1, 1, 1, 1]], dtype="f")
|
|
|
|
v = Vectors(data=data, keys=["A", "B", "C"])
|
|
|
|
keys, _, scores = v.most_similar(numpy.asarray([[4, 2, 2, 2]], dtype="f"))
|
|
|
|
assert scores[0][0] == 1.0 # not 1.0000002
|
|
|
|
data = numpy.asarray([[1, 2, 3], [1, 2, 3], [1, 1, 1]], dtype="f")
|
|
|
|
v = Vectors(data=data, keys=["A", "B", "C"])
|
|
|
|
keys, _, scores = v.most_similar(numpy.asarray([[1, 2, 3]], dtype="f"))
|
|
|
|
assert scores[0][0] == 1.0 # not 0.9999999
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", ["apple and orange"])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_token_vector(tokenizer_v, vectors, text):
|
|
|
|
doc = tokenizer_v(text)
|
2021-04-22 12:58:29 +00:00
|
|
|
assert vectors[0][0] == doc[0].text
|
|
|
|
assert all([a == b for a, b in zip(vectors[0][1], doc[0].vector)])
|
|
|
|
assert vectors[1][0] == doc[2].text
|
|
|
|
assert all([a == b for a, b in zip(vectors[1][1], doc[2].vector)])
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", ["apple", "orange"])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_lexeme_vector(vocab, text):
|
|
|
|
lex = vocab[text]
|
|
|
|
assert list(lex.vector)
|
|
|
|
assert lex.vector_norm
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", [["apple", "and", "orange"]])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_doc_vector(vocab, text):
|
2018-07-24 21:38:44 +00:00
|
|
|
doc = Doc(vocab, words=text)
|
2017-08-19 18:34:58 +00:00
|
|
|
assert list(doc.vector)
|
|
|
|
assert doc.vector_norm
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", [["apple", "and", "orange"]])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_span_vector(vocab, text):
|
2018-07-24 21:38:44 +00:00
|
|
|
span = Doc(vocab, words=text)[0:2]
|
2017-08-19 18:34:58 +00:00
|
|
|
assert list(span.vector)
|
|
|
|
assert span.vector_norm
|
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", ["apple orange"])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_token_token_similarity(tokenizer_v, text):
|
|
|
|
doc = tokenizer_v(text)
|
|
|
|
assert doc[0].similarity(doc[1]) == doc[1].similarity(doc[0])
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < doc[0].similarity(doc[1]) < 1.0
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text1,text2", [("apple", "orange")])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_token_lexeme_similarity(tokenizer_v, vocab, text1, text2):
|
|
|
|
token = tokenizer_v(text1)
|
|
|
|
lex = vocab[text2]
|
|
|
|
assert token.similarity(lex) == lex.similarity(token)
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < token.similarity(lex) < 1.0
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", [["apple", "orange", "juice"]])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_token_span_similarity(vocab, text):
|
2018-07-24 21:38:44 +00:00
|
|
|
doc = Doc(vocab, words=text)
|
2017-08-19 18:34:58 +00:00
|
|
|
assert doc[0].similarity(doc[1:3]) == doc[1:3].similarity(doc[0])
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < doc[0].similarity(doc[1:3]) < 1.0
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", [["apple", "orange", "juice"]])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_token_doc_similarity(vocab, text):
|
2018-07-24 21:38:44 +00:00
|
|
|
doc = Doc(vocab, words=text)
|
2017-08-19 18:34:58 +00:00
|
|
|
assert doc[0].similarity(doc) == doc.similarity(doc[0])
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < doc[0].similarity(doc) < 1.0
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", [["apple", "orange", "juice"]])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_lexeme_span_similarity(vocab, text):
|
2018-07-24 21:38:44 +00:00
|
|
|
doc = Doc(vocab, words=text)
|
2017-08-19 18:34:58 +00:00
|
|
|
lex = vocab[text[0]]
|
|
|
|
assert lex.similarity(doc[1:3]) == doc[1:3].similarity(lex)
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < doc.similarity(doc[1:3]) < 1.0
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text1,text2", [("apple", "orange")])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_lexeme_lexeme_similarity(vocab, text1, text2):
|
|
|
|
lex1 = vocab[text1]
|
|
|
|
lex2 = vocab[text2]
|
|
|
|
assert lex1.similarity(lex2) == lex2.similarity(lex1)
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < lex1.similarity(lex2) < 1.0
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", [["apple", "orange", "juice"]])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_lexeme_doc_similarity(vocab, text):
|
2018-07-24 21:38:44 +00:00
|
|
|
doc = Doc(vocab, words=text)
|
2017-08-19 18:34:58 +00:00
|
|
|
lex = vocab[text[0]]
|
|
|
|
assert lex.similarity(doc) == doc.similarity(lex)
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < lex.similarity(doc) < 1.0
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", [["apple", "orange", "juice"]])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_span_span_similarity(vocab, text):
|
2018-07-24 21:38:44 +00:00
|
|
|
doc = Doc(vocab, words=text)
|
2019-02-10 13:02:19 +00:00
|
|
|
with pytest.warns(UserWarning):
|
2018-05-20 23:22:38 +00:00
|
|
|
assert doc[0:2].similarity(doc[1:3]) == doc[1:3].similarity(doc[0:2])
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < doc[0:2].similarity(doc[1:3]) < 1.0
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize("text", [["apple", "orange", "juice"]])
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_span_doc_similarity(vocab, text):
|
2018-07-24 21:38:44 +00:00
|
|
|
doc = Doc(vocab, words=text)
|
2019-02-10 13:02:19 +00:00
|
|
|
with pytest.warns(UserWarning):
|
2018-05-20 23:22:38 +00:00
|
|
|
assert doc[0:2].similarity(doc) == doc.similarity(doc[0:2])
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < doc[0:2].similarity(doc) < 1.0
|
2017-08-19 18:34:58 +00:00
|
|
|
|
|
|
|
|
2018-11-27 00:09:36 +00:00
|
|
|
@pytest.mark.parametrize(
|
|
|
|
"text1,text2", [(["apple", "and", "apple", "pie"], ["orange", "juice"])]
|
|
|
|
)
|
2017-08-19 18:34:58 +00:00
|
|
|
def test_vectors_doc_doc_similarity(vocab, text1, text2):
|
2018-07-24 21:38:44 +00:00
|
|
|
doc1 = Doc(vocab, words=text1)
|
|
|
|
doc2 = Doc(vocab, words=text2)
|
2017-08-19 18:34:58 +00:00
|
|
|
assert doc1.similarity(doc2) == doc2.similarity(doc1)
|
2018-11-27 00:09:36 +00:00
|
|
|
assert -1.0 < doc1.similarity(doc2) < 1.0
|
2018-07-24 21:38:44 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_vocab_add_vector():
|
2019-09-16 13:16:54 +00:00
|
|
|
vocab = Vocab(vectors_name="test_vocab_add_vector")
|
2021-04-22 12:58:29 +00:00
|
|
|
data = OPS.xp.ndarray((5, 3), dtype="f")
|
2018-11-27 00:09:36 +00:00
|
|
|
data[0] = 1.0
|
|
|
|
data[1] = 2.0
|
|
|
|
vocab.set_vector("cat", data[0])
|
|
|
|
vocab.set_vector("dog", data[1])
|
|
|
|
cat = vocab["cat"]
|
|
|
|
assert list(cat.vector) == [1.0, 1.0, 1.0]
|
|
|
|
dog = vocab["dog"]
|
|
|
|
assert list(dog.vector) == [2.0, 2.0, 2.0]
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2020-05-13 20:08:28 +00:00
|
|
|
with pytest.raises(ValueError):
|
|
|
|
vocab.vectors.add(vocab["hamster"].orth, row=1000000)
|
|
|
|
|
2018-07-24 21:38:44 +00:00
|
|
|
|
|
|
|
def test_vocab_prune_vectors():
|
2019-09-16 13:16:54 +00:00
|
|
|
vocab = Vocab(vectors_name="test_vocab_prune_vectors")
|
2018-11-30 16:43:08 +00:00
|
|
|
_ = vocab["cat"] # noqa: F841
|
|
|
|
_ = vocab["dog"] # noqa: F841
|
|
|
|
_ = vocab["kitten"] # noqa: F841
|
2021-04-22 12:58:29 +00:00
|
|
|
data = OPS.xp.ndarray((5, 3), dtype="f")
|
|
|
|
data[0] = OPS.asarray([1.0, 1.2, 1.1])
|
|
|
|
data[1] = OPS.asarray([0.3, 1.3, 1.0])
|
|
|
|
data[2] = OPS.asarray([0.9, 1.22, 1.05])
|
2018-11-27 00:09:36 +00:00
|
|
|
vocab.set_vector("cat", data[0])
|
|
|
|
vocab.set_vector("dog", data[1])
|
|
|
|
vocab.set_vector("kitten", data[2])
|
2018-07-24 21:38:44 +00:00
|
|
|
|
2019-10-16 21:18:55 +00:00
|
|
|
remap = vocab.prune_vectors(2, batch_size=2)
|
2018-11-27 00:09:36 +00:00
|
|
|
assert list(remap.keys()) == ["kitten"]
|
2018-07-24 21:38:44 +00:00
|
|
|
neighbour, similarity = list(remap.values())[0]
|
2018-11-27 00:09:36 +00:00
|
|
|
assert neighbour == "cat", remap
|
2021-04-22 12:58:29 +00:00
|
|
|
cosine = get_cosine(data[0], data[2])
|
|
|
|
assert_allclose(float(similarity), cosine, atol=1e-4, rtol=1e-3)
|
2020-05-19 13:59:14 +00:00
|
|
|
|
|
|
|
|
2020-05-19 14:41:26 +00:00
|
|
|
def test_vectors_serialize():
|
2021-04-22 12:58:29 +00:00
|
|
|
data = OPS.asarray([[4, 2, 2, 2], [4, 2, 2, 2], [1, 1, 1, 1]], dtype="f")
|
2020-05-19 14:41:26 +00:00
|
|
|
v = Vectors(data=data, keys=["A", "B", "C"])
|
|
|
|
b = v.to_bytes()
|
|
|
|
v_r = Vectors()
|
|
|
|
v_r.from_bytes(b)
|
2021-04-22 12:58:29 +00:00
|
|
|
assert_equal(OPS.to_numpy(v.data), OPS.to_numpy(v_r.data))
|
2020-05-19 14:41:26 +00:00
|
|
|
assert v.key2row == v_r.key2row
|
|
|
|
v.resize((5, 4))
|
|
|
|
v_r.resize((5, 4))
|
2021-04-22 12:58:29 +00:00
|
|
|
row = v.add("D", vector=OPS.asarray([1, 2, 3, 4], dtype="f"))
|
|
|
|
row_r = v_r.add("D", vector=OPS.asarray([1, 2, 3, 4], dtype="f"))
|
2020-05-19 14:41:26 +00:00
|
|
|
assert row == row_r
|
2021-04-22 12:58:29 +00:00
|
|
|
assert_equal(OPS.to_numpy(v.data), OPS.to_numpy(v_r.data))
|
2020-05-19 14:41:26 +00:00
|
|
|
assert v.is_full == v_r.is_full
|
|
|
|
with make_tempdir() as d:
|
|
|
|
v.to_disk(d)
|
|
|
|
v_r.from_disk(d)
|
2021-04-22 12:58:29 +00:00
|
|
|
assert_equal(OPS.to_numpy(v.data), OPS.to_numpy(v_r.data))
|
2020-05-19 14:41:26 +00:00
|
|
|
assert v.key2row == v_r.key2row
|
|
|
|
v.resize((5, 4))
|
|
|
|
v_r.resize((5, 4))
|
2021-04-22 12:58:29 +00:00
|
|
|
row = v.add("D", vector=OPS.asarray([10, 20, 30, 40], dtype="f"))
|
|
|
|
row_r = v_r.add("D", vector=OPS.asarray([10, 20, 30, 40], dtype="f"))
|
2020-05-19 14:41:26 +00:00
|
|
|
assert row == row_r
|
2021-04-22 12:58:29 +00:00
|
|
|
assert_equal(OPS.to_numpy(v.data), OPS.to_numpy(v_r.data))
|
2020-05-19 14:41:26 +00:00
|
|
|
|
2020-05-21 12:14:01 +00:00
|
|
|
|
2020-05-19 13:59:14 +00:00
|
|
|
def test_vector_is_oov():
|
|
|
|
vocab = Vocab(vectors_name="test_vocab_is_oov")
|
2021-04-22 12:58:29 +00:00
|
|
|
data = OPS.xp.ndarray((5, 3), dtype="f")
|
2020-05-19 13:59:14 +00:00
|
|
|
data[0] = 1.0
|
|
|
|
data[1] = 2.0
|
|
|
|
vocab.set_vector("cat", data[0])
|
|
|
|
vocab.set_vector("dog", data[1])
|
2020-06-23 11:29:51 +00:00
|
|
|
assert vocab["cat"].is_oov is False
|
|
|
|
assert vocab["dog"].is_oov is False
|
|
|
|
assert vocab["hamster"].is_oov is True
|
2021-10-27 12:08:31 +00:00
|
|
|
|
|
|
|
|
|
|
|
def test_init_vectors_unset():
|
|
|
|
v = Vectors(shape=(10, 10))
|
|
|
|
assert v.is_full is False
|
|
|
|
assert v.data.shape == (10, 10)
|
|
|
|
|
|
|
|
with pytest.raises(ValueError):
|
|
|
|
v = Vectors(shape=(10, 10), mode="floret")
|
|
|
|
|
|
|
|
v = Vectors(data=OPS.xp.zeros((10, 10)), mode="floret", hash_count=1)
|
|
|
|
assert v.is_full is True
|
|
|
|
|
|
|
|
|
|
|
|
def test_vectors_clear():
|
|
|
|
data = OPS.asarray([[4, 2, 2, 2], [4, 2, 2, 2], [1, 1, 1, 1]], dtype="f")
|
|
|
|
v = Vectors(data=data, keys=["A", "B", "C"])
|
|
|
|
assert v.is_full is True
|
|
|
|
assert hash_string("A") in v
|
|
|
|
v.clear()
|
|
|
|
# no keys
|
|
|
|
assert v.key2row == {}
|
|
|
|
assert list(v) == []
|
|
|
|
assert v.is_full is False
|
|
|
|
assert "A" not in v
|
|
|
|
with pytest.raises(KeyError):
|
|
|
|
v["A"]
|
|
|
|
|
|
|
|
|
|
|
|
def test_vectors_get_batch():
|
|
|
|
data = OPS.asarray([[4, 2, 2, 2], [4, 2, 2, 2], [1, 1, 1, 1]], dtype="f")
|
|
|
|
v = Vectors(data=data, keys=["A", "B", "C"])
|
|
|
|
# check with mixed int/str keys
|
|
|
|
words = ["C", "B", "A", v.strings["B"]]
|
|
|
|
rows = v.find(keys=words)
|
|
|
|
vecs = OPS.as_contig(v.data[rows])
|
|
|
|
assert_equal(OPS.to_numpy(vecs), OPS.to_numpy(v.get_batch(words)))
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture()
|
|
|
|
def floret_vectors_hashvec_str():
|
|
|
|
"""The full hashvec table from floret with the settings:
|
|
|
|
bucket 10, dim 10, minn 2, maxn 3, hash count 2, hash seed 2166136261,
|
|
|
|
bow <, eow >"""
|
|
|
|
return """10 10 2 3 2 2166136261 < >
|
|
|
|
0 -2.2611 3.9302 2.6676 -11.233 0.093715 -10.52 -9.6463 -0.11853 2.101 -0.10145
|
|
|
|
1 -3.12 -1.7981 10.7 -6.171 4.4527 10.967 9.073 6.2056 -6.1199 -2.0402
|
|
|
|
2 9.5689 5.6721 -8.4832 -1.2249 2.1871 -3.0264 -2.391 -5.3308 -3.2847 -4.0382
|
|
|
|
3 3.6268 4.2759 -1.7007 1.5002 5.5266 1.8716 -12.063 0.26314 2.7645 2.4929
|
|
|
|
4 -11.683 -7.7068 2.1102 2.214 7.2202 0.69799 3.2173 -5.382 -2.0838 5.0314
|
|
|
|
5 -4.3024 8.0241 2.0714 -1.0174 -0.28369 1.7622 7.8797 -1.7795 6.7541 5.6703
|
|
|
|
6 8.3574 -5.225 8.6529 8.5605 -8.9465 3.767 -5.4636 -1.4635 -0.98947 -0.58025
|
|
|
|
7 -10.01 3.3894 -4.4487 1.1669 -11.904 6.5158 4.3681 0.79913 -6.9131 -8.687
|
|
|
|
8 -5.4576 7.1019 -8.8259 1.7189 4.955 -8.9157 -3.8905 -0.60086 -2.1233 5.892
|
|
|
|
9 8.0678 -4.4142 3.6236 4.5889 -2.7611 2.4455 0.67096 -4.2822 2.0875 4.6274
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
|
|
@pytest.fixture()
|
|
|
|
def floret_vectors_vec_str():
|
|
|
|
"""The top 10 rows from floret with the settings above, to verify
|
|
|
|
that the spacy floret vectors are equivalent to the fasttext static
|
|
|
|
vectors."""
|
|
|
|
return """10 10
|
|
|
|
, -5.7814 2.6918 0.57029 -3.6985 -2.7079 1.4406 1.0084 1.7463 -3.8625 -3.0565
|
|
|
|
. 3.8016 -1.759 0.59118 3.3044 -0.72975 0.45221 -2.1412 -3.8933 -2.1238 -0.47409
|
|
|
|
der 0.08224 2.6601 -1.173 1.1549 -0.42821 -0.097268 -2.5589 -1.609 -0.16968 0.84687
|
|
|
|
die -2.8781 0.082576 1.9286 -0.33279 0.79488 3.36 3.5609 -0.64328 -2.4152 0.17266
|
|
|
|
und 2.1558 1.8606 -1.382 0.45424 -0.65889 1.2706 0.5929 -2.0592 -2.6949 -1.6015
|
|
|
|
" -1.1242 1.4588 -1.6263 1.0382 -2.7609 -0.99794 -0.83478 -1.5711 -1.2137 1.0239
|
|
|
|
in -0.87635 2.0958 4.0018 -2.2473 -1.2429 2.3474 1.8846 0.46521 -0.506 -0.26653
|
|
|
|
von -0.10589 1.196 1.1143 -0.40907 -1.0848 -0.054756 -2.5016 -1.0381 -0.41598 0.36982
|
|
|
|
( 0.59263 2.1856 0.67346 1.0769 1.0701 1.2151 1.718 -3.0441 2.7291 3.719
|
|
|
|
) 0.13812 3.3267 1.657 0.34729 -3.5459 0.72372 0.63034 -1.6145 1.2733 0.37798
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
|
|
def test_floret_vectors(floret_vectors_vec_str, floret_vectors_hashvec_str):
|
|
|
|
nlp = English()
|
|
|
|
nlp_plain = English()
|
|
|
|
# load both vec and hashvec tables
|
|
|
|
with make_tempdir() as tmpdir:
|
|
|
|
p = tmpdir / "test.hashvec"
|
|
|
|
with open(p, "w") as fileh:
|
|
|
|
fileh.write(floret_vectors_hashvec_str)
|
|
|
|
convert_vectors(nlp, p, truncate=0, prune=-1, mode="floret")
|
|
|
|
p = tmpdir / "test.vec"
|
|
|
|
with open(p, "w") as fileh:
|
|
|
|
fileh.write(floret_vectors_vec_str)
|
|
|
|
convert_vectors(nlp_plain, p, truncate=0, prune=-1)
|
|
|
|
|
|
|
|
word = "der"
|
|
|
|
# ngrams: full padded word + padded 2-grams + padded 3-grams
|
|
|
|
ngrams = nlp.vocab.vectors._get_ngrams(word)
|
|
|
|
assert ngrams == ["<der>", "<d", "de", "er", "r>", "<de", "der", "er>"]
|
|
|
|
# rows: 2 rows per ngram
|
|
|
|
rows = OPS.xp.asarray(
|
|
|
|
[
|
|
|
|
h % nlp.vocab.vectors.data.shape[0]
|
|
|
|
for ngram in ngrams
|
|
|
|
for h in nlp.vocab.vectors._get_ngram_hashes(ngram)
|
|
|
|
],
|
|
|
|
dtype="uint32",
|
|
|
|
)
|
|
|
|
assert_equal(
|
|
|
|
OPS.to_numpy(rows),
|
|
|
|
numpy.asarray([5, 6, 7, 5, 8, 2, 8, 9, 3, 3, 4, 6, 7, 3, 0, 2]),
|
|
|
|
)
|
|
|
|
assert len(rows) == len(ngrams) * nlp.vocab.vectors.hash_count
|
|
|
|
# all vectors are equivalent for plain static table vs. hash ngrams
|
|
|
|
for word in nlp_plain.vocab.vectors:
|
|
|
|
word = nlp_plain.vocab.strings.as_string(word)
|
|
|
|
assert_almost_equal(
|
|
|
|
nlp.vocab[word].vector, nlp_plain.vocab[word].vector, decimal=3
|
|
|
|
)
|
|
|
|
|
|
|
|
# every word has a vector
|
|
|
|
assert nlp.vocab[word * 5].has_vector
|
|
|
|
|
|
|
|
# check that single and batched vector lookups are identical
|
|
|
|
words = [s for s in nlp_plain.vocab.vectors]
|
|
|
|
single_vecs = OPS.to_numpy(OPS.asarray([nlp.vocab[word].vector for word in words]))
|
|
|
|
batch_vecs = OPS.to_numpy(nlp.vocab.vectors.get_batch(words))
|
|
|
|
assert_equal(single_vecs, batch_vecs)
|
|
|
|
|
|
|
|
# an empty key returns 0s
|
|
|
|
assert_equal(
|
|
|
|
OPS.to_numpy(nlp.vocab[""].vector),
|
|
|
|
numpy.zeros((nlp.vocab.vectors.data.shape[0],)),
|
|
|
|
)
|
|
|
|
# an empty batch returns 0s
|
|
|
|
assert_equal(
|
|
|
|
OPS.to_numpy(nlp.vocab.vectors.get_batch([""])),
|
|
|
|
numpy.zeros((1, nlp.vocab.vectors.data.shape[0])),
|
|
|
|
)
|
|
|
|
# an empty key within a batch returns 0s
|
|
|
|
assert_equal(
|
|
|
|
OPS.to_numpy(nlp.vocab.vectors.get_batch(["a", "", "b"])[1]),
|
|
|
|
numpy.zeros((nlp.vocab.vectors.data.shape[0],)),
|
|
|
|
)
|
|
|
|
|
|
|
|
# the loaded ngram vector table cannot be modified
|
|
|
|
# except for clear: warning, then return without modifications
|
|
|
|
vector = list(range(nlp.vocab.vectors.shape[1]))
|
|
|
|
orig_bytes = nlp.vocab.vectors.to_bytes(exclude=["strings"])
|
|
|
|
with pytest.warns(UserWarning):
|
|
|
|
nlp.vocab.set_vector("the", vector)
|
|
|
|
assert orig_bytes == nlp.vocab.vectors.to_bytes(exclude=["strings"])
|
|
|
|
with pytest.warns(UserWarning):
|
|
|
|
nlp.vocab[word].vector = vector
|
|
|
|
assert orig_bytes == nlp.vocab.vectors.to_bytes(exclude=["strings"])
|
|
|
|
with pytest.warns(UserWarning):
|
|
|
|
nlp.vocab.vectors.add("the", row=6)
|
|
|
|
assert orig_bytes == nlp.vocab.vectors.to_bytes(exclude=["strings"])
|
|
|
|
with pytest.warns(UserWarning):
|
|
|
|
nlp.vocab.vectors.resize(shape=(100, 10))
|
|
|
|
assert orig_bytes == nlp.vocab.vectors.to_bytes(exclude=["strings"])
|
|
|
|
with pytest.raises(ValueError):
|
|
|
|
nlp.vocab.vectors.clear()
|
|
|
|
|
|
|
|
# data and settings are serialized correctly
|
|
|
|
with make_tempdir() as d:
|
|
|
|
nlp.vocab.to_disk(d)
|
|
|
|
vocab_r = Vocab()
|
|
|
|
vocab_r.from_disk(d)
|
|
|
|
assert nlp.vocab.vectors.to_bytes() == vocab_r.vectors.to_bytes()
|
|
|
|
assert_equal(
|
|
|
|
OPS.to_numpy(nlp.vocab.vectors.data), OPS.to_numpy(vocab_r.vectors.data)
|
|
|
|
)
|
|
|
|
assert_equal(nlp.vocab.vectors._get_cfg(), vocab_r.vectors._get_cfg())
|
|
|
|
assert_almost_equal(
|
|
|
|
OPS.to_numpy(nlp.vocab[word].vector),
|
|
|
|
OPS.to_numpy(vocab_r[word].vector),
|
|
|
|
decimal=6,
|
|
|
|
)
|