mirror of
https://github.com/explosion/spaCy.git
synced 2024-12-24 00:46:28 +03:00
Auto-format code with black
This commit is contained in:
parent
c5c4e96597
commit
ee37288a1f
|
@ -255,7 +255,7 @@ def test_token_api_non_conjuncts(en_vocab):
|
|||
|
||||
|
||||
def test_missing_head_dep(en_vocab):
|
||||
""" Check that the Doc constructor and Example.from_dict parse missing information the same"""
|
||||
"""Check that the Doc constructor and Example.from_dict parse missing information the same"""
|
||||
heads = [1, 1, 1, 1, 2, None] # element 5 is missing
|
||||
deps = ["", "ROOT", "dobj", "cc", "conj", None] # element 0 and 5 are missing
|
||||
words = ["I", "like", "London", "and", "Berlin", "."]
|
||||
|
|
|
@ -5,7 +5,7 @@ import pytest
|
|||
"text,expected_tokens", [("d'un", ["d'", "un"]), ("s'ha", ["s'", "ha"])]
|
||||
)
|
||||
def test_contractions(ca_tokenizer, text, expected_tokens):
|
||||
""" Test that the contractions are split into two tokens"""
|
||||
"""Test that the contractions are split into two tokens"""
|
||||
tokens = ca_tokenizer(text)
|
||||
assert len(tokens) == 2
|
||||
assert [t.text for t in tokens] == expected_tokens
|
||||
|
|
|
@ -5,7 +5,7 @@ import pytest
|
|||
"text,expected_tokens", [("c'è", ["c'", "è"]), ("l'ha", ["l'", "ha"])]
|
||||
)
|
||||
def test_contractions(it_tokenizer, text, expected_tokens):
|
||||
""" Test that the contractions are split into two tokens"""
|
||||
"""Test that the contractions are split into two tokens"""
|
||||
tokens = it_tokenizer(text)
|
||||
assert len(tokens) == 2
|
||||
assert [t.text for t in tokens] == expected_tokens
|
||||
|
|
|
@ -304,7 +304,7 @@ def test_empty_ner():
|
|||
|
||||
|
||||
def test_ruler_before_ner():
|
||||
""" Test that an NER works after an entity_ruler: the second can add annotations """
|
||||
"""Test that an NER works after an entity_ruler: the second can add annotations"""
|
||||
nlp = English()
|
||||
|
||||
# 1 : Entity Ruler - should set "this" to B and everything else to empty
|
||||
|
@ -334,7 +334,7 @@ def test_ner_constructor(en_vocab):
|
|||
|
||||
|
||||
def test_ner_before_ruler():
|
||||
""" Test that an entity_ruler works after an NER: the second can overwrite O annotations """
|
||||
"""Test that an entity_ruler works after an NER: the second can overwrite O annotations"""
|
||||
nlp = English()
|
||||
|
||||
# 1: untrained NER - should set everything to O
|
||||
|
@ -355,7 +355,7 @@ def test_ner_before_ruler():
|
|||
|
||||
|
||||
def test_block_ner():
|
||||
""" Test functionality for blocking tokens so they can't be in a named entity """
|
||||
"""Test functionality for blocking tokens so they can't be in a named entity"""
|
||||
# block "Antti L Korhonen" from being a named entity
|
||||
nlp = English()
|
||||
nlp.add_pipe("blocker", config={"start": 2, "end": 5})
|
||||
|
|
|
@ -197,7 +197,7 @@ def test_issue3555(en_vocab):
|
|||
|
||||
|
||||
def test_issue3611():
|
||||
""" Test whether adding n-grams in the textcat works even when n > token length of some docs """
|
||||
"""Test whether adding n-grams in the textcat works even when n > token length of some docs"""
|
||||
unique_classes = ["offensive", "inoffensive"]
|
||||
x_train = [
|
||||
"This is an offensive text",
|
||||
|
@ -282,7 +282,7 @@ def test_issue3830_with_subtok():
|
|||
|
||||
|
||||
def test_issue3839(en_vocab):
|
||||
"""Test that match IDs returned by the matcher are correct, are in the string """
|
||||
"""Test that match IDs returned by the matcher are correct, are in the string"""
|
||||
doc = Doc(en_vocab, words=["terrific", "group", "of", "people"])
|
||||
matcher = Matcher(en_vocab)
|
||||
match_id = "PATTERN"
|
||||
|
@ -366,7 +366,7 @@ def test_issue3951(en_vocab):
|
|||
|
||||
|
||||
def test_issue3959():
|
||||
""" Ensure that a modified pos attribute is serialized correctly."""
|
||||
"""Ensure that a modified pos attribute is serialized correctly."""
|
||||
nlp = English()
|
||||
doc = nlp(
|
||||
"displaCy uses JavaScript, SVG and CSS to show you how computers understand language"
|
||||
|
|
|
@ -38,7 +38,7 @@ def test_issue4002(en_vocab):
|
|||
|
||||
|
||||
def test_issue4030():
|
||||
""" Test whether textcat works fine with empty doc """
|
||||
"""Test whether textcat works fine with empty doc"""
|
||||
unique_classes = ["offensive", "inoffensive"]
|
||||
x_train = [
|
||||
"This is an offensive text",
|
||||
|
@ -237,7 +237,7 @@ def test_issue4190():
|
|||
|
||||
|
||||
def test_issue4267():
|
||||
""" Test that running an entity_ruler after ner gives consistent results"""
|
||||
"""Test that running an entity_ruler after ner gives consistent results"""
|
||||
nlp = English()
|
||||
ner = nlp.add_pipe("ner")
|
||||
ner.add_label("PEOPLE")
|
||||
|
@ -288,7 +288,7 @@ def test_multiple_predictions():
|
|||
|
||||
|
||||
def test_issue4313():
|
||||
""" This should not crash or exit with some strange error code """
|
||||
"""This should not crash or exit with some strange error code"""
|
||||
beam_width = 16
|
||||
beam_density = 0.0001
|
||||
nlp = English()
|
||||
|
|
|
@ -152,7 +152,7 @@ def test_issue4707():
|
|||
|
||||
|
||||
def test_issue4725_1():
|
||||
""" Ensure the pickling of the NER goes well"""
|
||||
"""Ensure the pickling of the NER goes well"""
|
||||
vocab = Vocab(vectors_name="test_vocab_add_vector")
|
||||
nlp = English(vocab=vocab)
|
||||
config = {
|
||||
|
|
|
@ -96,7 +96,7 @@ def test_issue5137():
|
|||
|
||||
|
||||
def test_issue5141(en_vocab):
|
||||
""" Ensure an empty DocBin does not crash on serialization """
|
||||
"""Ensure an empty DocBin does not crash on serialization"""
|
||||
doc_bin = DocBin(attrs=["DEP", "HEAD"])
|
||||
assert list(doc_bin.get_docs(en_vocab)) == []
|
||||
doc_bin_bytes = doc_bin.to_bytes()
|
||||
|
|
|
@ -238,7 +238,7 @@ def test_create_nlp_from_config_multiple_instances():
|
|||
|
||||
|
||||
def test_serialize_nlp():
|
||||
""" Create a custom nlp pipeline from config and ensure it serializes it correctly """
|
||||
"""Create a custom nlp pipeline from config and ensure it serializes it correctly"""
|
||||
nlp_config = Config().from_str(nlp_config_string)
|
||||
nlp = load_model_from_config(nlp_config, auto_fill=True)
|
||||
nlp.get_pipe("tagger").add_label("A")
|
||||
|
@ -258,7 +258,7 @@ def test_serialize_nlp():
|
|||
|
||||
|
||||
def test_serialize_custom_nlp():
|
||||
""" Create a custom nlp pipeline and ensure it serializes it correctly"""
|
||||
"""Create a custom nlp pipeline and ensure it serializes it correctly"""
|
||||
nlp = English()
|
||||
parser_cfg = dict()
|
||||
parser_cfg["model"] = {"@architectures": "my_test_parser"}
|
||||
|
@ -279,7 +279,7 @@ def test_serialize_custom_nlp():
|
|||
"parser_config_string", [parser_config_string_upper, parser_config_string_no_upper]
|
||||
)
|
||||
def test_serialize_parser(parser_config_string):
|
||||
""" Create a non-default parser config to check nlp serializes it correctly """
|
||||
"""Create a non-default parser config to check nlp serializes it correctly"""
|
||||
nlp = English()
|
||||
model_config = Config().from_str(parser_config_string)
|
||||
parser = nlp.add_pipe("parser", config=model_config)
|
||||
|
|
|
@ -275,7 +275,7 @@ def test_util_minibatch(doc_sizes, expected_batches):
|
|||
],
|
||||
)
|
||||
def test_util_minibatch_oversize(doc_sizes, expected_batches):
|
||||
""" Test that oversized documents are returned in their own batch"""
|
||||
"""Test that oversized documents are returned in their own batch"""
|
||||
docs = [get_random_doc(doc_size) for doc_size in doc_sizes]
|
||||
tol = 0.2
|
||||
batch_size = 1000
|
||||
|
|
|
@ -69,7 +69,7 @@ def read_conllx(
|
|||
ner_tag_pattern="",
|
||||
ner_map=None,
|
||||
):
|
||||
""" Yield docs, one for each sentence """
|
||||
"""Yield docs, one for each sentence"""
|
||||
vocab = Vocab() # need vocab to make a minimal Doc
|
||||
for sent in input_data.strip().split("\n\n"):
|
||||
lines = sent.strip().split("\n")
|
||||
|
|
|
@ -186,7 +186,7 @@ class Corpus:
|
|||
def read_docbin(
|
||||
self, vocab: Vocab, locs: Iterable[Union[str, Path]]
|
||||
) -> Iterator[Doc]:
|
||||
""" Yield training examples as example dicts """
|
||||
"""Yield training examples as example dicts"""
|
||||
i = 0
|
||||
for loc in locs:
|
||||
loc = util.ensure_path(loc)
|
||||
|
|
|
@ -110,6 +110,7 @@ def wandb_logger(
|
|||
):
|
||||
try:
|
||||
import wandb
|
||||
|
||||
# test that these are available
|
||||
from wandb import init, log, join # noqa: F401
|
||||
except ImportError:
|
||||
|
|
Loading…
Reference in New Issue
Block a user