From db2dbc8e59d1a61a0d16fea371925e4667c8dec9 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Fri, 14 Aug 2020 14:58:03 +0200 Subject: [PATCH 1/6] Remove unused warning --- spacy/errors.py | 6 ------ 1 file changed, 6 deletions(-) diff --git a/spacy/errors.py b/spacy/errors.py index c4eb4af28..26c0dba29 100644 --- a/spacy/errors.py +++ b/spacy/errors.py @@ -55,12 +55,6 @@ class Warnings: "loaded. (Shape: {shape})") W021 = ("Unexpected hash collision in PhraseMatcher. Matches may be " "incorrect. Modify PhraseMatcher._terminal_hash to fix.") - W022 = ("Training a new part-of-speech tagger using a model with no " - "lemmatization rules or data. This means that the trained model " - "may not be able to lemmatize correctly. If this is intentional " - "or the language you're using doesn't have lemmatization data, " - "you can ignore this warning. If this is surprising, make sure you " - "have the spacy-lookups-data package installed.") W024 = ("Entity '{entity}' - Alias '{alias}' combination already exists in " "the Knowledge Base.") W026 = ("Unable to set all sentence boundaries from dependency parses.") From cef97e4b6352be205e68a9c7f0d10b4c44151b88 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Fri, 14 Aug 2020 14:58:18 +0200 Subject: [PATCH 2/6] Fix path check --- spacy/gold/corpus.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/spacy/gold/corpus.py b/spacy/gold/corpus.py index 745d52e0e..774c3b840 100644 --- a/spacy/gold/corpus.py +++ b/spacy/gold/corpus.py @@ -62,7 +62,7 @@ class Corpus: if str(path) in seen: continue seen.add(str(path)) - if path.parts[-1].startswith("."): + if path.parts and path.parts[-1].startswith("."): continue elif path.is_dir(): paths.extend(path.iterdir()) From e4d0990857bb813a55e9f95de6c77c1026460006 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Fri, 14 Aug 2020 14:58:48 +0200 Subject: [PATCH 3/6] Only receive from listener if listener exists --- spacy/pipeline/tok2vec.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/spacy/pipeline/tok2vec.py b/spacy/pipeline/tok2vec.py index 44cd457e4..f2d138cf7 100644 --- a/spacy/pipeline/tok2vec.py +++ b/spacy/pipeline/tok2vec.py @@ -193,7 +193,8 @@ class Tok2Vec(Pipe): batch_id = Tok2VecListener.get_batch_id(docs) for listener in self.listeners[:-1]: listener.receive(batch_id, tokvecs, accumulate_gradient) - self.listeners[-1].receive(batch_id, tokvecs, backprop) + if self.listeners: + self.listeners[-1].receive(batch_id, tokvecs, backprop) if set_annotations: self.set_annotations(docs, tokvecs) return losses From ab1d165bba1ea77c723295cfff3c11772c057218 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Fri, 14 Aug 2020 14:59:22 +0200 Subject: [PATCH 4/6] Pass optimizer defined in config to resume/begin_training Otherwise, this would create a default optimizer, which isn't what we want? --- spacy/cli/train.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/spacy/cli/train.py b/spacy/cli/train.py index fbdb91ab9..c69fb92ea 100644 --- a/spacy/cli/train.py +++ b/spacy/cli/train.py @@ -102,9 +102,9 @@ def train( if resume_components: with nlp.select_pipes(enable=resume_components): msg.info(f"Resuming training for: {resume_components}") - nlp.resume_training() + nlp.resume_training(sgd=optimizer) with nlp.select_pipes(disable=[*frozen_components, *resume_components]): - nlp.begin_training(lambda: train_corpus(nlp)) + nlp.begin_training(lambda: train_corpus(nlp), sgd=optimizer) if tag_map: # Replace tag map with provided mapping From 37814b608d57fc9982d8dc84812a8688a01360c1 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Fri, 14 Aug 2020 14:59:54 +0200 Subject: [PATCH 5/6] Remove env_opt and simplfy default Optimizer --- spacy/cli/evaluate.py | 1 - spacy/cli/train.py | 1 - spacy/util.py | 46 +------------------------------------------ 3 files changed, 1 insertion(+), 47 deletions(-) diff --git a/spacy/cli/evaluate.py b/spacy/cli/evaluate.py index cf77fecfd..cf8f513fc 100644 --- a/spacy/cli/evaluate.py +++ b/spacy/cli/evaluate.py @@ -60,7 +60,6 @@ def evaluate( fix_random_seed() if use_gpu >= 0: require_gpu(use_gpu) - util.set_env_log(False) data_path = util.ensure_path(data_path) output_path = util.ensure_path(output) displacy_path = util.ensure_path(displacy_path) diff --git a/spacy/cli/train.py b/spacy/cli/train.py index c69fb92ea..f04387b30 100644 --- a/spacy/cli/train.py +++ b/spacy/cli/train.py @@ -48,7 +48,6 @@ def train_cli( used to register custom functions and architectures that can then be referenced in the config. """ - util.set_env_log(verbose) verify_cli_args(config_path, output_path) overrides = parse_config_overrides(ctx.args) import_code(code_path) diff --git a/spacy/util.py b/spacy/util.py index d10f83789..1e7703613 100644 --- a/spacy/util.py +++ b/spacy/util.py @@ -54,7 +54,6 @@ if TYPE_CHECKING: from .vocab import Vocab # noqa: F401 -_PRINT_ENV = False OOV_RANK = numpy.iinfo(numpy.uint64).max LEXEME_NORM_LANGS = ["da", "de", "el", "en", "id", "lb", "pt", "ru", "sr", "ta", "th"] @@ -109,11 +108,6 @@ class SimpleFrozenDict(dict): raise NotImplementedError(self.error) -def set_env_log(value: bool) -> None: - global _PRINT_ENV - _PRINT_ENV = value - - def lang_class_is_loaded(lang: str) -> bool: """Check whether a Language class is already loaded. Language classes are loaded lazily, to avoid expensive setup code associated with the language @@ -602,27 +596,6 @@ def get_async(stream, numpy_array): return array -def env_opt(name: str, default: Optional[Any] = None) -> Optional[Any]: - if type(default) is float: - type_convert = float - else: - type_convert = int - if "SPACY_" + name.upper() in os.environ: - value = type_convert(os.environ["SPACY_" + name.upper()]) - if _PRINT_ENV: - print(name, "=", repr(value), "via", "$SPACY_" + name.upper()) - return value - elif name in os.environ: - value = type_convert(os.environ[name]) - if _PRINT_ENV: - print(name, "=", repr(value), "via", "$" + name) - return value - else: - if _PRINT_ENV: - print(name, "=", repr(default), "by default") - return default - - def read_regex(path: Union[str, Path]) -> Pattern: path = ensure_path(path) with path.open(encoding="utf8") as file_: @@ -1067,24 +1040,7 @@ class DummyTokenizer: def create_default_optimizer() -> Optimizer: - # TODO: Do we still want to allow env_opt? - learn_rate = env_opt("learn_rate", 0.001) - beta1 = env_opt("optimizer_B1", 0.9) - beta2 = env_opt("optimizer_B2", 0.999) - eps = env_opt("optimizer_eps", 1e-8) - L2 = env_opt("L2_penalty", 1e-6) - grad_clip = env_opt("grad_norm_clip", 10.0) - L2_is_weight_decay = env_opt("L2_is_weight_decay", False) - optimizer = Adam( - learn_rate, - L2=L2, - beta1=beta1, - beta2=beta2, - eps=eps, - grad_clip=grad_clip, - L2_is_weight_decay=L2_is_weight_decay, - ) - return optimizer + return Adam() def minibatch(items, size): From 8128e5eb354d534692d13c29c47fce3a764cde84 Mon Sep 17 00:00:00 2001 From: Ines Montani Date: Fri, 14 Aug 2020 15:00:52 +0200 Subject: [PATCH 6/6] Replace lexeme_norm warning with logging --- spacy/__init__.py | 2 +- spacy/cli/train.py | 3 ++- spacy/pipeline/transition_parser.pyx | 2 +- spacy/tests/parser/test_ner.py | 15 +++++++++------ spacy/tests/regression/test_issue2001-2500.py | 2 -- spacy/tests/regression/test_issue2501-3000.py | 1 - spacy/tests/regression/test_issue3001-3500.py | 1 - spacy/tests/regression/test_issue3501-4000.py | 4 ---- spacy/tests/regression/test_issue4001-4500.py | 4 ---- spacy/tests/regression/test_issue4501-5000.py | 2 -- spacy/tests/regression/test_issue5152.py | 9 +++++---- spacy/tests/test_gold.py | 6 ++++-- spacy/tests/test_new_example.py | 5 +++-- spacy/util.py | 5 +++++ 14 files changed, 30 insertions(+), 31 deletions(-) diff --git a/spacy/__init__.py b/spacy/__init__.py index 73e828936..d07ee5674 100644 --- a/spacy/__init__.py +++ b/spacy/__init__.py @@ -14,7 +14,7 @@ from . import pipeline # noqa: F401 from .cli.info import info # noqa: F401 from .glossary import explain # noqa: F401 from .about import __version__ # noqa: F401 -from .util import registry # noqa: F401 +from .util import registry, logger # noqa: F401 from .errors import Errors from .language import Language diff --git a/spacy/cli/train.py b/spacy/cli/train.py index f04387b30..f2085ff80 100644 --- a/spacy/cli/train.py +++ b/spacy/cli/train.py @@ -9,6 +9,7 @@ from thinc.api import use_pytorch_for_gpu_memory, require_gpu, fix_random_seed from thinc.api import Config, Optimizer import random import typer +import logging from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error from ._util import import_code, get_sourced_components @@ -17,7 +18,6 @@ from .. import util from ..gold.example import Example from ..errors import Errors - # Don't remove - required to load the built-in architectures from ..ml import models # noqa: F401 @@ -48,6 +48,7 @@ def train_cli( used to register custom functions and architectures that can then be referenced in the config. """ + util.logger.setLevel(logging.DEBUG if verbose else logging.ERROR) verify_cli_args(config_path, output_path) overrides = parse_config_overrides(ctx.args) import_code(code_path) diff --git a/spacy/pipeline/transition_parser.pyx b/spacy/pipeline/transition_parser.pyx index 443f7f6a0..2eadfa6aa 100644 --- a/spacy/pipeline/transition_parser.pyx +++ b/spacy/pipeline/transition_parser.pyx @@ -409,7 +409,7 @@ cdef class Parser(Pipe): lexeme_norms = self.vocab.lookups.get_table("lexeme_norm", {}) if len(lexeme_norms) == 0 and self.vocab.lang in util.LEXEME_NORM_LANGS: langs = ", ".join(util.LEXEME_NORM_LANGS) - warnings.warn(Warnings.W033.format(model="parser or NER", langs=langs)) + util.logger.debug(Warnings.W033.format(model="parser or NER", langs=langs)) actions = self.moves.get_actions( examples=get_examples(), min_freq=self.cfg['min_action_freq'], diff --git a/spacy/tests/parser/test_ner.py b/spacy/tests/parser/test_ner.py index 0ffe74273..c7a1ed0d2 100644 --- a/spacy/tests/parser/test_ner.py +++ b/spacy/tests/parser/test_ner.py @@ -1,17 +1,17 @@ import pytest - from spacy import util from spacy.lang.en import English - from spacy.language import Language from spacy.lookups import Lookups from spacy.pipeline._parser_internals.ner import BiluoPushDown from spacy.gold import Example from spacy.tokens import Doc from spacy.vocab import Vocab +import logging from ..util import make_tempdir + TRAIN_DATA = [ ("Who is Shaka Khan?", {"entities": [(7, 17, "PERSON")]}), ("I like London and Berlin.", {"entities": [(7, 13, "LOC"), (18, 24, "LOC")]}), @@ -56,6 +56,7 @@ def test_get_oracle_moves(tsys, doc, entity_annots): assert names == ["U-PERSON", "O", "O", "B-GPE", "L-GPE", "O"] +@pytest.mark.filterwarnings("ignore::UserWarning") def test_get_oracle_moves_negative_entities(tsys, doc, entity_annots): entity_annots = [(s, e, "!" + label) for s, e, label in entity_annots] example = Example.from_dict(doc, {"entities": entity_annots}) @@ -332,19 +333,21 @@ def test_overfitting_IO(): assert ents2[0].label_ == "LOC" -def test_ner_warns_no_lookups(): +def test_ner_warns_no_lookups(caplog): nlp = English() assert nlp.lang in util.LEXEME_NORM_LANGS nlp.vocab.lookups = Lookups() assert not len(nlp.vocab.lookups) nlp.add_pipe("ner") - with pytest.warns(UserWarning): + with caplog.at_level(logging.DEBUG): nlp.begin_training() + assert "W033" in caplog.text + caplog.clear() nlp.vocab.lookups.add_table("lexeme_norm") nlp.vocab.lookups.get_table("lexeme_norm")["a"] = "A" - with pytest.warns(None) as record: + with caplog.at_level(logging.DEBUG): nlp.begin_training() - assert not record.list + assert "W033" not in caplog.text @Language.factory("blocker") diff --git a/spacy/tests/regression/test_issue2001-2500.py b/spacy/tests/regression/test_issue2001-2500.py index a09c6f4fb..259ca9b0c 100644 --- a/spacy/tests/regression/test_issue2001-2500.py +++ b/spacy/tests/regression/test_issue2001-2500.py @@ -25,7 +25,6 @@ def test_issue2070(): assert len(doc) == 11 -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue2179(): """Test that spurious 'extra_labels' aren't created when initializing NER.""" nlp = Italian() @@ -135,7 +134,6 @@ def test_issue2464(en_vocab): assert len(matches) == 3 -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue2482(): """Test we can serialize and deserialize a blank NER or parser model.""" nlp = Italian() diff --git a/spacy/tests/regression/test_issue2501-3000.py b/spacy/tests/regression/test_issue2501-3000.py index 2b0f9f427..3882df0a6 100644 --- a/spacy/tests/regression/test_issue2501-3000.py +++ b/spacy/tests/regression/test_issue2501-3000.py @@ -136,7 +136,6 @@ def test_issue2782(text, lang_cls): assert doc[0].like_num -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue2800(): """Test issue that arises when too many labels are added to NER model. Used to cause segfault. diff --git a/spacy/tests/regression/test_issue3001-3500.py b/spacy/tests/regression/test_issue3001-3500.py index 98a6b9aa0..3059eb5ab 100644 --- a/spacy/tests/regression/test_issue3001-3500.py +++ b/spacy/tests/regression/test_issue3001-3500.py @@ -90,7 +90,6 @@ def test_issue3199(): assert list(doc[0:3].noun_chunks) == [] -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue3209(): """Test issue that occurred in spaCy nightly where NER labels were being mapped to classes incorrectly after loading the model, when the labels diff --git a/spacy/tests/regression/test_issue3501-4000.py b/spacy/tests/regression/test_issue3501-4000.py index de554a5ec..fc2a3ed7c 100644 --- a/spacy/tests/regression/test_issue3501-4000.py +++ b/spacy/tests/regression/test_issue3501-4000.py @@ -91,7 +91,6 @@ def test_issue_3526_3(en_vocab): assert new_ruler.overwrite is not ruler.overwrite -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue_3526_4(en_vocab): nlp = Language(vocab=en_vocab) patterns = [{"label": "ORG", "pattern": "Apple"}] @@ -252,7 +251,6 @@ def test_issue3803(): assert [t.like_num for t in doc] == [True, True, True, True, True, True] -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue3830_no_subtok(): """Test that the parser doesn't have subtok label if not learn_tokens""" config = { @@ -270,7 +268,6 @@ def test_issue3830_no_subtok(): assert "subtok" not in parser.labels -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue3830_with_subtok(): """Test that the parser does have subtok label if learn_tokens=True.""" config = { @@ -333,7 +330,6 @@ def test_issue3879(en_vocab): assert len(matcher(doc)) == 2 # fails because of a FP match 'is a test' -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue3880(): """Test that `nlp.pipe()` works when an empty string ends the batch. diff --git a/spacy/tests/regression/test_issue4001-4500.py b/spacy/tests/regression/test_issue4001-4500.py index 2fae3484b..1789973e9 100644 --- a/spacy/tests/regression/test_issue4001-4500.py +++ b/spacy/tests/regression/test_issue4001-4500.py @@ -81,7 +81,6 @@ def test_issue4030(): assert doc.cats["inoffensive"] == 0.0 -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue4042(): """Test that serialization of an EntityRuler before NER works fine.""" nlp = English() @@ -110,7 +109,6 @@ def test_issue4042(): assert doc2.ents[0].label_ == "MY_ORG" -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue4042_bug2(): """ Test that serialization of an NER works fine when new labels were added. @@ -242,7 +240,6 @@ def test_issue4190(): assert result_1b == result_2 -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue4267(): """ Test that running an entity_ruler after ner gives consistent results""" nlp = English() @@ -324,7 +321,6 @@ def test_issue4313(): entity_scores[(start, end, label)] += score -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue4348(): """Test that training the tagger with empty data, doesn't throw errors""" nlp = English() diff --git a/spacy/tests/regression/test_issue4501-5000.py b/spacy/tests/regression/test_issue4501-5000.py index 96d4e1ca4..1e655851f 100644 --- a/spacy/tests/regression/test_issue4501-5000.py +++ b/spacy/tests/regression/test_issue4501-5000.py @@ -179,7 +179,6 @@ def test_issue4707(): assert "entity_ruler" in new_nlp.pipe_names -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue4725_1(): """ Ensure the pickling of the NER goes well""" vocab = Vocab(vectors_name="test_vocab_add_vector") @@ -198,7 +197,6 @@ def test_issue4725_1(): assert ner2.cfg["update_with_oracle_cut_size"] == 111 -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue4725_2(): # 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), diff --git a/spacy/tests/regression/test_issue5152.py b/spacy/tests/regression/test_issue5152.py index 3c1cee5c3..c7a70a99c 100644 --- a/spacy/tests/regression/test_issue5152.py +++ b/spacy/tests/regression/test_issue5152.py @@ -1,8 +1,7 @@ -import pytest from spacy.lang.en import English +import pytest -@pytest.mark.filterwarnings("ignore::UserWarning") def test_issue5152(): # Test that the comparison between a Span and a Token, goes well # There was a bug when the number of tokens in the span equaled the number of characters in the token (!) @@ -14,6 +13,8 @@ def test_issue5152(): span_2 = text[0:3] # Talk about being span_3 = text_var[0:3] # Talk of being token = y[0] # Let - assert span.similarity(token) == 0.0 + with pytest.warns(UserWarning): + assert span.similarity(token) == 0.0 assert span.similarity(span_2) == 1.0 - assert span_2.similarity(span_3) < 1.0 + with pytest.warns(UserWarning): + assert span_2.similarity(span_3) < 1.0 diff --git a/spacy/tests/test_gold.py b/spacy/tests/test_gold.py index 708c57837..334d9fc24 100644 --- a/spacy/tests/test_gold.py +++ b/spacy/tests/test_gold.py @@ -154,6 +154,7 @@ def test_example_from_dict_some_ner(en_vocab): assert ner_tags == ["U-LOC", None, None, None] +@pytest.mark.filterwarnings("ignore::UserWarning") def test_json2docs_no_ner(en_vocab): data = [ { @@ -506,6 +507,7 @@ def test_roundtrip_docs_to_docbin(doc): assert cats["BAKING"] == reloaded_example.reference.cats["BAKING"] +@pytest.mark.filterwarnings("ignore::UserWarning") def test_make_orth_variants(doc): nlp = English() with make_tempdir() as tmpdir: @@ -586,7 +588,7 @@ def test_tuple_format_implicit(): ("Uber blew through $1 million a week", {"entities": [(0, 4, "ORG")]}), ( "Spotify steps up Asia expansion", - {"entities": [(0, 8, "ORG"), (17, 21, "LOC")]}, + {"entities": [(0, 7, "ORG"), (17, 21, "LOC")]}, ), ("Google rebrands its business apps", {"entities": [(0, 6, "ORG")]}), ] @@ -601,7 +603,7 @@ def test_tuple_format_implicit_invalid(): ("Uber blew through $1 million a week", {"frumble": [(0, 4, "ORG")]}), ( "Spotify steps up Asia expansion", - {"entities": [(0, 8, "ORG"), (17, 21, "LOC")]}, + {"entities": [(0, 7, "ORG"), (17, 21, "LOC")]}, ), ("Google rebrands its business apps", {"entities": [(0, 6, "ORG")]}), ] diff --git a/spacy/tests/test_new_example.py b/spacy/tests/test_new_example.py index df6489aa8..321eaae95 100644 --- a/spacy/tests/test_new_example.py +++ b/spacy/tests/test_new_example.py @@ -46,6 +46,7 @@ def test_Example_from_dict_with_tags(pred_words, annots): assert aligned_tags == ["NN" for _ in predicted] +@pytest.mark.filterwarnings("ignore::UserWarning") def test_aligned_tags(): pred_words = ["Apply", "some", "sunscreen", "unless", "you", "can", "not"] gold_words = ["Apply", "some", "sun", "screen", "unless", "you", "cannot"] @@ -198,8 +199,8 @@ def test_Example_from_dict_with_entities(annots): def test_Example_from_dict_with_entities_invalid(annots): vocab = Vocab() predicted = Doc(vocab, words=annots["words"]) - example = Example.from_dict(predicted, annots) - # TODO: shouldn't this throw some sort of warning ? + with pytest.warns(UserWarning): + example = Example.from_dict(predicted, annots) assert len(list(example.reference.ents)) == 0 diff --git a/spacy/util.py b/spacy/util.py index 1e7703613..09b117952 100644 --- a/spacy/util.py +++ b/spacy/util.py @@ -24,6 +24,7 @@ import tempfile import shutil import shlex import inspect +import logging try: import cupy.random @@ -58,6 +59,10 @@ OOV_RANK = numpy.iinfo(numpy.uint64).max LEXEME_NORM_LANGS = ["da", "de", "el", "en", "id", "lb", "pt", "ru", "sr", "ta", "th"] +logging.basicConfig() +logger = logging.getLogger("spacy") + + class registry(thinc.registry): languages = catalogue.create("spacy", "languages", entry_points=True) architectures = catalogue.create("spacy", "architectures", entry_points=True)