Tidy up with flake8: imports, comparisons, etc.

setup.cfg

@@ -111,7 +111,7 @@ universal = false
 formats = gztar
 
 [flake8]
-ignore = E203, E266, E501, E731, W503, E741
+ignore = E203, E266, E501, E731, W503, E741, F541
 max-line-length = 80
 select = B,C,E,F,W,T4,B9
 exclude =

spacy/cli/assemble.py

@@ -6,7 +6,6 @@ import logging
 
 from ._util import app, Arg, Opt, parse_config_overrides, show_validation_error
 from ._util import import_code
-from ..training.initialize import init_nlp
 from .. import util
 from ..util import get_sourced_components, load_model_from_config
 

spacy/cli/debug_model.py

@@ -1,11 +1,11 @@
-from typing import Dict, Any, Optional, Iterable
+from typing import Dict, Any, Optional
 from pathlib import Path
 import itertools
 
 from spacy.training import Example
 from spacy.util import resolve_dot_names
 from wasabi import msg
-from thinc.api import fix_random_seed, set_dropout_rate, Adam
+from thinc.api import fix_random_seed, set_dropout_rate
 from thinc.api import Model, data_validation, set_gpu_allocator
 import typer
 
@@ -133,7 +133,6 @@ def debug_model(
         _print_model(model, print_settings)
 
     # STEP 2: Updating the model and printing again
-    optimizer = Adam(0.001)
     set_dropout_rate(model, 0.2)
     # ugly hack to deal with Tok2Vec/Transformer listeners
     upstream_component = None
@@ -144,7 +143,6 @@ def debug_model(
         and "transformer-listener" in model.get_ref("tok2vec").name
     ):
         upstream_component = nlp.get_pipe("transformer")
-    goldY = None
     for e in range(3):
         if upstream_component:
             upstream_component.update(examples)

spacy/cli/package.py

@@ -331,7 +331,7 @@ def _format_label_scheme(data: Dict[str, Any]) -> str:
             continue
         col1 = md.bold(md.code(pipe))
         col2 = ", ".join(
-            [md.code(label.replace("|", "\|")) for label in labels]
+            [md.code(label.replace("|", "\\|")) for label in labels]
         )  # noqa: W605
         label_data.append((col1, col2))
         n_labels += len(labels)

spacy/cli/validate.py

@@ -5,7 +5,6 @@ import requests
 from wasabi import msg, Printer
 import warnings
 
-from ..errors import Warnings
 from ._util import app
 from .. import about
 from ..util import get_package_version, get_installed_models, get_minor_version

spacy/lang/tokenizer_exceptions.py

@@ -35,8 +35,8 @@ URL_PATTERN = (
     # host & domain names
     # mods: match is case-sensitive, so include [A-Z]
     r"(?:"  # noqa: E131
-      r"(?:"
+      r"(?:"  # noqa: E131
-        r"[A-Za-z0-9\u00a1-\uffff]"
+        r"[A-Za-z0-9\u00a1-\uffff]"  # noqa: E131
         r"[A-Za-z0-9\u00a1-\uffff_-]{0,62}"
       r")?"
       r"[A-Za-z0-9\u00a1-\uffff]\."

spacy/language.py

@@ -693,7 +693,7 @@ class Language:
             or self.vocab.vectors.to_bytes() != source.vocab.vectors.to_bytes()
         ):
             warnings.warn(Warnings.W113.format(name=source_name))
-        if not source_name in source.component_names:
+        if source_name not in source.component_names:
             raise KeyError(
                 Errors.E944.format(
                     name=source_name,

spacy/pipeline/entityruler.py

@@ -3,7 +3,6 @@ from typing import Optional, Union, List, Dict, Tuple, Iterable, Any, Callable,
 from collections import defaultdict
 from pathlib import Path
 import srsly
-import warnings
 
 from .pipe import Pipe
 from ..training import Example

spacy/tests/doc/test_doc_api.py

@@ -381,9 +381,9 @@ def test_doc_api_from_docs(en_tokenizer, de_tokenizer):
     en_docs_tokens = [t for doc in en_docs for t in doc]
     assert len(m_doc) == len(en_docs_tokens)
     think_idx = len(en_texts[0]) + 1 + en_texts[2].index("think")
-    assert m_doc[2]._.is_ambiguous == True
+    assert m_doc[2]._.is_ambiguous is True
     assert m_doc[9].idx == think_idx
-    assert m_doc[9]._.is_ambiguous == True
+    assert m_doc[9]._.is_ambiguous is True
     assert not any([t._.is_ambiguous for t in m_doc[3:8]])
     assert "group" in m_doc.spans
     assert span_group_texts == sorted([s.text for s in m_doc.spans["group"]])

spacy/tests/doc/test_retokenize_merge.py

@@ -484,7 +484,7 @@ def test_doc_retokenize_merge_without_parse_keeps_sents(en_tokenizer):
     assert len(list(doc.sents)) == 2
     with doc.retokenize() as retokenizer:
         retokenizer.merge(doc[3:6])
-    assert doc[3].is_sent_start == None
+    assert doc[3].is_sent_start is None
 
     # merging over a sentence boundary and setting sent_start
     doc = Doc(tokens.vocab, words=[t.text for t in tokens], sent_starts=sent_starts)

spacy/tests/lang/bg/test_text.py

@@ -1,5 +1,4 @@
 import pytest
-from spacy.lang.bg.lex_attrs import like_num
 
 
 @pytest.mark.parametrize(

spacy/tests/lang/uk/test_lemmatizer.py

@@ -1,4 +1,3 @@
-import pytest
 from spacy.tokens import Doc
 
 

spacy/tests/lang/vi/test_serialize.py

@@ -23,11 +23,11 @@ def test_vi_tokenizer_serialize(vi_tokenizer):
     nlp_r = Vietnamese()
     nlp_r.from_bytes(nlp_bytes)
     assert nlp_bytes == nlp_r.to_bytes()
-    assert nlp_r.tokenizer.use_pyvi == False
+    assert nlp_r.tokenizer.use_pyvi is False
 
     with make_tempdir() as d:
         nlp.to_disk(d)
         nlp_r = Vietnamese()
         nlp_r.from_disk(d)
         assert nlp_bytes == nlp_r.to_bytes()
-        assert nlp_r.tokenizer.use_pyvi == False
+        assert nlp_r.tokenizer.use_pyvi is False

spacy/tests/matcher/test_dependency_matcher.py

@@ -354,7 +354,6 @@ def test_dependency_matcher_span_user_data(en_tokenizer):
     for token in doc:
         token.head = doc[0]
         token.dep_ = "a"
-    get_is_c = lambda token: token.text in ("c",)
     Token.set_extension("is_c", default=False)
     doc[2]._.is_c = True
     pattern = [

spacy/tests/pipeline/test_annotates_on_update.py

@@ -1,6 +1,5 @@
 from typing import Callable, Iterable, Iterator
 import pytest
-import io
 
 from thinc.api import Config
 from spacy.language import Language

spacy/tests/pipeline/test_entity_linker.py

@@ -11,7 +11,7 @@ from spacy.ml import load_kb
 from spacy.scorer import Scorer
 from spacy.training import Example
 from spacy.lang.en import English
-from spacy.tests.util import make_tempdir, make_tempfile
+from spacy.tests.util import make_tempdir
 from spacy.tokens import Span
 
 

spacy/tests/pipeline/test_tagger.py

@@ -132,8 +132,8 @@ def test_incomplete_data():
     # test the trained model
     test_text = "I like blue eggs"
     doc = nlp(test_text)
-    assert doc[1].tag_ is "V"
+    assert doc[1].tag_ == "V"
-    assert doc[2].tag_ is "J"
+    assert doc[2].tag_ == "J"
 
 
 def test_overfitting_IO():
@@ -154,20 +154,20 @@ def test_overfitting_IO():
     # test the trained model
     test_text = "I like blue eggs"
     doc = nlp(test_text)
-    assert doc[0].tag_ is "N"
+    assert doc[0].tag_ == "N"
-    assert doc[1].tag_ is "V"
+    assert doc[1].tag_ == "V"
-    assert doc[2].tag_ is "J"
+    assert doc[2].tag_ == "J"
-    assert doc[3].tag_ is "N"
+    assert doc[3].tag_ == "N"
 
     # Also test the results are still the same after IO
     with make_tempdir() as tmp_dir:
         nlp.to_disk(tmp_dir)
         nlp2 = util.load_model_from_path(tmp_dir)
         doc2 = nlp2(test_text)
-        assert doc2[0].tag_ is "N"
+        assert doc2[0].tag_ == "N"
-        assert doc2[1].tag_ is "V"
+        assert doc2[1].tag_ == "V"
-        assert doc2[2].tag_ is "J"
+        assert doc2[2].tag_ == "J"
-        assert doc2[3].tag_ is "N"
+        assert doc2[3].tag_ == "N"
 
     # Make sure that running pipe twice, or comparing to call, always amounts to the same predictions
     texts = [

spacy/tests/regression/test_issue8216.py

@@ -2,7 +2,6 @@ import pytest
 
 from spacy import registry
 from spacy.language import Language
-from spacy.pipeline import EntityRuler
 
 
 @pytest.fixture

spacy/tests/test_language.py

@@ -8,7 +8,7 @@ from spacy.vocab import Vocab
 from spacy.training import Example
 from spacy.lang.en import English
 from spacy.lang.de import German
-from spacy.util import registry, ignore_error, raise_error, logger
+from spacy.util import registry, ignore_error, raise_error
 import spacy
 from thinc.api import NumpyOps, get_current_ops
 

spacy/tests/test_misc.py

@@ -9,7 +9,7 @@ from spacy.ml._precomputable_affine import PrecomputableAffine
 from spacy.ml._precomputable_affine import _backprop_precomputable_affine_padding
 from spacy.util import dot_to_object, SimpleFrozenList, import_file
 from spacy.util import to_ternary_int
-from thinc.api import Config, Optimizer, ConfigValidationError, get_current_ops
+from thinc.api import Config, Optimizer, ConfigValidationError
 from thinc.api import set_current_ops
 from spacy.training.batchers import minibatch_by_words
 from spacy.lang.en import English

spacy/tests/tokenizer/test_tokenizer.py

@@ -209,10 +209,6 @@ def test_tokenizer_flush_specials(en_vocab):
         suffix_search=suffix_re.search,
         rules=rules,
     )
-    tokenizer2 = Tokenizer(
-        en_vocab,
-        suffix_search=suffix_re.search,
-    )
     assert [t.text for t in tokenizer1("a a.")] == ["a a", "."]
     tokenizer1.rules = {}
     assert [t.text for t in tokenizer1("a a.")] == ["a", "a", "."]

spacy/training/loggers.py

@@ -110,7 +110,8 @@ def wandb_logger(
 ):
     try:
         import wandb
-        from wandb import init, log, join  # test that these are available
+        # test that these are available
+        from wandb import init, log, join  # noqa: F401
     except ImportError:
         raise ImportError(Errors.E880)
 

spacy/training/loop.py

@@ -1,4 +1,4 @@
-from typing import List, Callable, Tuple, Dict, Iterable, Iterator, Union, Any, IO
+from typing import List, Callable, Tuple, Dict, Iterable, Union, Any, IO
 from typing import Optional, TYPE_CHECKING
 from pathlib import Path
 from timeit import default_timer as timer