Tidy up and auto-format

spacy/cli/debug_data.py

@@ -384,7 +384,10 @@ def debug_data(
         # rare labels in projectivized train
         rare_projectivized_labels = []
         for label in gold_train_data["deps"]:
-            if gold_train_data["deps"][label] <= DEP_LABEL_THRESHOLD and DELIMITER in label:
+            if (
+                gold_train_data["deps"][label] <= DEP_LABEL_THRESHOLD
+                and DELIMITER in label
+            ):
                 rare_projectivized_labels.append(
                     f"{label}: {gold_train_data['deps'][label]}"
                 )

spacy/cli/info.py

@@ -30,7 +30,11 @@ def info_cli(
 
 
 def info(
-    model: Optional[str] = None, *, markdown: bool = False, silent: bool = True, exclude: List[str]
+    model: Optional[str] = None,
+    *,
+    markdown: bool = False,
+    silent: bool = True,
+    exclude: List[str],
 ) -> Union[str, dict]:
     msg = Printer(no_print=silent, pretty=not silent)
     if model:
@@ -98,7 +102,9 @@ def info_model(model: str, *, silent: bool = True) -> Dict[str, Any]:
     }
 
 
-def get_markdown(data: Dict[str, Any], title: Optional[str] = None, exclude: List[str] = None) -> str:
+def get_markdown(
+    data: Dict[str, Any], title: Optional[str] = None, exclude: List[str] = None
+) -> str:
     """Get data in GitHub-flavoured Markdown format for issues etc.
 
     data (dict or list of tuples): Label/value pairs.
@@ -115,7 +121,7 @@ def get_markdown(data: Dict[str, Any], title: Optional[str] = None, exclude: Lis
         if isinstance(value, str):
             try:
                 existing_path = Path(value).exists()
-            except:
+            except Exception:
                 # invalid Path, like a URL string
                 existing_path = False
             if existing_path:

spacy/lang/am/lex_attrs.py

@@ -36,7 +36,7 @@ _num_words = [
     "ትሪሊዮን",
     "ኳድሪሊዮን",
     "ገጅሊዮን",
-    "ባዝሊዮን"
+    "ባዝሊዮን",
 ]
 
 _ordinal_words = [
@@ -60,8 +60,7 @@ _ordinal_words = [
     "አስራ ስምንተኛ",
     "አስራ ዘጠነኛ",
     "ሃያኛ",
-     "ሰላሳኛ"
+    "ሰላሳኛ" "አርባኛ",
-     "አርባኛ",
     "አምሳኛ",
     "ስድሳኛ",
     "ሰባኛ",
@@ -71,8 +70,10 @@ _ordinal_words = [
     "ሺኛ",
     "ሚሊዮንኛ",
     "ቢሊዮንኛ",
-     "ትሪሊዮንኛ"
+    "ትሪሊዮንኛ",
 ]
+
+
 def like_num(text):
     if text.startswith(("+", "-", "±", "~")):
         text = text[1:]

spacy/lang/am/tokenizer_exceptions.py

@@ -7,7 +7,6 @@ _exc = {}
 for exc_data in [
     {ORTH: "ት/ቤት"},
     {ORTH: "ወ/ሮ", NORM: "ወይዘሮ"},
-
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 

spacy/lang/es/syntax_iterators.py

@@ -1,4 +1,4 @@
-from typing import Union, Iterator, Optional, List, Tuple
+from typing import Union, Iterator
 
 from ...symbols import NOUN, PROPN, PRON, VERB, AUX
 from ...errors import Errors

spacy/lang/ti/lex_attrs.py

@@ -36,7 +36,7 @@ _num_words = [
     "ትሪልዮን",
     "ኳድሪልዮን",
     "ገጅልዮን",
-    "ባዝልዮን"
+    "ባዝልዮን",
 ]
 
 _ordinal_words = [
@@ -60,8 +60,7 @@ _ordinal_words = [
     "ኣሰርተ ስምንተኛ",
     "ኣሰርተ ዘጠነኛ",
     "ሃያኛ",
-     "ሰላሳኛ"
+    "ሰላሳኛ" "አርባኛ",
-     "አርባኛ",
     "አምሳኛ",
     "ስድሳኛ",
     "ሰባኛ",
@@ -71,8 +70,10 @@ _ordinal_words = [
     "ሺኛ",
     "ሚሊዮንኛ",
     "ቢሊዮንኛ",
-     "ትሪሊዮንኛ"
+    "ትሪሊዮንኛ",
 ]
+
+
 def like_num(text):
     if text.startswith(("+", "-", "±", "~")):
         text = text[1:]

spacy/lang/ti/tokenizer_exceptions.py

@@ -8,7 +8,6 @@ for exc_data in [
     {ORTH: "ት/ቤት"},
     {ORTH: "ወ/ሮ", NORM: "ወይዘሮ"},
     {ORTH: "ወ/ሪ", NORM: "ወይዘሪት"},
-
 ]:
     _exc[exc_data[ORTH]] = [exc_data]
 

spacy/ml/models/textcat.py

@@ -71,7 +71,9 @@ def build_text_classifier_v2(
     exclusive_classes = not linear_model.attrs["multi_label"]
     with Model.define_operators({">>": chain, "|": concatenate}):
         width = tok2vec.maybe_get_dim("nO")
-        attention_layer = ParametricAttention(width)   # TODO: benchmark performance difference of this layer
+        attention_layer = ParametricAttention(
+            width
+        )  # TODO: benchmark performance difference of this layer
         maxout_layer = Maxout(nO=width, nI=width)
         linear_layer = Linear(nO=nO, nI=width)
         cnn_model = (

spacy/ml/models/tok2vec.py

@@ -89,7 +89,7 @@ def build_hash_embed_cnn_tok2vec(
 
 # TODO: archive
 @registry.architectures.register("spacy.Tok2Vec.v1")
-def build_Tok2Vec_model(
+def _build_Tok2Vec_model(
     embed: Model[List[Doc], List[Floats2d]],
     encode: Model[List[Floats2d], List[Floats2d]],
 ) -> Model[List[Doc], List[Floats2d]]:
@@ -109,7 +109,6 @@ def build_Tok2Vec_model(
     return tok2vec
 
 
-
 @registry.architectures.register("spacy.Tok2Vec.v2")
 def build_Tok2Vec_model(
     embed: Model[List[Doc], List[Floats2d]],
@@ -130,7 +129,6 @@ def build_Tok2Vec_model(
     return tok2vec
 
 
-
 @registry.architectures.register("spacy.MultiHashEmbed.v1")
 def MultiHashEmbed(
     width: int,
@@ -280,7 +278,7 @@ def CharacterEmbed(
 
 # TODO: archive
 @registry.architectures.register("spacy.MaxoutWindowEncoder.v1")
-def MaxoutWindowEncoder(
+def _MaxoutWindowEncoder(
     width: int, window_size: int, maxout_pieces: int, depth: int
 ) -> Model[List[Floats2d], List[Floats2d]]:
     """Encode context using convolutions with maxout activation, layer
@@ -310,6 +308,7 @@ def MaxoutWindowEncoder(
     model.attrs["receptive_field"] = window_size * depth
     return model
 
+
 @registry.architectures.register("spacy.MaxoutWindowEncoder.v2")
 def MaxoutWindowEncoder(
     width: int, window_size: int, maxout_pieces: int, depth: int
@@ -344,7 +343,7 @@ def MaxoutWindowEncoder(
 
 # TODO: archive
 @registry.architectures.register("spacy.MishWindowEncoder.v1")
-def MishWindowEncoder(
+def _MishWindowEncoder(
     width: int, window_size: int, depth: int
 ) -> Model[List[Floats2d], List[Floats2d]]:
     """Encode context using convolutions with mish activation, layer

spacy/pipeline/textcat.py

@@ -388,7 +388,6 @@ class TextCategorizer(TrainablePipe):
             **kwargs,
         )
 
-
     def _validate_categories(self, examples: List[Example]):
         """Check whether the provided examples all have single-label cats annotations."""
         for ex in examples:

spacy/tests/conftest.py

@@ -28,10 +28,12 @@ def pytest_runtest_setup(item):
 def tokenizer():
     return get_lang_class("xx")().tokenizer
 
+
 @pytest.fixture(scope="session")
 def am_tokenizer():
     return get_lang_class("am")().tokenizer
 
+
 @pytest.fixture(scope="session")
 def ar_tokenizer():
     return get_lang_class("ar")().tokenizer
@@ -247,10 +249,12 @@ def th_tokenizer():
     pytest.importorskip("pythainlp")
     return get_lang_class("th")().tokenizer
 
+
 @pytest.fixture(scope="session")
 def ti_tokenizer():
     return get_lang_class("ti")().tokenizer
 
+
 @pytest.fixture(scope="session")
 def tr_tokenizer():
     return get_lang_class("tr")().tokenizer

spacy/tests/doc/test_graph.py

@@ -17,17 +17,8 @@ def test_graph_edges_and_nodes():
     assert graph.get_node((0,)) == node1
     node2 = graph.add_node((1, 3))
     assert list(node2) == [1, 3]
-    graph.add_edge(
+    graph.add_edge(node1, node2, label="one", weight=-10.5)
-        node1,
+    assert graph.has_edge(node1, node2, label="one")
-        node2,
-        label="one",
-        weight=-10.5
-    )
-    assert graph.has_edge(
-        node1,
-        node2,
-        label="one"
-    )
     assert node1.heads() == []
     assert [tuple(h) for h in node2.heads()] == [(0,)]
     assert [tuple(t) for t in node1.tails()] == [(1, 3)]
@@ -42,7 +33,7 @@ def test_graph_walk():
         nodes=[(0,), (1,), (2,), (3,)],
         edges=[(0, 1), (0, 2), (0, 3), (3, 0)],
         labels=None,
-        weights=None
+        weights=None,
     )
     node0, node1, node2, node3 = list(graph.nodes)
     assert [tuple(h) for h in node0.heads()] == [(3,)]

spacy/tests/lang/am/test_text.py

@@ -1,5 +1,4 @@
 import pytest
-from spacy.lang.am.lex_attrs import like_num
 
 
 def test_am_tokenizer_handles_long_text(am_tokenizer):

spacy/tests/lang/en/test_exceptions.py

@@ -121,9 +121,7 @@ def test_en_tokenizer_norm_exceptions(en_tokenizer, text, norms):
     assert [token.norm_ for token in tokens] == norms
 
 
-@pytest.mark.parametrize(
+@pytest.mark.parametrize("text,norm", [("Jan.", "January"), ("'cuz", "because")])
-    "text,norm", [("Jan.", "January"), ("'cuz", "because")]
-)
 def test_en_lex_attrs_norm_exceptions(en_tokenizer, text, norm):
     tokens = en_tokenizer(text)
     assert tokens[0].norm_ == norm

spacy/tests/lang/ti/test_text.py

@@ -1,5 +1,4 @@
 import pytest
-from spacy.lang.ti.lex_attrs import like_num
 
 
 def test_ti_tokenizer_handles_long_text(ti_tokenizer):

spacy/tests/pipeline/test_textcat.py

@@ -146,12 +146,12 @@ def test_no_resize(name):
 
 def test_error_with_multi_labels():
     nlp = Language()
-    textcat = nlp.add_pipe("textcat")
+    nlp.add_pipe("textcat")
     train_examples = []
     for text, annotations in TRAIN_DATA_MULTI_LABEL:
         train_examples.append(Example.from_dict(nlp.make_doc(text), annotations))
     with pytest.raises(ValueError):
-        optimizer = nlp.initialize(get_examples=lambda: train_examples)
+        nlp.initialize(get_examples=lambda: train_examples)
 
 
 @pytest.mark.parametrize(
@@ -273,7 +273,7 @@ def test_overfitting_IO_multi():
     assert_equal(batch_cats_1, no_batch_cats)
 
 
-def test_overfitting_IO_multi():
+def test_overfitting_IO_multi_2():
     # Simple test to try and quickly overfit the multi-label textcat component - ensuring the ML models work correctly
     fix_random_seed(0)
     nlp = English()
@@ -362,7 +362,9 @@ def test_positive_class():
     textcat_multilabel = nlp.add_pipe("textcat_multilabel")
     get_examples = make_get_examples_multi_label(nlp)
     with pytest.raises(TypeError):
-        textcat_multilabel.initialize(get_examples, labels=["POS", "NEG"], positive_label="POS")
+        textcat_multilabel.initialize(
+            get_examples, labels=["POS", "NEG"], positive_label="POS"
+        )
     textcat_multilabel.initialize(get_examples, labels=["FICTION", "DRAMA"])
     assert textcat_multilabel.labels == ("FICTION", "DRAMA")
     assert "positive_label" not in textcat_multilabel.cfg
@@ -381,7 +383,9 @@ def test_positive_class_not_binary():
     textcat = nlp.add_pipe("textcat")
     get_examples = make_get_examples_multi_label(nlp)
     with pytest.raises(ValueError):
-        textcat.initialize(get_examples, labels=["SOME", "THING", "POS"], positive_label="POS")
+        textcat.initialize(
+            get_examples, labels=["SOME", "THING", "POS"], positive_label="POS"
+        )
 
 
 def test_textcat_evaluation():

spacy/tests/regression/test_issue4001-4500.py

@@ -13,7 +13,6 @@ from spacy.lang.el import Greek
 from spacy.language import Language
 import spacy
 from thinc.api import compounding
-from collections import defaultdict
 
 from ..util import make_tempdir
 
@@ -311,9 +310,7 @@ def test_issue4313():
     # ensure the beam_parse still works with the new label
     docs = [doc]
     ner = nlp.get_pipe("beam_ner")
-    beams = ner.beam_parse(
+    ner.beam_parse(docs, drop=0.0, beam_width=beam_width, beam_density=beam_density)
-        docs, drop=0.0, beam_width=beam_width, beam_density=beam_density
-    )
 
 
 def test_issue4348():

spacy/tests/test_language.py

@@ -251,7 +251,9 @@ def test_language_from_config_before_after_init():
     nlp.initialize()
     assert nlp.meta["before_init"] == "before"
     assert nlp.meta["after_init"] == "after"
-    assert all([ran_before, ran_after, ran_after_pipeline, ran_before_init, ran_after_init])
+    assert all(
+        [ran_before, ran_after, ran_after_pipeline, ran_before_init, ran_after_init]
+    )
 
 
 def test_language_from_config_before_after_init_invalid():

spacy/tests/training/test_new_example.py

@@ -166,19 +166,11 @@ def test_Example_from_dict_with_entities(annots):
     vocab = Vocab()
     predicted = Doc(vocab, words=annots["words"])
     example = Example.from_dict(predicted, annots)
-
     assert len(list(example.reference.ents)) == 2
-    assert [example.reference[i].ent_iob_ for i in range(7)] == [
+    # fmt: off
-        "O",
+    assert [example.reference[i].ent_iob_ for i in range(7)] == ["O", "O", "B", "I", "O", "B", "O"]
-        "O",
-        "B",
-        "I",
-        "O",
-        "B",
-        "O",
-    ]
     assert example.get_aligned("ENT_IOB") == [2, 2, 3, 1, 2, 3, 2]
-
+    # fmt: on
     assert example.reference[2].ent_type_ == "LOC"
     assert example.reference[3].ent_type_ == "LOC"
     assert example.reference[5].ent_type_ == "LOC"
@@ -299,7 +291,8 @@ def test_Example_missing_heads():
     assert parsed_heads[2] == heads[2]
     assert parsed_heads[4] == heads[4]
     assert parsed_heads[5] == heads[5]
-    assert [t.has_head() for t in example.reference] == [True, True, True, False, True, True]
+    expected = [True, True, True, False, True, True]
-
+    assert [t.has_head() for t in example.reference] == expected
     # Ensure that the missing head doesn't create an artificial new sentence start
-    assert example.get_aligned_sent_starts() == [True, False, False, False, False, False]
+    expected = [True, False, False, False, False, False]
+    assert example.get_aligned_sent_starts() == expected