Tidy up and auto-format

spacy/cli/pretrain.py

@@ -120,7 +120,7 @@ def pretrain(
             window_size=1,
             char_embed=False,
             nM=64,
-            nC=8
+            nC=8,
         ),
     )
     # Load in pretrained weights

spacy/cli/train.py

@@ -9,7 +9,7 @@ from wasabi import msg
 import contextlib
 import random
 
-from ..util import create_default_optimizer, registry
+from ..util import create_default_optimizer
 from ..util import use_gpu as set_gpu
 from ..attrs import PROB, IS_OOV, CLUSTER, LANG
 from ..gold import GoldCorpus
@@ -161,7 +161,10 @@ def train(
                 raise ValueError(f"Component {pipe} currently not supported.")
             pipe_cfg = util.load_config(config_loc, create_objects=False)
             if vectors:
-                pretrained_config = {'@architectures': 'spacy.VocabVectors.v1', 'name': vectors}
+                pretrained_config = {
+                    "@architectures": "spacy.VocabVectors.v1",
+                    "name": vectors,
+                }
                 pipe_cfg["model"]["tok2vec"]["pretrained_vectors"] = pretrained_config
 
             if pipe == "parser":
@@ -202,7 +205,7 @@ def train(
         msg.text(f"Starting with blank model '{lang}'")
         lang_cls = util.get_lang_class(lang)
         nlp = lang_cls()
-        
+
         if vectors:
             msg.text(f"Loading vectors from model '{vectors}'")
 
@@ -222,7 +225,10 @@ def train(
                 raise ValueError(f"Component {pipe} currently not supported.")
             pipe_cfg = util.load_config(config_loc, create_objects=False)
             if vectors:
-                pretrained_config = {'@architectures': 'spacy.VocabVectors.v1', 'name': vectors}
+                pretrained_config = {
+                    "@architectures": "spacy.VocabVectors.v1",
+                    "name": vectors,
+                }
                 pipe_cfg["model"]["tok2vec"]["pretrained_vectors"] = pretrained_config
 
             if pipe == "parser":

spacy/cli/train_from_config.py

@@ -1,10 +1,8 @@
 from typing import Optional, Dict, List, Union, Sequence
-from pydantic import BaseModel, FilePath, StrictInt
-
+from pydantic import BaseModel, FilePath
 import plac
 import tqdm
 from pathlib import Path
-
 from wasabi import msg
 import thinc
 import thinc.schedules

spacy/language.py

@@ -130,7 +130,13 @@ class Language(object):
     factories = {"tokenizer": lambda nlp: nlp.Defaults.create_tokenizer(nlp)}
 
     def __init__(
-        self, vocab=True, make_doc=True, max_length=10 ** 6, meta={}, config=None, **kwargs
+        self,
+        vocab=True,
+        make_doc=True,
+        max_length=10 ** 6,
+        meta={},
+        config=None,
+        **kwargs,
     ):
         """Initialise a Language object.
 
@@ -176,20 +182,29 @@ class Language(object):
         self.max_length = max_length
         self._optimizer = None
 
-        from .ml.models.defaults import default_tagger_config, default_parser_config, default_ner_config, \
-            default_textcat_config, default_nel_config, default_morphologizer_config, default_sentrec_config, \
-            default_tensorizer_config, default_tok2vec_config
+        from .ml.models.defaults import (
+            default_tagger_config,
+            default_parser_config,
+            default_ner_config,
+            default_textcat_config,
+            default_nel_config,
+            default_morphologizer_config,
+            default_sentrec_config,
+            default_tensorizer_config,
+            default_tok2vec_config,
+        )
 
-        self.defaults = {"tagger": default_tagger_config(),
-                "parser": default_parser_config(),
-                "ner": default_ner_config(),
-                "textcat": default_textcat_config(),
-                "entity_linker": default_nel_config(),
-                "morphologizer": default_morphologizer_config(),
-                "sentrec": default_sentrec_config(),
-                "tensorizer": default_tensorizer_config(),
-                "tok2vec": default_tok2vec_config(),
-                }
+        self.defaults = {
+            "tagger": default_tagger_config(),
+            "parser": default_parser_config(),
+            "ner": default_ner_config(),
+            "textcat": default_textcat_config(),
+            "entity_linker": default_nel_config(),
+            "morphologizer": default_morphologizer_config(),
+            "sentrec": default_sentrec_config(),
+            "tensorizer": default_tensorizer_config(),
+            "tok2vec": default_tok2vec_config(),
+        }
 
     @property
     def path(self):
@@ -329,12 +344,14 @@ class Language(object):
                 model_cfg = None
             del config["model"]
         if model_cfg is None and default_config is not None:
-            user_warning(Warnings.W098)
+            user_warning(Warnings.W098.format(name=name))
             model_cfg = default_config["model"]
         model = None
         if model_cfg is not None:
-            self.config[name] = {"model":  model_cfg}
-            model = registry.make_from_config({"model": model_cfg}, validate=True)["model"]
+            self.config[name] = {"model": model_cfg}
+            model = registry.make_from_config({"model": model_cfg}, validate=True)[
+                "model"
+            ]
         return factory(self, model, **config)
 
     def add_pipe(

spacy/ml/models/__init__.py

@@ -1,6 +1,6 @@
-from .entity_linker import *
-from .parser import *
-from .tagger import *
-from .tensorizer import *
-from .textcat import *
-from .tok2vec import *
+from .entity_linker import *  # noqa
+from .parser import *  # noqa
+from .tagger import *  # noqa
+from .tensorizer import *  # noqa
+from .textcat import *  # noqa
+from .tok2vec import *  # noqa

spacy/ml/models/entity_linker.py

@@ -1,9 +1,7 @@
-from pathlib import Path
-
 from thinc.api import chain, clone, list2ragged, reduce_mean, residual
 from thinc.api import Model, Maxout, Linear
 
-from spacy.util import registry
+from ...util import registry
 
 
 @registry.architectures.register("spacy.EntityLinker.v1")

spacy/ml/models/parser.py

@@ -1,11 +1,10 @@
 from pydantic import StrictInt
-
-from spacy.util import registry
-from spacy.ml._layers import PrecomputableAffine
-from spacy.syntax._parser_model import ParserModel
-
 from thinc.api import Model, chain, list2array, Linear, zero_init, use_ops
 
+from ...util import registry
+from .._layers import PrecomputableAffine
+from ...syntax._parser_model import ParserModel
+
 
 @registry.architectures.register("spacy.TransitionBasedParser.v1")
 def build_tb_parser_model(

spacy/ml/models/tagger.py

@@ -1,6 +1,6 @@
 from thinc.api import zero_init, with_array, Softmax, chain, Model
 
-from spacy.util import registry
+from ...util import registry
 
 
 @registry.architectures.register("spacy.Tagger.v1")

spacy/ml/models/textcat.py

@@ -1,8 +1,9 @@
-from spacy.attrs import ORTH
-from spacy.util import registry
-from spacy.ml.extract_ngrams import extract_ngrams
+from thinc.api import Model, chain, reduce_mean, Linear, list2ragged, Logistic
+from thinc.api import SparseLinear, Softmax
 
-from thinc.api import Model, chain, reduce_mean, Linear, list2ragged, Logistic, SparseLinear, Softmax
+from ...attrs import ORTH
+from ...util import registry
+from ..extract_ngrams import extract_ngrams
 
 
 @registry.architectures.register("spacy.TextCatCNN.v1")
@@ -21,7 +22,9 @@ def build_simple_cnn_text_classifier(tok2vec, exclusive_classes, nO=None):
         else:
             # TODO: experiment with init_w=zero_init
             linear_layer = Linear(nO=nO, nI=tok2vec.get_dim("nO"))
-            model = tok2vec >> list2ragged() >> reduce_mean() >> linear_layer >> Logistic()
+            model = (
+                tok2vec >> list2ragged() >> reduce_mean() >> linear_layer >> Logistic()
+            )
             model.set_ref("output_layer", linear_layer)
     model.set_ref("tok2vec", tok2vec)
     model.set_dim("nO", nO)

spacy/ml/models/tok2vec.py

@@ -119,7 +119,7 @@ def hash_embed_bilstm_v1(
 
 
 @registry.architectures.register("spacy.HashCharEmbedBiLSTM.v1")
-def hash_embed_bilstm_v1(
+def hash_char_embed_bilstm_v1(
     pretrained_vectors, width, depth, embed_size, subword_features, nM=0, nC=0
 ):
     # Allows using character embeddings by setting nC, nM and char_embed=True

spacy/pipeline/tok2vec.py

@@ -10,7 +10,6 @@ from ..util import link_vectors_to_models, minibatch, eg2doc
 
 @component("tok2vec", assigns=["doc.tensor"])
 class Tok2Vec(Pipe):
-
     @classmethod
     def from_nlp(cls, nlp, model, **cfg):
         return cls(nlp.vocab, model, **cfg)

spacy/tests/parser/test_add_label.py

@@ -73,7 +73,8 @@ def test_add_label_deserializes_correctly():
 
 
 @pytest.mark.parametrize(
-    "pipe_cls,n_moves,model", [(DependencyParser, 5, default_parser()), (EntityRecognizer, 4, default_ner())]
+    "pipe_cls,n_moves,model",
+    [(DependencyParser, 5, default_parser()), (EntityRecognizer, 4, default_ner())],
 )
 def test_add_label_get_label(pipe_cls, n_moves, model):
     """Test that added labels are returned correctly. This test was added to

spacy/tests/parser/test_ner.py

@@ -212,7 +212,8 @@ def test_empty_ner():
     nlp.begin_training()
     doc = nlp("John is watching the news about Croatia's elections")
     # if this goes wrong, the initialization of the parser's upper layer is probably broken
-    assert [token.ent_iob_ for token in doc] == ['O', 'O', 'O', 'O', 'O', 'O', 'O', 'O', 'O']
+    result = ["O", "O", "O", "O", "O", "O", "O", "O", "O"]
+    assert [token.ent_iob_ for token in doc] == result
 
 
 def test_ruler_before_ner():

spacy/tests/regression/test_issue1501-2000.py

@@ -237,7 +237,7 @@ def test_issue1889(word):
     assert is_stop(word, STOP_WORDS) == is_stop(word.upper(), STOP_WORDS)
 
 
-@pytest.mark.skip(reason="This test has become obsolete with the config refactor of v.3")
+@pytest.mark.skip(reason="obsolete with the config refactor of v.3")
 def test_issue1915():
     cfg = {"hidden_depth": 2}  # should error out
     nlp = Language()

spacy/tests/serialize/test_serialize_config.py

@@ -58,10 +58,22 @@ subword_features = false
 
 @registry.architectures.register("my_test_parser")
 def my_parser():
-    tok2vec = build_Tok2Vec_model(width=321, embed_size=5432, pretrained_vectors=None, window_size=3,
-                                  maxout_pieces=4, subword_features=True, char_embed=True, nM=64, nC=8,
-                                  conv_depth=2, bilstm_depth=0)
-    parser = build_tb_parser_model(tok2vec=tok2vec, nr_feature_tokens=7, hidden_width=65, maxout_pieces=5)
+    tok2vec = build_Tok2Vec_model(
+        width=321,
+        embed_size=5432,
+        pretrained_vectors=None,
+        window_size=3,
+        maxout_pieces=4,
+        subword_features=True,
+        char_embed=True,
+        nM=64,
+        nC=8,
+        conv_depth=2,
+        bilstm_depth=0,
+    )
+    parser = build_tb_parser_model(
+        tok2vec=tok2vec, nr_feature_tokens=7, hidden_width=65, maxout_pieces=5
+    )
     return parser
 
 
@@ -88,7 +100,7 @@ def test_serialize_custom_nlp():
     """ Create a custom nlp pipeline and ensure it serializes it correctly"""
     nlp = English()
     parser_cfg = dict()
-    parser_cfg["model"] = {'@architectures': "my_test_parser"}
+    parser_cfg["model"] = {"@architectures": "my_test_parser"}
     parser = nlp.create_pipe("parser", parser_cfg)
     nlp.add_pipe(parser)
     nlp.begin_training()

spacy/tests/serialize/test_serialize_pipeline.py

@@ -1,7 +1,8 @@
 import pytest
 from spacy.pipeline import Tagger, DependencyParser, EntityRecognizer
 from spacy.pipeline import Tensorizer, TextCategorizer, SentenceRecognizer
-from spacy.ml.models.defaults import default_parser, default_tensorizer, default_tagger, default_textcat, default_sentrec
+from spacy.ml.models.defaults import default_parser, default_tensorizer, default_tagger
+from spacy.ml.models.defaults import default_textcat, default_sentrec
 
 from ..util import make_tempdir
 
@@ -114,7 +115,9 @@ def test_serialize_tensorizer_roundtrip_disk(en_vocab):
 
 def test_serialize_textcat_empty(en_vocab):
     # See issue #1105
-    textcat = TextCategorizer(en_vocab, default_textcat(), labels=["ENTITY", "ACTION", "MODIFIER"])
+    textcat = TextCategorizer(
+        en_vocab, default_textcat(), labels=["ENTITY", "ACTION", "MODIFIER"]
+    )
     textcat.to_bytes(exclude=["vocab"])
 
 

spacy/tests/test_tok2vec.py

@@ -67,8 +67,8 @@ def test_tok2vec_batch_sizes(batch_size, width, embed_size):
         {"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 6, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": True},
         {"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 1, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
         {"width": 8, "embed_size": 100, "char_embed": False, "nM": 64, "nC": 8, "pretrained_vectors": None, "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
-        {"width": 8, "embed_size": 100, "char_embed": True, "nM": 81, "nC": 8, "pretrained_vectors": None,  "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
-        {"width": 8, "embed_size": 100, "char_embed": True, "nM": 81, "nC": 9, "pretrained_vectors": None,  "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
+        {"width": 8, "embed_size": 100, "char_embed": True, "nM": 81, "nC": 8, "pretrained_vectors": None, "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
+        {"width": 8, "embed_size": 100, "char_embed": True, "nM": 81, "nC": 9, "pretrained_vectors": None, "window_size": 3, "conv_depth": 2, "bilstm_depth": 0, "maxout_pieces": 3, "subword_features": False},
     ],
 )
 # fmt: on