Tidy up and auto-format

spacy/cli/train.py

@@ -225,7 +225,9 @@ def train(
                             exits=1,
                         )
                 msg.text("Extending component from base model '{}'".format(pipe))
-        disabled_pipes = nlp.disable_pipes([p for p in nlp.pipe_names if p not in pipeline])
+        disabled_pipes = nlp.disable_pipes(
+            [p for p in nlp.pipe_names if p not in pipeline]
+        )
     else:
         msg.text("Starting with blank model '{}'".format(lang))
         lang_cls = util.get_lang_class(lang)
@@ -415,10 +417,10 @@ def train(
                             losses=losses,
                         )
                     except ValueError as e:
-                        msg.warn("Error during training")
+                        err = "Error during training"
                         if init_tok2vec:
-                            msg.warn("Did you provide the same parameters during 'train' as during 'pretrain'?")
+                            err += " Did you provide the same parameters during 'train' as during 'pretrain'?"
-                        msg.fail("Original error message: {}".format(e), exits=1)
+                        msg.fail(err, "Original error message: {}".format(e), exits=1)
                     if raw_text:
                         # If raw text is available, perform 'rehearsal' updates,
                         # which use unlabelled data to reduce overfitting.
@@ -546,7 +548,10 @@ def train(
                         )
                         break
     except Exception as e:
-        msg.warn("Aborting and saving the final best model. Encountered exception: {}".format(e))
+        msg.warn(
+            "Aborting and saving the final best model. "
+            "Encountered exception: {}".format(e)
+        )
     finally:
         best_pipes = nlp.pipe_names
         if disabled_pipes:
@@ -563,13 +568,20 @@ def train(
             final_meta["speed"].setdefault("gpu", None)
             # combine cpu and gpu speeds with the base model speeds
             if final_meta["speed"]["cpu"] and meta["speed"]["cpu"]:
-                speed = _get_total_speed([final_meta["speed"]["cpu"], meta["speed"]["cpu"]])
+                speed = _get_total_speed(
+                    [final_meta["speed"]["cpu"], meta["speed"]["cpu"]]
+                )
                 final_meta["speed"]["cpu"] = speed
             if final_meta["speed"]["gpu"] and meta["speed"]["gpu"]:
-                speed = _get_total_speed([final_meta["speed"]["gpu"], meta["speed"]["gpu"]])
+                speed = _get_total_speed(
+                    [final_meta["speed"]["gpu"], meta["speed"]["gpu"]]
+                )
                 final_meta["speed"]["gpu"] = speed
             # if there were no speeds to update, overwrite with meta
-            if final_meta["speed"]["cpu"] is None and final_meta["speed"]["gpu"] is None:
+            if (
+                final_meta["speed"]["cpu"] is None
+                and final_meta["speed"]["gpu"] is None
+            ):
                 final_meta["speed"].update(meta["speed"])
             # note: beam speeds are not combined with the base model
             if has_beam_widths:

spacy/displacy/__init__.py

@@ -146,9 +146,14 @@ def parse_deps(orig_doc, options={}):
                 retokenizer.merge(span, attrs=attrs)
     fine_grained = options.get("fine_grained")
     add_lemma = options.get("add_lemma")
-    words = [{"text": w.text,
+    words = [
+        {
+            "text": w.text,
             "tag": w.tag_ if fine_grained else w.pos_,
-              "lemma": w.lemma_ if add_lemma else None} for w in doc]
+            "lemma": w.lemma_ if add_lemma else None,
+        }
+        for w in doc
+    ]
 
     arcs = []
     for word in doc:

spacy/displacy/render.py

@@ -3,7 +3,13 @@ from __future__ import unicode_literals
 
 import uuid
 
-from .templates import TPL_DEP_SVG, TPL_DEP_WORDS, TPL_DEP_WORDS_LEMMA, TPL_DEP_ARCS, TPL_ENTS
+from .templates import (
+    TPL_DEP_SVG,
+    TPL_DEP_WORDS,
+    TPL_DEP_WORDS_LEMMA,
+    TPL_DEP_ARCS,
+    TPL_ENTS,
+)
 from .templates import TPL_ENT, TPL_ENT_RTL, TPL_FIGURE, TPL_TITLE, TPL_PAGE
 from ..util import minify_html, escape_html, registry
 from ..errors import Errors
@@ -83,7 +89,10 @@ class DependencyRenderer(object):
         self.width = self.offset_x + len(words) * self.distance
         self.height = self.offset_y + 3 * self.word_spacing
         self.id = render_id
-        words = [self.render_word(w["text"], w["tag"],  w.get("lemma", None), i) for i, w in enumerate(words)]
+        words = [
+            self.render_word(w["text"], w["tag"], w.get("lemma", None), i)
+            for i, w in enumerate(words)
+        ]
         arcs = [
             self.render_arrow(a["label"], a["start"], a["end"], a["dir"], i)
             for i, a in enumerate(arcs)
@@ -101,7 +110,9 @@ class DependencyRenderer(object):
             lang=self.lang,
         )
 
-    def render_word(self, text, tag, lemma, i,):
+    def render_word(
+        self, text, tag, lemma, i,
+    ):
         """Render individual word.
 
         text (unicode): Word text.
@@ -115,7 +126,9 @@ class DependencyRenderer(object):
             x = self.width - x
         html_text = escape_html(text)
         if lemma is not None:
-            return TPL_DEP_WORDS_LEMMA.format(text=html_text, tag=tag, lemma=lemma, x=x, y=y)
+            return TPL_DEP_WORDS_LEMMA.format(
+                text=html_text, tag=tag, lemma=lemma, x=x, y=y
+            )
         return TPL_DEP_WORDS.format(text=html_text, tag=tag, x=x, y=y)
 
     def render_arrow(self, label, start, end, direction, i):

spacy/errors.py

@@ -112,7 +112,6 @@ class Warnings(object):
             "in problems with the vocab further on in the pipeline.")
 
 
-
 @add_codes
 class Errors(object):
     E001 = ("No component '{name}' found in pipeline. Available names: {opts}")

spacy/lang/de/punctuation.py

@@ -2,7 +2,7 @@
 from __future__ import unicode_literals
 
 from ..char_classes import LIST_ELLIPSES, LIST_ICONS, LIST_PUNCT, LIST_QUOTES
-from ..char_classes import LIST_CURRENCY, CURRENCY, UNITS, PUNCT
+from ..char_classes import CURRENCY, UNITS, PUNCT
 from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
 from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES
 

spacy/lang/eu/examples.py

@@ -10,5 +10,5 @@ Example sentences to test spaCy and its language models.
 
 sentences = [
     "bilbon ko castinga egin da eta nik jakin ez zuetako inork egin al du edota parte hartu duen ezagunik ba al du",
-    "gaur telebistan entzunda denok martetik gatoz hortaz martzianoak gara beno nire ustez batzuk beste batzuk baino martzianoagoak dira"
+    "gaur telebistan entzunda denok martetik gatoz hortaz martzianoak gara beno nire ustez batzuk beste batzuk baino martzianoagoak dira",
 ]

spacy/lang/eu/lex_attrs.py

@@ -59,7 +59,6 @@ behin
 """.split()
 
 
-
 def like_num(text):
     if text.startswith(("+", "-", "±", "~")):
         text = text[1:]

spacy/lang/fr/punctuation.py

@@ -16,7 +16,9 @@ _hyphen_suffixes += " " + _hyphen_suffixes.upper()
 
 
 _prefixes = TOKENIZER_PREFIXES + [
-    r"(?:({pe})[{el}])(?=[{a}])".format(a=ALPHA, el=ELISION, pe=merge_chars(_prefixes_elision))
+    r"(?:({pe})[{el}])(?=[{a}])".format(
+        a=ALPHA, el=ELISION, pe=merge_chars(_prefixes_elision)
+    )
 ]
 
 _suffixes = (
@@ -33,7 +35,9 @@ _suffixes = (
             al=ALPHA_LOWER, e=r"%²\-\+", q=CONCAT_QUOTES
         ),
         r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
-        r"(?<=[{a}])[{h}]({hs})".format(a=ALPHA, h=HYPHENS, hs=merge_chars(_hyphen_suffixes)),
+        r"(?<=[{a}])[{h}]({hs})".format(
+            a=ALPHA, h=HYPHENS, hs=merge_chars(_hyphen_suffixes)
+        ),
     ]
 )
 

spacy/lang/fr/tokenizer_exceptions.py

@@ -6,7 +6,7 @@ import re
 from .punctuation import ELISION, HYPHENS
 from ..tokenizer_exceptions import URL_PATTERN
 from ..char_classes import ALPHA_LOWER, ALPHA
-from ...symbols import ORTH, LEMMA, TAG
+from ...symbols import ORTH, LEMMA
 
 # not using the large _tokenizer_exceptions_list by default as it slows down the tokenizer
 # from ._tokenizer_exceptions_list import FR_BASE_EXCEPTIONS

spacy/lang/it/punctuation.py

@@ -1,7 +1,7 @@
 # coding: utf8
 from __future__ import unicode_literals
 
-from ..punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
+from ..punctuation import TOKENIZER_PREFIXES as BASE_TOKENIZER_PREFIXES
 from ..char_classes import LIST_ELLIPSES, LIST_ICONS
 from ..char_classes import ALPHA, HYPHENS, CONCAT_QUOTES
 from ..char_classes import ALPHA_LOWER, ALPHA_UPPER
@@ -10,14 +10,7 @@ from ..char_classes import ALPHA_LOWER, ALPHA_UPPER
 ELISION = "'’"
 
 
-_prefixes = (
+_prefixes = [r"'[0-9][0-9]", r"[0-9]+°"] + BASE_TOKENIZER_PREFIXES
-    [
-        r"'[0-9][0-9]",
-        r"[0-9]+°",
-
-    ]
-    + TOKENIZER_PREFIXES
-)
 
 
 _infixes = (
@@ -31,7 +24,7 @@ _infixes = (
         r"(?<=[{a}]),(?=[{a}])".format(a=ALPHA),
         r"(?<=[{a}])(?:{h})(?=[{al}])".format(a=ALPHA, h=HYPHENS, al=ALPHA_LOWER),
         r"(?<=[{a}0-9])[:<>=\/](?=[{a}])".format(a=ALPHA),
-        r"(?<=[{a}][{el}])(?=[{a}0-9\"])".format(a=ALPHA, el=ELISION)
+        r"(?<=[{a}][{el}])(?=[{a}0-9\"])".format(a=ALPHA, el=ELISION),
     ]
 )
 

spacy/lang/it/tokenizer_exceptions.py

@@ -10,7 +10,7 @@ _exc = {
     "l'art.": [{ORTH: "l'"}, {ORTH: "art."}],
     "nell'art.": [{ORTH: "nell'"}, {ORTH: "art."}],
     "po'": [{ORTH: "po'", LEMMA: "poco"}],
-    "sett..": [{ORTH: "sett."}, {ORTH: "."}]
+    "sett..": [{ORTH: "sett."}, {ORTH: "."}],
 }
 
 for orth in [
@@ -32,7 +32,7 @@ for orth in [
     "col.",
     "Cost.",
     "d.C.",
-    'de"'
+    'de"',
     "distr.",
     "E'",
     "ecc.",

spacy/lang/lt/__init__.py

@@ -29,7 +29,9 @@ class LithuanianDefaults(Language.Defaults):
 
     infixes = TOKENIZER_INFIXES
     suffixes = TOKENIZER_SUFFIXES
-    mod_base_exceptions = {exc: val for exc, val in BASE_EXCEPTIONS.items() if not exc.endswith(".")}
+    mod_base_exceptions = {
+        exc: val for exc, val in BASE_EXCEPTIONS.items() if not exc.endswith(".")
+    }
     del mod_base_exceptions["8)"]
     tokenizer_exceptions = update_exc(mod_base_exceptions, TOKENIZER_EXCEPTIONS)
     stop_words = STOP_WORDS

spacy/lang/nb/punctuation.py

@@ -24,7 +24,6 @@ _prefixes = (
 )
 
 
-
 _infixes = (
     LIST_ELLIPSES
     + _list_icons

spacy/lang/pt/tokenizer_exceptions.py

@@ -1,7 +1,7 @@
 # coding: utf8
 from __future__ import unicode_literals
 
-from ...symbols import ORTH, NORM
+from ...symbols import ORTH
 
 
 _exc = {}

spacy/lang/sk/tag_map.py

@@ -1,8 +1,8 @@
 # coding: utf8
 from __future__ import unicode_literals
 
-from ...symbols import POS, AUX, PUNCT, SYM, ADJ, CCONJ, NUM, DET, ADV, ADP, X, VERB
+from ...symbols import POS, AUX, ADJ, CCONJ, NUM, ADV, ADP, X, VERB
-from ...symbols import NOUN, PROPN, PART, INTJ, SPACE, PRON
+from ...symbols import NOUN, PART, INTJ, PRON
 
 # Source https://universaldependencies.org/tagset-conversion/sk-snk-uposf.html
 # fmt: off

spacy/lang/tokenizer_exceptions.py

@@ -37,7 +37,7 @@ URL_PATTERN = (
     r"|"
     # host & domain names
     # mods: match is case-sensitive, so include [A-Z]
-      "(?:"
+      "(?:"  # noqa
         "(?:"
           "[A-Za-z0-9\u00a1-\uffff]"
           "[A-Za-z0-9\u00a1-\uffff_-]{0,62}"

spacy/language.py

@@ -612,7 +612,7 @@ class Language(object):
         link_vectors_to_models(self.vocab)
         if self.vocab.vectors.data.shape[1]:
             cfg["pretrained_vectors"] = self.vocab.vectors.name
-            cfg['pretrained_dims'] = self.vocab.vectors.data.shape[1]
+            cfg["pretrained_dims"] = self.vocab.vectors.data.shape[1]
         if sgd is None:
             sgd = create_default_optimizer(Model.ops)
         self._optimizer = sgd
@@ -857,7 +857,14 @@ class Language(object):
         procs = [
             mp.Process(
                 target=_apply_pipes,
-                args=(self.make_doc, pipes, rch, sch, Underscore.get_state(), load_nlp.VECTORS),
+                args=(
+                    self.make_doc,
+                    pipes,
+                    rch,
+                    sch,
+                    Underscore.get_state(),
+                    load_nlp.VECTORS,
+                ),
             )
             for rch, sch in zip(texts_q, bytedocs_send_ch)
         ]

spacy/pipeline/entityruler.py

@@ -222,11 +222,9 @@ class EntityRuler(object):
             for label, pattern, ent_id in zip(
                 phrase_pattern_labels,
                 self.nlp.pipe(phrase_pattern_texts),
-                phrase_pattern_ids
+                phrase_pattern_ids,
             ):
-                phrase_pattern = {
+                phrase_pattern = {"label": label, "pattern": pattern, "id": ent_id}
-                    "label": label, "pattern": pattern, "id": ent_id
-                }
                 if ent_id:
                     phrase_pattern["id"] = ent_id
                 phrase_patterns.append(phrase_pattern)

spacy/tests/doc/test_array.py

@@ -71,9 +71,7 @@ def test_doc_array_to_from_string_attrs(en_vocab, attrs):
 def test_doc_array_idx(en_vocab):
     """Test that Doc.to_array can retrieve token start indices"""
     words = ["An", "example", "sentence"]
-    doc = Doc(en_vocab, words=words)
     offsets = Doc(en_vocab, words=words).to_array("IDX")
-
     assert offsets[0] == 0
     assert offsets[1] == 3
     assert offsets[2] == 11

spacy/tests/lang/eu/test_text.py

@@ -10,7 +10,13 @@ def test_eu_tokenizer_handles_long_text(eu_tokenizer):
     assert len(tokens) == 5
 
 
-@pytest.mark.parametrize("text,length", [("milesker ederra joan zen hitzaldia plazer hutsa", 7), ("astelehen guztia sofan pasau biot", 5)])
+@pytest.mark.parametrize(
+    "text,length",
+    [
+        ("milesker ederra joan zen hitzaldia plazer hutsa", 7),
+        ("astelehen guztia sofan pasau biot", 5),
+    ],
+)
 def test_eu_tokenizer_handles_cnts(eu_tokenizer, text, length):
     tokens = eu_tokenizer(text)
     assert len(tokens) == length

spacy/tests/lang/hu/test_tokenizer.py

@@ -297,12 +297,7 @@ WIKI_TESTS = [
 ]
 
 EXTRA_TESTS = (
-    DOT_TESTS
+    DOT_TESTS + QUOTE_TESTS + NUMBER_TESTS + HYPHEN_TESTS + WIKI_TESTS + TYPO_TESTS
-    + QUOTE_TESTS
-    + NUMBER_TESTS
-    + HYPHEN_TESTS
-    + WIKI_TESTS
-    + TYPO_TESTS
 )
 
 # normal: default tests + 10% of extra tests
@@ -311,7 +306,14 @@ TESTS.extend([x for i, x in enumerate(EXTRA_TESTS) if i % 10 == 0])
 
 # slow: remaining 90% of extra tests
 SLOW_TESTS = [x for i, x in enumerate(EXTRA_TESTS) if i % 10 != 0]
-TESTS.extend([pytest.param(x[0], x[1], marks=pytest.mark.slow()) if not isinstance(x[0], tuple) else x for x in SLOW_TESTS])
+TESTS.extend(
+    [
+        pytest.param(x[0], x[1], marks=pytest.mark.slow())
+        if not isinstance(x[0], tuple)
+        else x
+        for x in SLOW_TESTS
+    ]
+)
 
 
 @pytest.mark.parametrize("text,expected_tokens", TESTS)

spacy/tests/matcher/test_matcher_api.py

@@ -6,7 +6,8 @@ import re
 from mock import Mock
 from spacy.matcher import Matcher, DependencyMatcher
 from spacy.tokens import Doc, Token
-from ..doc.test_underscore import clean_underscore
+
+from ..doc.test_underscore import clean_underscore  # noqa: F401
 
 
 @pytest.fixture

spacy/tests/pipeline/test_entity_ruler.py

@@ -152,10 +152,5 @@ def test_entity_ruler_validate(nlp):
 
 def test_entity_ruler_properties(nlp, patterns):
     ruler = EntityRuler(nlp, patterns=patterns, overwrite_ents=True)
-    assert sorted(ruler.labels) == sorted([
+    assert sorted(ruler.labels) == sorted(["HELLO", "BYE", "COMPLEX", "TECH_ORG"])
-        "HELLO",
-        "BYE",
-        "COMPLEX",
-        "TECH_ORG"
-    ])
     assert sorted(ruler.ent_ids) == ["a1", "a2"]

spacy/tests/regression/test_issue4725.py

@@ -23,4 +23,3 @@ def test_issue4725():
     docs = ["Kurt is in London."] * 10
     for _ in nlp.pipe(docs, batch_size=2, n_process=2):
         pass
-

spacy/tests/regression/test_issue4849.py

@@ -9,11 +9,12 @@ def test_issue4849():
     nlp = English()
 
     ruler = EntityRuler(
-        nlp, patterns=[
+        nlp,
-            {"label": "PERSON", "pattern": 'joe biden', "id": 'joe-biden'},
+        patterns=[
-            {"label": "PERSON", "pattern": 'bernie sanders', "id": 'bernie-sanders'},
+            {"label": "PERSON", "pattern": "joe biden", "id": "joe-biden"},
+            {"label": "PERSON", "pattern": "bernie sanders", "id": "bernie-sanders"},
         ],
-        phrase_matcher_attr="LOWER"
+        phrase_matcher_attr="LOWER",
     )
 
     nlp.add_pipe(ruler)
@@ -27,10 +28,10 @@ def test_issue4849():
     count_ents = 0
     for doc in nlp.pipe([text], n_process=1):
         count_ents += len([ent for ent in doc.ents if ent.ent_id > 0])
-    assert(count_ents == 2)
+    assert count_ents == 2
 
     # USING 2 PROCESSES
     count_ents = 0
     for doc in nlp.pipe([text], n_process=2):
         count_ents += len([ent for ent in doc.ents if ent.ent_id > 0])
-    assert (count_ents == 2)
+    assert count_ents == 2

spacy/tests/serialize/test_serialize_tokenizer.py

@@ -22,7 +22,7 @@ def test_serialize_custom_tokenizer(en_vocab, en_tokenizer):
     tokenizer_bytes = tokenizer.to_bytes()
     Tokenizer(en_vocab).from_bytes(tokenizer_bytes)
 
-    tokenizer = Tokenizer(en_vocab, rules={"ABC.": [{"ORTH": "ABC", "ORTH": "."}]})
+    tokenizer = Tokenizer(en_vocab, rules={"ABC.": [{"ORTH": "ABC"}, {"ORTH": "."}]})
     tokenizer.rules = {}
     tokenizer_bytes = tokenizer.to_bytes()
     tokenizer_reloaded = Tokenizer(en_vocab).from_bytes(tokenizer_bytes)

spacy/tests/util.py

@@ -28,7 +28,9 @@ def make_tempdir():
     shutil.rmtree(path2str(d))
 
 
-def get_doc(vocab, words=[], pos=None, heads=None, deps=None, tags=None, ents=None, lemmas=None):
+def get_doc(
+    vocab, words=[], pos=None, heads=None, deps=None, tags=None, ents=None, lemmas=None
+):
     """Create Doc object from given vocab, words and annotations."""
     if deps and not heads:
         heads = [0] * len(deps)