style: Moved to ruff as the main linter

docs/conf.py

@@ -41,7 +41,7 @@
     "sphinx_design",
 ]
 
-# autodoc_mock_imports = ["dacy"]
+# autodoc_mock_imports = ["dacy"]  # noqa
 
 # Add any paths that contain templates here, relative to this directory.
 templates_path = ["_templates"]
@@ -92,7 +92,7 @@
                 <svg stroke="currentColor" fill="currentColor" stroke-width="0" viewBox="0 0 16 16">
                     <path fill-rule="evenodd" d="M8 0C3.58 0 0 3.58 0 8c0 3.54 2.29 6.53 5.47 7.59.4.07.55-.17.55-.38 0-.19-.01-.82-.01-1.49-2.01.37-2.53-.49-2.69-.94-.09-.23-.48-.94-.82-1.13-.28-.15-.68-.52-.01-.53.63-.01 1.08.58 1.23.82.72 1.21 1.87.87 2.33.66.07-.52.28-.87.51-1.07-1.78-.2-3.64-.89-3.64-3.95 0-.87.31-1.59.82-2.15-.08-.2-.36-1.02.08-2.12 0 0 .67-.21 2.2.82.64-.18 1.32-.27 2-.27.68 0 1.36.09 2 .27 1.53-1.04 2.2-.82 2.2-.82.44 1.1.16 1.92.08 2.12.51.56.82 1.27.82 2.15 0 3.07-1.87 3.75-3.65 3.95.29.25.54.73.54 1.48 0 1.07-.01 1.93-.01 2.2 0 .21.15.46.55.38A8.013 8.013 0 0 0 16 8c0-4.42-3.58-8-8-8z"></path>
                 </svg>
-            """,  # noqa: E501
+            """,
             "class": "",
         },
     ],
@@ -113,5 +113,3 @@
     "navigation_with_keys": True,
 }
 
-# pygments_style = "monokai"
-# pygments_dark_style = "monokai"

docs/create_augmenters_table.py

@@ -1,12 +1,11 @@
 import os
 
-from wasabi import MarkdownRenderer
-
 import augmenty
+from wasabi import MarkdownRenderer
 
 print("Running create_augmenters_table.py")
 
-os.chdir(os.path.dirname(os.path.abspath(__file__)))
+os.chdir(os.path.dirname(os.path.abspath(__file__)))  # noqa
 
 md = MarkdownRenderer()
 meta = augmenty.meta()
@@ -40,8 +39,8 @@
             if not isinstance(r, list):
                 r = [r]
             for ref_dict in r:
-                ref = f"{ref}: "
-                ref += md.link(
+                ref = f"{ref}: "  # noqa
+                ref += md.link(  # noqa
                     f"{ref_dict['authors']} ({ref_dict['year']})",
                     ref_dict["link"],
                 )
@@ -83,5 +82,5 @@
 md.add(table)
 
 
-with open("../docs/augmenters_overview.md", "w") as f:  # type: ignore
+with open("../docs/augmenters_overview.md", "w") as f:  # type: ignore # noqa
     f.write(md.text)  # type: ignore

docs/tutorials/training_using_augmenty/training_using_augmenty.ipynb

@@ -101,20 +101,22 @@
     "\n",
     "import augmenty\n",
     "\n",
+    "\n",
     "# register the augmenter such with the name you want to specify in the config\n",
     "@spacy.registry.augmenters(\"my_augmenter\")\n",
     "def my_augmenters():\n",
     "    # create the augmenters you wish to use\n",
     "    keystroke_augmenter = augmenty.load(\n",
-    "        \"keystroke_error_v1\", keyboard=\"en_qwerty_v1\", level=0.05  # 5% of characters might be too much\n",
+    "        \"keystroke_error_v1\",\n",
+    "        keyboard=\"en_qwerty_v1\",\n",
+    "        level=0.05,  # 5% of characters might be too much\n",
     "    )\n",
     "\n",
     "    char_swap_augmenter = augmenty.load(\"char_swap_v1\", level=0.03)\n",
     "\n",
     "    # combine them into a single augmenter to be used for training\n",
     "    # the order of the augmenters is important, as the first augmenter will be applied first\n",
-    "    return augmenty.combine([keystroke_augmenter, char_swap_augmenter])\n",
-    "\n"
+    "    return augmenty.combine([keystroke_augmenter, char_swap_augmenter])"
    ]
   },
   {
@@ -156,7 +158,7 @@
     "    augmented_texts = augmenty.texts(texts, augmenter, nlp=nlp)\n",
     "\n",
     "    for text in augmented_texts:\n",
-    "        print(text)\n"
+    "        print(text)"
    ]
   },
   {

makefile

@@ -1,6 +1,6 @@
 install:
 	@echo "--- 🚀 Installing project ---"
-	pip install -e ".[dev, docs, tests]" 
+	pip install -e ".[dev, docs, tests,tutorials,all]" 
 
 static-type-check:
 	@echo "--- 🔍 Running static type check ---"

src/augmenty/span/entities.py

@@ -144,9 +144,7 @@ def ent_augmenter_v1(
                 if isinstance(ent_dict[ent.label_], Generator):
                     new_ent = next(ent_dict[ent.label_])  # type: ignore
                 else:
-                    new_ent = random.sample(ent_dict[ent.label_], k=1)[  # type: ignore
-                        0
-                    ]
+                    new_ent = random.sample(ent_dict[ent.label_], k=1)[0]  # type: ignore
                 if replace_consistency:
                     replaced_ents[ent.text] = new_ent
 

tests/fixtures.py

@@ -1,39 +1,42 @@
+from typing import Any
+
 import pytest
 import spacy
 from dacy.datasets import dane
+from spacy.language import Language
 from spacy.training import Example
 
 from .books import BOOKS
 
 
 # pipelines
 @pytest.fixture()
-def nlp_en():
+def nlp_en() -> Language:
     return spacy.blank("en")
 
 
 @pytest.fixture()
-def nlp_da():
+def nlp_da() -> Language:
     return spacy.blank("da")
 
 
 @pytest.fixture()
-def nlp_en_md():
+def nlp_en_md() -> Language:
     return spacy.load("en_core_web_md")
 
 
 @pytest.fixture()
-def dane_test(nlp_da):
-    return dane(splits=["test"])(nlp_da)
+def dane_test(nlp_da: Language) -> Any:
+    return dane(splits=["test"])(nlp_da)  # type: ignore
 
 
 @pytest.fixture()
-def books_w_annotations(nlp_en_md):
+def books_w_annotations(nlp_en_md: Language) -> list:
     docs = nlp_en_md.pipe(BOOKS)
     return [Example(doc, doc) for doc in docs]
 
 
 @pytest.fixture()
-def books_without_annotations(nlp_en):
+def books_without_annotations(nlp_en: Language) -> list:
     docs = nlp_en.pipe(BOOKS)
     return [Example(doc, doc) for doc in docs]

tests/test_all_augmenters.py

@@ -1,18 +1,26 @@
 """Pytest script for testing all augmenters in a variety of cases."""
 
-import numpy as np
-import pytest
+from typing import Callable
 
 import augmenty
+import numpy as np
+import pytest
+from spacy.language import Language
+from spacy.tokens import Token
 
-from .fixtures import books_without_annotations  # noqa
-from .fixtures import nlp_en  # noqa
-from .fixtures import books_w_annotations, dane_test, nlp_da, nlp_en_md  # noqa
+from .fixtures import (
+    books_w_annotations,
+    books_without_annotations,
+    dane_test,
+    nlp_da,
+    nlp_en,
+    nlp_en_md,
+)
 
 np.seterr(divide="raise", invalid="raise")
 
 
-def is_pronoun(token):
+def is_pronoun(token: Token) -> bool:
     if token.pos_ == "PRON":
         return True
     return False
@@ -79,11 +87,11 @@ def is_pronoun(token):
 }
 
 
-@pytest.mark.parametrize("aug,args", [(k, augmenters_args[k]) for k in augmenters_args])
+@pytest.mark.parametrize("aug,args", [(k, augmenters_args[k]) for k in augmenters_args])  # noqa
 @pytest.mark.parametrize("level", [0.1, 0.5, 1])
 @pytest.mark.timeout(100)
 @pytest.mark.parametrize(
-    "examples,nlp",
+    "examples,nlp",  # noqa
     [
         (pytest.lazy_fixture("dane_test"), pytest.lazy_fixture("nlp_da")),
         (
@@ -92,12 +100,10 @@ def is_pronoun(token):
         ),
     ],
 )
-def test_augmenters(aug, args, examples, nlp, level):
+def test_augmenters(aug: Callable, args: dict, examples, nlp: Language, level: float):  # noqa
     args["level"] = level
     aug = augmenty.load(aug, **args)
-    augmented_examples = [  # noqa
-        e for ex in examples for e in aug(nlp=nlp, example=ex)
-    ]
+    augmented_examples = [e for ex in examples for e in aug(nlp=nlp, example=ex)]
 
 
 def test_check_untested():

tests/test_augmentation_utilities.py

@@ -1,8 +1,7 @@
-from spacy.tokens import Doc, Span
-
 import augmenty
+from spacy.tokens import Doc, Span
 
-from .fixtures import nlp_en, nlp_en_md  # noqa
+from .fixtures import nlp_en, nlp_en_md
 
 
 def test_combine(nlp_en_md):  # noqa F811
@@ -58,4 +57,4 @@ def test_set_doc_level(nlp_en):  # noqa F811
     aug = augmenty.set_doc_level(aug, level=0.5)
 
     # simply testing it it runs
-    augmented_docs = list(augmenty.texts(texts, augmenter=aug, nlp=nlp_en))  # noqa
+    augmented_docs = list(augmenty.texts(texts, augmenter=aug, nlp=nlp_en))

tests/test_character.py

@@ -1,8 +1,7 @@
-import spacy  # type: ignore
-
 import augmenty
+import spacy  # type: ignore
 
-from .fixtures import nlp_da, nlp_en  # noqa
+from .fixtures import nlp_da, nlp_en
 
 
 def test_create_random_casing_augmenter(nlp_en):  # noqa F811

tests/test_doc.py

@@ -1,8 +1,7 @@
-from spacy.tokens import Span
-
 import augmenty
+from spacy.tokens import Span
 
-from .fixtures import nlp_en  # noqa
+from .fixtures import nlp_en
 
 
 def test_create_spongebob_augmenter(nlp_en):  # noqa F811
@@ -39,7 +38,7 @@ def test_paragraph_subset_augmenter(nlp_en):  # noqa F811
     )
 
     for t in doc:
-        t.is_sent_start = True if t.text == "." else False
+        t.is_sent_start = True if t.text == "." else False  # noqa
 
     p_subset_aug = augmenty.load(
         "paragraph_subset_augmenter_v1",

tests/test_issue_170.py

@@ -3,22 +3,22 @@
 https://github.com/KennethEnevoldsen/augmenty/issues/170.
 """
 
+import augmenty
 import pytest
 import spacy
+from spacy.language import Language
 from spacy.tokens import Doc, Span
 
-import augmenty
-
 
-@pytest.fixture
-def nlp():
+@pytest.fixture()
+def nlp() -> Language:
     nlp_ = spacy.blank("en")
     nlp_.add_pipe("sentencizer")
     return nlp_
 
 
-@pytest.fixture
-def example_doc(nlp) -> Doc:
+@pytest.fixture()
+def example_doc(nlp: Language) -> Doc:
     text = "Joc Pederson and Thairo Estrada (concussion protocol) are each progressing. SS Brandon Crawford"
     doc = nlp(text)
     doc.ents = [
@@ -55,7 +55,7 @@ def example_doc(nlp) -> Doc:
     return doc
 
 
-def test_entity_with_no_dep(nlp, example_doc: Doc):
+def test_entity_with_no_dep(nlp: Language, example_doc: Doc):
     level = 1.0
     docs = [example_doc]
     augmenter = augmenty.load(
@@ -65,7 +65,7 @@ def test_entity_with_no_dep(nlp, example_doc: Doc):
         replace_consistency=True,
         resolve_dependencies=True,
     )
-    aug_doc = list(augmenty.docs(docs, augmenter, nlp))[0]
+    aug_doc = list(augmenty.docs(docs, augmenter, nlp))[0]  # noqa
     assert len(aug_doc.ents) == len(docs[0].ents)
     assert (
         aug_doc.text

tests/test_spans.py

@@ -1,15 +1,14 @@
 from typing import Callable
 
+import augmenty
 import pytest
 from spacy.language import Language
 from spacy.tokens import Doc
 
-import augmenty
-
-from .fixtures import nlp_en, nlp_en_md  # noqa
+from .fixtures import nlp_en, nlp_en_md
 
 
-@pytest.fixture
+@pytest.fixture()
 def doc(nlp_en: Language) -> Doc:  # noqa
     doc = Doc(
         nlp_en.vocab,
@@ -29,8 +28,8 @@ def doc(nlp_en: Language) -> Doc:  # noqa
     return doc
 
 
-@pytest.fixture
-def ent_augmenter():
+@pytest.fixture()
+def ent_augmenter() -> Callable:
     ent_augmenter = augmenty.load(
         "ents_replace_v1",  # type: ignore
         level=1.00,

tests/test_static_embedding.py

@@ -1,6 +1,6 @@
 from augmenty.token.static_embedding_util import static_embedding
 
-from .fixtures import nlp_en_md  # noqa
+from .fixtures import nlp_en_md
 
 
 def test_static_embedding_util(nlp_en_md):  # noqa F811

tests/test_token.py

@@ -1,11 +1,10 @@
-import spacy  # type: ignore
-from spacy.tokens import Doc  # type: ignore
-
 import augmenty
+import spacy  # type: ignore
 from augmenty.token.insert import create_token_insert_random_augmenter_v1
+from spacy.tokens import Doc  # type: ignore
 
 from .books import BOOKS
-from .fixtures import nlp_da, nlp_en, nlp_en_md  # noqa
+from .fixtures import nlp_da, nlp_en, nlp_en_md
 
 
 def test_create_starting_case_augmenter(nlp_en):  # noqa F811
@@ -30,7 +29,7 @@ def test_create_conditional_token_casing_augmenter(nlp_en):  # noqa F811
 
     doc = Doc(nlp_en.vocab, words=tokens, pos=pos, spaces=spaces)
 
-    def conditional(token):
+    def conditional(token):  # noqa
         if token.pos_ == "PRON":
             return True
         return False
@@ -181,7 +180,7 @@ def test_create_token_insert_augmenter(nlp_en):  # noqa F811
     words = ["cat"]
     spaces = [False]
     doc = Doc(nlp_en.vocab, words=words, spaces=spaces, pos=["NOUN"])
-    insert_fun = lambda t: {"ORTH": "word"}  # noqa: E731
+    insert_fun = lambda: {"ORTH": "word"}  # noqa: E731
     aug = augmenty.load("token_insert_v1", level=1, insert=insert_fun)
     docs = list(augmenty.docs([doc], augmenter=aug, nlp=nlp_en))
     assert len(docs[0]) == 2