ci: updated ruf

docs/tutorials/filter_corpus_using_quality.ipynb

@@ -73,7 +73,9 @@
     "from datasets import load_dataset\n",
     "\n",
     "# stream in the dataset\n",
-    "dataset = load_dataset(\"mc4\", \"en\", streaming=True, split=\"train\", trust_remote_code=True)\n",
+    "dataset = load_dataset(\n",
+    "    \"mc4\", \"en\", streaming=True, split=\"train\", trust_remote_code=True\n",
+    ")\n",
     "\n",
     "# download the first 1 000\n",
     "dataset = dataset.take(1000)\n",

docs/tutorials/sklearn_integration.ipynb

@@ -128,6 +128,7 @@
    ],
    "source": [
     "from textdescriptives.utils import load_sms_data\n",
+    "\n",
     "df = load_sms_data()\n",
     "df.head()"
    ]
@@ -152,7 +153,7 @@
     "# to textdescriptives.extract_metrics\n",
     "descriptive_stats_extractor = TextDescriptivesFeaturizer(\n",
     "    lang=\"en\", metrics=[\"descriptive_stats\"]\n",
-    "    )"
+    ")"
    ]
   },
   {
@@ -184,7 +185,7 @@
     "from sklearn.pipeline import Pipeline\n",
     "from sklearn.ensemble import RandomForestClassifier\n",
     "from sklearn.compose import ColumnTransformer\n",
-    "from sklearn.model_selection import train_test_split \n",
+    "from sklearn.model_selection import train_test_split\n",
     "from sklearn.impute import SimpleImputer\n",
     "from sklearn import set_config\n",
     "\n",
@@ -197,10 +198,9 @@
     "        (\n",
     "            \"featurizer\",\n",
     "            ColumnTransformer(\n",
-    "                [(\"text_processing\", descriptive_stats_extractor, \"message\")]\n",
-    "            ,\n",
-    "            # removes the `text_processing__` prefix from feature names\n",
-    "            verbose_feature_names_out=False, \n",
+    "                [(\"text_processing\", descriptive_stats_extractor, \"message\")],\n",
+    "                # removes the `text_processing__` prefix from feature names\n",
+    "                verbose_feature_names_out=False,\n",
     "            ),\n",
     "        ),\n",
     "        (\"imputer\", SimpleImputer(strategy=\"median\")),\n",
@@ -366,6 +366,7 @@
    ],
    "source": [
     "import pandas as pd\n",
+    "\n",
     "# extract feature importances\n",
     "feature_importance_mapping = list(\n",
     "    zip(\n",

pyproject.toml

@@ -34,7 +34,7 @@ keywords = [
 
 dependencies = [
     "spacy[lookups]>=3.6.0",
-    "numpy>=1.20.0,<2.0.0",  # due to https://stackoverflow.com/questions/78634235/numpy-dtype-size-changed-may-indicate-binary-incompatibility-expected-96-from
+    "numpy>=1.20.0,<2.0.0", # due to https://stackoverflow.com/questions/78634235/numpy-dtype-size-changed-may-indicate-binary-incompatibility-expected-96-from
     "pandas>=1.0.0",
     "pyphen>=0.11.0",
     "ftfy>=6.0.3",
@@ -49,7 +49,7 @@ repository = "https://github.com/HLasse/textdescriptives"
 documentation = "https://hlasse.github.io/TextDescriptives/"
 
 [project.optional-dependencies]
-style = ["ruff==0.1.15"]
+style = ["ruff==0.8.3"]
 tests = ["pytest>=7.1.3", "pytest-cov>=3.0.0", "pytest-xdist"]
 docs = [
     "pydantic==2.1",

src/textdescriptives/about.py

@@ -1,4 +1,4 @@
-""" About textdescriptives, version number is specified in the setup.cfg
+"""About textdescriptives, version number is specified in the setup.cfg
 file."""
 
 # if python >= 3.8, use importlib.metadata otherwise use pkg_resources

src/textdescriptives/components/dependency_distance.py

@@ -1,4 +1,4 @@
-""" Calculation of statistics related to dependency distance."""
+"""Calculation of statistics related to dependency distance."""
 
 from typing import Callable
 

src/textdescriptives/components/descriptive_stats.py

@@ -1,4 +1,4 @@
-""" Calculation of descriptive statistics."""
+"""Calculation of descriptive statistics."""
 
 from typing import Callable, Dict, Union
 

src/textdescriptives/components/information_theory.py

@@ -1,4 +1,4 @@
-""" Calculate the entropy and perplexity of a corpus."""
+"""Calculate the entropy and perplexity of a corpus."""
 
 from typing import Callable, Dict, Union
 

src/textdescriptives/components/pos_proportions.py

@@ -1,4 +1,4 @@
-""" Calculation of statistics that require a pos-tagger in the pipeline."""
+"""Calculation of statistics that require a pos-tagger in the pipeline."""
 
 from typing import Callable, Counter, List, Union
 

src/textdescriptives/components/quality.py

@@ -1,4 +1,4 @@
-""" Component for calculating quality metrics."""
+"""Component for calculating quality metrics."""
 
 from collections import Counter, defaultdict
 from typing import Callable, Dict, List, Mapping, Optional, Tuple, Union

src/textdescriptives/components/quality_data_classes.py

@@ -1,4 +1,4 @@
-""" Data classes used for the quality component."""
+"""Data classes used for the quality component."""
 
 from typing import Any, Dict, Optional, Tuple, Union
 

src/textdescriptives/components/readability.py

@@ -1,4 +1,4 @@
-""" Calculation of various readability metrics."""
+"""Calculation of various readability metrics."""
 
 from typing import Callable, Dict
 

src/textdescriptives/components/utils.py

@@ -1,4 +1,4 @@
-""" Utility functions for calculating various text descriptives."""
+"""Utility functions for calculating various text descriptives."""
 
 from typing import Union
 

src/textdescriptives/extractors.py

@@ -1,4 +1,4 @@
-""" Extract metrics as Pandas DataFrame."""
+"""Extract metrics as Pandas DataFrame."""
 
 from typing import Any, Dict, Iterable, List, Optional, Union
 

src/textdescriptives/load_components.py

@@ -1,4 +1,4 @@
-""" Adds all components to a spaCy pipeline."""
+"""Adds all components to a spaCy pipeline."""
 
 from spacy.language import Language
 from spacy.tokens import Doc

tests/books.py

@@ -1,5 +1,6 @@
-""" These books and several tests are borrowed from
+"""These books and several tests are borrowed from
 https://github.com/mholtzscher/spacy_readability."""
+
 from __future__ import annotations
 
 oliver_twist = """Among other public buildings in a certain town, which for many reasons

tests/test_coherence.py

@@ -5,6 +5,7 @@
 import numpy as np
 import pytest
 import spacy
+
 import textdescriptives as td  # noqa: F401
 
 

tests/test_dependency_distance.py

@@ -4,6 +4,7 @@
 import numpy as np
 import pytest
 import spacy
+
 import textdescriptives as td  # noqa: F401
 
 from .books import flatland, oliver_twist, secret_garden

tests/test_descriptive_stats.py

@@ -5,6 +5,7 @@
 import ftfy
 import pytest
 from spacy.lang.en import English
+
 from textdescriptives.components import DescriptiveStatistics  # noqa: F401
 
 from .books import flatland, oliver_twist, secret_garden

tests/test_extractors.py

@@ -2,6 +2,7 @@
 
 import pytest
 import spacy
+
 import textdescriptives as td
 from textdescriptives.utils import _create_spacy_pipeline, _download_spacy_model
 

tests/test_information.py

@@ -3,6 +3,7 @@
 import numpy as np
 import pytest
 import spacy
+
 import textdescriptives as td
 from textdescriptives.components.information_theory import (
     entropy_getter,

tests/test_load_components.py

@@ -2,6 +2,7 @@
 
 import pytest
 import spacy
+
 import textdescriptives as td  # noqa: F401
 
 

tests/test_pos_proportions.py

@@ -2,9 +2,10 @@
 
 import pytest
 import spacy
-import textdescriptives as td  # noqa: F401
 from spacy.tokens import Doc
 
+import textdescriptives as td  # noqa: F401
+
 
 @pytest.fixture(scope="function")
 def nlp():

tests/test_quality.py

@@ -1,8 +1,10 @@
-""" Tests for the quality module."""
+"""Tests for the quality module."""
+
 from __future__ import annotations
 
 import pytest
 import spacy
+
 import textdescriptives as td
 from textdescriptives.components.quality import (
     alpha_ratio,

tests/test_readability.py

@@ -7,6 +7,7 @@
 import pytest
 import spacy
 from spacy.lang.en import English
+
 from textdescriptives.utils import _remove_textdescriptives_extensions  # noqa: F401
 
 from .books import (