refactor: use ruff

ruff replaces `black`, `isort` & `pylint` for formatting & linting.
Note that `isort` is still used to sort imports when exporting to notebook since ruff
does not provide a Python API.

.github/workflows/test.yaml

@@ -45,9 +45,8 @@ jobs:
           poetry run python -m pytest -n auto --disable-warnings --cov=edvart tests/
       - name: Lint
         run: |
-          poetry run pylint --rcfile=.pylintrc edvart/
-          poetry run black --check --line-length 100 edvart/ tests/
-          poetry run isort --check --line-length 100 --profile black edvart/ tests/
+          poetry run ruff check .
+          poetry run ruff format --check .
 
   dismiss-stale-reviews:
     runs-on: ubuntu-22.04

docs/conf.py

@@ -14,28 +14,27 @@
 #
 import os
 import sys
-import re
 from datetime import datetime
 from pathlib import Path
 
-sys.path.insert(0, os.path.abspath('.'))
-sys.path.insert(0, os.path.abspath('../'))
+import toml  # make sure that toml is a developer dependency
 
-# -- Project information -----------------------------------------------------
+sys.path.insert(0, os.path.abspath("."))
+sys.path.insert(0, os.path.abspath("../"))
 
-project = 'edvart'
-copyright = f'{datetime.now().year}, Datamole'
-author = 'Hellen team'
+# -- Project information -----------------------------------------------------
 
+project = "edvart"
+copyright = f"{datetime.now().year}, Datamole"
+author = "Hellen team"
 
-import toml  # make sure that toml is a developer dependency
 
 metadata = toml.load(Path(__file__).parent.parent / "pyproject.toml")["tool"]["poetry"]
 version = release = metadata["version"]
 
 version_long = version
 # The short X.Y.Z version
-version = '.'.join(version_long.split('.')[0:3])
+version = ".".join(version_long.split(".")[0:3])
 # The full version, including alpha/beta/rc tags
 release = version_long
 
@@ -51,29 +50,29 @@
 # extensions coming with Sphinx (named 'sphinx.ext.*') or your custom
 # ones.
 extensions = [
-    'sphinx.ext.autodoc',
-    'sphinx.ext.intersphinx',
-    'sphinx.ext.mathjax',
-    'sphinx.ext.viewcode',
-    'sphinx.ext.napoleon',
-    'sphinx_copybutton',
+    "sphinx.ext.autodoc",
+    "sphinx.ext.intersphinx",
+    "sphinx.ext.mathjax",
+    "sphinx.ext.viewcode",
+    "sphinx.ext.napoleon",
+    "sphinx_copybutton",
 ]
 
 # napoleon_google_docstring = False
 # napoleon_use_param = False
 # napoleon_use_ivar = True
 
 # Add any paths that contain templates here, relative to this directory.
-templates_path = ['_templates']
+templates_path = ["_templates"]
 
 # The suffix(es) of source filenames.
 # You can specify multiple suffix as a list of string:
 #
 # source_suffix = ['.rst', '.md']
-source_suffix = '.rst'
+source_suffix = ".rst"
 
 # The master toctree document.
-master_doc = 'index'
+master_doc = "index"
 
 # The language for content autogenerated by Sphinx. Refer to documentation
 # for a list of supported languages.
@@ -85,20 +84,20 @@
 # List of patterns, relative to source directory, that match files and
 # directories to ignore when looking for source files.
 # This pattern also affects html_static_path and html_extra_path .
-exclude_patterns = ['_build', 'Thumbs.db', '.DS_Store']
+exclude_patterns = ["_build", "Thumbs.db", ".DS_Store"]
 
 # The name of the Pygments (syntax highlighting) style to use.
-pygments_style = 'sphinx'
+pygments_style = "sphinx"
 
 
 # -- Options for HTML output -------------------------------------------------
 
 # The theme to use for HTML and HTML Help pages.  See the documentation for
 # a list of builtin themes.
 #
-#html_theme = 'alabaster'
-#html_theme = 'sphinx_rtd_theme'
-html_theme = 'sphinx_rtd_theme'
+# html_theme = 'alabaster'
+# html_theme = 'sphinx_rtd_theme'
+html_theme = "sphinx_rtd_theme"
 
 # Theme options are theme-specific and customize the look and feel of a theme
 # further.  For a list of options available for each theme, see the
@@ -109,7 +108,7 @@
 # Add any paths that contain custom static files (such as style sheets) here,
 # relative to this directory. They are copied after the builtin static files,
 # so a file named "default.css" will overwrite the builtin "default.css".
-html_static_path = ['_static']
+html_static_path = ["_static"]
 
 # Custom sidebar templates, must be a dictionary that maps document names
 # to template names.
@@ -125,7 +124,7 @@
 # -- Options for HTMLHelp output ---------------------------------------------
 
 # Output file base name for HTML help builder.
-htmlhelp_basename = 'edvartdoc'
+htmlhelp_basename = "edvartdoc"
 
 
 # -- Options for LaTeX output ------------------------------------------------
@@ -134,15 +133,12 @@
     # The paper size ('letterpaper' or 'a4paper').
     #
     # 'papersize': 'letterpaper',
-
     # The font size ('10pt', '11pt' or '12pt').
     #
     # 'pointsize': '10pt',
-
     # Additional stuff for the LaTeX preamble.
     #
     # 'preamble': '',
-
     # Latex figure (float) alignment
     #
     # 'figure_align': 'htbp',
@@ -152,19 +148,21 @@
 # (source start file, target name, title,
 #  author, documentclass [howto, manual, or own class]).
 latex_documents = [
-    (master_doc, 'edvart.tex', 'edvart Documentation',
-     'Your name (or your organization/company/team)', 'manual'),
+    (
+        master_doc,
+        "edvart.tex",
+        "edvart Documentation",
+        "Your name (or your organization/company/team)",
+        "manual",
+    ),
 ]
 
 
 # -- Options for manual page output ------------------------------------------
 
 # One entry per manual page. List of tuples
 # (source start file, name, description, authors, manual section).
-man_pages = [
-    (master_doc, 'edvart', 'edvart Documentation',
-     [author], 1)
-]
+man_pages = [(master_doc, "edvart", "edvart Documentation", [author], 1)]
 
 
 # -- Options for Texinfo output ----------------------------------------------
@@ -173,9 +171,15 @@
 # (source start file, target name, title, author,
 #  dir menu entry, description, category)
 texinfo_documents = [
-    (master_doc, 'edvart', 'edvart Documentation',
-     author, 'edvart', 'One line description of project.',
-     'Miscellaneous'),
+    (
+        master_doc,
+        "edvart",
+        "edvart Documentation",
+        author,
+        "edvart",
+        "One line description of project.",
+        "Miscellaneous",
+    ),
 ]
 
 
@@ -184,4 +188,4 @@
 # -- Options for intersphinx extension ---------------------------------------
 
 # Example configuration for intersphinx: refer to the Python standard library.
-intersphinx_mapping = {'https://docs.python.org/': None}
+intersphinx_mapping = {"https://docs.python.org/": None}

edvart/data_types.py

@@ -5,7 +5,7 @@
 import pandas as pd
 
 try:
-    import pyarrow  # pylint: disable=unused-import
+    import pyarrow  # noqa: F401
 except ImportError:
     PYARROW_PANDAS_BACKEND_AVAILABLE = False
 else:

edvart/report_sections/bivariate_analysis.py

@@ -986,8 +986,7 @@ def contingency_table(
         n_digits_max = 1 + np.floor(np.log10(table.max().max()))
         size_factor = (
             # Constants chosen empirically to make the numbers fit in the cells
-            0.18
-            * max(4, n_digits_max)
+            0.18 * max(4, n_digits_max)
         )
     ax.figure.set_size_inches(size_factor * len(table.columns), size_factor * len(table))
     # Set y axis

edvart/report_sections/code_string_formatting.py

@@ -18,7 +18,7 @@ def total_dedent(input_string: str) -> str:
         input_string with no whitespace at the beginning of each line.
     """
     input_string = input_string.strip()
-    lstripped_lines = [l.strip() for l in input_string.split("\n")]
+    lstripped_lines = [line.strip() for line in input_string.split("\n")]
     return "\n".join(lstripped_lines)
 
 
@@ -53,7 +53,7 @@ def dedecorate(input_string: str) -> str:
         input_string with beginning lines starting with '@' removed.
     """
     lines = input_string.splitlines()
-    filtered_lines = dropwhile(lambda l: l.lstrip().startswith("@"), lines)
+    filtered_lines = dropwhile(lambda line_: line_.lstrip().startswith("@"), lines)
 
     return "\n".join(filtered_lines)
 

edvart/report_sections/timeseries_analysis/short_time_ft.py

@@ -128,7 +128,7 @@ def show_short_time_ft(
     columns: Optional[List[str]] = None,
     overlap: Optional[int] = None,
     log: bool = True,
-    window: Union[str, Tuple, "array-like"] = "hamming",
+    window: Union[str, Tuple, np.typing.ArrayLike] = "hamming",
     scaling: str = "spectrum",
     figsize: Tuple[float, float] = (20, 7),
     colormap: Any = "viridis",

edvart/report_sections/timeseries_analysis/stationarity_tests.py

@@ -1,6 +1,6 @@
 import warnings
 from functools import partial
-from typing import Any, Callable, Dict, List, Optional
+from typing import Any, Callable, Dict, List, Optional, Tuple
 
 import nbformat.v4 as nbfv4
 import pandas as pd
@@ -96,7 +96,7 @@ def show(self, df: pd.DataFrame) -> None:
         show_stationarity_tests(df=df, columns=self.columns)
 
 
-def default_stationarity_tests() -> Dict[pd.Series, Callable[[pd.Series], "test_result"]]:
+def default_stationarity_tests() -> Dict[str, Callable[[pd.Series], Tuple]]:
     """Return a dictionary of stationarity test and functions.
 
     Stationarity tests are:

edvart/report_sections/timeseries_analysis/timeseries_analysis.py

@@ -144,9 +144,9 @@ def __init__(
         }
         # Add FT and STFT only if required parameters specified
         if sampling_rate is not None:
-            enum_to_implementation[
-                TimeseriesAnalysisSubsection.FourierTransform
-            ] = FourierTransform(sampling_rate, verbosity_fourier_transform, columns)
+            enum_to_implementation[TimeseriesAnalysisSubsection.FourierTransform] = (
+                FourierTransform(sampling_rate, verbosity_fourier_transform, columns)
+            )
             if stft_window_size is not None:
                 enum_to_implementation[TimeseriesAnalysisSubsection.ShortTimeFT] = ShortTimeFT(
                     sampling_rate, stft_window_size, verbosity_short_time_ft, columns

pyproject.toml

@@ -48,11 +48,30 @@ sphinx = "~7.1"
 sphinx-rtd-theme = "~1.3.0"
 toml = "^0.10.0"
 jupyter = "*"
-black = "^22.3.0"
-pylint = "~3.1"
 sphinx-copybutton = "^0.5.2"
 pytest-xdist = "^3.3.1"
+ruff = "^0.3.0"
 
 [build-system]
 requires = ["poetry_core>=1.0.0"]
 build-backend = "poetry.core.masonry.api"
+
+[tool.ruff]
+line-length = 100
+target-version = "py310"
+src = ["task"]
+
+[tool.ruff.lint]
+select = [
+    "E",
+    "F",
+    "N",
+    "W",
+    "I001",
+]
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["E402", "F401"]
+
+[tool.ruff.lint.isort]
+known-first-party = ["edvart"]

tests/test_multivariate_analysis.py

@@ -6,8 +6,6 @@
 import plotly.io as pio
 import pytest
 
-pio.renderers.default = "json"
-
 from edvart import utils
 from edvart.report_sections import multivariate_analysis
 from edvart.report_sections.code_string_formatting import code_dedent, get_code
@@ -25,6 +23,8 @@
 from .execution_utils import check_section_executes
 from .pyarrow_utils import pyarrow_parameterize
 
+pio.renderers.default = "json"
+
 
 def get_test_df(pyarrow_dtypes: bool = False) -> pd.DataFrame:
     test_df = pd.DataFrame(

tests/test_timeseries_analysis.py

@@ -168,18 +168,18 @@ def test_ft_stft_included():
 
 def test_ft_no_sampling_rate_error():
     with pytest.raises(ValueError):
-        ts = TimeseriesAnalysis(subsections=[TimeseriesAnalysisSubsection.FourierTransform])
+        _ts = TimeseriesAnalysis(subsections=[TimeseriesAnalysisSubsection.FourierTransform])
     with pytest.raises(ValueError):
-        ts = TimeseriesAnalysis(
+        _ts = TimeseriesAnalysis(
             subsections=[TimeseriesAnalysisSubsection.FourierTransform],
             stft_window_size=2,
         )
     with pytest.raises(ValueError):
-        ts = TimeseriesAnalysis(
+        _ts = TimeseriesAnalysis(
             subsections=[TimeseriesAnalysisSubsection.ShortTimeFT],
         )
     with pytest.raises(ValueError):
-        ts = TimeseriesAnalysis(
+        _ts = TimeseriesAnalysis(
             subsections=[TimeseriesAnalysisSubsection.ShortTimeFT],
             sampling_rate=1,
         )
@@ -424,7 +424,7 @@ def month_func(x: datetime) -> str:
 
 
 def test_boxplots_over_time_lambda():
-    month_lambda = lambda x: x.month
+    month_lambda = lambda x: x.month  # noqa: E731
 
     boxplots_sub = BoxplotsOverTime(grouping_name="Month", grouping_function=month_lambda)
 
@@ -451,7 +451,7 @@ def test_imports_verbosity_low():
 
     exported_imports = ts_section.required_imports()
     expected_imports = [
-        "from edvart.report_sections.timeseries_analysis.timeseries_analysis import show_timeseries_analysis"
+        "from edvart.report_sections.timeseries_analysis.timeseries_analysis import show_timeseries_analysis"  # noqa: E501
     ]
 
     assert isinstance(exported_imports, list)
@@ -504,8 +504,8 @@ def test_imports_verbosity_low_different_subsection_verbosities():
     exported_imports = ts_section.required_imports()
 
     expected_imports = {
-        "from edvart.report_sections.timeseries_analysis.timeseries_analysis import show_timeseries_analysis",
-        "from edvart.report_sections.timeseries_analysis.timeseries_analysis import TimeseriesAnalysisSubsection",
+        "from edvart.report_sections.timeseries_analysis.timeseries_analysis import show_timeseries_analysis",  # noqa: E501
+        "from edvart.report_sections.timeseries_analysis.timeseries_analysis import TimeseriesAnalysisSubsection",  # noqa: E501
     }
     for s in ts_section.subsections:
         if s.verbosity > Verbosity.LOW: