[MAINT]: Add support for ruff linter (#231)

* update: add ruff config in pyproject.toml

* chore: remove isort and flake8 configs and envs from tox.ini

* chore: add ruff badge in README

* update: expand target-version for black and cosmetic chages in pyproject.toml

* update: use ruff in lint.yml

* chore: ruff autofixes

* chore: fix ruff N803 issues

* chore: fix ruff C901 issues

* chore: add missing module, function, class and method docstrings

* chore: further ruff fixes and improve typing and docstrings

* chore: ruff F401 checks

* chore: sort imports via ruff

* fix: typo

* chore: add entries in nitpick_ignore_regex in conf.py to build docs

* chore: add changelog 231.misc

* chore: remove unnecessary commands from tox.ini

* fix: E721 issue in test_confounds.py

* Fix codespell

* Add joblib to intersphinx

* Fix some sklearn ignores

* chore: update lint.yml to fix ruff config

* remove this file

---------

Co-authored-by: Fede <[email protected]>
Co-authored-by: Fede Raimondo <[email protected]>

.github/workflows/lint.yml

@@ -6,26 +6,18 @@ on:
 
 jobs:
   lint:
-    runs-on: ${{ matrix.os }}
-    strategy:
-      fail-fast: false
-      matrix:
-        os: [ubuntu-latest]
-        python-version: ['3.11']
-
+    runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - name: Set up Python ${{ matrix.python-version }}
+      - name: Install Python
         uses: actions/setup-python@v4
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: "3.11"
       - name: Install dependencies
         run: |
-          python -m pip install --upgrade pip setuptools wheel
-          python -m pip install tox tox-gh-actions
-      - name: Check with flake8
-        run: |
-          tox -e flake8
-      - name: Check with codespell
-        run: |
-          tox -e codespell
+          python -m pip install --upgrade pip
+          python -m pip install tox "ruff>=0.1.0"
+      - name: Run ruff
+        run: ruff check --output-format=github .
+      - name: Run codespell
+        run: tox -e codespell

.gitignore

@@ -73,6 +73,7 @@ docs/_build/
 docs/auto_examples
 docs/**/generated
 docs/make.bat
+docs/sg_execution_times.rst
 
 # PyBuilder
 .pybuilder/

README.md

@@ -5,6 +5,7 @@
 ![PyPI - Wheel](https://img.shields.io/pypi/wheel/julearn?style=flat-square)
 ![GitHub](https://img.shields.io/github/license/juaml/julearn?style=flat-square)
 ![Codecov](https://img.shields.io/codecov/c/github/juaml/julearn?style=flat-square)
+[![Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/charliermarsh/ruff)
 [![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)
 
 ## About

docs/changes/newsfragments/231.misc

@@ -0,0 +1 @@
+Adopt ``ruff`` as the only linter for the codebase by `Synchon Mandal`_

docs/conf.py

@@ -5,20 +5,18 @@
 # https://www.sphinx-doc.org/en/master/usage/configuration.html
 import os
 import re
-from sphinx_gallery.sorting import ExplicitOrder
+import sys
 
 # -- Path setup --------------------------------------------------------------
-
 # If extensions (or modules to document with autodoc) are in another directory,
 # add these directories to sys.path here. If the directory is relative to the
 # documentation root, use os.path.abspath to make it absolute, like shown here.
 #
 # import os
 # import sys
 # sys.path.insert(0, os.path.abspath('.'))
-
 from pathlib import Path
-import sys
+
 
 # Check if sphinx-multiversion is installed
 use_multiversion = False
@@ -87,6 +85,7 @@
     # Sklearn doc issue to be solved in next release
     ("py:class", "pipeline.Pipeline"),
     ("py:class", "sklearn.utils.metadata_routing.MetadataRequest"),
+    ("py:class", "julearn.inspect._pipeline.PipelineInspector"),
 ]
 
 
@@ -157,9 +156,9 @@
     "nilearn": ("https://nilearn.github.io/stable/", None),
     "nibabel": ("https://nipy.org/nibabel/", None),
     "numpy": ("https://numpy.org/doc/stable/", None),
-    "numpy": ("https://numpy.org/doc/stable/", None),
     "pandas": ("https://pandas.pydata.org/pandas-docs/dev", None),
     # "sqlalchemy": ("https://docs.sqlalchemy.org/en/20/", None),
+    "joblib": ("https://joblib.readthedocs.io/en/latest/", None),
     "scipy": ("https://docs.scipy.org/doc/scipy/", None),
 }
 
@@ -219,7 +218,7 @@ def __init__(self, src_dir):
         self.regex = re.compile(r"^([\w ]+)\n-", re.MULTILINE)
 
     def __repr__(self):
-        return "<%s>" % (self.__class__.__name__,)
+        return f"<{self.__class__.__name__}>"
 
     def __call__(self, directory):
         src_path = os.path.normpath(os.path.join(self.src_dir, directory))
@@ -231,7 +230,7 @@ def __call__(self, directory):
         readme = os.path.join(src_path, "README.txt")
 
         try:
-            with open(readme, "r") as f:
+            with open(readme) as f:
                 content = f.read()
         except FileNotFoundError:
             return directory

docs/contributing.rst

@@ -165,7 +165,7 @@ Writing Examples
 The format used for text is reST. Check the `sphinx RST reference`_ for more
 details. The examples are run and displayed in HTML format using
 `sphinx gallery`_. To add an example, just create a ``.py`` file that starts
-either with ``plot_`` or ``run_``, dependending on whether the example generates
+either with ``plot_`` or ``run_``, depending on whether the example generates
 a figure or not.
 
 The first lines of the example should be a Python block comment with a title,

docs/sphinxext/gh_substitutions.py

@@ -1,8 +1,8 @@
-# -*- coding: utf-8 -*-
 
 from docutils.nodes import reference
 from docutils.parsers.rst.roles import set_classes
 
+
 # Taken from MNE-Python
 # adapted from
 # https://doughellmann.com/blog/2010/05/09/defining-custom-roles-in-sphinx/

examples/04_confounds/plot_confound_removal_classification.py

@@ -151,7 +151,7 @@
 ###############################################################################
 # While this plot allows us to see the mean performance values and compare
 # them, these samples are paired. In order to see if there is a systematic
-# difference, we need to check the distribution of differeces between the
+# difference, we need to check the distribution of differences between the
 # the models.
 #
 # First, we remove the column "confounds" from the index and make the difference

ignore_words.txt

@@ -5,3 +5,4 @@ fpr
 master
 whis
 jupyter
+arange

julearn/api.py

@@ -4,8 +4,7 @@
 #          Sami Hamdan <[email protected]>
 # License: AGPL
 
-from typing import List, Optional, Union, Dict
-
+from typing import Dict, List, Optional, Union
 
 import numpy as np
 import pandas as pd
@@ -14,26 +13,26 @@
 from sklearn.model_selection._search import BaseSearchCV
 from sklearn.pipeline import Pipeline
 
+from .inspect import Inspector
 from .pipeline import PipelineCreator
 from .pipeline.merger import merge_pipelines
 from .prepare import check_consistency, prepare_input_data
 from .scoring import check_scoring
-from .utils import logger, raise_error, _compute_cvmdsum
-from .inspect import Inspector
+from .utils import _compute_cvmdsum, logger, raise_error
 
 
-def run_cross_validation(
-    X: List[str],
+def run_cross_validation(  # noqa: C901
+    X: List[str],  # noqa: N803
     y: str,
     model: Union[str, PipelineCreator, BaseEstimator, List[PipelineCreator]],
-    X_types: Optional[Dict] = None,
+    X_types: Optional[Dict] = None,  # noqa: N803
     data: Optional[pd.DataFrame] = None,
     problem_type: Optional[str] = None,
     preprocess: Union[None, str, List[str]] = None,
     return_estimator: Optional[str] = None,
     return_inspector: bool = False,
     return_train_score: bool = False,
-    cv: Union[None, int] = None,
+    cv: Optional[int] = None,
     groups: Optional[str] = None,
     scoring: Union[str, List[str], None] = None,
     pos_labels: Union[str, List[str], None] = None,
@@ -47,10 +46,10 @@ def run_cross_validation(
 
     Parameters
     ----------
-    X : str, list(str) or numpy.array
+    X : list of str
         The features to use.
         See :ref:`data_usage` for details.
-    y : str or numpy.array
+    y : str
         The targets to predict.
         See :ref:`data_usage` for details.
     model : str or scikit-learn compatible model.
@@ -106,7 +105,7 @@ def run_cross_validation(
         * CV Splitter (see scikit-learn documentation on CV)
         * An iterable yielding (train, test) splits as arrays of indices.
 
-    groups : str or numpy.array | None
+    groups : str | None
         The grouping labels in case a Group CV is used.
         See :ref:`data_usage` for details.
     scoring : ScorerLike, optional
@@ -145,11 +144,16 @@ def run_cross_validation(
     seed : int | None
         If not None, set the random seed before any operation. Useful for
         reproducibility.
+    n_jobs : int, optional
+        Number of jobs to run in parallel. Training the estimator and computing
+        the score are parallelized over the cross-validation splits.
+        ``None`` means 1 unless in a :obj:`joblib.parallel_backend` context.
+        ``-1`` means using all processors (default None).
     verbose: int
         Verbosity level of outer cross-validation.
         Follows scikit-learn/joblib converntions.
         0 means no additional information is printed.
-        Larger number genereally mean more information is printed.
+        Larger number generally mean more information is printed.
         Note: verbosity up to 50 will print into standard error,
         while larger than 50 will print in standrad output.
 
@@ -237,7 +241,7 @@ def run_cross_validation(
         else:
             model = [model]
 
-        problem_types = set([m.problem_type for m in model])
+        problem_types = {m.problem_type for m in model}
         if len(problem_types) > 1:
             raise_error(
                 "If model is a list of PipelineCreator, all elements must have"
@@ -345,9 +349,7 @@ def run_cross_validation(
     check_consistency(y, cv, groups, problem_type)
 
     cv_return_estimator = return_estimator in ["cv", "all"]
-    scoring = check_scoring(pipeline, scoring,
-                            wrap_score=wrap_score
-                            )
+    scoring = check_scoring(pipeline, scoring, wrap_score=wrap_score)
 
     cv_mdsum = _compute_cvmdsum(cv_outer)
     fit_params = {}

julearn/base/column_types.py

@@ -48,7 +48,7 @@ def get_column_type(column):
     return column.split("__:type:__")[1]
 
 
-def get_renamer(X_df):
+def get_renamer(X_df):  # noqa: N803
     """Get the dictionary that will rename the columns to add the type.
 
     Parameters
@@ -68,26 +68,28 @@ def get_renamer(X_df):
     }
 
 
-class make_type_selector(object):
-    def __init__(self, pattern):
-        """Make a type selector.
+class make_type_selector:
+    """Make a type selector.
 
-        This type selector is to be used with
-        :class:`sklearn.compose.ColumnTransformer`
+    This type selector is to be used with
+    :class:`sklearn.compose.ColumnTransformer`
 
-        Parameters
-        ----------
-        pattern : str
-            The pattern to select the columns.
+    Parameters
+    ----------
+    pattern : str
+        The pattern to select the columns.
 
-        Returns
-        -------
-        function
-            The type selector.
-        """
+    Returns
+    -------
+    function
+        The type selector.
+
+    """
+
+    def __init__(self, pattern):
         self.pattern = pattern
 
-    def __call__(self, X_df):
+    def __call__(self, X_df):  # noqa: N803
         """Select the columns based on the pattern.
 
         Parameters
@@ -137,7 +139,7 @@ def __init__(self, column_types: ColumnTypesLike):
         if isinstance(column_types, ColumnTypes):
             _types = column_types._column_types.copy()
         elif isinstance(column_types, str):
-            _types = set([column_types])
+            _types = {column_types}
         elif not isinstance(column_types, Set):
             _types = set(column_types)
         elif isinstance(column_types, Set):