ci: Update tooling (#1298)

* ci: Migrate everything to pyproject.toml

* style: Apply ruff fixes

* style: Apply (more) ruff fixes

* style(ruff): Add some file specific ignores

* ci: Fix build with setuptools

* ci(ruff): Allow prints in cli.py

* fix: Circular import

* test: Use raises(..., match=)

* fix(cli): re-add missing print statements

* fix: Fix some over ruff-ized code

* add make check to documentation

* ci: Change to `build` for sdist

* ci: Add ruff to `"test"` deps

---------

Co-authored-by: Lennart Purucker <[email protected]>

Author: eddiebergman

.flake8

@@ -13,7 +13,8 @@ jobs:
         python-version: 3.8
     - name: Build dist
       run: |
-        python setup.py sdist
+        pip install build
+        python -m build --sdist
     - name: Twine check
       run: |
         pip install twine

.github/workflows/dist.yaml

@@ -1,42 +1,48 @@
+default_language_version:
+  python: python3
+files: |
+  (?x)^(
+    openml|
+    tests
+  )/.*\.py$
 repos:
-  - repo: https://github.com/psf/black
-    rev: 23.12.1
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.1.5
     hooks:
-      - id: black
-        args: [--line-length=100]
+      - id: ruff
+        args: [--fix, --exit-non-zero-on-fix, --no-cache]
+      - id: ruff-format
   - repo: https://github.com/pre-commit/mirrors-mypy
     rev: v1.8.0
     hooks:
       - id: mypy
-        name: mypy openml
-        files: openml/.*
         additional_dependencies:
           - types-requests
           - types-python-dateutil
-      - id: mypy
-        name: mypy tests
-        files: tests/.*
-        additional_dependencies:
-          - types-requests
-          - types-python-dateutil
-      - id: mypy
-        name: mypy top-level-functions
-        files: openml/_api_calls.py
-        additional_dependencies:
-          - types-requests
-          - types-python-dateutil
-        args: [ --disallow-untyped-defs, --disallow-any-generics,
-                --disallow-any-explicit, --implicit-optional ]
-  - repo: https://github.com/pycqa/flake8
-    rev: 6.1.0
+  - repo: https://github.com/python-jsonschema/check-jsonschema
+    rev: 0.27.1
     hooks:
-      - id: flake8
-        name: flake8 openml
-        files: openml/.*
-        additional_dependencies:
-          - flake8-print==5.0.0
-      - id: flake8
-        name: flake8 tests
-        files: tests/.*
-        additional_dependencies:
-          - flake8-print==5.0.0
+      - id: check-github-workflows
+        files: '^github/workflows/.*\.ya?ml$'
+        types: ["yaml"]
+      - id: check-dependabot
+        files: '^\.github/dependabot\.ya?ml$'
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-added-large-files
+        files: ".*"
+      - id: check-case-conflict
+        files: ".*"
+      - id: check-merge-conflict
+        files: ".*"
+      - id: check-yaml
+        files: ".*"
+      - id: end-of-file-fixer
+        files: ".*"
+        types: ["yaml"]
+      - id: check-toml
+        files: ".*"
+        types: ["toml"]
+      - id: debug-statements
+        files: '^src/.*\.py$'

.nojekyll

@@ -214,28 +214,32 @@ Before each commit, it will automatically run:
    but make sure to make adjustments if it does fail.
 
 If you want to run the pre-commit tests without doing a commit, run:
-  ```bash
-  $ pre-commit run --all-files
-  ```
+```bash
+$ make check
+```
+or on a system without make, like Windows:
+```bash
+$ pre-commit run --all-files
+```
 Make sure to do this at least once before your first commit to check your setup works.
 
 Executing a specific unit test can be done by specifying the module, test case, and test.
 To obtain a hierarchical list of all tests, run
 
-  ```bash
-  $  pytest --collect-only
-
-    <Module 'tests/test_datasets/test_dataset.py'>
-      <UnitTestCase 'OpenMLDatasetTest'>
-        <TestCaseFunction 'test_dataset_format_constructor'>
-        <TestCaseFunction 'test_get_data'>
-        <TestCaseFunction 'test_get_data_rowid_and_ignore_and_target'>
-        <TestCaseFunction 'test_get_data_with_ignore_attributes'>
-        <TestCaseFunction 'test_get_data_with_rowid'>
-        <TestCaseFunction 'test_get_data_with_target'>
-      <UnitTestCase 'OpenMLDatasetTestOnTestServer'>
-        <TestCaseFunction 'test_tagging'>
-   ```
+```bash
+$  pytest --collect-only
+
+ <Module 'tests/test_datasets/test_dataset.py'>
+   <UnitTestCase 'OpenMLDatasetTest'>
+     <TestCaseFunction 'test_dataset_format_constructor'>
+     <TestCaseFunction 'test_get_data'>
+     <TestCaseFunction 'test_get_data_rowid_and_ignore_and_target'>
+     <TestCaseFunction 'test_get_data_with_ignore_attributes'>
+     <TestCaseFunction 'test_get_data_with_rowid'>
+     <TestCaseFunction 'test_get_data_with_target'>
+   <UnitTestCase 'OpenMLDatasetTestOnTestServer'>
+     <TestCaseFunction 'test_tagging'>
+```
 
 You may then run a specific module, test case, or unit test respectively:
 ```bash

.pre-commit-config.yaml

@@ -7,6 +7,9 @@ CTAGS ?= ctags
 
 all: clean inplace test
 
+check:
+	pre-commit run --all-files
+
 clean:
 	$(PYTHON) setup.py clean
 	rm -rf dist openml.egg-info

CONTRIBUTING.md

@@ -17,36 +17,36 @@
 
 # License: BSD 3-Clause
 
-from . import _api_calls
-from . import config
-from .datasets import OpenMLDataset, OpenMLDataFeature
-from . import datasets
-from . import evaluations
+from . import (
+    _api_calls,
+    config,
+    datasets,
+    evaluations,
+    exceptions,
+    extensions,
+    flows,
+    runs,
+    setups,
+    study,
+    tasks,
+    utils,
+)
+from .__version__ import __version__
+from .datasets import OpenMLDataFeature, OpenMLDataset
 from .evaluations import OpenMLEvaluation
-from . import extensions
-from . import exceptions
-from . import tasks
+from .flows import OpenMLFlow
+from .runs import OpenMLRun
+from .setups import OpenMLParameter, OpenMLSetup
+from .study import OpenMLBenchmarkSuite, OpenMLStudy
 from .tasks import (
-    OpenMLTask,
-    OpenMLSplit,
-    OpenMLSupervisedTask,
     OpenMLClassificationTask,
-    OpenMLRegressionTask,
     OpenMLClusteringTask,
     OpenMLLearningCurveTask,
+    OpenMLRegressionTask,
+    OpenMLSplit,
+    OpenMLSupervisedTask,
+    OpenMLTask,
 )
-from . import runs
-from .runs import OpenMLRun
-from . import flows
-from .flows import OpenMLFlow
-from . import study
-from .study import OpenMLStudy, OpenMLBenchmarkSuite
-from . import utils
-from . import setups
-from .setups import OpenMLSetup, OpenMLParameter
-
-
-from .__version__ import __version__  # noqa: F401
 
 
 def populate_cache(task_ids=None, dataset_ids=None, flow_ids=None, run_ids=None):

Makefile

@@ -3,4 +3,6 @@
 # License: BSD 3-Clause
 
 # The following line *must* be the last in the module, exactly as formatted:
+from __future__ import annotations
+
 __version__ = "0.14.1"