[MNT] Fixes, Py12 and release 0.4.0 (#46)

* fixes

* commed mypy

* c22

* transform no longer requires y

* fixes

* fixes

* fixes

* v0.3.0

* yml

* py 12 and fixes

* readme

* pyfftw bound

* fda bound again

* mrsqm

* skip pyfftw docs

* fix

Author: MatthewMiddlehurst

.github/workflows/precommit_autoupdate.yml

@@ -34,4 +34,4 @@ jobs:
           branch: pre-commit-hooks-update
           title: "[MNT] Automated `pre-commit` hook update"
           body: "Automated weekly update to `.pre-commit-config.yaml` hook versions."
-          labels: maintenance, full pre-commit, no changelog
+          labels: maintenance, full pre-commit

.github/workflows/release.yml

@@ -52,7 +52,7 @@ jobs:
     strategy:
       matrix:
         os: [ ubuntu-22.04, macOS-12, windows-2022 ]
-        python-version: [ "3.8", "3.9", "3.10", "3.11" ]
+        python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12" ]
 
     steps:
       - uses: actions/checkout@v4

.github/workflows/tests.yml

@@ -28,7 +28,7 @@ jobs:
       fail-fast: false
       matrix:
         os: [ ubuntu-22.04, macOS-12, windows-2022 ]
-        python-version: [ "3.8", "3.9", "3.10", "3.11" ]
+        python-version: [ "3.8", "3.9", "3.10", "3.11", "3.12" ]
 
     steps:
       - uses: actions/checkout@v4
@@ -38,7 +38,11 @@ jobs:
           python-version: ${{ matrix.python-version }}
 
       - name: Install
-        run: python -m pip install .[dev,all_extras,unstable_extras]
+        uses: nick-fields/retry@v2
+        with:
+          timeout_minutes: 30
+          max_attempts: 3
+          command: python -m pip install .[dev,all_extras,unstable_extras]
 
       - name: Tests
         run: python -m pytest

.pre-commit-config.yaml

@@ -2,9 +2,9 @@ repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v4.5.0
     hooks:
+    - id: check-ast
     - id: check-added-large-files
       args: ["--maxkb=10000"]
-    - id: check-ast
     - id: check-case-conflict
     - id: check-docstring-first
     - id: check-merge-conflict
@@ -21,26 +21,44 @@ repos:
     - id: requirements-txt-fixer
     - id: trailing-whitespace
 
+  - repo: https://github.com/lk16/detect-missing-init
+    rev: v0.1.6
+    hooks:
+      - id: detect-missing-init
+        args: [ "--create", "--python-folders", "tsml" ]
+
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.4.1
+    hooks:
+      - id: ruff
+        args: [ "--fix" ]
+
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v3.15.2
+    hooks:
+      - id: pyupgrade
+        args: [ "--py38-plus" ]
+
   - repo: https://github.com/pycqa/isort
     rev: 5.13.2
     hooks:
       - id: isort
         name: isort (python)
         args: [ "--profile=black", "--multi-line=3" ]
 
-  - repo: https://github.com/psf/black
-    rev: 23.12.1
-    hooks:
-      - id: black
-        language_version: python3
-
   - repo: https://github.com/pycqa/flake8
     rev: 7.0.0
     hooks:
       - id: flake8
         additional_dependencies: [ flake8-bugbear, flake8-print, Flake8-pyproject ]
         args: [ "--max-line-length=88", "--extend-ignore=E203" ]
 
+  - repo: https://github.com/psf/black
+    rev: 23.12.1
+    hooks:
+      - id: black
+        language_version: python3
+
   - repo: https://github.com/nbQA-dev/nbQA
     rev: 1.7.1
     hooks:
@@ -54,20 +72,6 @@ repos:
         additional_dependencies: [ flake8 ]
         args: [ "--nbqa-dont-skip-bad-cells", "--extend-ignore=E402,E203", "--max-line-length=88" ]
 
-  - repo: https://github.com/pycqa/pydocstyle
-    rev: 6.3.0
-    hooks:
-      - id: pydocstyle
-        args: ["--convention=numpy"]
-        additional_dependencies: [ toml, tomli ]
-
-#  - repo: https://github.com/pre-commit/mirrors-mypy
-#    rev: v1.8.0
-#    hooks:
-#      - id: mypy
-#        files: tsml/
-#        additional_dependencies: [ pytest ]
-
   - repo: https://github.com/mgedmin/check-manifest
     rev: "0.49"
     hooks:

README.md

@@ -13,7 +13,12 @@
 
 A toolkit for time series machine learning algorithms.
 
-The current release of `tsml` is v0.3.0.
+Please see [`tsml_eval`](https://github.com/time-series-machine-learning/tsml-eval) and
+[`aeon`](https://github.com/aeon-toolkit/aeon) for more developed packages. This package
+is more of a sandbox for testing out new ideas and algorithms. It may contain some
+algorithms and implementations that are not available in the other toolkits.
+
+The current release of `tsml` is v0.4.0.
 
 ## Installation
 

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tsml"
-version = "0.3.0"
+version = "0.4.0"
 description = "A toolkit for time series machine learning algorithms."
 authors = [
     {name = "Matthew Middlehurst", email = "m.b.middlehurst@soton.ac.uk"},
@@ -13,7 +13,7 @@ maintainers = [
     {name = "Matthew Middlehurst", email = "m.b.middlehurst@soton.ac.uk"},
 ]
 readme = "README.md"
-requires-python = ">=3.8,<3.12"
+requires-python = ">=3.8,<3.13"
 keywords = [
     "data-science",
     "machine-learning",
@@ -36,6 +36,7 @@ classifiers = [
     "Programming Language :: Python :: 3.9",
     "Programming Language :: Python :: 3.10",
     "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
 ]
 dependencies = [
     "numba>=0.55.0",
@@ -47,25 +48,26 @@ dependencies = [
 
 [project.optional-dependencies]
 all_extras = [
-    "pyfftw>=0.12.0",
-    "statsmodels>=0.12.1",
-    "wildboar>=1.1.0",
+    "grailts",
     "scikit-fda>=0.7.0",
+    "statsmodels>=0.12.1",
     "stumpy>=1.6.0",
-    "grailts",
+    "wildboar>=1.1.0",
+
     # temp
-    "fdasrsf<=2.5.2",  # currently above this breaks on some OS
+    "fdasrsf<=2.5.2",  # temporary, currently above this breaks on some OS
 ]
 unstable_extras = [
-    "mrsqm>=0.0.1 ; platform_system == 'Darwin'",  # requires gcc and fftw to be installed for Windows and some other OS (see http://www.fftw.org/index.html)
+    "mrsqm>=0.0.1 ; platform_system == 'Darwin' and python_version < '3.12'",  # requires gcc and fftw to be installed for Windows and some other OS (see http://www.fftw.org/index.html)
     "pycatch22<=0.4.3",  # Known to fail installation on some setups
+    "pyfftw>=0.12.0; python_version < '3.12'", # requires fftw to be installed for Windows and some other OS (see http://www.fftw.org/index.html)
 ]
 dev = [
     "pre-commit",
     "pytest",
     "pytest-randomly",
     "pytest-timeout",
-    "pytest-xdist",
+    "pytest-xdist[psutil]",
     "pytest-cov",
     "pytest-rerunfailures",
 ]
@@ -74,7 +76,7 @@ binder = [
     "jupyterlab",
 ]
 docs = [
-    "sphinx<8.0.0",
+    "sphinx<7.3.0",
     "sphinx-design",
     "sphinx-version-warning",
     "sphinx_issues",
@@ -106,13 +108,21 @@ ignore = [
     "local/**",
 ]
 
+[tool.ruff.lint]
+select = ["D"]
+
+[tool.ruff.lint.pydocstyle]
+convention = "numpy"
+
 [tool.pytest.ini_options]
 testpaths = "tsml"
 addopts = '''
+    --doctest-modules
     --durations 20
     --timeout 600
     --showlocals
-    --doctest-modules
-    --numprocesses auto
+    --numprocesses logical
+    --dist worksteal
     --reruns 2
+    --only-rerun "crashed while running"
 '''

tsml/__init__.py

@@ -1,3 +1,3 @@
 """tsml."""
 
-__version__ = "0.3.0"
+__version__ = "0.4.0"

tsml/distance_based/_grail.py

@@ -6,6 +6,7 @@
 
 import os
 import sys
+import warnings
 
 import numpy as np
 from sklearn.base import ClassifierMixin
@@ -38,7 +39,7 @@ def __init__(self, classifier="svm"):
 
         _check_optional_dependency("grailts", "GRAIL", self)
 
-        super(GRAILClassifier, self).__init__()
+        super().__init__()
 
     def fit(self, X, y):
         """Fit the estimator to training data.
@@ -85,11 +86,19 @@ def fit(self, X, y):
         ) = self._modified_GRAIL_rep_fit(X, self._d)
 
         if self.classifier == "svm":
-            self._clf = GridSearchCV(
-                SVC(kernel="linear", probability=True),
-                param_grid={"C": [i**2 for i in np.arange(-10, 20, 0.11)]},
-                cv=min(min(class_count), 5),
-            )
+            cv = min(min(class_count), 5)
+            if cv == 1:
+                warnings.warn(
+                    "Only one class was found in y, so no cross-validation.",
+                    stacklevel=2,
+                )
+                self._clf = SVC(kernel="linear", probability=True, C=1)
+            else:
+                self._clf = GridSearchCV(
+                    SVC(kernel="linear", probability=True),
+                    param_grid={"C": [i**2 for i in np.arange(-10, 20, 0.11)]},
+                    cv=min(min(class_count), 5),
+                )
             self._clf.fit(Xt, y)
         elif self.classifier == "knn":
             self._train_Xt = Xt

tsml/hybrid/_rist.py

@@ -112,10 +112,10 @@ class RISTClassifier(ClassifierMixin, BaseTimeSeriesEstimator):
     >>> from tsml.hybrid import RISTClassifier
     >>> from tsml.utils.testing import generate_3d_test_data
     >>> X, y = generate_3d_test_data(n_samples=8, series_length=10, random_state=0)
-    >>> clf = RISTClassifier(random_state=0)
-    >>> clf.fit(X, y)
+    >>> clf = RISTClassifier(random_state=0)  # doctest: +SKIP
+    >>> clf.fit(X, y)  # doctest: +SKIP
     RISTClassifier(...)
-    >>> clf.predict(X)
+    >>> clf.predict(X)  # doctest: +SKIP
     array([0, 1, 1, 0, 0, 1, 0, 1])
     """
 
@@ -144,7 +144,7 @@ def __init__(
         if use_pyfftw:
             _check_optional_dependency("pyfftw", "pyfftw", self)
 
-        super(RISTClassifier, self).__init__()
+        super().__init__()
 
     def fit(self, X: Union[np.ndarray, List[np.ndarray]], y: np.ndarray) -> object:
         """Fit the estimator to training data.
@@ -363,10 +363,10 @@ class RISTRegressor(RegressorMixin, BaseTimeSeriesEstimator):
     >>> from tsml.utils.testing import generate_3d_test_data
     >>> X, y = generate_3d_test_data(n_samples=8, series_length=10,
     ...                              regression_target=True, random_state=0)
-    >>> reg = RISTRegressor(random_state=0)
-    >>> reg.fit(X, y)
+    >>> reg = RISTRegressor(random_state=0)  # doctest: +SKIP
+    >>> reg.fit(X, y)  # doctest: +SKIP
     RISTRegressor(...)
-    >>> reg.predict(X)
+    >>> reg.predict(X)  # doctest: +SKIP
     array([0.31798318, 1.41426301, 1.06414747, 0.6924721 , 0.56660146,
            1.26538944, 0.52324808, 1.0939405 ])
     """
@@ -396,7 +396,7 @@ def __init__(
         if use_pyfftw:
             _check_optional_dependency("pyfftw", "pyfftw", self)
 
-        super(RISTRegressor, self).__init__()
+        super().__init__()
 
     def fit(self, X: Union[np.ndarray, List[np.ndarray]], y: np.ndarray) -> object:
         """Fit the estimator to training data.

tsml/interval_based/_base.py

@@ -129,7 +129,7 @@ class BaseIntervalForest(BaseTimeSeriesEstimator, metaclass=ABCMeta):
     contract_max_n_estimators : int, default=500
         Max number of estimators when time_limit_in_minutes is set.
     save_transformed_data : bool, default=False
-        Save the data transformed in fit for use in _get_train_probs.
+        Save the data transformed in fit.
     random_state : int, RandomState instance or None, default=None
         If `int`, random_state is the seed used by the random number generator;
         If `RandomState` instance, random_state is the random number generator;
@@ -211,7 +211,7 @@ def __init__(
         self.n_jobs = n_jobs
         self.parallel_backend = parallel_backend
 
-        super(BaseIntervalForest, self).__init__()
+        super().__init__()
 
     # if subsampling attributes, an interval_features transformer must contain a
     # parameter name from transformer_feature_selection and an attribute name