Release v0.10.0 (#1782)

* classification checks in progress * changelog start * changelog and fixes * highlights * organising class weights
aeon-toolkit · Jul 11, 2024 · 0ab30bf · 0ab30bf
1 parent 0b52cdf
commit 0ab30bf
Show file tree

Hide file tree

Showing 16 changed files with 384 additions and 66 deletions.
diff --git a/.github/workflows/pr_precommit.yml b/.github/workflows/pr_precommit.yml
@@ -17,19 +17,8 @@ jobs:
     runs-on: ubuntu-20.04
 
     steps:
-      - name: Create app token
-        uses: actions/create-github-app-token@v1
-        id: app-token
-        with:
-          app-id: ${{ vars.PR_APP_ID }}
-          private-key: ${{ secrets.PR_APP_KEY }}
-
       - name: Checkout
         uses: actions/checkout@v4
-        with:
-          repository: ${{ github.event.pull_request.head.repo.full_name }}
-          ref: ${{ github.head_ref }}
-          token: ${{ steps.app-token.outputs.token }}
 
       - name: Setup Python 3.10
         uses: actions/setup-python@v5
@@ -43,6 +32,7 @@ jobs:
       - name: List changed files
         run: echo '${{ steps.changed-files.outputs.all_changed_files }}'
 
+      # only check the full repository if PR and correctly labelled
       - if: ${{ github.event_name == 'pull_request_target' && contains(github.event.pull_request.labels.*.name, 'full pre-commit') }}
         name: Full pre-commit
         uses: pre-commit/action@v3.0.1
@@ -54,6 +44,23 @@ jobs:
         with:
           extra_args: --files ${{ steps.changed-files.outputs.all_changed_files }}
 
+      # push fixes if pre-commit fails and PR is eligible
+      - if: ${{ failure() && github.event_name == 'pull_request_target' && !github.event.pull_request.draft && !contains(github.event.pull_request.labels.*.name, 'stop pre-commit fixes') }}
+        name: Create app token
+        uses: actions/create-github-app-token@v1
+        id: app-token
+        with:
+          app-id: ${{ vars.PR_APP_ID }}
+          private-key: ${{ secrets.PR_APP_KEY }}
+
+      - if: ${{ failure() && github.event_name == 'pull_request_target' && !github.event.pull_request.draft && !contains(github.event.pull_request.labels.*.name, 'stop pre-commit fixes') }}
+        name: Checkout
+        uses: actions/checkout@v4
+        with:
+          repository: ${{ github.event.pull_request.head.repo.full_name }}
+          ref: ${{ github.head_ref }}
+          token: ${{ steps.app-token.outputs.token }}
+
       - if: ${{ failure() && github.event_name == 'pull_request_target' && !github.event.pull_request.draft && !contains(github.event.pull_request.labels.*.name, 'stop pre-commit fixes') }}
         name: Push pre-commit fixes
         uses: stefanzweifel/git-auto-commit-action@v5

diff --git a/README.md b/README.md
@@ -13,7 +13,7 @@ We strive to provide a broad library of time series algorithms including the
 latest advances, offer efficient implementations using numba, and interfaces with other
 time series packages to provide a single framework for algorithm comparison.
 
-The latest `aeon` release is `v0.9.0`. You can view the full changelog
+The latest `aeon` release is `v0.10.0`. You can view the full changelog
 [here](https://www.aeon-toolkit.org/en/stable/changelog.html).
 
 Our webpage and documentation is available at https://aeon-toolkit.org.

diff --git a/aeon/__init__.py b/aeon/__init__.py
@@ -1,6 +1,6 @@
 """aeon toolkit."""
 
-__version__ = "0.9.0"
+__version__ = "0.10.0"
 
 __all__ = ["show_versions"]
 

diff --git a/aeon/classification/convolution_based/_arsenal.py b/aeon/classification/convolution_based/_arsenal.py
@@ -51,6 +51,17 @@ class Arsenal(BaseClassifier):
         Default of 0 means n_estimators is used.
     contract_max_n_estimators : int, default=100
         Max number of estimators when time_limit_in_minutes is set.
+    class_weight{“balanced”, “balanced_subsample”}, dict or list of dicts, default=None
+        From sklearn documentation:
+        If not given, all classes are supposed to have weight one.
+        The “balanced” mode uses the values of y to automatically adjust weights
+        inversely proportional to class frequencies in the input data as
+        n_samples / (n_classes * np.bincount(y))
+        The “balanced_subsample” mode is the same as “balanced” except that weights
+        are computed based on the bootstrap sample for every tree grown.
+        For multi-output, the weights of each column of y will be multiplied.
+        Note that these weights will be multiplied with sample_weight (passed through
+        the fit method) if sample_weight is specified.
     n_jobs : int, default=1
         The number of jobs to run in parallel for both `fit` and `predict`.
         ``-1`` means using all processors.
@@ -76,17 +87,6 @@ class Arsenal(BaseClassifier):
         The collections of estimators trained in fit.
     weights_ : list of shape (n_estimators) of float
         Weight of each estimator in the ensemble.
-    class_weight{“balanced”, “balanced_subsample”}, dict or list of dicts, default=None
-        From sklearn documentation:
-        If not given, all classes are supposed to have weight one.
-        The “balanced” mode uses the values of y to automatically adjust weights
-        inversely proportional to class frequencies in the input data as
-        n_samples / (n_classes * np.bincount(y))
-        The “balanced_subsample” mode is the same as “balanced” except that weights
-        are computed based on the bootstrap sample for every tree grown.
-        For multi-output, the weights of each column of y will be multiplied.
-        Note that these weights will be multiplied with sample_weight (passed through
-        the fit method) if sample_weight is specified.
     n_estimators_ : int
         The number of estimators in the ensemble.
 
@@ -147,10 +147,10 @@ def __init__(
         self.n_features_per_kernel = n_features_per_kernel
         self.time_limit_in_minutes = time_limit_in_minutes
         self.contract_max_n_estimators = contract_max_n_estimators
-        self.class_weight = class_weight
 
-        self.random_state = random_state
+        self.class_weight = class_weight
         self.n_jobs = n_jobs
+        self.random_state = random_state
 
         self.n_cases_ = 0
         self.n_channels_ = 0

diff --git a/aeon/classification/convolution_based/_hydra.py b/aeon/classification/convolution_based/_hydra.py
@@ -88,7 +88,7 @@ class HydraClassifier(BaseClassifier):
     }
 
     def __init__(
-        self, n_kernels=8, n_groups=64, n_jobs=1, class_weight=None, random_state=None
+        self, n_kernels=8, n_groups=64, class_weight=None, n_jobs=1, random_state=None
     ):
         self.n_kernels = n_kernels
         self.n_groups = n_groups

diff --git a/aeon/classification/convolution_based/_mr_hydra.py b/aeon/classification/convolution_based/_mr_hydra.py
@@ -82,7 +82,7 @@ class MultiRocketHydraClassifier(BaseClassifier):
     }
 
     def __init__(
-        self, n_kernels=8, n_groups=64, n_jobs=1, class_weight=None, random_state=None
+        self, n_kernels=8, n_groups=64, class_weight=None, n_jobs=1, random_state=None
     ):
         self.n_kernels = n_kernels
         self.n_groups = n_groups

diff --git a/aeon/classification/convolution_based/_rocket_classifier.py b/aeon/classification/convolution_based/_rocket_classifier.py
@@ -57,14 +57,14 @@ class RocketClassifier(BaseClassifier):
         For multi-output, the weights of each column of y will be multiplied.
         Note that these weights will be multiplied with sample_weight (passed through
         the fit method) if sample_weight is specified.
+    n_jobs : int, default=1
+        The number of jobs to run in parallel for both `fit` and `predict`.
+        ``-1`` means using all processors.
     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;
         If `None`, the random number generator is the `RandomState` instance used
         by `np.random`.
-    n_jobs : int, default=1
-        The number of jobs to run in parallel for both `fit` and `predict`.
-        ``-1`` means using all processors.
 
     Attributes
     ----------
@@ -116,19 +116,20 @@ def __init__(
         rocket_transform="rocket",
         max_dilations_per_kernel=32,
         n_features_per_kernel=4,
-        class_weight=None,
         estimator=None,
-        random_state=None,
+        class_weight=None,
         n_jobs=1,
+        random_state=None,
     ):
         self.num_kernels = num_kernels
         self.rocket_transform = rocket_transform
         self.max_dilations_per_kernel = max_dilations_per_kernel
         self.n_features_per_kernel = n_features_per_kernel
-        self.random_state = random_state
-        self.class_weight = class_weight
         self.estimator = estimator
+
+        self.class_weight = class_weight
         self.n_jobs = n_jobs
+        self.random_state = random_state
 
         super().__init__()
 

diff --git a/aeon/classification/dictionary_based/_muse.py b/aeon/classification/dictionary_based/_muse.py
@@ -162,19 +162,20 @@ def __init__(
         self.word_lengths = [4, 6]
         self.bigrams = bigrams
         self.binning_strategies = ["equi-width", "equi-depth"]
-        self.random_state = random_state
         self.min_window = 6
         self.max_window = 100
         self.window_inc = window_inc
         self.window_sizes = []
         self.SFA_transformers = []
         self.clf = None
-        self.n_jobs = n_jobs
         self.support_probabilities = support_probabilities
         self.total_features_count = 0
-        self.class_weight = class_weight
         self.feature_selection = feature_selection
 
+        self.class_weight = class_weight
+        self.n_jobs = n_jobs
+        self.random_state = random_state
+
         super().__init__()
 
     def _fit(self, X, y):

diff --git a/aeon/classification/dictionary_based/_weasel.py b/aeon/classification/dictionary_based/_weasel.py
@@ -144,10 +144,10 @@ def __init__(
         window_inc=2,
         p_threshold=0.05,
         alphabet_size=4,
-        n_jobs=1,
         feature_selection="chi2",
         support_probabilities=False,
         class_weight=None,
+        n_jobs=1,
         random_state=None,
     ):
         self.alphabet_size = alphabet_size
@@ -158,7 +158,6 @@ def __init__(
         self.word_lengths = [4, 6]
         self.bigrams = bigrams
         self.binning_strategy = binning_strategy
-        self.random_state = random_state
         self.min_window = 6
         self.max_window = 100
         self.feature_selection = feature_selection
@@ -169,10 +168,14 @@ def __init__(
         self.n_cases = 0
         self.SFA_transformers = []
         self.clf = None
-        self.n_jobs = n_jobs
         self.support_probabilities = support_probabilities
+
+        self.random_state = random_state
+        self.n_jobs = n_jobs
         self.class_weight = class_weight
+
         set_num_threads(n_jobs)
+
         super().__init__()
 
     def _fit(self, X, y):

diff --git a/aeon/classification/dictionary_based/_weasel_v2.py b/aeon/classification/dictionary_based/_weasel_v2.py
@@ -138,24 +138,21 @@ def __init__(
         use_first_differences=(True, False),
         feature_selection="chi2_top_k",
         max_feature_count=30_000,
-        random_state=None,
         class_weight=None,
-        n_jobs=4,
+        n_jobs=1,
+        random_state=None,
     ):
         self.norm_options = norm_options
         self.word_lengths = word_lengths
-
-        self.random_state = random_state
-
         self.min_window = min_window
-
         self.max_feature_count = max_feature_count
         self.use_first_differences = use_first_differences
         self.feature_selection = feature_selection
-        self.class_weight = class_weight
-
         self.clf = None
+
+        self.class_weight = class_weight
         self.n_jobs = n_jobs
+        self.random_state = random_state
 
         super().__init__()
 

diff --git a/aeon/classification/interval_based/_quant.py b/aeon/classification/interval_based/_quant.py
@@ -91,14 +91,14 @@ def __init__(
         interval_depth=6,
         quantile_divisor=4,
         estimator=None,
-        random_state=None,
         class_weight=None,
+        random_state=None,
     ):
         self.interval_depth = interval_depth
         self.quantile_divisor = quantile_divisor
         self.estimator = estimator
-        self.random_state = random_state
         self.class_weight = class_weight
+        self.random_state = random_state
         super().__init__()
 
     def _fit(self, X, y):

diff --git a/aeon/classification/shapelet_based/_rdst.py b/aeon/classification/shapelet_based/_rdst.py
@@ -66,6 +66,8 @@ class RDSTClassifier(BaseClassifier):
     estimator : BaseEstimator or None, default=None
         Base estimator for the ensemble, can be supplied a sklearn `BaseEstimator`. If
         `None` a default `RidgeClassifierCV` classifier is used with standard scalling.
+    save_transformed_data : bool, default=False
+        If True, the transformed training dataset for all classifiers will be saved.
     class_weight{“balanced”, “balanced_subsample”}, dict or list of dicts, default=None
         Only applies if estimator is None, and the default is used.
         From sklearn documentation:
@@ -78,8 +80,6 @@ class RDSTClassifier(BaseClassifier):
         For multi-output, the weights of each column of y will be multiplied.
         Note that these weights will be multiplied with sample_weight (passed through
         the fit method) if sample_weight is specified.
-    save_transformed_data : bool, default=False
-        If True, the transformed training dataset for all classifiers will be saved.
     n_jobs : int, default=1
         The number of jobs to run in parallel for both ``fit`` and ``predict``.
         `-1` means using all processors.
@@ -147,10 +147,10 @@ def __init__(
         threshold_percentiles=None,
         alpha_similarity: float = 0.5,
         use_prime_dilations: bool = False,
+        distance: str = "manhattan",
         estimator=None,
         save_transformed_data: bool = False,
         class_weight=None,
-        distance: str = "manhattan",
         n_jobs: int = 1,
         random_state: Union[int, Type[np.random.RandomState], None] = None,
     ) -> None:
@@ -160,12 +160,13 @@ def __init__(
         self.threshold_percentiles = threshold_percentiles
         self.alpha_similarity = alpha_similarity
         self.use_prime_dilations = use_prime_dilations
-        self.class_weight = class_weight
         self.distance = distance
         self.estimator = estimator
         self.save_transformed_data = save_transformed_data
+        self.class_weight = class_weight
         self.random_state = random_state
         self.n_jobs = n_jobs
+
         self.transformed_data_ = []
 
         self._transformer = None

diff --git a/build_tools/pr_labeler.py b/build_tools/pr_labeler.py
@@ -31,17 +31,17 @@
 title = pr.title
 
 title_regex_to_labels = [
-    (r"\bENH\b", "enhancement"),
-    (r"\bMNT\b", "maintenance"),
-    (r"\bBUG\b", "bug"),
-    (r"\bDOC\b", "documentation"),
-    (r"\bREF\b", "refactor"),
-    (r"\bDEP\b", "deprecation"),
-    (r"\bGOV\b", "governance"),
+    (r"\benh\b", "enhancement"),
+    (r"\bmnt\b", "maintenance"),
+    (r"\bbug\b", "bug"),
+    (r"\bdoc\b", "documentation"),
+    (r"\bref\b", "refactor"),
+    (r"\bdep\b", "deprecation"),
+    (r"\bgov\b", "governance"),
 ]
 
 title_labels = [
-    label for regex, label in title_regex_to_labels if re.search(regex, title)
+    label for regex, label in title_regex_to_labels if re.search(regex, title.lower())
 ]
 title_labels_to_add = list(set(title_labels) - set(labels))
 

diff --git a/docs/changelog.md b/docs/changelog.md
@@ -1,14 +1,15 @@
 # Changelog
 
 All notable changes to this project will be documented in this file. The format is
-based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) and we adhere
+based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), and we adhere
 to [Semantic Versioning](https://semver.org/spec/v2.0.0.html). The source code for
 all [releases](https://github.com/aeon-toolkit/aeon/releases) is available on GitHub.
 
-To stay up-to-date with aeon releases, subscribe to aeon
+To stay up to date with aeon releases, subscribe to aeon
 [here](https://libraries.io/pypi/aeon) or follow us on
 [Twitter](https://twitter.com/aeon_toolbox).
 
+- [Version 0.10.0](changelogs/v0.10.md)
 - [Version 0.9.0](changelogs/v0.9.md)
 - [Version 0.8.0](changelogs/v0.8.md)
 - [Version 0.7.0](changelogs/v0.7.md)