Merge branch 'main' into ajb/ets_rework

Author: TonyBagnall

.all-contributorsrc

@@ -2747,6 +2747,15 @@
       "contributions": [
         "doc"
       ]
+    },
+    {
+      "login": "CodeFor2001",
+      "name": "Saniya S Inamdar",
+      "avatar_url": "https://avatars.githubusercontent.com/u/39870781?v=4",
+      "profile": "https://github.com/CodeFor2001",
+      "contributions": [
+        "doc"
+      ]
     }
   ],
   "commitType": "docs"

.github/actions/numba_cache/action.yml

@@ -62,6 +62,6 @@ runs:
         path: ${{ github.workspace }}/.numba_cache
         # Try restore using today's date
         key: numba-${{ inputs.cache_name }}-${{ inputs.runner_os }}-${{ inputs.python_version }}-${{ env.CURRENT_DATE }}
-        # If cant restore with today's date try another cache (without date)
+        # If can't restore with today's date try another cache (without date)
         restore-keys: |
           numba-${{ inputs.cache_name }}-${{ inputs.runner_os }}-${{ inputs.python_version }}-

.github/utilities/codespell_ignore_words.txt

@@ -0,0 +1,4 @@
+fpr
+mape
+recuse
+strat

.github/workflows/pr_precommit.yml

@@ -60,3 +60,27 @@ jobs:
         with:
           commit_message: Automatic `pre-commit` fixes
           commit_user_name: aeon-actions-bot[bot]
+
+  codespell-annotations:
+    runs-on: ubuntu-24.04
+
+    steps:
+      - name: Create app token
+        uses: actions/create-github-app-token@v2
+        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: Annotate locations with typos
+        uses: codespell-project/codespell-problem-matcher@v1
+
+      - name: Codespell
+        uses: codespell-project/actions-codespell@v2

.pre-commit-config.yaml

@@ -78,3 +78,11 @@ repos:
     hooks:
       - id: check-manifest
         stages: [ manual ]
+
+  - repo: https://github.com/codespell-project/codespell
+    # Configuration for codespell is in pyproject.toml
+    rev: v2.4.1
+    hooks:
+      - id: codespell
+        additional_dependencies:
+          - tomli  # for python_version < '3.11'

CONTRIBUTORS.md

@@ -42,7 +42,7 @@ class KMeansAD(BaseSeriesAnomalyDetector):
 
     stride : int, default=1
         The stride of the sliding window. The stride determines how many time points
-        the windows are spaced appart. A stride of 1 means that the window is moved one
+        the windows are spaced apart. A stride of 1 means that the window is moved one
         time point forward compared to the previous window. The larger the stride, the
         fewer windows are created, which leads to noisier anomaly scores.
 

aeon/anomaly_detection/series/distance_based/_kmeans.py

@@ -102,26 +102,26 @@ def _predict(self, X):
 
         r = 2 * np.sqrt(self.min_length)
         distances = np.full(len(lengths), -1.0)
-        indicies = np.full(len(lengths), -1)
+        indices = np.full(len(lengths), -1)
 
-        indicies[0], distances[0] = self._find_index(X, lengths[0], r, np.multiply, 0.5)
+        indices[0], distances[0] = self._find_index(X, lengths[0], r, np.multiply, 0.5)
 
         for i in range(1, min(5, len(lengths))):
             r = distances[i - 1] * 0.99
-            indicies[i], distances[i] = self._find_index(
+            indices[i], distances[i] = self._find_index(
                 X, lengths[i], r, np.multiply, 0.99
             )
 
         for i in range(min(5, len(lengths)), len(lengths)):
             m = mean(distances[i - 5 : i])
             s = std(distances[i - 5 : i])
             r = m - 2 * s
-            indicies[i], distances[i] = self._find_index(
+            indices[i], distances[i] = self._find_index(
                 X, lengths[i], r, np.subtract, s
             )
 
         anomalies = np.zeros(X.shape[0], dtype=bool)
-        for i in indicies:
+        for i in indices:
             if i > -1:
                 anomalies[i] = True
 

aeon/anomaly_detection/series/distance_based/_merlin.py

@@ -20,7 +20,7 @@ class STRAY(BaseSeriesAnomalyDetector):
     ability to detect clusters of outliers in multidimensional data without
     requiring a model of the typical behavior of the system. However, it suffers
     from some limitations that affect its accuracy. STRAY is an extension of
-    HDoutliers that uses extreme value theory for the anomolous threshold
+    HDoutliers that uses extreme value theory for the anomalous threshold
     calculation, to deal with data streams that exhibit non-stationary behavior.
 
     Parameters
@@ -39,7 +39,7 @@ class STRAY(BaseSeriesAnomalyDetector):
         Proportion of possible candidates for outliers. This defines the starting point
         for the bottom up searching algorithm.
     size_threshold : int, default=50
-        Sample size to calculate an emperical threshold.
+        Sample size to calculate an empirical threshold.
     outlier_tail : str {"min", "max"}, default="max"
         Direction of the outlier tail.
 

aeon/anomaly_detection/series/outlier_detection/_stray.py

@@ -42,7 +42,7 @@ class BaseCollectionEnsemble(ComposableEstimatorMixin, BaseCollectionEstimator):
         Only used if weights is a float. The method used to generate a performance
         estimation from the training data set i.e. cross-validation.
         If None, predictions are made using that estimators fit_predict or
-            fit_predict_proba methods. These are somtimes overridden for efficient
+            fit_predict_proba methods. These are sometimes overridden for efficient
             performance evaluations, i.e. out-of-bag predictions.
         If int or sklearn object input, the parameter is passed directly to the cv
             parameter of the cross_val_predict function from sklearn.