Automatic pre-commit fixes

aeon/anomaly_detection/_idk.py

@@ -1,4 +1,5 @@
 """IDK2 anomaly detector."""
+
 from typing import Optional
 
 import numpy as np
@@ -169,22 +170,28 @@ def _idk_fixed_window(self, X, rng):
                 featuremap_count, [featuremap_count.shape[0] - 1], axis=0
             )
 
-        return self._compute_idk_score(featuremap_count, psi=self.psi2, t=self.t, rng=rng)
+        return self._compute_idk_score(
+            featuremap_count, psi=self.psi2, t=self.t, rng=rng
+        )
 
     def _idk_square_sliding(self, X, rng):
-        point_fm_list = self._generate_feature_map(X=X, psi=self.psi1, t=self.t, rng=rng)
+        point_fm_list = self._generate_feature_map(
+            X=X, psi=self.psi1, t=self.t, rng=rng
+        )
         point_fm_list = np.insert(point_fm_list, 0, 0, axis=0)
         cumsum = np.cumsum(point_fm_list, axis=0)
 
         subsequence_fm_list = (cumsum[self.width :] - cumsum[: -self.width]) / float(
             self.width
         )
 
-        return self._compute_idk_score(X=subsequence_fm_list, psi=self.psi2, t=self.t, rng=rng)
+        return self._compute_idk_score(
+            X=subsequence_fm_list, psi=self.psi2, t=self.t, rng=rng
+        )
 
     def _predict(self, X):
         rng = np.random.default_rng(self.random_state)
-        if self.sliding :
+        if self.sliding:
             sliding_output = self._idk_square_sliding(X, rng)
             reversed_output = reverse_windowing(
                 y=sliding_output,
@@ -217,4 +224,4 @@ def _get_test_params(cls, parameter_set="default"):
             "psi1": 8,
             "psi2": 2,
             "width": 1,
-        }
+        }

aeon/anomaly_detection/tests/test_idk.py

@@ -50,7 +50,7 @@ def test_idk_univariate_custom_series():
             -0.55382284,
         ]
     )
-    expected = [0.21 ,0.17 ,0.17 ,0.3  ,0.38 ,0.35 ,0.17 ,0.36 ,0.21 ,0.17]
+    expected = [0.21, 0.17, 0.17, 0.3, 0.38, 0.35, 0.17, 0.36, 0.21, 0.17]
 
     ad_2 = IDK2(psi1=4, psi2=2, width=1, t=10, random_state=2)
     pred2 = ad_2.fit_predict(series1)