Fix docstring inconsistencies in benchmarking module - resolves aeon-toolkit#809

Author: adityagh006

aeon/benchmarking/metrics/anomaly_detection/thresholding.py

@@ -69,7 +69,7 @@ def top_k_points_threshold(
     Computes a threshold based on the number of expected anomalies (number of
     anomalies). This method iterates over all possible thresholds from high to low to
     find the first threshold that yields ``k`` or more anomalous points. If ``k``
-    is ``None``,the ground truth data is used to calculate the real number of 
+    is ``None``,the ground truth data is used to calculate the real number of
     anomalies.
 
     Parameters
@@ -79,7 +79,7 @@ def top_k_points_threshold(
     y_score : np.ndarray
         Anomaly scores for each point of the time series of shape (n_instances,).
     k : optional int
-        Number of expected anomalies. If ``k`` is ``None``, the ground truth data 
+        Number of expected anomalies. If ``k`` is ``None``, the ground truth data
         is used to calculate the real number of anomalies.
 
     Returns
@@ -103,7 +103,7 @@ def top_k_ranges_threshold(
     Computes a threshold based on the number of expected anomalous subsequences /
     ranges (number of anomalies). This method iterates over all possible thresholds
     from high to low to find the first threshold that yields `k` or more continuous
-    anomalous ranges. If ``k`` is ``None``, the ground truth data is used to 
+    anomalous ranges. If ``k`` is ``None``, the ground truth data is used to
     calculate the real number of anomalies (anomalous ranges).
 
     Parameters
@@ -113,8 +113,8 @@ def top_k_ranges_threshold(
     y_score : np.ndarray
         Anomaly scores for each point of the time series of shape (n_instances,).
     k : optional int
-        Number of expected anomalies. If ``k`` is ``None``, the ground truth data is used
-        to calculate the real number of anomalies.
+        Number of expected anomalies. If ``k`` is ``None``, the ground truth data
+        is used to calculate the real number of anomalies.
 
     Returns
     -------

aeon/benchmarking/published_results.py

@@ -318,4 +318,4 @@ def load_classification_bake_off_2023_results(num_resamples=30, as_array=False):
             res, classifiers, univariate_equal_length, False
         )
         return res, datasets, classifiers
-    return res
+    return res

aeon/benchmarking/resampling.py

@@ -95,7 +95,7 @@ def resample_data_indices(y_train, y_test, random_state=None):
     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 
+        If ``None``, the random number generator is the ``RandomState`` instance
         used by ``np.random``.
 
     Returns
@@ -138,7 +138,7 @@ def stratified_resample_data(X_train, y_train, X_test, y_test, random_state=None
     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 
+        If ``None``, the random number generator is the ``RandomState`` instance
         used by ``np.random``.
 
     Returns
@@ -202,7 +202,7 @@ def stratified_resample_data_indices(y_train, y_test, random_state=None):
     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 
+        If ``None``, the random number generator is the ``RandomState`` instance
         used by ``np.random``.
 
     Returns
@@ -247,4 +247,4 @@ def stratified_resample_data_indices(y_train, y_test, random_state=None):
             [test_indices, indices[counts_train[label_index] :]], axis=None
         )
 
-    return train_indices, test_indices
+    return train_indices, test_indices

aeon/benchmarking/results_loaders.py

@@ -471,4 +471,4 @@ def _results_dict_to_array(res_dict, estimators, datasets, include_missing):
         if include:
             results.append(r)
             names.append(data)
-    return np.array(results), names
+    return np.array(results), names

aeon/benchmarking/stats.py

@@ -311,4 +311,4 @@ def wilcoxon_test(results, labels, lower_better=False):
                     zero_method="wilcox",
                     alternative="less" if lower_better else "greater",
                 ).pvalue
-    return p_values
+    return p_values