[MNT] cluster init_algorithm removed across all clusterers

aeon/clustering/_clara.py

@@ -30,8 +30,8 @@ class TimeSeriesCLARA(BaseClusterer):
     n_clusters : int, default=8
         The number of clusters to form as well as the number of
         centroids to generate.
-    init_algorithm : str or np.ndarray, default='random'
-        Method for initializing cluster centers. Any of the following are valid:
+    init : str or np.ndarray, default='random'
+        Method for initialising cluster centers. Any of the following are valid:
         ['kmedoids++', 'random', 'first'].
         Random is the default as it is very fast and it was found in [2] to
         perform about as well as the other methods.
@@ -118,7 +118,7 @@ class TimeSeriesCLARA(BaseClusterer):
     def __init__(
         self,
         n_clusters: int = 8,
-        init_algorithm: Union[str, np.ndarray] = "random",
+        init: Union[str, np.ndarray] = "random",
         distance: Union[str, Callable] = "msm",
         n_samples: Optional[int] = None,
         n_sampling_iters: int = 10,
@@ -129,8 +129,8 @@ def __init__(
         random_state: Optional[Union[int, RandomState]] = None,
         distance_params: Optional[dict] = None,
     ):
-        self.init_algorithm = init_algorithm
         self.distance = distance
+        self.init = init
         self.n_init = n_init
         self.max_iter = max_iter
         self.tol = tol
@@ -175,7 +175,7 @@ def _fit(self, X: np.ndarray, y=None):
                 )
             pam = TimeSeriesKMedoids(
                 n_clusters=self.n_clusters,
-                init_algorithm=self.init_algorithm,
+                init=self.init,
                 distance=self.distance,
                 n_init=self.n_init,
                 max_iter=self.max_iter,
@@ -228,7 +228,7 @@ def _get_test_params(cls, parameter_set="default"):
         """
         return {
             "n_clusters": 2,
-            "init_algorithm": "random",
+            "init": "random",
             "distance": "euclidean",
             "n_init": 1,
             "max_iter": 1,

aeon/clustering/_clarans.py

@@ -31,8 +31,8 @@ class TimeSeriesCLARANS(TimeSeriesKMedoids):
     n_clusters : int, default=8
         The number of clusters to form as well as the number of
         centroids to generate.
-    init_algorithm : str or np.ndarray, default='random'
-        Method for initializing cluster centers. Any of the following are valid:
+    init : str or np.ndarray, default='random'
+        Method for initialising cluster centers. Any of the following are valid:
         ['kmedoids++', 'random', 'first'].
         Random is the default as it is very fast and it was found in [2] to
         perform about as well as the other methods.
@@ -104,7 +104,7 @@ class TimeSeriesCLARANS(TimeSeriesKMedoids):
     def __init__(
         self,
         n_clusters: int = 8,
-        init_algorithm: Union[str, np.ndarray] = "random",
+        init: Union[str, np.ndarray] = "random",
         distance: Union[str, Callable] = "msm",
         max_neighbours: Optional[int] = None,
         n_init: int = 10,
@@ -116,7 +116,7 @@ def __init__(
 
         super().__init__(
             n_clusters=n_clusters,
-            init_algorithm=init_algorithm,
+            init=init,
             distance=distance,
             n_init=n_init,
             verbose=verbose,
@@ -127,10 +127,10 @@ def __init__(
     def _fit_one_init(self, X: np.ndarray, max_neighbours: int):
         j = 0
         X_indexes = np.arange(X.shape[0], dtype=int)
-        if isinstance(self._init_algorithm, Callable):
-            best_medoids = self._init_algorithm(X)
+        if isinstance(self._init, Callable):
+            best_medoids = self._init(X)
         else:
-            best_medoids = self._init_algorithm
+            best_medoids = self._init
         best_non_medoids = np.setdiff1d(X_indexes, best_medoids)
         best_cost = (
             self._compute_pairwise(X, best_non_medoids, best_medoids).min(axis=1).sum()
@@ -203,7 +203,7 @@ def _get_test_params(cls, parameter_set="default"):
         """
         return {
             "n_clusters": 2,
-            "init_algorithm": "random",
+            "init": "random",
             "distance": "euclidean",
             "max_neighbours": None,
             "n_init": 1,

aeon/clustering/_k_medoids.py

@@ -44,8 +44,8 @@ class TimeSeriesKMedoids(BaseClusterer):
     ----------
     n_clusters : int, default=8
         The number of clusters to form as well as the number of centroids to generate.
-    init_algorithm : str or np.ndarray, default='random'
-        Method for initializing cluster centers. Any of the following are valid:
+    init : str or np.ndarray, default='random'
+        Method for initialising cluster centers. Any of the following are valid:
         ['kmedoids++', 'random', 'first'].
         Random is the default as it is very fast and it was found in [2] to
         perform about as well as the other methods.
@@ -152,7 +152,7 @@ class TimeSeriesKMedoids(BaseClusterer):
     def __init__(
         self,
         n_clusters: int = 8,
-        init_algorithm: Union[str, np.ndarray] = "random",
+        init: Union[str, np.ndarray] = "random",
         distance: Union[str, Callable] = "msm",
         method: str = "pam",
         n_init: int = 10,
@@ -162,8 +162,8 @@ def __init__(
         random_state: Optional[Union[int, RandomState]] = None,
         distance_params: Optional[dict] = None,
     ):
-        self.init_algorithm = init_algorithm
         self.distance = distance
+        self.init = init
         self.n_init = n_init
         self.max_iter = max_iter
         self.tol = tol
@@ -179,7 +179,7 @@ def __init__(
         self.n_iter_ = 0
 
         self._random_state = None
-        self._init_algorithm = None
+        self._init = None
         self._distance_cache = None
         self._distance_callable = None
         self._fit_method = None
@@ -267,10 +267,10 @@ def _pam_fit(self, X: np.ndarray):
         old_inertia = np.inf
         n_cases = X.shape[0]
 
-        if isinstance(self._init_algorithm, Callable):
-            medoids_idxs = self._init_algorithm(X)
+        if isinstance(self._init, Callable):
+            medoids_idxs = self._init(X)
         else:
-            medoids_idxs = self._init_algorithm
+            medoids_idxs = self._init
         not_medoid_idxs = np.arange(n_cases, dtype=int)
         distance_matrix = self._compute_pairwise(X, not_medoid_idxs, not_medoid_idxs)
         distance_closest_medoid, distance_second_closest_medoid = np.sort(
@@ -388,9 +388,9 @@ def _compute_optimal_swaps(
             return None
 
     def _alternate_fit(self, X) -> tuple[np.ndarray, np.ndarray, float, int]:
-        cluster_center_indexes = self._init_algorithm
-        if isinstance(self._init_algorithm, Callable):
-            cluster_center_indexes = self._init_algorithm(X)
+        cluster_center_indexes = self._init
+        if isinstance(self._init, Callable):
+            cluster_center_indexes = self._init(X)
         old_inertia = np.inf
         old_indexes = None
         for i in range(self.max_iter):
@@ -428,24 +428,21 @@ def _assign_clusters(
     def _check_params(self, X: np.ndarray) -> None:
         self._random_state = check_random_state(self.random_state)
 
-        if isinstance(self.init_algorithm, str):
-            if self.init_algorithm == "random":
-                self._init_algorithm = self._random_center_initializer
-            elif self.init_algorithm == "kmedoids++":
-                self._init_algorithm = self._kmedoids_plus_plus_center_initializer
-            elif self.init_algorithm == "first":
-                self._init_algorithm = self._first_center_initializer
-            elif self.init_algorithm == "build":
-                self._init_algorithm = self._pam_build_center_initializer
+        if isinstance(self.init, str):
+            if self.init == "random":
+                self._init = self._random_center_initializer
+            elif self.init == "kmedoids++":
+                self._init = self._kmedoids_plus_plus_center_initializer
+            elif self.init == "first":
+                self._init = self._first_center_initializer
+            elif self.init == "build":
+                self._init = self._pam_build_center_initializer
         else:
-            if (
-                isinstance(self.init_algorithm, np.ndarray)
-                and len(self.init_algorithm) == self.n_clusters
-            ):
-                self._init_algorithm = self.init_algorithm
+            if isinstance(self.init, np.ndarray) and len(self.init) == self.n_clusters:
+                self._init = self.init
             else:
                 raise ValueError(
-                    f"The value provided for init_algorithm: {self.init_algorithm} is "
+                    f"The value provided for init: {self.init} is "
                     f"invalid. The following are a list of valid init algorithms "
                     f"strings: random, kmedoids++, first. You can also pass a"
                     f"np.ndarray of size (n_clusters, n_channels, n_timepoints)"
@@ -469,7 +466,7 @@ def _check_params(self, X: np.ndarray) -> None:
         else:
             raise ValueError(f"method {self.method} is not supported")
 
-        if isinstance(self.init_algorithm, str) and self.init_algorithm == "build":
+        if isinstance(self.init, str) and self.init == "build":
             if self.n_init != 10 and self.n_init > 1:
                 warnings.warn(
                     "When using build n_init does not need to be greater than 1. "
@@ -558,7 +555,7 @@ def _get_test_params(cls, parameter_set="default"):
         """
         return {
             "n_clusters": 2,
-            "init_algorithm": "random",
+            "init": "random",
             "distance": "euclidean",
             "n_init": 1,
             "max_iter": 1,

aeon/clustering/_k_shape.py

@@ -16,8 +16,8 @@ class TimeSeriesKShape(BaseClusterer):
     n_clusters: int, default=8
         The number of clusters to form as well as the number of
         centroids to generate.
-    init_algorithm: str or np.ndarray, default='random'
-        Method for initializing cluster centres. Any of the following are valid:
+    init: str or np.ndarray, default='random'
+        Method for initialising cluster centres. Any of the following are valid:
         ['random']. Or a np.ndarray of shape (n_clusters, n_channels, n_timepoints)
         and gives the initial cluster centres.
     n_init: int, default=10
@@ -76,15 +76,15 @@ class TimeSeriesKShape(BaseClusterer):
     def __init__(
         self,
         n_clusters: int = 8,
-        init_algorithm: Union[str, np.ndarray] = "random",
+        init: Union[str, np.ndarray] = "random",
         n_init: int = 10,
         max_iter: int = 300,
         tol: float = 1e-4,
         verbose: bool = False,
         random_state: Optional[Union[int, RandomState]] = None,
     ):
-        self.init_algorithm = init_algorithm
         self.n_init = n_init
+        self.init = init
         self.max_iter = max_iter
         self.tol = tol
         self.verbose = verbose
@@ -124,7 +124,7 @@ def _fit(self, X, y=None):
             random_state=self.random_state,
             n_init=self.n_init,
             verbose=self.verbose,
-            init=self.init_algorithm,
+            init=self.init,
         )
 
         _X = X.swapaxes(1, 2)
@@ -173,7 +173,7 @@ def _get_test_params(cls, parameter_set="default"):
         """
         return {
             "n_clusters": 2,
-            "init_algorithm": "random",
+            "init": "random",
             "n_init": 1,
             "max_iter": 1,
             "tol": 1e-4,

aeon/clustering/tests/test_clara.py

@@ -23,7 +23,7 @@ def test_clara_uni():
         n_samples=10,
         n_init=2,
         max_iter=5,
-        init_algorithm="first",
+        init="first",
         distance="euclidean",
         n_clusters=2,
     )
@@ -68,7 +68,7 @@ def test_clara_multi():
         n_samples=10,
         n_init=2,
         max_iter=5,
-        init_algorithm="first",
+        init="first",
         distance="euclidean",
         n_clusters=2,
     )

aeon/clustering/tests/test_clarans.py

@@ -24,7 +24,7 @@ def test_clarans_uni():
     clarans = TimeSeriesCLARANS(
         random_state=1,
         n_init=2,
-        init_algorithm="first",
+        init="first",
         distance="euclidean",
         n_clusters=2,
     )
@@ -67,7 +67,7 @@ def test_clara_multi():
     clarans = TimeSeriesCLARANS(
         random_state=1,
         n_init=2,
-        init_algorithm="first",
+        init="first",
         distance="euclidean",
         n_clusters=2,
     )
@@ -106,7 +106,7 @@ def test_medoids_init():
     kmedoids = TimeSeriesCLARANS(
         random_state=1,
         n_init=1,
-        init_algorithm="first",
+        init="first",
         distance="euclidean",
         n_clusters=num_clusters,
     )
@@ -131,7 +131,7 @@ def test_medoids_init():
     kmedoids = TimeSeriesCLARANS(
         random_state=1,
         n_init=1,
-        init_algorithm=custom_init_centres,
+        init=custom_init_centres,
         distance="euclidean",
         n_clusters=num_clusters,
     )

aeon/clustering/tests/test_k_medoids.py

@@ -43,7 +43,7 @@ def _pam_uni_medoids(X_train, y_train, X_test, y_test):
         random_state=1,
         n_init=2,
         max_iter=5,
-        init_algorithm="first",
+        init="first",
         distance="euclidean",
         method="pam",
     )
@@ -70,7 +70,7 @@ def _alternate_uni_medoids(X_train, y_train, X_test, y_test):
         n_init=2,
         max_iter=5,
         method="alternate",
-        init_algorithm="first",
+        init="first",
         distance="euclidean",
     )
     train_medoids_result = kmedoids.fit_predict(X_train)
@@ -95,7 +95,7 @@ def _pam_multi_medoids(X_train, y_train, X_test, y_test):
         random_state=1,
         n_init=2,
         max_iter=5,
-        init_algorithm="first",
+        init="first",
         distance="euclidean",
         method="pam",
     )
@@ -121,7 +121,7 @@ def _alternate_multi_medoids(X_train, y_train, X_test, y_test):
         random_state=1,
         n_init=2,
         max_iter=5,
-        init_algorithm="first",
+        init="first",
         method="alternate",
         distance="euclidean",
     )
@@ -169,7 +169,7 @@ def test_medoids_init():
         random_state=1,
         n_init=1,
         max_iter=5,
-        init_algorithm="first",
+        init="first",
         distance="euclidean",
         n_clusters=num_clusters,
     )
@@ -194,7 +194,7 @@ def test_medoids_init():
         random_state=1,
         n_init=1,
         max_iter=5,
-        init_algorithm=custom_init_centres,
+        init=custom_init_centres,
         distance="euclidean",
         n_clusters=num_clusters,
     )
@@ -209,7 +209,7 @@ def _get_model_centres(data, distance, method="pam", distance_params=None):
         method=method,
         n_init=2,
         n_clusters=2,
-        init_algorithm="random",
+        init="random",
         distance=distance,
         distance_params=distance_params,
     )