[JTH] add kma max iterations flag

Author: tausiaj

bluemath_tk/core/decorators.py

@@ -120,6 +120,7 @@ def wrapper(
         directional_variables: List[str] = [],
         custom_scale_factor: dict = {},
         min_number_of_points: int = None,
+        max_number_of_iterations: int = 10,
         normalize_data: bool = True,
     ):
         if data is None:
@@ -133,6 +134,11 @@ def wrapper(
         if min_number_of_points is not None:
             if not isinstance(min_number_of_points, int) or min_number_of_points <= 0:
                 raise ValueError("Minimum number of points must be integer and > 0")
+        if (
+            not isinstance(max_number_of_iterations, int)
+            or max_number_of_iterations <= 0
+        ):
+            raise ValueError("Maximum number of iterations must be integer and > 0")
         if not isinstance(normalize_data, bool):
             raise TypeError("Normalize data must be a boolean")
         return func(

bluemath_tk/datamining/kma.py

@@ -182,6 +182,7 @@ def fit(
         directional_variables: List[str] = [],
         custom_scale_factor: dict = {},
         min_number_of_points: int = None,
+        max_number_of_iterations: int = 10,
         normalize_data: bool = True,
     ) -> None:
         """
@@ -206,6 +207,10 @@ def fit(
         min_number_of_points : int, optional
             The minimum number of points to consider a cluster.
             Default is None.
+        max_number_of_iterations : int, optional
+            The maximum number of iterations for the K-Means algorithm.
+            This is used when min_number_of_points is not None.
+            Default is 10.
         normalize_data : bool, optional
             A flag to normalize the data. Default is True.
         """
@@ -248,9 +253,10 @@ def fit(
                 if np.all(counts >= min_number_of_points):
                     stable_kma_child = True
                 number_of_tries += 1
-                if number_of_tries > 10:
+                if number_of_tries > max_number_of_iterations:
                     raise ValueError(
-                        "Failed to find a stable K-Means configuration after 10 attempts."
+                        f"Failed to find a stable K-Means configuration after {max_number_of_iterations} attempts."
+                        "Change max_number_of_iterations or min_number_of_points."
                     )
             self.logger.info(
                 f"Found a stable K-Means configuration after {number_of_tries} attempts."