Improve error message for invalid init strategy

Add InitStrategy Literal type and show valid options in error message
when an unsupported init strategy is passed. This helps catch common
typos like "kmeans++" instead of "k-means++".

Closes #116

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

Author: patcon

reddwarf/sklearn/cluster.py

@@ -1,4 +1,4 @@
-from typing import List, Optional
+from typing import List, Literal, Optional
 
 import numpy as np
 from numpy.typing import ArrayLike, NDArray
@@ -9,6 +9,9 @@
 
 from reddwarf.sklearn.model_selection import GridSearchNonCV
 
+InitStrategy = Literal["k-means++", "random", "polis"]
+VALID_INIT_STRATEGIES: List[str] = ["k-means++", "random", "polis"]
+
 
 def _to_range(r) -> range:
     """
@@ -76,8 +79,8 @@ class PolisKMeans(KMeans):
     def __init__(
         self,
         n_clusters=8,
-        init="k-means++",  # or 'random', 'polis'
-        init_centers: Optional[ArrayLike] = None,  # array-like, optional
+        init: InitStrategy = "k-means++",
+        init_centers: Optional[ArrayLike] = None,
         n_init="auto",
         max_iter=300,
         tol=1e-4,
@@ -120,7 +123,10 @@ def _generate_centers(self, X, x_squared_norms, n_to_generate, random_state) ->
                 raise ValueError("Not enough unique rows in X for 'polis' strategy.")
             centers = unique_X[:n_to_generate]
         else:
-            raise ValueError(f"Unsupported init strategy: {self._init_strategy}")
+            raise ValueError(
+                f"Unsupported init strategy: {self._init_strategy!r}. "
+                f"Valid options are: {VALID_INIT_STRATEGIES}"
+            )
         return centers
 
     def fit(self, X, y=None, sample_weight=None):
@@ -178,7 +184,7 @@ def __init__(
         self,
         n_clusters: int = 100,
         random_state: Optional[int] = None,
-        init: str = "k-means++",
+        init: InitStrategy = "k-means++",
         init_centers: Optional[ArrayLike] = None,
     ):
         self.n_clusters = n_clusters
@@ -232,7 +238,7 @@ class BestPolisKMeans(BaseEstimator):
     def __init__(
         self,
         k_bounds: Optional[List[int]] = None,
-        init: str = "polis",
+        init: InitStrategy = "polis",
         init_centers: Optional[ArrayLike] = None,
         random_state: Optional[int] = None,
     ):

reddwarf/utils/clusterer/kmeans.py

@@ -2,7 +2,7 @@
 import pandas as pd
 import numpy as np
 from reddwarf.sklearn.model_selection import GridSearchNonCV
-from reddwarf.sklearn.cluster import PolisKMeans
+from reddwarf.sklearn.cluster import InitStrategy, PolisKMeans
 from sklearn.metrics import silhouette_score
 from typing import List, Optional
 
@@ -33,7 +33,7 @@ def to_range(r: RangeLike) -> range:
 def run_kmeans(
         dataframe: pd.DataFrame,
         n_clusters: int = 2,
-        init="k-means++",
+        init: InitStrategy = "k-means++",
         # TODO: Improve this type. 3d?
         init_centers: Optional[List] = None,
         random_state: Optional[int] = None,
@@ -66,7 +66,7 @@ def run_kmeans(
 def find_best_kmeans(
         X_to_cluster: NDArray,
         k_bounds: RangeLike = [2, 5],
-        init="k-means++",
+        init: InitStrategy = "k-means++",
         init_centers: Optional[List] = None,
         random_state: Optional[int] = None,
 ) -> tuple[int, float, PolisKMeans | None]:

tests/sklearn/test_cluster.py

@@ -184,12 +184,12 @@ def test_init_centers_wrong_n_features(self, simple_data):
             pkm.fit(X)
 
     def test_unsupported_init_strategy(self, simple_data):
-        """Test that unsupported init strategy raises error."""
+        """Test that unsupported init strategy raises error with valid options."""
         X, _ = simple_data
-        pkm = PolisKMeans(n_clusters=3, init="invalid")
+        pkm = PolisKMeans(n_clusters=3, init="k-means++")
         pkm._init_strategy = "invalid"  # Bypass __init__ validation
 
-        with pytest.raises(ValueError, match="Unsupported init strategy"):
+        with pytest.raises(ValueError, match=r"Unsupported init strategy.*k-means\+\+.*random.*polis"):
             pkm.fit(X)
 
     def test_reproducibility_with_random_state(self, simple_data):