[SPARK-51329][ML][PYTHON] Add numFeatures for clustering models

### What changes were proposed in this pull request?
Add `numFeatures` for clustering models

### Why are the changes needed?
for feature parity between python and scala, these methods were missing in python world

### Does this PR introduce _any_ user-facing change?
yes, new methods

### How was this patch tested?
updated tests

### Was this patch authored or co-authored using generative AI tooling?
no

Closes #50095 from zhengruifeng/ml_km_nf.

Authored-by: Ruifeng Zheng <ruifengz@apache.org>
Signed-off-by: Ruifeng Zheng <ruifengz@apache.org>

Author: zhengruifeng

python/pyspark/ml/clustering.py

@@ -214,6 +214,14 @@ def setProbabilityCol(self, value: str) -> "GaussianMixtureModel":
         """
         return self._set(probabilityCol=value)
 
+    @property
+    @since("4.1.0")
+    def numFeatures(self) -> int:
+        """
+        Number of features, i.e., length of Vectors which this transforms.
+        """
+        return self._call_java("numFeatures")
+
     @property
     @since("2.0.0")
     def weights(self) -> List[float]:
@@ -686,6 +694,14 @@ def clusterCenters(self) -> List[np.ndarray]:
         matrix = self._call_java("clusterCenterMatrix")
         return [vec for vec in matrix.toArray()]
 
+    @property
+    @since("4.1.0")
+    def numFeatures(self) -> int:
+        """
+        Number of features, i.e., length of Vectors which this transforms.
+        """
+        return self._call_java("numFeatures")
+
     @property
     @since("2.1.0")
     def summary(self) -> KMeansSummary:
@@ -1025,6 +1041,14 @@ def computeCost(self, dataset: DataFrame) -> float:
         )
         return self._call_java("computeCost", dataset)
 
+    @property
+    @since("4.1.0")
+    def numFeatures(self) -> int:
+        """
+        Number of features, i.e., length of Vectors which this transforms.
+        """
+        return self._call_java("numFeatures")
+
     @property
     @since("2.1.0")
     def summary(self) -> "BisectingKMeansSummary":

python/pyspark/ml/tests/test_clustering.py

@@ -73,12 +73,10 @@ def test_kmeans(self):
 
         centers = model.clusterCenters()
         self.assertEqual(len(centers), 2)
+        self.assertEqual(model.numFeatures, 2)
         self.assertTrue(np.allclose(centers[0], [-0.372, -0.338], atol=1e-3), centers[0])
         self.assertTrue(np.allclose(centers[1], [0.8625, 0.83375], atol=1e-3), centers[1])
 
-        # TODO: support KMeansModel.numFeatures in Python
-        # self.assertEqual(model.numFeatures, 2)
-
         output = model.transform(df)
         expected_cols = ["weight", "features", "prediction"]
         self.assertEqual(output.columns, expected_cols)
@@ -148,12 +146,10 @@ def test_bisecting_kmeans(self):
 
         centers = model.clusterCenters()
         self.assertEqual(len(centers), 2)
+        self.assertEqual(model.numFeatures, 2)
         self.assertTrue(np.allclose(centers[0], [-0.372, -0.338], atol=1e-3), centers[0])
         self.assertTrue(np.allclose(centers[1], [0.8625, 0.83375], atol=1e-3), centers[1])
 
-        # TODO: support KMeansModel.numFeatures in Python
-        # self.assertEqual(model.numFeatures, 2)
-
         output = model.transform(df)
         expected_cols = ["weight", "features", "prediction"]
         self.assertEqual(output.columns, expected_cols)
@@ -224,8 +220,7 @@ def test_gaussian_mixture(self):
 
         model = gmm.fit(df)
         self.assertEqual(gmm.uid, model.uid)
-        # TODO: support GMM.numFeatures in Python
-        # self.assertEqual(model.numFeatures, 2)
+        self.assertEqual(model.numFeatures, 2)
         self.assertEqual(len(model.weights), 2)
         self.assertTrue(
             np.allclose(model.weights, [0.541014115744985, 0.4589858842550149], atol=1e-4),