scikit-learn
diff --git a/‎sklearn/random_projection.py
Lines changed: 21 additions & 0 deletions b/‎sklearn/random_projection.py
Lines changed: 21 additions & 0 deletions
diff --git a/‎sklearn/tests/test_common.py
Lines changed: 0 additions & 1 deletion b/‎sklearn/tests/test_common.py
Lines changed: 0 additions & 1 deletion
diff --git a/‎sklearn/tests/test_random_projection.py
Lines changed: 14 additions & 0 deletions b/‎sklearn/tests/test_random_projection.py
Lines changed: 14 additions & 0 deletions
@@ -34,6 +34,7 @@
 import scipy.sparse as sp
 
 from .base import BaseEstimator, TransformerMixin
+from .base import _check_feature_names_in
 
 from .utils import check_random_state
 from .utils.extmath import safe_sparse_dot
@@ -420,6 +421,26 @@ def transform(self, X):
         X_new = safe_sparse_dot(X, self.components_.T, dense_output=self.dense_output)
         return X_new
 
+    def get_feature_names_out(self, input_features=None):
+        """Get output feature names for transformation.
+
+        Parameters
+        ----------
+        input_features : array-like of str or None, default=None
+            Not used, present here for API consistency by convention.
+
+        Returns
+        -------
+        feature_names_out : ndarray of str objects
+            Transformed feature names.
+        """
+        _check_feature_names_in(self, input_features)
+        class_name = self.__class__.__name__.lower()
+        return np.asarray(
+            [f"{class_name}{i}" for i in range(self.n_components)],
+            dtype=object,
+        )
+
 
 class GaussianRandomProjection(BaseRandomProjection):
     """Reduce dimensionality through Gaussian random projection.
 
@@ -372,7 +372,6 @@ def test_pandas_column_name_consistency(estimator):
     "manifold",
     "neighbors",
     "neural_network",
-    "random_projection",
 ]
 
 
 
@@ -359,3 +359,17 @@ def test_johnson_lindenstrauss_min_dim():
     Regression test for #17111: before #19374, 32-bit systems would fail.
     """
     assert johnson_lindenstrauss_min_dim(100, eps=1e-5) == 368416070986
+
+
+@pytest.mark.parametrize("random_projection_cls", all_RandomProjection)
+def test_random_projection_feature_names_out(random_projection_cls):
+    random_projection = random_projection_cls(n_components=2)
+    random_projection.fit(data)
+    names_out = random_projection.get_feature_names_out()
+    class_name_lower = random_projection_cls.__name__.lower()
+    expected_names_out = np.array(
+        [f"{class_name_lower}{i}" for i in range(random_projection.n_components_)],
+        dtype=object,
+    )
+
+    assert_array_equal(names_out, expected_names_out)