scikit-learn · glemaitre · Feb 1, 2024 · Jan 19, 2024 · Jan 19, 2024 · Jan 25, 2024
diff --git a/doc/whats_new/v1.4.rst b/doc/whats_new/v1.4.rst
@@ -20,6 +20,19 @@ Version 1.4.1
 
 **In Development**
 
+Metadata Routing
+----------------
+
+- |FIX| Fix routing issue with :class:`~compose.ColumnTransformer` when used
+  inside another meta-estimator.
+  :pr:`28188` by `Adrin Jalali`_.
+
+DataFrame Support
+-----------------
+
+- |Enhancement| Pandas and Polars dataframe are validated directly without ducktyping
+  checks. :pr:`28195` by `Thomas Fan`_.
+
 Changes impacting all modules
 -----------------------------
 
@@ -70,9 +83,6 @@ Changelog
   larger than the number of non-duplicate samples.
   :pr:`28165` by :user:`Jérémie du Boisberranger <jeremiedbb>`.
 
-- |Enhancement| Pandas and Polars dataframe are validated directly without ducktyping
-  checks. :pr:`28195` by `Thomas Fan`_.
-
 :mod:`sklearn.compose`
 ......................
 

diff --git a/sklearn/compose/_column_transformer.py b/sklearn/compose/_column_transformer.py
@@ -1204,12 +1204,12 @@ def get_metadata_routing(self):
             routing information.
         """
         router = MetadataRouter(owner=self.__class__.__name__)
-        for name, step, _, _ in self._iter(
-            fitted=False,
-            column_as_labels=False,
-            skip_drop=True,
-            skip_empty_columns=True,
-        ):
+        # Here we don't care about which columns are used for which
+        # transformers, and whether or not a transformer is used at all, which
+        # might happen if no columns are selected for that transformer. We
+        # request all metadata requested by all transformers.
+        transformers = chain(self.transformers, [("remainder", self.remainder, None)])
+        for name, step, _ in transformers:
             method_mapping = MethodMapping()
             if hasattr(step, "fit_transform"):
                 (

diff --git a/sklearn/compose/tests/test_column_transformer.py b/sklearn/compose/tests/test_column_transformer.py
@@ -1,6 +1,7 @@
 """
 Test the ColumnTransformer.
 """
+
 import pickle
 import re
 import warnings
@@ -2526,5 +2527,45 @@ def test_metadata_routing_error_for_column_transformer(method):
             getattr(trs, method)(X, y, sample_weight=sample_weight, metadata=metadata)
 
 
+@pytest.mark.usefixtures("enable_slep006")
+def test_get_metadata_routing_works_without_fit():
+    # Regression test for https://github.com/scikit-learn/scikit-learn/issues/28186
+    # Make sure ct.get_metadata_routing() works w/o having called fit.
+    ct = ColumnTransformer([("trans", ConsumingTransformer(), [0])])
+    ct.get_metadata_routing()
+
+
+@pytest.mark.usefixtures("enable_slep006")
+def test_remainder_request_always_present():
+    # Test that remainder request is always present.
+    ct = ColumnTransformer(
+        [("trans", StandardScaler(), [0])],
+        remainder=ConsumingTransformer()
+        .set_fit_request(metadata=True)
+        .set_transform_request(metadata=True),
+    )
+    router = ct.get_metadata_routing()
+    assert router.consumes("fit", ["metadata"]) == set(["metadata"])
+
+
+@pytest.mark.usefixtures("enable_slep006")
+def test_unused_transformer_request_present():
+    # Test that the request of a transformer is always present even when not
+    # used due to no selected columns.
+    ct = ColumnTransformer(
+        [
+            (
+                "trans",
+                ConsumingTransformer()
+                .set_fit_request(metadata=True)
+                .set_transform_request(metadata=True),
+                lambda X: [],
+            )
+        ]
+    )
+    router = ct.get_metadata_routing()
+    assert router.consumes("fit", ["metadata"]) == set(["metadata"])
+
+
 # End of Metadata Routing Tests
 # =============================