Merge tag 'v2.0.2' into release_2.0.2-rocm

python-package/pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "packager.pep517"
 
 [project]
 name = "xgboost"
-version = "2.0.1"
+version = "2.0.2"
 authors = [
     { name = "Hyunsu Cho", email = "chohyu01@cs.washington.edu" },
     { name = "Jiaming Yuan", email = "jm.yuan@outlook.com" }

python-package/xgboost/VERSION

@@ -1 +1 @@
-2.0.1
+2.0.2

python-package/xgboost/sklearn.py

@@ -2093,7 +2093,17 @@ class XGBRanker(XGBModel, XGBRankerMixIn):
 
         """
         X, qid = _get_qid(X, None)
-        Xyq = DMatrix(X, y, qid=qid)
+        # fixme(jiamingy): base margin and group weight is not yet supported. We might
+        # need to make extra special fields in the dataframe.
+        Xyq = DMatrix(
+            X,
+            y,
+            qid=qid,
+            missing=self.missing,
+            enable_categorical=self.enable_categorical,
+            nthread=self.n_jobs,
+            feature_types=self.feature_types,
+        )
         if callable(self.eval_metric):
             metric = ltr_metric_decorator(self.eval_metric, self.n_jobs)
             result_str = self.get_booster().eval_set([(Xyq, "eval")], feval=metric)

python-package/xgboost/testing/ranking.py

@@ -75,3 +75,28 @@ def run_ranking_qid_df(impl: ModuleType, tree_method: str) -> None:
 
     with pytest.raises(ValueError, match="Either `group` or `qid`."):
         ranker.fit(df, y, eval_set=[(X, y)])
+
+
+def run_ranking_categorical(device: str) -> None:
+    """Test LTR with categorical features."""
+    from sklearn.model_selection import cross_val_score
+
+    X, y = tm.make_categorical(
+        n_samples=512, n_features=10, n_categories=3, onehot=False
+    )
+    rng = np.random.default_rng(1994)
+    qid = rng.choice(3, size=y.shape[0])
+    qid = np.sort(qid)
+    X["qid"] = qid
+
+    ltr = xgb.XGBRanker(enable_categorical=True, device=device)
+    ltr.fit(X, y)
+    score = ltr.score(X, y)
+    assert score > 0.9
+
+    ltr = xgb.XGBRanker(enable_categorical=True, device=device)
+
+    # test using the score function inside sklearn.
+    scores = cross_val_score(ltr, X, y)
+    for s in scores:
+        assert s > 0.7