Deprecate LabelEncoder in XGBClassifier; Enable cuDF/cuPy inputs in XGBClassifier (#6269)

* Deprecate LabelEncoder in XGBClassifier; skip LabelEncoder for cuDF/cuPy inputs

* Add unit tests for cuDF and cuPy inputs with XGBClassifier

* Fix lint

* Clarify warning

* Move use_label_encoder option to XGBClassifier constructor

* Add a test for cudf.Series

* Add use_label_encoder to XGBRFClassifier doc

* Address reviewer feedback

tests/python-gpu/test_from_cudf.py

@@ -172,6 +172,34 @@ Arrow specification.'''
         _test_cudf_metainfo(xgb.DeviceQuantileDMatrix)
 
 
+@pytest.mark.skipif(**tm.no_cudf())
+@pytest.mark.skipif(**tm.no_cupy())
+@pytest.mark.skipif(**tm.no_sklearn())
+@pytest.mark.skipif(**tm.no_pandas())
+def test_cudf_training_with_sklearn():
+    from cudf import DataFrame as df
+    from cudf import Series as ss
+    import pandas as pd
+    np.random.seed(1)
+    X = pd.DataFrame(np.random.randn(50, 10))
+    y = pd.DataFrame((np.random.randn(50) > 0).astype(np.int8))
+    weights = np.random.random(50) + 1.0
+    cudf_weights = df.from_pandas(pd.DataFrame(weights))
+    base_margin = np.random.random(50)
+    cudf_base_margin = df.from_pandas(pd.DataFrame(base_margin))
+
+    X_cudf = df.from_pandas(X)
+    y_cudf = df.from_pandas(y)
+    y_cudf_series = ss(data=y.iloc[:, 0])
+
+    for y_obj in [y_cudf, y_cudf_series]:
+        clf = xgb.XGBClassifier(gpu_id=0, tree_method='gpu_hist', use_label_encoder=False)
+        clf.fit(X_cudf, y_obj, sample_weight=cudf_weights, base_margin=cudf_base_margin,
+                eval_set=[(X_cudf, y_obj)])
+        pred = clf.predict(X_cudf)
+        assert np.array_equal(np.unique(pred), np.array([0, 1]))
+
+
 class IterForDMatrixTest(xgb.core.DataIter):
     '''A data iterator for XGBoost DMatrix.
 

tests/python-gpu/test_from_cupy.py

@@ -108,6 +108,25 @@ def _test_cupy_metainfo(DMatrixT):
                           dmat_cupy.get_uint_info('group_ptr'))
 
 
+@pytest.mark.skipif(**tm.no_cupy())
+@pytest.mark.skipif(**tm.no_sklearn())
+def test_cupy_training_with_sklearn():
+    import cupy as cp
+    np.random.seed(1)
+    cp.random.seed(1)
+    X = cp.random.randn(50, 10, dtype='float32')
+    y = (cp.random.randn(50, dtype='float32') > 0).astype('int8')
+    weights = np.random.random(50) + 1
+    cupy_weights = cp.array(weights)
+    base_margin = np.random.random(50)
+    cupy_base_margin = cp.array(base_margin)
+
+    clf = xgb.XGBClassifier(gpu_id=0, tree_method='gpu_hist', use_label_encoder=False)
+    clf.fit(X, y, sample_weight=cupy_weights, base_margin=cupy_base_margin, eval_set=[(X, y)])
+    pred = clf.predict(X)
+    assert np.array_equal(np.unique(pred), np.array([0, 1]))
+
+
 class TestFromCupy:
     '''Tests for constructing DMatrix from data structure conforming Apache
 Arrow specification.'''