Merge pull request #13448 from rapidsai/branch-23.06

Forward-merge branch-23.06 to branch-23.08
rapidsai · May 25, 2023 · 53c685b · 53c685b
2 parents 2def7f1 + 03f0c0c
commit 53c685b
Show file tree

Hide file tree

Showing 2 changed files with 15 additions and 25 deletions.
diff --git a/python/cudf/cudf/_lib/transform.pyx b/python/cudf/cudf/_lib/transform.pyx
@@ -163,7 +163,7 @@ def one_hot_encode(Column input_column, Column categories):
         move(c_result.second),
         owner=owner,
         column_names=[
-            x if x is not None else 'null' for x in pylist_categories
+            x if x is not None else '<NA>' for x in pylist_categories
         ]
     )
     return encodings

diff --git a/python/cudf/cudf/tests/test_onehot.py b/python/cudf/cudf/tests/test_onehot.py
@@ -7,7 +7,6 @@
 import pytest
 
 import cudf
-from cudf import DataFrame
 from cudf.testing._utils import assert_eq
 
 pytestmark = pytest.mark.spilling
@@ -24,7 +23,7 @@
     ],
 )
 def test_get_dummies(data, index):
-    gdf = DataFrame({"x": data}, index=index)
+    gdf = cudf.DataFrame({"x": data}, index=index)
     pdf = pd.DataFrame({"x": data}, index=index)
 
     encoded_expected = pd.get_dummies(pdf, prefix="test")
@@ -66,16 +65,16 @@ def test_onehot_get_dummies_multicol(n_cols):
 @pytest.mark.parametrize("dummy_na", [True, False])
 def test_onehost_get_dummies_dummy_na(nan_as_null, dummy_na):
     pdf = pd.DataFrame({"a": [0, 1, np.nan]})
-    df = DataFrame.from_pandas(pdf, nan_as_null=nan_as_null)
+    df = cudf.DataFrame.from_pandas(pdf, nan_as_null=nan_as_null)
 
     expected = pd.get_dummies(pdf, dummy_na=dummy_na, columns=["a"])
     with pytest.warns(FutureWarning):
-        got = cudf.get_dummies(df, dummy_na=dummy_na, columns=["a"])
+        actual = cudf.get_dummies(df, dummy_na=dummy_na, columns=["a"])
 
     if dummy_na and nan_as_null:
-        got = got.rename(columns={"a_null": "a_nan"})[expected.columns]
+        actual = actual.rename(columns={"a_<NA>": "a_nan"})[expected.columns]
 
-    assert_eq(expected, got)
+    assert_eq(expected, actual)
 
 
 @pytest.mark.parametrize(
@@ -104,7 +103,7 @@ def test_get_dummies_prefix_sep(prefix, prefix_sep):
         "third": ["ji", "ji", "ji"],
     }
 
-    gdf = DataFrame(data)
+    gdf = cudf.DataFrame(data)
     pdf = pd.DataFrame(data)
 
     encoded_expected = pd.get_dummies(
@@ -122,15 +121,11 @@ def test_get_dummies_with_nan():
     df = cudf.DataFrame(
         {"a": cudf.Series([1, 2, np.nan, None], nan_as_null=False)}
     )
-    expected = cudf.DataFrame(
-        {
-            "a_1.0": [1, 0, 0, 0],
-            "a_2.0": [0, 1, 0, 0],
-            "a_nan": [0, 0, 1, 0],
-            "a_null": [0, 0, 0, 1],
-        },
-        dtype="uint8",
+
+    expected = pd.get_dummies(
+        df.to_pandas(nullable=True), dummy_na=True, columns=["a"]
     )
+
     with pytest.warns(FutureWarning):
         actual = cudf.get_dummies(df, dummy_na=True, columns=["a"])
 
@@ -166,16 +161,11 @@ def test_get_dummies_array_like(data, prefix_sep, prefix, dtype):
 
 def test_get_dummies_array_like_with_nan():
     ser = cudf.Series([0.1, 2, 3, None, np.nan], nan_as_null=False)
-    expected = cudf.DataFrame(
-        {
-            "a_0.1": [1, 0, 0, 0, 0],
-            "a_2.0": [0, 1, 0, 0, 0],
-            "a_3.0": [0, 0, 1, 0, 0],
-            "a_nan": [0, 0, 0, 0, 1],
-            "a_null": [0, 0, 0, 1, 0],
-        },
-        dtype="uint8",
+
+    expected = pd.get_dummies(
+        ser.to_pandas(nullable=True), dummy_na=True, prefix="a", prefix_sep="_"
     )
+
     with pytest.warns(FutureWarning):
         actual = cudf.get_dummies(
             ser, dummy_na=True, prefix="a", prefix_sep="_"