Create objects from iterables that contain cudf.NA

python/cudf/cudf/core/scalar.py

@@ -3,6 +3,7 @@
 
 import numpy as np
 import pyarrow as pa
+from pandas._libs.missing import NAType as pd_NAType
 
 from cudf._lib.scalar import DeviceScalar, _is_null_host_scalar
 from cudf.core.column.column import ColumnBase
@@ -354,15 +355,11 @@ def astype(self, dtype):
         return Scalar(self.value, dtype)
 
 
-class _NAType(object):
-    def __init__(self):
-        pass
-
-    def __repr__(self):
-        return "<NA>"
-
-    def __bool__(self):
-        raise TypeError("boolean value of cudf.NA is ambiguous")
+class _NAType(pd_NAType):
+    # Pandas NAType enforces a single instance exists at a time
+    # instantiating this class will yield the existing instance
+    # of pandas._libs.missing.NAType, id(cudf.NA) == id(pd.NA).
+    pass
 
 
 NA = _NAType()

python/cudf/cudf/tests/test_categorical.py

@@ -9,7 +9,7 @@
 
 import cudf
 from cudf.core._compat import PANDAS_GE_110
-from cudf.tests.utils import assert_eq, assert_exceptions_equal
+from cudf.tests.utils import NUMERIC_TYPES, assert_eq, assert_exceptions_equal
 
 
 @pytest.fixture
@@ -790,3 +790,17 @@ def test_categorical_setitem_with_nan():
         [1, np.nan, np.nan, np.nan, np.nan, None], nan_as_null=False
     ).astype(gs.dtype)
     assert_eq(gs, expected_series)
+
+
+@pytest.mark.parametrize("dtype", list(NUMERIC_TYPES) + ["object"])
+@pytest.mark.parametrize("input_obj", [[1, cudf.NA, 3]])
+def test_series_construction_with_nulls(input_obj, dtype):
+    dtype = np.dtype(dtype)
+    input_obj = [
+        dtype.type(v) if v is not cudf.NA else cudf.NA for v in input_obj
+    ]
+
+    expect = pd.Series(input_obj, dtype="category")
+    got = cudf.Series(input_obj, dtype="category").to_pandas()
+
+    assert_eq(expect, got)

python/cudf/cudf/tests/test_decimal.py

@@ -1,5 +1,6 @@
 # Copyright (c) 2021, NVIDIA CORPORATION.
 
+import decimal
 from decimal import Decimal
 
 import numpy as np
@@ -286,3 +287,13 @@ def test_series_setitem_decimal(args):
         expect = _decimal_series(expect, dtype)
         data[to] = item
         assert_eq(data, expect)
+
+
+@pytest.mark.parametrize(
+    "input_obj", [[decimal.Decimal(1), cudf.NA, decimal.Decimal(3)]]
+)
+def test_series_construction_with_nulls(input_obj):
+    expect = pa.array(input_obj, from_pandas=True)
+    got = cudf.Series(input_obj).to_arrow()
+
+    assert expect == got

python/cudf/cudf/tests/test_list.py

@@ -350,3 +350,13 @@ def test_list_getitem(indata, expect):
     list_sr = cudf.Series([indata])
     # __getitem__ shall fill None with cudf.NA
     assert list_sr[0] == expect
+
+
+@pytest.mark.parametrize(
+    "input_obj", [[[1, cudf.NA, 3]], [[1, cudf.NA, 3], [4, 5, cudf.NA]]]
+)
+def test_construction_series_with_nulls(input_obj):
+    expect = pa.array(input_obj, from_pandas=True)
+    got = cudf.Series(input_obj).to_arrow()
+
+    assert expect == got

python/cudf/cudf/tests/test_numerical.py

@@ -6,7 +6,8 @@
 
 import cudf
 from cudf.core._compat import PANDAS_GE_100
-from cudf.tests.utils import assert_eq
+from cudf.tests.utils import NUMERIC_TYPES, assert_eq
+from cudf.utils.dtypes import cudf_dtypes_to_pandas_dtypes
 
 
 def test_can_cast_safely_same_kind():
@@ -384,3 +385,24 @@ def test_to_numeric_error(data, errors):
         got = cudf.to_numeric(data, errors=errors)
 
         assert_eq(expect, got)
+
+
+@pytest.mark.parametrize("dtype", NUMERIC_TYPES)
+@pytest.mark.parametrize("input_obj", [[1, cudf.NA, 3]])
+def test_series_construction_with_nulls(dtype, input_obj):
+    dtype = np.dtype(dtype)
+    # numpy case
+
+    expect = pd.Series(input_obj, dtype=cudf_dtypes_to_pandas_dtypes[dtype])
+    got = cudf.Series(input_obj, dtype=dtype).to_pandas(nullable=True)
+
+    assert_eq(expect, got)
+
+    # Test numpy array of objects case
+    np_data = np.array(
+        [dtype.type(v) if v is not cudf.NA else cudf.NA for v in input_obj]
+    )
+
+    expect = pd.Series(input_obj, dtype=cudf_dtypes_to_pandas_dtypes[dtype])
+    got = cudf.Series(input_obj, dtype=dtype).to_pandas(nullable=True)
+    assert_eq(expect, got)

python/cudf/cudf/tests/test_scalar.py

@@ -329,11 +329,7 @@ def test_scalar_invalid_implicit_conversion(cls, dtype):
     try:
         cls(pd.NA)
     except TypeError as e:
-
-        error = (
-            str(e).replace("NAType", "_NAType").replace(" NA ", " cudf.NA ")
-        )
-        with pytest.raises(TypeError, match=re.escape(str(error))):
+        with pytest.raises(TypeError, match=re.escape(str(e))):
             slr = pycudf_scalar(None, dtype=dtype)
             cls(slr)
 

python/cudf/cudf/tests/test_struct.py

@@ -1,6 +1,7 @@
 # Copyright (c) 2020, NVIDIA CORPORATION.
 
 import pandas as pd
+import pyarrow as pa
 import pytest
 
 import cudf
@@ -44,3 +45,11 @@ def test_struct_for_field(key, expect):
     expect = cudf.Series(expect)
     got = sr.struct.field(key)
     assert_eq(expect, got)
+
+
+@pytest.mark.parametrize("input_obj", [[{"a": 1, "b": cudf.NA, "c": 3}]])
+def test_series_construction_with_nulls(input_obj):
+    expect = pa.array(input_obj, from_pandas=True)
+    got = cudf.Series(input_obj).to_arrow()
+
+    assert expect == got