Allow None when nan_as_null=False in column constructor

python/cudf/cudf/core/column/column.py

@@ -1948,9 +1948,17 @@ def as_column(
                 raise TypeError(
                     f"Cannot convert a {inferred_dtype} of object type"
                 )
+            elif (
+                nan_as_null is False
+                and inferred_dtype in {"string"}
+                and pd.Series(arbitrary)
+                .apply(lambda x: isinstance(x, float) and np.isnan(x))
+                .any()
+            ):
+                raise MixedTypeError(f"Cannot have NaN with {inferred_dtype}")
             elif nan_as_null is False and (
                 pd.isna(arbitrary).any()
-                and inferred_dtype not in ("decimal", "empty")
+                and inferred_dtype not in ("decimal", "empty", "string")
             ):
                 # Decimal can hold float("nan")
                 # All np.nan is not restricted by type

python/cudf/cudf/tests/test_dataframe.py

@@ -4008,44 +4008,28 @@ def test_diff(dtype, period, data_empty):
 
 @pytest.mark.parametrize("df", _dataframe_na_data())
 @pytest.mark.parametrize("nan_as_null", [True, False, None])
-def test_dataframe_isnull_isna(df, nan_as_null):
-    if nan_as_null is False and (
-        df.select_dtypes(object).isna().any().any()
-        and not df.select_dtypes(object).isna().all().all()
-    ):
-        with pytest.raises(MixedTypeError):
-            cudf.DataFrame.from_pandas(df, nan_as_null=nan_as_null)
-    else:
-        gdf = cudf.DataFrame.from_pandas(df, nan_as_null=nan_as_null)
+@pytest.mark.parametrize("api_call", ["isnull", "isna", "notna", "notnull"])
+def test_dataframe_isnull_isna_and_reverse(df, nan_as_null, api_call):
+    def detect_nan(x):
+        # Check if the input is a float and if it is nan
+        return x.apply(lambda v: isinstance(v, float) and np.isnan(v))
 
-        assert_eq(df.isnull(), gdf.isnull())
-        assert_eq(df.isna(), gdf.isna())
-
-        # Test individual columns
-        for col in df:
-            assert_eq(df[col].isnull(), gdf[col].isnull())
-            assert_eq(df[col].isna(), gdf[col].isna())
-
-
-@pytest.mark.parametrize("df", _dataframe_na_data())
-@pytest.mark.parametrize("nan_as_null", [True, False, None])
-def test_dataframe_notna_notnull(df, nan_as_null):
+    nan_contains = df.select_dtypes(object).apply(detect_nan)
     if nan_as_null is False and (
-        df.select_dtypes(object).isna().any().any()
-        and not df.select_dtypes(object).isna().all().all()
+        nan_contains.any().any() and not nan_contains.all().all()
     ):
         with pytest.raises(MixedTypeError):
             cudf.DataFrame.from_pandas(df, nan_as_null=nan_as_null)
     else:
         gdf = cudf.DataFrame.from_pandas(df, nan_as_null=nan_as_null)
 
-        assert_eq(df.notnull(), gdf.notnull())
-        assert_eq(df.notna(), gdf.notna())
+        assert_eq(getattr(df, api_call)(), getattr(gdf, api_call)())
 
         # Test individual columns
         for col in df:
-            assert_eq(df[col].notnull(), gdf[col].notnull())
-            assert_eq(df[col].notna(), gdf[col].notna())
+            assert_eq(
+                getattr(df[col], api_call)(), getattr(gdf[col], api_call)()
+            )
 
 
 def test_ndim():

python/cudf/cudf/tests/test_series.py

@@ -774,8 +774,9 @@ def test_round_nan_as_null_false(series, decimal):
 @pytest.mark.parametrize("ps", _series_na_data())
 @pytest.mark.parametrize("nan_as_null", [True, False, None])
 def test_series_isnull_isna(ps, nan_as_null):
+    nan_contains = ps.apply(lambda x: isinstance(x, float) and np.isnan(x))
     if nan_as_null is False and (
-        ps.isna().any() and not ps.isna().all() and ps.dtype == object
+        nan_contains.any() and not nan_contains.all() and ps.dtype == object
     ):
         with pytest.raises(MixedTypeError):
             cudf.Series.from_pandas(ps, nan_as_null=nan_as_null)
@@ -789,8 +790,9 @@ def test_series_isnull_isna(ps, nan_as_null):
 @pytest.mark.parametrize("ps", _series_na_data())
 @pytest.mark.parametrize("nan_as_null", [True, False, None])
 def test_series_notnull_notna(ps, nan_as_null):
+    nan_contains = ps.apply(lambda x: isinstance(x, float) and np.isnan(x))
     if nan_as_null is False and (
-        ps.isna().any() and not ps.isna().all() and ps.dtype == object
+        nan_contains.any() and not nan_contains.all() and ps.dtype == object
     ):
         with pytest.raises(MixedTypeError):
             cudf.Series.from_pandas(ps, nan_as_null=nan_as_null)