ENH: Add na_value argument to DataFrame.to_numpy

doc/source/whatsnew/v1.1.0.rst

@@ -149,7 +149,7 @@ Other enhancements
   such as ``dict`` and ``list``, mirroring the behavior of :meth:`DataFrame.update` (:issue:`33215`)
 - :meth:`~pandas.core.groupby.GroupBy.transform` and :meth:`~pandas.core.groupby.GroupBy.aggregate` has gained ``engine`` and ``engine_kwargs`` arguments that supports executing functions with ``Numba`` (:issue:`32854`, :issue:`33388`)
 - :meth:`~pandas.core.resample.Resampler.interpolate` now supports SciPy interpolation method :class:`scipy.interpolate.CubicSpline` as method ``cubicspline`` (:issue:`33670`)
--
+- :meth:`DataFrame.to_numpy` now supports the ``na_value`` keyword to control the NA sentinel in the output array (:issue:`33820`)
 
 .. ---------------------------------------------------------------------------
 

pandas/core/frame.py

@@ -1284,7 +1284,9 @@ def from_dict(cls, data, orient="columns", dtype=None, columns=None) -> "DataFra
 
         return cls(data, index=index, columns=columns, dtype=dtype)
 
-    def to_numpy(self, dtype=None, copy: bool = False) -> np.ndarray:
+    def to_numpy(
+        self, dtype=None, copy: bool = False, na_value=lib.no_default, **kwargs
+    ) -> np.ndarray:
         """
         Convert the DataFrame to a NumPy array.
 
@@ -1305,6 +1307,11 @@ def to_numpy(self, dtype=None, copy: bool = False) -> np.ndarray:
             another array. Note that ``copy=False`` does not *ensure* that
             ``to_numpy()`` is no-copy. Rather, ``copy=True`` ensure that
             a copy is made, even if not strictly necessary.
+        na_value : Any, optional
+            The value to use for missing values. The default value depends
+            on `dtype` and the type of the array.
+
+            .. versionadded:: 1.1.0
 
         Returns
         -------
@@ -1336,7 +1343,12 @@ def to_numpy(self, dtype=None, copy: bool = False) -> np.ndarray:
         array([[1, 3.0, Timestamp('2000-01-01 00:00:00')],
                [2, 4.5, Timestamp('2000-01-02 00:00:00')]], dtype=object)
         """
-        result = np.array(self.values, dtype=dtype, copy=copy)
+        arr = [
+            self[c].to_numpy(dtype=dtype, na_value=na_value, **kwargs)
+            for c in self.columns
+        ]
+        result = np.array(arr).T
+
         return result
 
     def to_dict(self, orient="dict", into=dict):

pandas/tests/base/test_conversion.py

@@ -407,3 +407,22 @@ def test_to_numpy_kwargs_raises():
     s = pd.Series([1, 2, 3], dtype="Int64")
     with pytest.raises(TypeError, match=msg):
         s.to_numpy(foo=True)
+
+
+@pytest.mark.parametrize(
+    "data",
+    [
+        {"a": [1, 2, 3], "b": [1, 2, None]},
+        {"a": np.array([1, 2, 3]), "b": np.array([1, 2, np.nan])},
+        {"a": pd.array([1, 2, 3]), "b": pd.array([1, 2, None])},
+    ],
+)
+@pytest.mark.parametrize(
+    "dtype, na_value", [(float, np.nan), (object, None), (object, pd.NA)]
+)
+def test_to_numpy_dataframe_na_value(data, dtype, na_value):
+    # https://github.com/pandas-dev/pandas/issues/33820
+    df = pd.DataFrame(data)
+    result = df.to_numpy(dtype=dtype, na_value=na_value)
+    expected = np.array([[1, 1], [2, 2], [3, na_value]], dtype=dtype)
+    tm.assert_numpy_array_equal(result, expected)