BUG: ArrowExtensionArray.mode(dropna=False) not respecting NAs

doc/source/whatsnew/v2.0.0.rst

@@ -1229,6 +1229,7 @@ Numeric
 - Bug in DataFrame reduction methods (e.g. :meth:`DataFrame.sum`) with object dtype, ``axis=1`` and ``numeric_only=False`` would not be coerced to float (:issue:`49551`)
 - Bug in :meth:`DataFrame.sem` and :meth:`Series.sem` where an erroneous ``TypeError`` would always raise when using data backed by an :class:`ArrowDtype` (:issue:`49759`)
 - Bug in :meth:`Series.__add__` casting to object for list and masked :class:`Series` (:issue:`22962`)
+- Bug in :meth:`~arrays.ArrowExtensionArray.mode` where ``dropna=False`` was not respected when there was ``NA`` values (:issue:`50982`)
 - Bug in :meth:`DataFrame.query` with ``engine="numexpr"`` and column names are ``min`` or ``max`` would raise a ``TypeError`` (:issue:`50937`)
 
 Conversion

pandas/core/arrays/arrow/array.py

@@ -1345,7 +1345,6 @@ def _mode(self: ArrowExtensionArrayT, dropna: bool = True) -> ArrowExtensionArra
         ----------
         dropna : bool, default True
             Don't consider counts of NA values.
-            Not implemented by pyarrow.
 
         Returns
         -------
@@ -1364,12 +1363,13 @@ def _mode(self: ArrowExtensionArrayT, dropna: bool = True) -> ArrowExtensionArra
         else:
             data = self._data
 
-        modes = pc.mode(data, pc.count_distinct(data).as_py())
-        values = modes.field(0)
-        counts = modes.field(1)
-        # counts sorted descending i.e counts[0] = max
-        mask = pc.equal(counts, counts[0])
-        most_common = values.filter(mask)
+        if dropna:
+            data = data.drop_null()
+
+        res = pc.value_counts(data)
+        most_common = res.field("values").filter(
+            pc.equal(res.field("counts"), pc.max(res.field("counts")))
+        )
 
         if pa.types.is_temporal(pa_type):
             most_common = most_common.cast(pa_type)

pandas/tests/extension/test_arrow.py

@@ -1339,38 +1339,31 @@ def test_quantile(data, interpolation, quantile, request):
         tm.assert_series_equal(result, expected)
 
 
-@pytest.mark.parametrize("dropna", [True, False])
 @pytest.mark.parametrize(
     "take_idx, exp_idx",
-    [[[0, 0, 2, 2, 4, 4], [4, 0]], [[0, 0, 0, 2, 4, 4], [0]]],
+    [[[0, 0, 2, 2, 4, 4], [0, 4]], [[0, 0, 0, 2, 4, 4], [0]]],
     ids=["multi_mode", "single_mode"],
 )
-def test_mode(data_for_grouping, dropna, take_idx, exp_idx, request):
-    pa_dtype = data_for_grouping.dtype.pyarrow_dtype
-    if pa.types.is_string(pa_dtype) or pa.types.is_binary(pa_dtype):
-        request.node.add_marker(
-            pytest.mark.xfail(
-                raises=pa.ArrowNotImplementedError,
-                reason=f"mode not supported by pyarrow for {pa_dtype}",
-            )
-        )
-    elif (
-        pa.types.is_boolean(pa_dtype)
-        and "multi_mode" in request.node.nodeid
-        and pa_version_under9p0
-    ):
-        request.node.add_marker(
-            pytest.mark.xfail(
-                reason="https://issues.apache.org/jira/browse/ARROW-17096",
-            )
-        )
+def test_mode_dropna_true(data_for_grouping, take_idx, exp_idx):
     data = data_for_grouping.take(take_idx)
     ser = pd.Series(data)
-    result = ser.mode(dropna=dropna)
+    result = ser.mode(dropna=True)
     expected = pd.Series(data_for_grouping.take(exp_idx))
     tm.assert_series_equal(result, expected)
 
 
+def test_mode_dropna_false_mode_na(data):
+    # GH 50982
+    more_nans = pd.Series([None, None, data[0]], dtype=data.dtype)
+    result = more_nans.mode(dropna=False)
+    expected = pd.Series([None], dtype=data.dtype)
+    tm.assert_series_equal(result, expected)
+
+    expected = pd.Series([None, data[0]], dtype=data.dtype)
+    result = expected.mode(dropna=False)
+    tm.assert_series_equal(result, expected)
+
+
 def test_is_bool_dtype():
     # GH 22667
     data = ArrowExtensionArray(pa.array([True, False, True]))