ENH: Add na_position support to midx.sort_values (#51651)

Author: phofl

doc/source/whatsnew/v2.1.0.rst

@@ -28,6 +28,7 @@ enhancement2
 
 Other enhancements
 ^^^^^^^^^^^^^^^^^^
+- :meth:`MultiIndex.sort_values` now supports ``na_position`` (:issue:`51612`)
 - :meth:`MultiIndex.sortlevel` and :meth:`Index.sortlevel` gained a new keyword ``na_position`` (:issue:`51612`)
 - Improve error message when setting :class:`DataFrame` with wrong number of columns through :meth:`DataFrame.isetitem` (:issue:`51701`)
 - Let :meth:`DataFrame.to_feather` accept a non-default :class:`Index` and non-string column names (:issue:`51787`)

pandas/core/indexes/base.py

@@ -5600,7 +5600,7 @@ def sort_values(
  items=idx, ascending=ascending, na_position=na_position, key=key
  )
  else:
- _as = idx.argsort()
+ _as = idx.argsort(na_position=na_position)
  if not ascending:
  _as = _as[::-1]
 

pandas/core/indexes/multi.py

@@ -2132,11 +2132,15 @@ def append(self, other):
  except (TypeError, IndexError):
  return Index(new_tuples)
 
- def argsort(self, *args, **kwargs) -> npt.NDArray[np.intp]:
+ def argsort(
+ self, *args, na_position: str = "last", **kwargs
+ ) -> npt.NDArray[np.intp]:
  if len(args) == 0 and len(kwargs) == 0:
  # lexsort is significantly faster than self._values.argsort()
  target = self._sort_levels_monotonic(raise_if_incomparable=True)
- return lexsort_indexer(target._get_codes_for_sorting())
+ return lexsort_indexer(
+ target._get_codes_for_sorting(), na_position=na_position
+ )
  return self._values.argsort(*args, **kwargs)
 
  @Appender(_index_shared_docs["repeat"] % _index_doc_kwargs)

pandas/tests/indexes/multi/test_sorting.py

@@ -14,6 +14,7 @@
  Index,
  MultiIndex,
  RangeIndex,
+ Series,
  Timestamp,
 )
 import pandas._testing as tm
@@ -311,3 +312,27 @@ def test_sort_values_incomparable():
  match = "'<' not supported between instances of 'Timestamp' and 'int'"
  with pytest.raises(TypeError, match=match):
  mi.sort_values()
+
+
+@pytest.mark.parametrize("na_position", ["first", "last"])
+@pytest.mark.parametrize("dtype", ["float64", "Int64", "Float64"])
+def test_sort_values_with_na_na_position(dtype, na_position):
+ # 51612
+ arrays = [
+ Series([1, 1, 2], dtype=dtype),
+ Series([1, None, 3], dtype=dtype),
+ ]
+ index = MultiIndex.from_arrays(arrays)
+ result = index.sort_values(na_position=na_position)
+ if na_position == "first":
+ arrays = [
+ Series([1, 1, 2], dtype=dtype),
+ Series([None, 1, 3], dtype=dtype),
+ ]
+ else:
+ arrays = [
+ Series([1, 1, 2], dtype=dtype),
+ Series([1, None, 3], dtype=dtype),
+ ]
+ expected = MultiIndex.from_arrays(arrays)
+ tm.assert_index_equal(result, expected)