DEPR MultiIndex.is_lexsorted and MultiIndex.lexsort_depth

doc/source/user_guide/advanced.rst

@@ -658,20 +658,18 @@ Furthermore, if you try to index something that is not fully lexsorted, this can
     In [5]: dfm.loc[(0, 'y'):(1, 'z')]
     UnsortedIndexError: 'Key length (2) was greater than MultiIndex lexsort depth (1)'
 
-The :meth:`~MultiIndex.is_lexsorted` method on a ``MultiIndex`` shows if the
-index is sorted, and the ``lexsort_depth`` property returns the sort depth:
+The :meth:`~MultiIndex.is_monotonic_increasing` method on a ``MultiIndex`` shows if the
+index is sorted:
 
 .. ipython:: python
 
-   dfm.index.is_lexsorted()
-   dfm.index.lexsort_depth
+   dfm.index.is_monotonic_increasing()
 
 .. ipython:: python
 
    dfm = dfm.sort_index()
    dfm
-   dfm.index.is_lexsorted()
-   dfm.index.lexsort_depth
+   dfm.index.is_monotonic_increasing()
 
 And now selection works as expected.
 

doc/source/whatsnew/v1.3.0.rst

@@ -149,7 +149,7 @@ Deprecations
 - Deprecating allowing scalars passed to the :class:`Categorical` constructor (:issue:`38433`)
 - Deprecated allowing subclass-specific keyword arguments in the :class:`Index` constructor, use the specific subclass directly instead (:issue:`14093`,:issue:`21311`,:issue:`22315`,:issue:`26974`)
 - Deprecated ``astype`` of datetimelike (``timedelta64[ns]``, ``datetime64[ns]``, ``Datetime64TZDtype``, ``PeriodDtype``) to integer dtypes, use ``values.view(...)`` instead (:issue:`38544`)
--
+- Deprecated :meth:`MultiIndex.is_lexsorted` as a public method, users should use :meth:`MultiIndex.is_monotonic_increasing` instead (:issue:`32259`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/core/indexes/multi.py

@@ -1809,6 +1809,15 @@ def _is_all_dates(self) -> bool:
         return False
 
     def is_lexsorted(self) -> bool:
+        warnings.warn(
+            "MultiIndex.is_lexsorted is deprecated as a public function, "
+            "users should use MultiIndex.is_monotonic_increasing instead.",
+            FutureWarning,
+            stacklevel=2,
+        )
+        return self._is_lexsorted()
+
+    def _is_lexsorted(self) -> bool:
         """
         Return True if the codes are lexicographically sorted.
 
@@ -1821,29 +1830,39 @@ def is_lexsorted(self) -> bool:
         In the below examples, the first level of the MultiIndex is sorted because
         a<b<c, so there is no need to look at the next level.
 
-        >>> pd.MultiIndex.from_arrays([['a', 'b', 'c'], ['d', 'e', 'f']]).is_lexsorted()
+        >>> pd.MultiIndex.from_arrays([['a', 'b'], ['d', 'e']])._is_lexsorted()
         True
-        >>> pd.MultiIndex.from_arrays([['a', 'b', 'c'], ['d', 'f', 'e']]).is_lexsorted()
+        >>> pd.MultiIndex.from_arrays([['a', 'b'], ['d', 'f']])._is_lexsorted()
         True
 
         In case there is a tie, the lexicographical sorting looks
         at the next level of the MultiIndex.
 
-        >>> pd.MultiIndex.from_arrays([[0, 1, 1], ['a', 'b', 'c']]).is_lexsorted()
+        >>> pd.MultiIndex.from_arrays([[0, 1, 1], ['a', 'b', 'c']])._is_lexsorted()
         True
-        >>> pd.MultiIndex.from_arrays([[0, 1, 1], ['a', 'c', 'b']]).is_lexsorted()
+        >>> pd.MultiIndex.from_arrays([[0, 1, 1], ['a', 'c', 'b']])._is_lexsorted()
         False
         >>> pd.MultiIndex.from_arrays([['a', 'a', 'b', 'b'],
-        ...                            ['aa', 'bb', 'aa', 'bb']]).is_lexsorted()
+        ...                            ['aa', 'bb', 'aa', 'bb']])._is_lexsorted()
         True
         >>> pd.MultiIndex.from_arrays([['a', 'a', 'b', 'b'],
-        ...                            ['bb', 'aa', 'aa', 'bb']]).is_lexsorted()
+        ...                            ['bb', 'aa', 'aa', 'bb']])._is_lexsorted()
         False
         """
-        return self.lexsort_depth == self.nlevels
+        return self._get_lexsort_depth == self.nlevels
 
-    @cache_readonly
     def lexsort_depth(self):
+        warnings.warn(
+            "MultiIndex.lexsort_depth is deprecated as a public function, "
+            "users should use MultiIndex.is_monotonic_increasing to check "
+            "is a MultiIndex is sorted.",
+            FutureWarning,
+            stacklevel=2,
+        )
+        return self._get_lexsort_depth()
+
+    @cache_readonly
+    def _get_lexsort_depth(self):
         if self.sortorder is not None:
             return self.sortorder
 
@@ -1898,7 +1917,7 @@ def _sort_levels_monotonic(self):
                     ('b', 'bb')],
                    )
         """
-        if self.is_lexsorted() and self.is_monotonic:
+        if self._is_lexsorted() and self.is_monotonic:
             return self
 
         new_levels = []
@@ -2181,7 +2200,7 @@ def drop(self, codes, level=None, errors="raise"):
                     step = loc.step if loc.step is not None else 1
                     inds.extend(range(loc.start, loc.stop, step))
                 elif com.is_bool_indexer(loc):
-                    if self.lexsort_depth == 0:
+                    if self._get_lexsort_depth == 0:
                         warnings.warn(
                             "dropping on a non-lexsorted multi-index "
                             "without a level parameter may impact performance.",
@@ -2752,10 +2771,10 @@ def slice_locs(self, start=None, end=None, step=None, kind=None):
         return super().slice_locs(start, end, step, kind=kind)
 
     def _partial_tup_index(self, tup, side="left"):
-        if len(tup) > self.lexsort_depth:
+        if len(tup) > self._get_lexsort_depth:
             raise UnsortedIndexError(
                 f"Key length ({len(tup)}) was greater than MultiIndex lexsort depth "
-                f"({self.lexsort_depth})"
+                f"({self._get_lexsort_depth})"
             )
 
         n = len(tup)
@@ -2894,7 +2913,7 @@ def _maybe_to_slice(loc):
         # break the key into 2 parts based on the lexsort_depth of the index;
         # the first part returns a continuous slice of the index; the 2nd part
         # needs linear search within the slice
-        i = self.lexsort_depth
+        i = self._get_lexsort_depth
         lead_key, follow_key = key[:i], key[i:]
         start, stop = (
             self.slice_locs(lead_key, lead_key) if lead_key else (0, len(self))
@@ -3147,7 +3166,7 @@ def convert_indexer(start, stop, step, indexer=indexer, codes=level_codes):
                 stop = getattr(stop, "stop", stop)
                 return convert_indexer(start, stop, step)
 
-            elif level > 0 or self.lexsort_depth == 0 or step is not None:
+            elif level > 0 or self._get_lexsort_depth == 0 or step is not None:
                 # need to have like semantics here to right
                 # searching as when we are using a slice
                 # so include the stop+1 (so we include stop)
@@ -3162,7 +3181,7 @@ def convert_indexer(start, stop, step, indexer=indexer, codes=level_codes):
 
             idx = self._get_loc_single_level_index(level_index, key)
 
-            if level > 0 or self.lexsort_depth == 0:
+            if level > 0 or self._get_lexsort_depth == 0:
                 # Desired level is not sorted
                 locs = np.array(level_codes == idx, dtype=bool, copy=False)
                 if not locs.any():
@@ -3219,10 +3238,10 @@ def get_locs(self, seq):
 
         # must be lexsorted to at least as many levels
         true_slices = [i for (i, s) in enumerate(com.is_true_slices(seq)) if s]
-        if true_slices and true_slices[-1] >= self.lexsort_depth:
+        if true_slices and true_slices[-1] >= self._get_lexsort_depth:
             raise UnsortedIndexError(
                 "MultiIndex slicing requires the index to be lexsorted: slicing "
-                f"on levels {true_slices}, lexsort depth {self.lexsort_depth}"
+                f"on levels {true_slices}, lexsort depth {self._get_lexsort_depth}"
             )
         # indexer
         # this is the list of all values that we want to select
@@ -3344,7 +3363,7 @@ def _reorder_indexer(
         """
         # If the index is lexsorted and the list_like label in seq are sorted
         # then we do not need to sort
-        if self.is_lexsorted():
+        if self._is_lexsorted():
             need_sort = False
             for i, k in enumerate(seq):
                 if is_list_like(k):

pandas/core/reshape/reshape.py

@@ -617,7 +617,7 @@ def _convert_level_number(level_num, columns):
             roll_columns = roll_columns.swaplevel(lev1, lev2)
         this.columns = roll_columns
 
-    if not this.columns.is_lexsorted():
+    if not this.columns._is_lexsorted():
         # Workaround the edge case where 0 is one of the column names,
         # which interferes with trying to sort based on the first
         # level

pandas/tests/frame/methods/test_drop.py

@@ -162,7 +162,7 @@ def test_drop_multiindex_not_lexsorted(self):
             [("a", ""), ("b1", "c1"), ("b2", "c2")], names=["b", "c"]
         )
         lexsorted_df = DataFrame([[1, 3, 4]], columns=lexsorted_mi)
-        assert lexsorted_df.columns.is_lexsorted()
+        assert lexsorted_df.columns._is_lexsorted()
 
         # define the non-lexsorted version
         not_lexsorted_df = DataFrame(
@@ -172,7 +172,7 @@ def test_drop_multiindex_not_lexsorted(self):
             index="a", columns=["b", "c"], values="d"
         )
         not_lexsorted_df = not_lexsorted_df.reset_index()
-        assert not not_lexsorted_df.columns.is_lexsorted()
+        assert not not_lexsorted_df.columns._is_lexsorted()
 
         # compare the results
         tm.assert_frame_equal(lexsorted_df, not_lexsorted_df)

pandas/tests/frame/methods/test_sort_index.py

@@ -24,7 +24,7 @@ def test_sort_index_and_reconstruction_doc_example(self):
                 levels=[["a", "b"], ["bb", "aa"]], codes=[[0, 0, 1, 1], [0, 1, 0, 1]]
             ),
         )
-        assert df.index.is_lexsorted()
+        assert df.index._is_lexsorted()
         assert not df.index.is_monotonic
 
         # sort it
@@ -35,15 +35,15 @@ def test_sort_index_and_reconstruction_doc_example(self):
             ),
         )
         result = df.sort_index()
-        assert result.index.is_lexsorted()
+        assert result.index._is_lexsorted()
         assert result.index.is_monotonic
 
         tm.assert_frame_equal(result, expected)
 
         # reconstruct
         result = df.sort_index().copy()
         result.index = result.index._sort_levels_monotonic()
-        assert result.index.is_lexsorted()
+        assert result.index._is_lexsorted()
         assert result.index.is_monotonic
 
         tm.assert_frame_equal(result, expected)
@@ -524,14 +524,14 @@ def test_sort_index_and_reconstruction(self):
                 [(0.5, "a"), (0.5, "b"), (0.8, "a"), (0.8, "b")]
             ),
         )
-        assert expected.index.is_lexsorted()
+        assert expected.index._is_lexsorted()
 
         result = DataFrame(
             [[1, 1], [2, 2], [1, 1], [2, 2]],
             index=MultiIndex.from_product([[0.5, 0.8], list("ab")]),
         )
         result = result.sort_index()
-        assert result.index.is_lexsorted()
+        assert result.index._is_lexsorted()
         assert result.index.is_monotonic
 
         tm.assert_frame_equal(result, expected)
@@ -543,14 +543,14 @@ def test_sort_index_and_reconstruction(self):
             ),
         )
         result = result.sort_index()
-        assert result.index.is_lexsorted()
+        assert result.index._is_lexsorted()
 
         tm.assert_frame_equal(result, expected)
 
         concatted = pd.concat([df, df], keys=[0.8, 0.5])
         result = concatted.sort_index()
 
-        assert result.index.is_lexsorted()
+        assert result.index._is_lexsorted()
         assert result.index.is_monotonic
 
         tm.assert_frame_equal(result, expected)
@@ -567,13 +567,13 @@ def test_sort_index_and_reconstruction(self):
         df.columns = df.columns.set_levels(
             pd.to_datetime(df.columns.levels[1]), level=1
         )
-        assert not df.columns.is_lexsorted()
+        assert not df.columns._is_lexsorted()
         assert not df.columns.is_monotonic
         result = df.sort_index(axis=1)
-        assert result.columns.is_lexsorted()
+        assert result.columns._is_lexsorted()
         assert result.columns.is_monotonic
         result = df.sort_index(axis=1, level=1)
-        assert result.columns.is_lexsorted()
+        assert result.columns._is_lexsorted()
         assert result.columns.is_monotonic
 
     # TODO: better name, de-duplicate with test_sort_index_level above
@@ -614,7 +614,7 @@ def test_sort_index_level_large_cardinality(self):
 
         # it works!
         result = df.sort_index(level=0)
-        assert result.index.lexsort_depth == 3
+        assert result.index._get_lexsort_depth == 3
 
         # GH#2684 (int32)
         index = MultiIndex.from_arrays([np.arange(4000)] * 3)
@@ -623,7 +623,7 @@ def test_sort_index_level_large_cardinality(self):
         # it works!
         result = df.sort_index(level=0)
         assert (result.dtypes.values == df.dtypes.values).all()
-        assert result.index.lexsort_depth == 3
+        assert result.index._get_lexsort_depth == 3
 
     def test_sort_index_level_by_name(self):
         mi = MultiIndex(

pandas/tests/groupby/test_groupby.py

@@ -1571,7 +1571,7 @@ def test_groupby_multiindex_not_lexsorted():
         [("a", ""), ("b1", "c1"), ("b2", "c2")], names=["b", "c"]
     )
     lexsorted_df = DataFrame([[1, 3, 4]], columns=lexsorted_mi)
-    assert lexsorted_df.columns.is_lexsorted()
+    assert lexsorted_df.columns._is_lexsorted()
 
     # define the non-lexsorted version
     not_lexsorted_df = DataFrame(
@@ -1581,7 +1581,7 @@ def test_groupby_multiindex_not_lexsorted():
         index="a", columns=["b", "c"], values="d"
     )
     not_lexsorted_df = not_lexsorted_df.reset_index()
-    assert not not_lexsorted_df.columns.is_lexsorted()
+    assert not not_lexsorted_df.columns._is_lexsorted()
 
     # compare the results
     tm.assert_frame_equal(lexsorted_df, not_lexsorted_df)
@@ -1596,7 +1596,7 @@ def test_groupby_multiindex_not_lexsorted():
     df = DataFrame(
         {"x": ["a", "a", "b", "a"], "y": [1, 1, 2, 2], "z": [1, 2, 3, 4]}
     ).set_index(["x", "y"])
-    assert not df.index.is_lexsorted()
+    assert not df.index._is_lexsorted()
 
     for level in [0, 1, [0, 1]]:
         for sort in [False, True]:

pandas/tests/indexes/multi/test_drop.py

@@ -126,7 +126,7 @@ def test_drop_not_lexsorted():
     # define the lexsorted version of the multi-index
     tuples = [("a", ""), ("b1", "c1"), ("b2", "c2")]
     lexsorted_mi = MultiIndex.from_tuples(tuples, names=["b", "c"])
-    assert lexsorted_mi.is_lexsorted()
+    assert lexsorted_mi._is_lexsorted()
 
     # and the not-lexsorted version
     df = pd.DataFrame(
@@ -135,7 +135,7 @@ def test_drop_not_lexsorted():
     df = df.pivot_table(index="a", columns=["b", "c"], values="d")
     df = df.reset_index()
     not_lexsorted_mi = df.columns
-    assert not not_lexsorted_mi.is_lexsorted()
+    assert not not_lexsorted_mi._is_lexsorted()
 
     # compare the results
     tm.assert_index_equal(lexsorted_mi, not_lexsorted_mi)

pandas/tests/indexes/multi/test_lexsort.py

@@ -8,18 +8,18 @@ def test_is_lexsorted(self):
         index = MultiIndex(
             levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 1, 2]]
         )
-        assert index.is_lexsorted()
+        assert index._is_lexsorted()
 
         index = MultiIndex(
             levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 2, 1]]
         )
-        assert not index.is_lexsorted()
+        assert not index._is_lexsorted()
 
         index = MultiIndex(
             levels=levels, codes=[[0, 0, 1, 0, 1, 1], [0, 1, 0, 2, 2, 1]]
         )
-        assert not index.is_lexsorted()
-        assert index.lexsort_depth == 0
+        assert not index._is_lexsorted()
+        assert index._get_lexsort_depth == 0
 
 
 class TestLexsortDepth:
@@ -33,14 +33,14 @@ def test_lexsort_depth(self):
         index = MultiIndex(
             levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 1, 2]], sortorder=2
         )
-        assert index.lexsort_depth == 2
+        assert index._get_lexsort_depth == 2
 
         index = MultiIndex(
             levels=levels, codes=[[0, 0, 0, 1, 1, 1], [0, 1, 2, 0, 2, 1]], sortorder=1
         )
-        assert index.lexsort_depth == 1
+        assert index._get_lexsort_depth == 1
 
         index = MultiIndex(
             levels=levels, codes=[[0, 0, 1, 0, 1, 1], [0, 1, 0, 2, 2, 1]], sortorder=0
         )
-        assert index.lexsort_depth == 0
+        assert index._get_lexsort_depth == 0