Add to_flat_index method to MultiIndex

doc/source/api.rst

@@ -1724,6 +1724,7 @@ MultiIndex Components
    MultiIndex.set_levels
    MultiIndex.set_labels
    MultiIndex.to_hierarchical
+   MultiIndex.to_flat_index
    MultiIndex.to_frame
    MultiIndex.is_lexsorted
    MultiIndex.sortlevel

doc/source/whatsnew/v0.24.0.txt

@@ -238,6 +238,7 @@ Other Enhancements
 - :func:`~DataFrame.to_parquet` now supports writing a ``DataFrame`` as a directory of parquet files partitioned by a subset of the columns when ``engine = 'pyarrow'`` (:issue:`23283`)
 - :meth:`Timestamp.tz_localize`, :meth:`DatetimeIndex.tz_localize`, and :meth:`Series.tz_localize` have gained the ``nonexistent`` argument for alternative handling of nonexistent times. See :ref:`timeseries.timezone_nonexistent` (:issue:`8917`)
 - :meth:`read_excel()` now accepts ``usecols`` as a list of column names or callable (:issue:`18273`)
+- :meth:`MultiIndex.to_flat_index` has been added to flatten multiple levels into a single-level :class:`Index` object.
 
 .. _whatsnew_0240.api_breaking:
 

pandas/core/indexes/base.py

@@ -1113,6 +1113,26 @@ def _format_attrs(self):
         """
         return format_object_attrs(self)
 
+    def to_flat_index(self):
+        """
+        Identity method.
+
+        .. versionadded:: 0.24.0
+
+        This is implemented for compatability with subclass implementations
+        when chaining.
+
+        Returns
+        -------
+        pd.Index
+            Caller.
+
+        See Also
+        --------
+        MultiIndex.to_flat_index : Subclass implementation.
+        """
+        return self
+
     def to_series(self, index=None, name=None):
         """
         Create a Series with both index and values equal to the index keys

pandas/core/indexes/multi.py

@@ -193,6 +193,7 @@ class MultiIndex(Index):
     set_levels
     set_labels
     to_frame
+    to_flat_index
     is_lexsorted
     sortlevel
     droplevel
@@ -1246,6 +1247,34 @@ def to_hierarchical(self, n_repeat, n_shuffle=1):
                       FutureWarning, stacklevel=2)
         return MultiIndex(levels=levels, labels=labels, names=names)
 
+    def to_flat_index(self):
+        """
+        Convert a MultiIndex to an Index of Tuples containing the level values.
+
+        .. versionadded:: 0.24.0
+
+        Returns
+        -------
+        pd.Index
+            Index with the MultiIndex data represented in Tuples.
+
+        Notes
+        -----
+        This method will simply return the caller if called by anything other
+        than a MultiIndex.
+
+        Examples
+        --------
+        >>> index = pd.MultiIndex.from_product(
+        ...     [['foo', 'bar'], ['baz', 'qux']],
+        ...     names=['a', 'b'])
+        >>> index.to_flat_index()
+        Index([('foo', 'baz'), ('foo', 'qux'),
+               ('bar', 'baz'), ('bar', 'qux')],
+              dtype='object')
+        """
+        return Index(self.values, tupleize_cols=False)
+
     @property
     def is_all_dates(self):
         return False

pandas/tests/indexes/multi/test_conversion.py

@@ -170,3 +170,11 @@ def test_to_series_with_arguments(idx):
     assert s.values is not idx.values
     assert s.index is not idx
     assert s.name != idx.name
+
+
+def test_to_flat_index(idx):
+    expected = pd.Index((('foo', 'one'), ('foo', 'two'), ('bar', 'one'),
+                         ('baz', 'two'), ('qux', 'one'), ('qux', 'two')),
+                        tupleize_cols=False)
+    result = idx.to_flat_index()
+    tm.assert_index_equal(result, expected)

pandas/tests/indexes/test_base.py

@@ -2266,6 +2266,14 @@ def test_tab_complete_warning(self, ip):
             with provisionalcompleter('ignore'):
                 list(ip.Completer.completions('idx.', 4))
 
+    def test_to_flat_index(self, indices):
+        # 22866
+        if isinstance(indices, MultiIndex):
+            pytest.skip("Separate expectation for MultiIndex")
+
+        result = indices.to_flat_index()
+        tm.assert_index_equal(result, indices)
+
 
 class TestMixedIntIndex(Base):
     # Mostly the tests from common.py for which the results differ