ENH: Add allow_duplicates to MultiIndex.to_frame (#45318)

Author: johnzangwill

doc/source/whatsnew/v1.5.0.rst

@@ -31,6 +31,7 @@ enhancement2
 
 Other enhancements
 ^^^^^^^^^^^^^^^^^^
+- :meth:`MultiIndex.to_frame` now supports the argument ``allow_duplicates`` and raises on duplicate labels if it is missing or False (:issue:`45245`)
 - :class:`StringArray` now accepts array-likes containing nan-likes (``None``, ``np.nan``) for the ``values`` parameter in its constructor in addition to strings and :attr:`pandas.NA`. (:issue:`40839`)
 - Improved the rendering of ``categories`` in :class:`CategoricalIndex` (:issue:`45218`)
 - :meth:`to_numeric` now preserves float64 arrays when downcasting would generate values not representable in float32 (:issue:`43693`)

pandas/core/indexes/base.py

@@ -1354,6 +1354,18 @@ def _format_attrs(self) -> list[tuple[str_t, str_t | int | bool | None]]:
             attrs.append(("length", len(self)))
         return attrs
 
+    @final
+    def _get_level_names(self) -> Hashable | Sequence[Hashable]:
+        """
+        Return a name or list of names with None replaced by the level number.
+        """
+        if self._is_multi:
+            return [
+                level if name is None else name for level, name in enumerate(self.names)
+            ]
+        else:
+            return 0 if self.name is None else self.name
+
     @final
     def _mpl_repr(self) -> np.ndarray:
         # how to represent ourselves to matplotlib
@@ -1640,7 +1652,7 @@ def to_frame(
             name = lib.no_default
 
         if name is lib.no_default:
-            name = self.name or 0
+            name = self._get_level_names()
         result = DataFrame({name: self._values.copy()})
 
         if index:

pandas/core/indexes/multi.py

@@ -1710,7 +1710,12 @@ def unique(self, level=None):
             level = self._get_level_number(level)
             return self._get_level_values(level=level, unique=True)
 
-    def to_frame(self, index: bool = True, name=lib.no_default) -> DataFrame:
+    def to_frame(
+        self,
+        index: bool = True,
+        name=lib.no_default,
+        allow_duplicates: bool = False,
+    ) -> DataFrame:
         """
         Create a DataFrame with the levels of the MultiIndex as columns.
 
@@ -1725,6 +1730,11 @@ def to_frame(self, index: bool = True, name=lib.no_default) -> DataFrame:
         name : list / sequence of str, optional
             The passed names should substitute index level names.
 
+        allow_duplicates : bool, optional default False
+            Allow duplicate column labels to be created.
+
+            .. versionadded:: 1.5.0
+
         Returns
         -------
         DataFrame : a DataFrame containing the original MultiIndex data.
@@ -1783,16 +1793,19 @@ def to_frame(self, index: bool = True, name=lib.no_default) -> DataFrame:
                 )
             idx_names = name
         else:
-            idx_names = self.names
+            idx_names = self._get_level_names()
+
+        if not allow_duplicates and len(set(idx_names)) != len(idx_names):
+            raise ValueError(
+                "Cannot create duplicate column labels if allow_duplicates is False"
+            )
 
         # Guarantee resulting column order - PY36+ dict maintains insertion order
         result = DataFrame(
-            {
-                (level if lvlname is None else lvlname): self._get_level_values(level)
-                for lvlname, level in zip(idx_names, range(len(self.levels)))
-            },
+            {level: self._get_level_values(level) for level in range(len(self.levels))},
             copy=False,
         )
+        result.columns = idx_names
 
         if index:
             result.index = self

pandas/tests/indexes/multi/test_conversion.py

@@ -126,6 +126,28 @@ def test_to_frame_resulting_column_order():
     assert result == expected
 
 
+def test_to_frame_duplicate_labels():
+    # GH 45245
+    data = [(1, 2), (3, 4)]
+    names = ["a", "a"]
+    index = MultiIndex.from_tuples(data, names=names)
+    with pytest.raises(ValueError, match="Cannot create duplicate column labels"):
+        index.to_frame()
+
+    result = index.to_frame(allow_duplicates=True)
+    expected = DataFrame(data, index=index, columns=names)
+    tm.assert_frame_equal(result, expected)
+
+    names = [None, 0]
+    index = MultiIndex.from_tuples(data, names=names)
+    with pytest.raises(ValueError, match="Cannot create duplicate column labels"):
+        index.to_frame()
+
+    result = index.to_frame(allow_duplicates=True)
+    expected = DataFrame(data, index=index, columns=[0, 0])
+    tm.assert_frame_equal(result, expected)
+
+
 def test_to_flat_index(idx):
     expected = pd.Index(
         (