ENH: add MultiIndex.to_dataframe

closes #12397

Author: Jeff Reback <[email protected]>

Closes #15216 from jreback/to_dataframe and squashes the following commits:

b744fb5 [Jeff Reback] ENH: add MultiIndex.to_dataframe

Author: jreback

doc/source/api.rst

@@ -1460,6 +1460,7 @@ MultiIndex Components
    MultiIndex.set_levels
    MultiIndex.set_labels
    MultiIndex.to_hierarchical
+   MultiIndex.to_frame
    MultiIndex.is_lexsorted
    MultiIndex.droplevel
    MultiIndex.swaplevel

doc/source/whatsnew/v0.20.0.txt

@@ -131,7 +131,7 @@ Other enhancements
 - New ``UnsortedIndexError`` (subclass of ``KeyError``) raised when indexing/slicing into an
   unsorted MultiIndex (:issue:`11897`). This allows differentiation between errors due to lack
   of sorting or an incorrect key. See :ref:`here <advanced.unsorted>`
-
+- ``MultiIndex`` has gained a ``.to_frame()`` method to convert to a ``DataFrame`` (:issue:`12397`)
 - ``pd.cut`` and ``pd.qcut`` now support datetime64 and timedelta64 dtypes (:issue:`14714`, :issue:`14798`)
 - ``pd.qcut`` has gained the ``duplicates='raise'|'drop'`` option to control whether to raise on duplicated edges (:issue:`7751`)
 - ``Series`` provides a ``to_excel`` method to output Excel files (:issue:`8825`)

pandas/indexes/multi.py

@@ -827,6 +827,30 @@ def _to_safe_for_reshape(self):
         """ convert to object if we are a categorical """
         return self.set_levels([i._to_safe_for_reshape() for i in self.levels])
 
+    def to_frame(self, index=True):
+        """
+        Create a DataFrame with the columns the levels of the MultiIndex
+
+        .. versionadded:: 0.20.0
+
+        Parameters
+        ----------
+        index : boolean, default True
+            return this MultiIndex as the index
+
+        Returns
+        -------
+        DataFrame
+        """
+
+        from pandas import DataFrame
+        result = DataFrame({(name or level): self.get_level_values(level)
+                            for name, level in
+                            zip(self.names, range(len(self.levels)))})
+        if index:
+            result.index = self
+        return result
+
     def to_hierarchical(self, n_repeat, n_shuffle=1):
         """
         Return a MultiIndex reshaped to conform to the

pandas/tests/indexes/test_multi.py

@@ -1348,6 +1348,43 @@ def test_format_sparse_config(self):
 
         warnings.filters = warn_filters
 
+    def test_to_frame(self):
+        tuples = [(1, 'one'), (1, 'two'), (2, 'one'), (2, 'two')]
+
+        index = MultiIndex.from_tuples(tuples)
+        result = index.to_frame(index=False)
+        expected = DataFrame(tuples)
+        tm.assert_frame_equal(result, expected)
+
+        result = index.to_frame()
+        expected.index = index
+        tm.assert_frame_equal(result, expected)
+
+        tuples = [(1, 'one'), (1, 'two'), (2, 'one'), (2, 'two')]
+        index = MultiIndex.from_tuples(tuples, names=['first', 'second'])
+        result = index.to_frame(index=False)
+        expected = DataFrame(tuples)
+        expected.columns = ['first', 'second']
+        tm.assert_frame_equal(result, expected)
+
+        result = index.to_frame()
+        expected.index = index
+        tm.assert_frame_equal(result, expected)
+
+        index = MultiIndex.from_product([range(5),
+                                         pd.date_range('20130101', periods=3)])
+        result = index.to_frame(index=False)
+        expected = DataFrame(
+            {0: np.repeat(np.arange(5, dtype='int64'), 3),
+             1: np.tile(pd.date_range('20130101', periods=3), 5)})
+        tm.assert_frame_equal(result, expected)
+
+        index = MultiIndex.from_product([range(5),
+                                         pd.date_range('20130101', periods=3)])
+        result = index.to_frame()
+        expected.index = index
+        tm.assert_frame_equal(result, expected)
+
     def test_to_hierarchical(self):
         index = MultiIndex.from_tuples([(1, 'one'), (1, 'two'), (2, 'one'), (
             2, 'two')])