Revert "Implement symmetric_difference of Index & MultiIndex (#953)"

This reverts commit 5c59a82.

Author: HyukjinKwon

databricks/koalas/indexes.py

@@ -36,7 +36,6 @@
 from databricks.koalas.internal import _InternalFrame
 from databricks.koalas.missing.indexes import _MissingPandasLikeIndex, _MissingPandasLikeMultiIndex
 from databricks.koalas.series import Series
-from databricks.koalas.internal import _InternalFrame
 from databricks.koalas.utils import name_like_string
 
 
@@ -465,70 +464,6 @@ def copy(self, name=None):
             result.name = name
         return result
 
-    def symmetric_difference(self, other, result_name=None, sort=None):
-        """
-        Compute the symmetric difference of two Index objects.
-
-        Parameters
-        ----------
-        other : Index or array-like
-        result_name : str
-        sort : True or None, default None
-            Whether to sort the resulting index.
-            * True : Attempt to sort the result.
-            * None : Do not sort the result.
-
-        Returns
-        -------
-        symmetric_difference : Index
-
-        Notes
-        -----
-        ``symmetric_difference`` contains elements that appear in either
-        ``idx1`` or ``idx2`` but not both. Equivalent to the Index created by
-        ``idx1.difference(idx2) | idx2.difference(idx1)`` with duplicates
-        dropped.
-
-        Examples
-        --------
-        >>> s1 = ks.Series([1, 2, 3, 4], index=[1, 2, 3, 4])
-        >>> s2 = ks.Series([1, 2, 3, 4], index=[2, 3, 4, 5])
-
-        >>> s1.index.symmetric_difference(s2.index)
-        Int64Index([5, 1], dtype='int64')
-
-        You can set name of result Index.
-
-        >>> s1.index.symmetric_difference(s2.index, result_name='koalas')
-        Int64Index([5, 1], dtype='int64', name='koalas')
-
-        You can set sort to `True`, if you want to sort the resulting index.
-
-        >>> s1.index.symmetric_difference(s2.index, sort=True)
-        Int64Index([1, 5], dtype='int64')
-
-        You can also use the ``^`` operator:
-
-        >>> s1.index ^ s2.index
-        Int64Index([5, 1], dtype='int64')
-        """
-        sdf_self = self._kdf._sdf.select(self._internal.index_scols)
-        sdf_other = other._kdf._sdf.select(other._internal.index_scols)
-
-        sdf_symdiff = sdf_self.union(sdf_other) \
-                              .subtract(sdf_self.intersect(sdf_other))
-
-        if sort:
-            sdf_symdiff = sdf_symdiff.sort(self._internal.index_scols)
-
-        internal = self._kdf._internal.copy(sdf=sdf_symdiff)
-        result = Index(DataFrame(internal))
-
-        if result_name:
-            result.name = result_name
-
-        return result
-
     def __getattr__(self, item: str) -> Any:
         if hasattr(_MissingPandasLikeIndex, item):
             property_or_func = getattr(_MissingPandasLikeIndex, item)
@@ -556,9 +491,6 @@ def __repr__(self):
     def __iter__(self):
         return _MissingPandasLikeIndex.__iter__(self)
 
-    def __xor__(self, other):
-        return self.symmetric_difference(other)
-
 
 class MultiIndex(Index):
     """
@@ -717,88 +649,6 @@ def copy(self):
         result = MultiIndex(ks.DataFrame(internal))
         return result
 
-    def symmetric_difference(self, other, result_name=None, sort=None):
-        """
-        Compute the symmetric difference of two MultiIndex objects.
-
-        Parameters
-        ----------
-        other : Index or array-like
-        result_name : list
-        sort : True or None, default None
-            Whether to sort the resulting index.
-            * True : Attempt to sort the result.
-            * None : Do not sort the result.
-
-        Returns
-        -------
-        symmetric_difference : MiltiIndex
-
-        Notes
-        -----
-        ``symmetric_difference`` contains elements that appear in either
-        ``idx1`` or ``idx2`` but not both. Equivalent to the Index created by
-        ``idx1.difference(idx2) | idx2.difference(idx1)`` with duplicates
-        dropped.
-
-        Examples
-        --------
-        >>> midx1 = pd.MultiIndex([['lama', 'cow', 'falcon'],
-        ...                        ['speed', 'weight', 'length']],
-        ...                       [[0, 0, 0, 1, 1, 1, 2, 2, 2],
-        ...                        [0, 0, 0, 0, 1, 2, 0, 1, 2]])
-        >>> midx2 = pd.MultiIndex([['koalas', 'cow', 'falcon'],
-        ...                        ['speed', 'weight', 'length']],
-        ...                       [[0, 0, 0, 1, 1, 1, 2, 2, 2],
-        ...                        [0, 0, 0, 0, 1, 2, 0, 1, 2]])
-        >>> s1 = ks.Series([45, 200, 1.2, 30, 250, 1.5, 320, 1, 0.3],
-        ...                index=midx1)
-        >>> s2 = ks.Series([45, 200, 1.2, 30, 250, 1.5, 320, 1, 0.3],
-        ...              index=midx2)
-
-        >>> s1.index.symmetric_difference(s2.index)  # doctest: +SKIP
-        MultiIndex([('koalas', 'speed'),
-                    (  'lama', 'speed')],
-                   )
-
-        You can set names of result Index.
-
-        >>> s1.index.symmetric_difference(s2.index, result_name=['a', 'b'])  # doctest: +SKIP
-        MultiIndex([('koalas', 'speed'),
-                    (  'lama', 'speed')],
-                   names=['a', 'b'])
-
-        You can set sort to `True`, if you want to sort the resulting index.
-
-        >>> s1.index.symmetric_difference(s2.index, sort=True)  # doctest: +SKIP
-        MultiIndex([('koalas', 'speed'),
-                    (  'lama', 'speed')],
-                   )
-
-        You can also use the ``^`` operator:
-
-        >>> s1.index ^ s2.index  # doctest: +SKIP
-        MultiIndex([('koalas', 'speed'),
-                    (  'lama', 'speed')],
-                   )
-        """
-        sdf_self = self._kdf._sdf.select(self._internal.index_scols)
-        sdf_other = other._kdf._sdf.select(other._internal.index_scols)
-
-        sdf_symdiff = sdf_self.union(sdf_other) \
-                              .subtract(sdf_self.intersect(sdf_other))
-
-        if sort:
-            sdf_symdiff = sdf_symdiff.sort(self._internal.index_scols)
-
-        internal = self._kdf._internal.copy(sdf=sdf_symdiff)
-        result = MultiIndex(DataFrame(internal))
-
-        if result_name:
-            result.names = result_name
-
-        return result
-
     def __getattr__(self, item: str) -> Any:
         if hasattr(_MissingPandasLikeMultiIndex, item):
             property_or_func = getattr(_MissingPandasLikeMultiIndex, item)

databricks/koalas/missing/indexes.py

@@ -92,6 +92,7 @@ class _MissingPandasLikeIndex(object):
     sort = unsupported_function('sort')
     sort_values = unsupported_function('sort_values')
     sortlevel = unsupported_function('sortlevel')
+    symmetric_difference = unsupported_function('symmetric_difference')
     take = unsupported_function('take')
     to_flat_index = unsupported_function('to_flat_index')
     to_frame = unsupported_function('to_frame')
@@ -198,6 +199,7 @@ class _MissingPandasLikeMultiIndex(object):
     sort_values = unsupported_function('sort_values')
     sortlevel = unsupported_function('sortlevel')
     swaplevel = unsupported_function('swaplevel')
+    symmetric_difference = unsupported_function('symmetric_difference')
     take = unsupported_function('take')
     to_flat_index = unsupported_function('to_flat_index')
     to_frame = unsupported_function('to_frame')

docs/source/reference/indexing.rst

@@ -57,13 +57,6 @@ Conversion
 
 .. _api.multiindex:
 
-Combining / joining / set operations
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-.. autosummary::
-   :toctree: api/
-
-   Index.symmetric_difference
-
 Selecting
 ~~~~~~~~~
 .. autosummary::
@@ -99,10 +92,3 @@ MultiIndex Modifying and computations
    :toctree: api/
 
    Index.copy
-
-MultiIndex Combining / joining / set operations
-~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
-.. autosummary::
-   :toctree: api/
-
-   MultiIndex.symmetric_difference