DEPR: get_duplicates (#30004)

Author: jbrockmendel

doc/redirects.csv

@@ -636,7 +636,6 @@ generated/pandas.Index.equals,../reference/api/pandas.Index.equals
 generated/pandas.Index.factorize,../reference/api/pandas.Index.factorize
 generated/pandas.Index.fillna,../reference/api/pandas.Index.fillna
 generated/pandas.Index.format,../reference/api/pandas.Index.format
-generated/pandas.Index.get_duplicates,../reference/api/pandas.Index.get_duplicates
 generated/pandas.Index.get_indexer_for,../reference/api/pandas.Index.get_indexer_for
 generated/pandas.Index.get_indexer,../reference/api/pandas.Index.get_indexer
 generated/pandas.Index.get_indexer_non_unique,../reference/api/pandas.Index.get_indexer_non_unique

doc/source/reference/indexing.rst

@@ -152,7 +152,6 @@ Selecting
    Index.asof
    Index.asof_locs
    Index.contains
-   Index.get_duplicates
    Index.get_indexer
    Index.get_indexer_for
    Index.get_indexer_non_unique

doc/source/whatsnew/v1.0.0.rst

@@ -548,7 +548,7 @@ or ``matplotlib.Axes.plot``. See :ref:`plotting.formatters` for more.
 - Removed the previously properties :attr:`DataFrame.is_copy`, :attr:`Series.is_copy` (:issue:`18812`)
 - Removed the previously deprecated :meth:`DataFrame.get_ftype_counts`, :meth:`Series.get_ftype_counts` (:issue:`18243`)
 - Removed the previously deprecated :meth:`DataFrame.ftypes`, :meth:`Series.ftypes`, :meth:`Series.ftype` (:issue:`26744`)
-- Removed the previously deprecated :meth:`Index.get_duplicated`, use ``idx[idx.duplicated()].unique()`` instead (:issue:`20239`)
+- Removed the previously deprecated :meth:`Index.get_duplicates`, use ``idx[idx.duplicated()].unique()`` instead (:issue:`20239`)
 - Removed the previously deprecated :meth:`Series.clip_upper`, :meth:`Series.clip_lower`, :meth:`DataFrame.clip_upper`, :meth:`DataFrame.clip_lower` (:issue:`24203`)
 - Removed the ability to alter :attr:`DatetimeIndex.freq`, :attr:`TimedeltaIndex.freq`, or :attr:`PeriodIndex.freq` (:issue:`20772`)
 - Removed the previously deprecated :attr:`DatetimeIndex.offset` (:issue:`20730`)

pandas/core/indexes/base.py

@@ -2138,68 +2138,6 @@ def duplicated(self, keep="first"):
         """
         return super().duplicated(keep=keep)
 
-    def get_duplicates(self):
-        """
-        Extract duplicated index elements.
-
-        .. deprecated:: 0.23.0
-            Use idx[idx.duplicated()].unique() instead
-
-        Returns a sorted list of index elements which appear more than once in
-        the index.
-
-        Returns
-        -------
-        array-like
-            List of duplicated indexes.
-
-        See Also
-        --------
-        Index.duplicated : Return boolean array denoting duplicates.
-        Index.drop_duplicates : Return Index with duplicates removed.
-
-        Examples
-        --------
-
-        Works on different Index of types.
-
-        >>> pd.Index([1, 2, 2, 3, 3, 3, 4]).get_duplicates()  # doctest: +SKIP
-        [2, 3]
-
-        Note that for a DatetimeIndex, it does not return a list but a new
-        DatetimeIndex:
-
-        >>> dates = pd.to_datetime(['2018-01-01', '2018-01-02', '2018-01-03',
-        ...                         '2018-01-03', '2018-01-04', '2018-01-04'],
-        ...                        format='%Y-%m-%d')
-        >>> pd.Index(dates).get_duplicates()  # doctest: +SKIP
-        DatetimeIndex(['2018-01-03', '2018-01-04'],
-                      dtype='datetime64[ns]', freq=None)
-
-        Sorts duplicated elements even when indexes are unordered.
-
-        >>> pd.Index([1, 2, 3, 2, 3, 4, 3]).get_duplicates()  # doctest: +SKIP
-        [2, 3]
-
-        Return empty array-like structure when all elements are unique.
-
-        >>> pd.Index([1, 2, 3, 4]).get_duplicates()  # doctest: +SKIP
-        []
-        >>> dates = pd.to_datetime(['2018-01-01', '2018-01-02', '2018-01-03'],
-        ...                        format='%Y-%m-%d')
-        >>> pd.Index(dates).get_duplicates()  # doctest: +SKIP
-        DatetimeIndex([], dtype='datetime64[ns]', freq=None)
-        """
-        warnings.warn(
-            "'get_duplicates' is deprecated and will be removed in "
-            "a future release. You can use "
-            "idx[idx.duplicated()].unique() instead",
-            FutureWarning,
-            stacklevel=2,
-        )
-
-        return self[self.duplicated()].unique()
-
     def _get_unique_index(self, dropna=False):
         """
         Returns an index containing unique values.

pandas/tests/indexes/datetimes/test_datetime.py

@@ -188,25 +188,6 @@ def test_string_index_series_name_converted(self):
         result = df.T["1/3/2000"]
         assert result.name == df.index[2]
 
-    def test_get_duplicates(self):
-        idx = DatetimeIndex(
-            [
-                "2000-01-01",
-                "2000-01-02",
-                "2000-01-02",
-                "2000-01-03",
-                "2000-01-03",
-                "2000-01-04",
-            ]
-        )
-
-        with tm.assert_produces_warning(FutureWarning):
-            # Deprecated - see GH20239
-            result = idx.get_duplicates()
-
-        ex = DatetimeIndex(["2000-01-02", "2000-01-03"])
-        tm.assert_index_equal(result, ex)
-
     def test_argmin_argmax(self):
         idx = DatetimeIndex(["2000-01-04", "2000-01-01", "2000-01-02"])
         assert idx.argmin() == 1

pandas/tests/indexes/multi/test_duplicates.py

@@ -251,16 +251,13 @@ def test_duplicated_large(keep):
     tm.assert_numpy_array_equal(result, expected)
 
 
-def test_get_duplicates():
+def test_duplicated2():
+    # TODO: more informative test name
     # GH5873
     for a in [101, 102]:
         mi = MultiIndex.from_arrays([[101, a], [3.5, np.nan]])
         assert not mi.has_duplicates
 
-        with tm.assert_produces_warning(FutureWarning):
-            # Deprecated - see GH20239
-            assert mi.get_duplicates().equals(MultiIndex.from_arrays([[], []]))
-
         tm.assert_numpy_array_equal(mi.duplicated(), np.zeros(2, dtype="bool"))
 
     for n in range(1, 6):  # 1st level shape
@@ -274,10 +271,6 @@ def test_get_duplicates():
             assert len(mi) == (n + 1) * (m + 1)
             assert not mi.has_duplicates
 
-            with tm.assert_produces_warning(FutureWarning):
-                # Deprecated - see GH20239
-                assert mi.get_duplicates().equals(MultiIndex.from_arrays([[], []]))
-
             tm.assert_numpy_array_equal(
                 mi.duplicated(), np.zeros(len(mi), dtype="bool")
             )

pandas/tests/indexes/test_base.py

@@ -2394,11 +2394,6 @@ def test_cached_properties_not_settable(self):
         with pytest.raises(AttributeError, match="Can't set attribute"):
             index.is_unique = False
 
-    def test_get_duplicates_deprecated(self):
-        index = pd.Index([1, 2, 3])
-        with tm.assert_produces_warning(FutureWarning):
-            index.get_duplicates()
-
     def test_tab_complete_warning(self, ip):
         # https://github.com/pandas-dev/pandas/issues/16409
         pytest.importorskip("IPython", minversion="6.0.0")

pandas/tests/indexes/timedeltas/test_timedelta.py

@@ -179,16 +179,6 @@ def test_sort_values(self):
 
         tm.assert_numpy_array_equal(dexer, np.array([0, 2, 1]), check_dtype=False)
 
-    def test_get_duplicates(self):
-        idx = TimedeltaIndex(["1 day", "2 day", "2 day", "3 day", "3day", "4day"])
-
-        with tm.assert_produces_warning(FutureWarning):
-            # Deprecated - see GH20239
-            result = idx.get_duplicates()
-
-        ex = TimedeltaIndex(["2 day", "3day"])
-        tm.assert_index_equal(result, ex)
-
     def test_argmin_argmax(self):
         idx = TimedeltaIndex(["1 day 00:00:05", "1 day 00:00:01", "1 day 00:00:02"])
         assert idx.argmin() == 1