DEPR: Removal of cols keyword in favor of subset in DataFrame.duplicated() and DataFrame.drop_duplicates(), xref pandas-dev#6680

Author: jreback

doc/source/whatsnew/v0.18.0.txt

@@ -447,7 +447,7 @@ Removal of prior version deprecations/changes
 - Removal of ``rolling_corr_pairwise`` in favor of ``.rolling().corr(pairwise=True)`` (:issue:`4950`)
 - Removal of ``expanding_corr_pairwise`` in favor of ``.expanding().corr(pairwise=True)`` (:issue:`4950`)
 - Removal of ``DataMatrix`` module. This was not imported into the pandas namespace in any event (:issue:`12111`)
-
+- Removal of ``cols`` keyword in favor of ``subset`` in ``DataFrame.duplicated()`` and ``DataFrame.drop_duplicates()`` (:issue:`6680`)
 
 
 .. _whatsnew_0180.performance:
@@ -544,4 +544,4 @@ Bug Fixes
 
 - Bug in ``.skew`` and ``.kurt`` due to roundoff error for highly similar values (:issue:`11974`)
 
-- Bug in ``buffer_rd_bytes`` src->buffer could be freed more than once if reading failed, causing a segfault (:issue:`12098`) 
+- Bug in ``buffer_rd_bytes`` src->buffer could be freed more than once if reading failed, causing a segfault (:issue:`12098`)

pandas/core/frame.py

@@ -3012,7 +3012,6 @@ def dropna(self, axis=0, how='any', thresh=None, subset=None,
 
     @deprecate_kwarg('take_last', 'keep', mapping={True: 'last',
                                                    False: 'first'})
-    @deprecate_kwarg(old_arg_name='cols', new_arg_name='subset', stacklevel=3)
     def drop_duplicates(self, subset=None, keep='first', inplace=False):
         """
         Return DataFrame with duplicate rows removed, optionally only
@@ -3030,7 +3029,6 @@ def drop_duplicates(self, subset=None, keep='first', inplace=False):
         take_last : deprecated
         inplace : boolean, default False
             Whether to drop duplicates in place or to return a copy
-        cols : kwargs only argument of subset [deprecated]
 
         Returns
         -------
@@ -3047,7 +3045,6 @@ def drop_duplicates(self, subset=None, keep='first', inplace=False):
 
     @deprecate_kwarg('take_last', 'keep', mapping={True: 'last',
                                                    False: 'first'})
-    @deprecate_kwarg(old_arg_name='cols', new_arg_name='subset', stacklevel=3)
     def duplicated(self, subset=None, keep='first'):
         """
         Return boolean Series denoting duplicate rows, optionally only
@@ -3065,7 +3062,6 @@ def duplicated(self, subset=None, keep='first'):
               last occurrence.
             - False : Mark all duplicates as ``True``.
         take_last : deprecated
-        cols : kwargs only argument of subset [deprecated]
 
         Returns
         -------

pandas/tests/frame/test_analytics.py

@@ -1670,40 +1670,6 @@ def test_drop_duplicates_for_take_all(self):
         expected = df.iloc[[0, 1, 2, 6]]
         assert_frame_equal(result, expected)
 
-    def test_drop_duplicates_deprecated_warning(self):
-        df = DataFrame({'AAA': ['foo', 'bar', 'foo', 'bar',
-                                'foo', 'bar', 'bar', 'foo'],
-                        'B': ['one', 'one', 'two', 'two',
-                              'two', 'two', 'one', 'two'],
-                        'C': [1, 1, 2, 2, 2, 2, 1, 2],
-                        'D': lrange(8)})
-        expected = df[:2]
-
-        # Raises warning
-        with tm.assert_produces_warning(False):
-            result = df.drop_duplicates(subset='AAA')
-        assert_frame_equal(result, expected)
-
-        with tm.assert_produces_warning(FutureWarning):
-            result = df.drop_duplicates(cols='AAA')
-        assert_frame_equal(result, expected)
-
-        # Does not allow both subset and cols
-        self.assertRaises(TypeError, df.drop_duplicates,
-                          kwargs={'cols': 'AAA', 'subset': 'B'})
-
-        # Does not allow unknown kwargs
-        self.assertRaises(TypeError, df.drop_duplicates,
-                          kwargs={'subset': 'AAA', 'bad_arg': True})
-
-        # deprecate take_last
-        # Raises warning
-        with tm.assert_produces_warning(FutureWarning):
-            result = df.drop_duplicates(take_last=False, subset='AAA')
-        assert_frame_equal(result, expected)
-
-        self.assertRaises(ValueError, df.drop_duplicates, keep='invalid_name')
-
     def test_drop_duplicates_tuple(self):
         df = DataFrame({('AA', 'AB'): ['foo', 'bar', 'foo', 'bar',
                                        'foo', 'bar', 'bar', 'foo'],
@@ -1960,29 +1926,6 @@ def test_drop_duplicates_inplace(self):
         result = df2
         assert_frame_equal(result, expected)
 
-    def test_duplicated_deprecated_warning(self):
-        df = DataFrame({'AAA': ['foo', 'bar', 'foo', 'bar',
-                                'foo', 'bar', 'bar', 'foo'],
-                        'B': ['one', 'one', 'two', 'two',
-                              'two', 'two', 'one', 'two'],
-                        'C': [1, 1, 2, 2, 2, 2, 1, 2],
-                        'D': lrange(8)})
-
-        # Raises warning
-        with tm.assert_produces_warning(False):
-            result = df.duplicated(subset='AAA')
-
-        with tm.assert_produces_warning(FutureWarning):
-            result = df.duplicated(cols='AAA')  # noqa
-
-        # Does not allow both subset and cols
-        self.assertRaises(TypeError, df.duplicated,
-                          kwargs={'cols': 'AAA', 'subset': 'B'})
-
-        # Does not allow unknown kwargs
-        self.assertRaises(TypeError, df.duplicated,
-                          kwargs={'subset': 'AAA', 'bad_arg': True})
-
     # Rounding
 
     def test_round(self):