ENH: provide "inplace" argument to set_axis()

closes pandas-dev#14636

Author: Pietro Battiston <[email protected]>

Closes pandas-dev#16994 from toobaz/set_axis_inplace and squashes the following commits:

8fb9d0f [Pietro Battiston] REF: adapt NDFrame.set_axis() calls to new signature
409f502 [Pietro Battiston] ENH: provide "inplace" argument to set_axis(), change signature

Author: toobaz

doc/source/api.rst

@@ -410,6 +410,7 @@ Reindexing / Selection / Label manipulation
    Series.reset_index
    Series.sample
    Series.select
+   Series.set_axis
    Series.take
    Series.tail
    Series.truncate

doc/source/whatsnew/v0.21.0.txt

@@ -67,6 +67,7 @@ Other Enhancements
 - :func:`Series.to_dict` and :func:`DataFrame.to_dict` now support an ``into`` keyword which allows you to specify the ``collections.Mapping`` subclass that you would like returned.  The default is ``dict``, which is backwards compatible. (:issue:`16122`)
 - :func:`RangeIndex.append` now returns a ``RangeIndex`` object when possible (:issue:`16212`)
 - :func:`Series.rename_axis` and :func:`DataFrame.rename_axis` with ``inplace=True`` now return ``None`` while renaming the axis inplace. (:issue:`15704`)
+- :func:`Series.set_axis` and :func:`DataFrame.set_axis` now support the ``inplace`` parameter. (:issue:`14636`)
 - :func:`Series.to_pickle` and :func:`DataFrame.to_pickle` have gained a ``protocol`` parameter (:issue:`16252`). By default, this parameter is set to `HIGHEST_PROTOCOL <https://docs.python.org/3/library/pickle.html#data-stream-format>`__
 - :func:`api.types.infer_dtype` now infers decimals. (:issue:`15690`)
 - :func:`read_feather` has gained the ``nthreads`` parameter for multi-threaded operations (:issue:`16359`)
@@ -202,6 +203,7 @@ Other API Changes
 - ``Index.get_indexer_non_unique()`` now returns a ndarray indexer rather than an ``Index``; this is consistent with ``Index.get_indexer()`` (:issue:`16819`)
 - Removed the ``@slow`` decorator from ``pandas.util.testing``, which caused issues for some downstream packages' test suites. Use ``@pytest.mark.slow`` instead, which achieves the same thing (:issue:`16850`)
 - Moved definition of ``MergeError`` to the ``pandas.errors`` module.
+- The signature of :func:`Series.set_axis` and :func:`DataFrame.set_axis` has been changed from ``set_axis(axis, labels)`` to ``set_axis(labels, axis=0)``, for consistency with the rest of the API. The old signature is still supported and causes a ``FutureWarning`` to be emitted (:issue:`14636`)
 
 
 .. _whatsnew_0210.deprecations:

pandas/core/generic.py

@@ -466,9 +466,91 @@ def _expand_axes(self, key):
 
         return new_axes
 
-    def set_axis(self, axis, labels):
-        """ public verson of axis assignment """
-        setattr(self, self._get_axis_name(axis), labels)
+    _shared_docs['set_axis'] = """Assign desired index to given axis
+
+        Parameters
+        ----------
+        labels: list-like or Index
+            The values for the new index
+        axis : int or string, default 0
+        inplace : boolean, default None
+            Whether to return a new %(klass)s instance.
+
+            WARNING: inplace=None currently falls back to to True, but
+            in a future version, will default to False.  Use inplace=True
+            explicitly rather than relying on the default.
+
+        .. versionadded:: 0.21.0
+            The signature is make consistent to the rest of the API.
+            Previously, the "axis" and "labels" arguments were respectively
+            the first and second positional arguments.
+
+        Returns
+        -------
+        renamed : %(klass)s or None
+            An object of same type as caller if inplace=False, None otherwise.
+
+        See Also
+        --------
+        pandas.NDFrame.rename
+
+        Examples
+        --------
+        >>> s = pd.Series([1, 2, 3])
+        >>> s
+        0    1
+        1    2
+        2    3
+        dtype: int64
+        >>> s.set_axis(['a', 'b', 'c'], axis=0, inplace=False)
+        a    1
+        b    2
+        c    3
+        dtype: int64
+        >>> df = pd.DataFrame({"A": [1, 2, 3], "B": [4, 5, 6]})
+        >>> df.set_axis(['a', 'b', 'c'], axis=0, inplace=False)
+           A  B
+        a  1  4
+        b  2  5
+        c  3  6
+        >>> df.set_axis(['I', 'II'], axis=1, inplace=False)
+           I  II
+        0  1   4
+        1  2   5
+        2  3   6
+        >>> df.set_axis(['i', 'ii'], axis=1, inplace=True)
+        >>> df
+           i  ii
+        0  1   4
+        1  2   5
+        2  3   6
+
+        """
+
+    @Appender(_shared_docs['set_axis'] % dict(klass='NDFrame'))
+    def set_axis(self, labels, axis=0, inplace=None):
+        if is_scalar(labels):
+            warnings.warn(
+                'set_axis now takes "labels" as first argument, and '
+                '"axis" as named parameter. The old form, with "axis" as '
+                'first parameter and \"labels\" as second, is still supported '
+                'but will be deprecated in a future version of pandas.',
+                FutureWarning, stacklevel=2)
+            labels, axis = axis, labels
+
+        if inplace is None:
+            warnings.warn(
+                'set_axis currently defaults to operating inplace.\nThis '
+                'will change in a future version of pandas, use '
+                'inplace=True to avoid this warning.',
+                FutureWarning, stacklevel=2)
+            inplace = True
+        if inplace:
+            setattr(self, self._get_axis_name(axis), labels)
+        else:
+            obj = self.copy()
+            obj.set_axis(labels, axis=axis, inplace=True)
+            return obj
 
     def _set_axis(self, axis, labels):
         self._data.set_axis(axis, labels)
@@ -875,7 +957,7 @@ def _set_axis_name(self, name, axis=0, inplace=False):
 
         inplace = validate_bool_kwarg(inplace, 'inplace')
         renamed = self if inplace else self.copy()
-        renamed.set_axis(axis, idx)
+        renamed.set_axis(idx, axis=axis, inplace=True)
         if not inplace:
             return renamed
 
@@ -5721,7 +5803,7 @@ def slice_shift(self, periods=1, axis=0):
 
         new_obj = self._slice(vslicer, axis=axis)
         shifted_axis = self._get_axis(axis)[islicer]
-        new_obj.set_axis(axis, shifted_axis)
+        new_obj.set_axis(shifted_axis, axis=axis, inplace=True)
 
         return new_obj.__finalize__(self)
 
@@ -5881,7 +5963,7 @@ def _tz_convert(ax, tz):
             ax = _tz_convert(ax, tz)
 
         result = self._constructor(self._data, copy=copy)
-        result.set_axis(axis, ax)
+        result.set_axis(ax, axis=axis, inplace=True)
         return result.__finalize__(self)
 
     @deprecate_kwarg(old_arg_name='infer_dst', new_arg_name='ambiguous',
@@ -5949,7 +6031,7 @@ def _tz_localize(ax, tz, ambiguous):
             ax = _tz_localize(ax, tz, ambiguous)
 
         result = self._constructor(self._data, copy=copy)
-        result.set_axis(axis, ax)
+        result.set_axis(ax, axis=axis, inplace=True)
         return result.__finalize__(self)
 
     # ----------------------------------------------------------------------

pandas/core/groupby.py

@@ -530,10 +530,11 @@ def _set_result_index_ordered(self, result):
         if not self.grouper.is_monotonic:
             index = Index(np.concatenate(
                 self._get_indices(self.grouper.result_index)))
-            result.set_axis(self.axis, index)
+            result.set_axis(index, axis=self.axis, inplace=True)
             result = result.sort_index(axis=self.axis)
 
-        result.set_axis(self.axis, self.obj._get_axis(self.axis))
+        result.set_axis(self.obj._get_axis(self.axis), axis=self.axis,
+                        inplace=True)
         return result
 
     def _dir_additions(self):

pandas/core/reshape/pivot.py

@@ -312,8 +312,9 @@ def _all_key(key):
                 except TypeError:
 
                     # we cannot reshape, so coerce the axis
-                    piece.set_axis(cat_axis, piece._get_axis(
-                        cat_axis)._to_safe_for_reshape())
+                    piece.set_axis(piece._get_axis(
+                                   cat_axis)._to_safe_for_reshape(),
+                                   axis=cat_axis, inplace=True)
                     piece[all_key] = margin[key]
 
                 table_pieces.append(piece)

pandas/tests/frame/test_alter_axes.py

@@ -908,3 +908,62 @@ def test_set_reset_index(self):
         df = df.set_index('B')
 
         df = df.reset_index()
+
+    def test_set_axis_inplace(self):
+        # GH14636
+        df = DataFrame({'A': [1.1, 2.2, 3.3],
+                        'B': [5.0, 6.1, 7.2],
+                        'C': [4.4, 5.5, 6.6]},
+                       index=[2010, 2011, 2012])
+
+        expected = {0: df.copy(),
+                    1: df.copy()}
+        expected[0].index = list('abc')
+        expected[1].columns = list('abc')
+        expected['index'] = expected[0]
+        expected['columns'] = expected[1]
+
+        for axis in expected:
+            # inplace=True
+            # The FutureWarning comes from the fact that we would like to have
+            # inplace default to False some day
+            for inplace, warn in (None, FutureWarning), (True, None):
+                kwargs = {'inplace': inplace}
+
+                result = df.copy()
+                with tm.assert_produces_warning(warn):
+                    result.set_axis(list('abc'), axis=axis, **kwargs)
+                tm.assert_frame_equal(result, expected[axis])
+
+            # inplace=False
+            result = df.set_axis(list('abc'), axis=axis, inplace=False)
+            tm.assert_frame_equal(expected[axis], result)
+
+        # omitting the "axis" parameter
+        with tm.assert_produces_warning(None):
+            result = df.set_axis(list('abc'), inplace=False)
+        tm.assert_frame_equal(result, expected[0])
+
+        # wrong values for the "axis" parameter
+        for axis in 3, 'foo':
+            with tm.assert_raises_regex(ValueError, 'No axis named'):
+                df.set_axis(list('abc'), axis=axis, inplace=False)
+
+    def test_set_axis_prior_to_deprecation_signature(self):
+        df = DataFrame({'A': [1.1, 2.2, 3.3],
+                        'B': [5.0, 6.1, 7.2],
+                        'C': [4.4, 5.5, 6.6]},
+                       index=[2010, 2011, 2012])
+
+        expected = {0: df.copy(),
+                    1: df.copy()}
+        expected[0].index = list('abc')
+        expected[1].columns = list('abc')
+        expected['index'] = expected[0]
+        expected['columns'] = expected[1]
+
+        # old signature
+        for axis in expected:
+            with tm.assert_produces_warning(FutureWarning):
+                result = df.set_axis(axis, list('abc'), inplace=False)
+            tm.assert_frame_equal(result, expected[axis])

pandas/tests/series/test_alter_axes.py

@@ -234,3 +234,47 @@ def test_rename_axis_inplace(self):
 
         assert no_return is None
         assert_series_equal(result, expected)
+
+    def test_set_axis_inplace(self):
+        # GH14636
+
+        s = Series(np.arange(4), index=[1, 3, 5, 7], dtype='int64')
+
+        expected = s.copy()
+        expected.index = list('abcd')
+
+        for axis in 0, 'index':
+            # inplace=True
+            # The FutureWarning comes from the fact that we would like to have
+            # inplace default to False some day
+            for inplace, warn in (None, FutureWarning), (True, None):
+                result = s.copy()
+                kwargs = {'inplace': inplace}
+                with tm.assert_produces_warning(warn):
+                    result.set_axis(list('abcd'), axis=axis, **kwargs)
+                tm.assert_series_equal(result, expected)
+
+        # inplace=False
+        result = s.set_axis(list('abcd'), axis=0, inplace=False)
+        tm.assert_series_equal(expected, result)
+
+        # omitting the "axis" parameter
+        with tm.assert_produces_warning(None):
+            result = s.set_axis(list('abcd'), inplace=False)
+        tm.assert_series_equal(result, expected)
+
+        # wrong values for the "axis" parameter
+        for axis in 2, 'foo':
+            with tm.assert_raises_regex(ValueError, 'No axis named'):
+                s.set_axis(list('abcd'), axis=axis, inplace=False)
+
+    def test_set_axis_prior_to_deprecation_signature(self):
+        s = Series(np.arange(4), index=[1, 3, 5, 7], dtype='int64')
+
+        expected = s.copy()
+        expected.index = list('abcd')
+
+        for axis in 0, 'index':
+            with tm.assert_produces_warning(FutureWarning):
+                result = s.set_axis(0, list('abcd'), inplace=False)
+            tm.assert_series_equal(result, expected)