ENH: Add errors parameter to DataFrame.rename (#25535)

* ENH: GH13473 Add errors parameter to DataFrame.rename

Author: MaxVanDeursen

doc/source/whatsnew/v0.25.0.rst

@@ -25,7 +25,7 @@ Other Enhancements
 - ``Series.str`` has gained :meth:`Series.str.casefold` method to removes all case distinctions present in a string (:issue:`25405`)
 - :meth:`DataFrame.set_index` now works for instances of ``abc.Iterator``, provided their output is of the same length as the calling frame (:issue:`22484`, :issue:`24984`)
 - :meth:`DatetimeIndex.union` now supports the ``sort`` argument. The behaviour of the sort parameter matches that of :meth:`Index.union` (:issue:`24994`)
--
+- :meth:`DataFrame.rename` now supports the ``errors`` argument to raise errors when attempting to rename nonexistent keys (:issue:`13473`)
 
 .. _whatsnew_0250.api_breaking:
 

pandas/core/frame.py

@@ -3911,7 +3911,8 @@ def drop(self, labels=None, axis=0, index=None, columns=None,
 
     @rewrite_axis_style_signature('mapper', [('copy', True),
                                              ('inplace', False),
-                                             ('level', None)])
+                                             ('level', None),
+                                             ('errors', 'ignore')])
     def rename(self, *args, **kwargs):
         """
         Alter axes labels.
@@ -3924,30 +3925,49 @@ def rename(self, *args, **kwargs):
 
         Parameters
         ----------
-        mapper, index, columns : dict-like or function, optional
-            dict-like or functions transformations to apply to
+        mapper : dict-like or function
+            Dict-like or functions transformations to apply to
             that axis' values. Use either ``mapper`` and ``axis`` to
             specify the axis to target with ``mapper``, or ``index`` and
             ``columns``.
-        axis : int or str, optional
+        index : dict-like or function
+            Alternative to specifying axis (``mapper, axis=0``
+            is equivalent to ``index=mapper``).
+        columns : dict-like or function
+            Alternative to specifying axis (``mapper, axis=1``
+            is equivalent to ``columns=mapper``).
+        axis : int or str
             Axis to target with ``mapper``. Can be either the axis name
             ('index', 'columns') or number (0, 1). The default is 'index'.
-        copy : boolean, default True
-            Also copy underlying data
-        inplace : boolean, default False
+        copy : bool, default True
+            Also copy underlying data.
+        inplace : bool, default False
             Whether to return a new DataFrame. If True then value of copy is
             ignored.
         level : int or level name, default None
             In case of a MultiIndex, only rename labels in the specified
             level.
+        errors : {'ignore', 'raise'}, default 'ignore'
+            If 'raise', raise a `KeyError` when a dict-like `mapper`, `index`,
+            or `columns` contains labels that are not present in the Index
+            being transformed.
+            If 'ignore', existing keys will be renamed and extra keys will be
+            ignored.
 
         Returns
         -------
         DataFrame
+            DataFrame with the renamed axis labels.
+
+        Raises
+        ------
+        KeyError
+            If any of the labels is not found in the selected axis and
+            "errors='raise'".
 
         See Also
         --------
-        DataFrame.rename_axis
+        DataFrame.rename_axis : Set the name of the axis.
 
         Examples
         --------
@@ -3973,6 +3993,10 @@ def rename(self, *args, **kwargs):
         1  2  5
         2  3  6
 
+        >>> df.rename(index=str, columns={"A": "a", "C": "c"}, errors="raise")
+        Traceback (most recent call last):
+        KeyError: ['C'] not found in axis
+
         Using axis-style parameters
 
         >>> df.rename(str.lower, axis='columns')

pandas/core/generic.py

@@ -981,11 +981,23 @@ def rename(self, *args, **kwargs):
         level : int or level name, default None
             In case of a MultiIndex, only rename labels in the specified
             level.
+        errors : {'ignore', 'raise'}, default 'ignore'
+            If 'raise', raise a `KeyError` when a dict-like `mapper`, `index`,
+            or `columns` contains labels that are not present in the Index
+            being transformed.
+            If 'ignore', existing keys will be renamed and extra keys will be
+            ignored.
 
         Returns
         -------
         renamed : %(klass)s (new object)
 
+        Raises
+        ------
+        KeyError
+            If any of the labels is not found in the selected axis and
+            "errors='raise'".
+
         See Also
         --------
         NDFrame.rename_axis
@@ -1065,6 +1077,7 @@ def rename(self, *args, **kwargs):
         inplace = kwargs.pop('inplace', False)
         level = kwargs.pop('level', None)
         axis = kwargs.pop('axis', None)
+        errors = kwargs.pop('errors', 'ignore')
         if axis is not None:
             # Validate the axis
             self._get_axis_number(axis)
@@ -1085,10 +1098,19 @@ def rename(self, *args, **kwargs):
             if v is None:
                 continue
             f = com._get_rename_function(v)
-
             baxis = self._get_block_manager_axis(axis)
             if level is not None:
                 level = self.axes[axis]._get_level_number(level)
+
+            # GH 13473
+            if not callable(v):
+                indexer = self.axes[axis].get_indexer_for(v)
+                if errors == 'raise' and len(indexer[indexer == -1]):
+                    missing_labels = [label for index, label in enumerate(v)
+                                      if indexer[index] == -1]
+                    raise KeyError('{} not found in axis'
+                                   .format(missing_labels))
+
             result._data = result._data.rename_axis(f, axis=baxis, copy=copy,
                                                     level=level)
             result._clear_item_cache()

pandas/tests/frame/test_alter_axes.py

@@ -872,6 +872,23 @@ def test_rename_bug2(self):
                              columns=["a"])
         tm.assert_frame_equal(df, expected)
 
+    def test_rename_errors_raises(self):
+        df = DataFrame(columns=['A', 'B', 'C', 'D'])
+        with pytest.raises(KeyError, match='\'E\'] not found in axis'):
+            df.rename(columns={'A': 'a', 'E': 'e'}, errors='raise')
+
+    @pytest.mark.parametrize('mapper, errors, expected_columns', [
+        ({'A': 'a', 'E': 'e'}, 'ignore', ['a', 'B', 'C', 'D']),
+        ({'A': 'a'}, 'raise', ['a', 'B', 'C', 'D']),
+        (str.lower, 'raise', ['a', 'b', 'c', 'd'])])
+    def test_rename_errors(self, mapper, errors, expected_columns):
+        # GH 13473
+        # rename now works with errors parameter
+        df = DataFrame(columns=['A', 'B', 'C', 'D'])
+        result = df.rename(columns=mapper, errors=errors)
+        expected = DataFrame(columns=expected_columns)
+        tm.assert_frame_equal(result, expected)
+
     def test_reorder_levels(self):
         index = MultiIndex(levels=[['bar'], ['one', 'two', 'three'], [0, 1]],
                            codes=[[0, 0, 0, 0, 0, 0],
@@ -1329,7 +1346,7 @@ def test_rename_signature(self):
         sig = inspect.signature(DataFrame.rename)
         parameters = set(sig.parameters)
         assert parameters == {"self", "mapper", "index", "columns", "axis",
-                              "inplace", "copy", "level"}
+                              "inplace", "copy", "level", "errors"}
 
     @pytest.mark.skipif(PY2, reason="inspect.signature")
     def test_reindex_signature(self):