Merge pull request #6639 from jreback/sort_error

API: A tuple passed to DataFame.sort_index will be interpreted as the levels of the index (GH4370)

Author: jreback

doc/source/basics.rst

@@ -1287,9 +1287,18 @@ Some other sorting notes / nuances:
   * ``Series.sort`` sorts a Series by value in-place. This is to provide
     compatibility with NumPy methods which expect the ``ndarray.sort``
     behavior.
-  * ``DataFrame.sort`` takes a ``column`` argument instead of ``by``. This
-    method will likely be deprecated in a future release in favor of just using
-    ``sort_index``.
+
+Sorting by a multi-index column
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+You must be explicit about sorting when the column is a multi-index, and fully specify
+all levels to ``by``.
+
+.. ipython:: python
+
+   df1.columns = MultiIndex.from_tuples([('a','one'),('a','two'),('b','three')])
+   df1.sort_index(by=('a','two'))
+
 
 Copying
 -------

doc/source/release.rst

@@ -133,6 +133,17 @@ API Changes
 
 - Allow specification of a more complex groupby, via ``pd.Groupby`` (:issue:`3794`)
 
+- A tuple passed to ``DataFame.sort_index`` will be interpreted as the levels of
+  the index, rather than requiring a list of tuple (:issue:`4370`)
+
+Deprecations
+~~~~~~~~~~~~
+
+Prior Version Deprecations/Changes
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+- Remove ``column`` keyword from ``DataFrame.sort`` (:issue:`4370`)
+
 Experimental Features
 ~~~~~~~~~~~~~~~~~~~~~
 

doc/source/v0.14.0.txt

@@ -288,7 +288,9 @@ You can use a right-hand-side of an alignable object as well.
 Prior Version Deprecations/Changes
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-There are no announced changes in 0.13.1 or prior that are taking effect as of 0.14.0
+Therse are prior version deprecations that are taking effect as of 0.14.0.
+
+- Remove ``column`` keyword from ``DataFrame.sort`` (:issue:`4370`)
 
 Deprecations
 ~~~~~~~~~~~~

pandas/core/frame.py

@@ -2530,7 +2530,7 @@ def _m8_to_i8(x):
     #----------------------------------------------------------------------
     # Sorting
 
-    def sort(self, columns=None, column=None, axis=0, ascending=True,
+    def sort(self, columns=None, axis=0, ascending=True,
              inplace=False):
         """
         Sort DataFrame either by labels (along either axis) or by the values in
@@ -2539,8 +2539,9 @@ def sort(self, columns=None, column=None, axis=0, ascending=True,
         Parameters
         ----------
         columns : object
-            Column name(s) in frame. Accepts a column name or a list or tuple
-            for a nested sort.
+            Column name(s) in frame. Accepts a column name or a list
+            for a nested sort. A tuple will be interpreted as the
+            levels of a multi-index.
         ascending : boolean or list, default True
             Sort ascending vs. descending. Specify list for multiple sort
             orders
@@ -2557,9 +2558,6 @@ def sort(self, columns=None, column=None, axis=0, ascending=True,
         -------
         sorted : DataFrame
         """
-        if column is not None:  # pragma: no cover
-            warnings.warn("column is deprecated, use columns", FutureWarning)
-            columns = column
         return self.sort_index(by=columns, axis=axis, ascending=ascending,
                                inplace=inplace)
 
@@ -2574,8 +2572,9 @@ def sort_index(self, axis=0, by=None, ascending=True, inplace=False,
         axis : {0, 1}
             Sort index/rows versus columns
         by : object
-            Column name(s) in frame. Accepts a column name or a list or tuple
-            for a nested sort.
+            Column name(s) in frame. Accepts a column name or a list
+            for a nested sort. A tuple will be interpreted as the
+            levels of a multi-index.
         ascending : boolean or list, default True
             Sort ascending vs. descending. Specify list for multiple sort
             orders
@@ -2602,7 +2601,7 @@ def sort_index(self, axis=0, by=None, ascending=True, inplace=False,
             if axis != 0:
                 raise ValueError('When sorting by column, axis must be 0 '
                                  '(rows)')
-            if not isinstance(by, (tuple, list)):
+            if not isinstance(by, list):
                 by = [by]
             if com._is_sequence(ascending) and len(by) != len(ascending):
                 raise ValueError('Length of ascending (%d) != length of by'
@@ -2629,6 +2628,13 @@ def trans(v):
                 by = by[0]
                 k = self[by].values
                 if k.ndim == 2:
+
+                    # try to be helpful
+                    if isinstance(self.columns, MultiIndex):
+                        raise ValueError('Cannot sort by column %s in a multi-index'
+                                         '  you need to explicity provide all the levels'
+                                         % str(by))
+
                     raise ValueError('Cannot sort by duplicate column %s'
                                      % str(by))
                 if isinstance(ascending, (tuple, list)):

pandas/tests/test_frame.py

@@ -9797,6 +9797,17 @@ def test_sort_index_duplicates(self):
             # multi-column 'by' is separate codepath
             df.sort_index(by=['a', 'b'])
 
+        # with multi-index
+        # GH4370
+        df = DataFrame(np.random.randn(4,2),columns=MultiIndex.from_tuples([('a',0),('a',1)]))
+        with assertRaisesRegexp(ValueError, 'levels'):
+            df.sort_index(by='a')
+
+        # convert tuples to a list of tuples
+        expected = df.sort_index(by=[('a',1)])
+        result = df.sort_index(by=('a',1))
+        assert_frame_equal(result, expected)
+
     def test_sort_datetimes(self):
 
         # GH 3461, argsort / lexsort differences for a datetime column