ENH/GBY: add nlargest/nsmallest to Series.groupby

doc/source/groupby.rst

@@ -664,6 +664,18 @@ In this example, we chopped the collection of time series into yearly chunks
 then independently called :ref:`fillna <missing_data.fillna>` on the
 groups.
 
+.. versionadded:: 0.14.1
+
+The ``nlargest`` and ``nsmallest`` methods work on ``Series`` style groupbys:
+
+.. ipython:: python
+
+   s = Series([9, 8, 7, 5, 19, 1, 4.2, 3.3])
+   g = Series(list('abababab'))
+   gb = s.groupby(g)
+   gb.nlargest(3)
+   gb.nsmallest(3)
+
 .. _groupby.apply:
 
 Flexible ``apply``

doc/source/v0.14.1.txt

@@ -114,6 +114,9 @@ Enhancements
 
 - Implemented ``sem`` (standard error of the mean) operation for ``Series``,
   ``DataFrame``, ``Panel``, and ``Groupby`` (:issue:`6897`)
+- Add ``nlargest`` and ``nsmallest`` to the ``Series`` ``groupby`` whitelist,
+  which means you can now use these methods on a ``SeriesGroupBy`` object
+  (:issue:`7053`).
 
 
 

pandas/core/groupby.py

@@ -78,7 +78,8 @@
 
 _series_apply_whitelist = \
     (_common_apply_whitelist - set(['boxplot'])) | \
-    frozenset(['dtype', 'value_counts', 'unique', 'nunique'])
+    frozenset(['dtype', 'value_counts', 'unique', 'nunique',
+               'nlargest', 'nsmallest'])
 
 _dataframe_apply_whitelist = \
     _common_apply_whitelist | frozenset(['dtypes', 'corrwith'])

pandas/tests/test_groupby.py

@@ -4047,6 +4047,7 @@ def test_groupby_whitelist(self):
             'value_counts',
             'diff',
             'unique', 'nunique',
+            'nlargest', 'nsmallest',
         ])
 
         for obj, whitelist in zip((df, s),
@@ -4381,6 +4382,27 @@ def test_max_nan_bug(self):
         tm.assert_frame_equal(r, e)
         self.assertFalse(r['File'].isnull().any())
 
+    def test_nlargest(self):
+        a = Series([1, 3, 5, 7, 2, 9, 0, 4, 6, 10])
+        b = Series(list('a' * 5 + 'b' * 5))
+        gb = a.groupby(b)
+        r = gb.nlargest(3)
+        e = Series([7, 5, 3, 10, 9, 6],
+                   index=MultiIndex.from_arrays([list('aaabbb'),
+                                                 [3, 2, 1, 9, 5, 8]]))
+        tm.assert_series_equal(r, e)
+
+    def test_nsmallest(self):
+        a = Series([1, 3, 5, 7, 2, 9, 0, 4, 6, 10])
+        b = Series(list('a' * 5 + 'b' * 5))
+        gb = a.groupby(b)
+        r = gb.nsmallest(3)
+        e = Series([1, 2, 3, 0, 4, 6],
+                   index=MultiIndex.from_arrays([list('aaabbb'),
+                                                 [0, 4, 1, 6, 7, 8]]))
+        tm.assert_series_equal(r, e)
+
+
 def assert_fp_equal(a, b):
     assert (np.abs(a - b) < 1e-12).all()