Merge pull request #11079 from cpcloud/fix-series-nunique-groupby-with-object

BUG: Fix Series nunique groupby with object dtype

Author: cpcloud

doc/source/whatsnew/v0.17.0.txt

@@ -1014,7 +1014,7 @@ Performance Improvements
 - Development support for benchmarking with the `Air Speed Velocity library <https://github.com/spacetelescope/asv/>`_ (:issue:`8316`)
 - Added vbench benchmarks for alternative ExcelWriter engines and reading Excel files (:issue:`7171`)
 - Performance improvements in ``Categorical.value_counts`` (:issue:`10804`)
-- Performance improvements in ``SeriesGroupBy.nunique`` and ``SeriesGroupBy.value_counts`` (:issue:`10820`)
+- Performance improvements in ``SeriesGroupBy.nunique`` and ``SeriesGroupBy.value_counts`` (:issue:`10820`, :issue:`11077`)
 - Performance improvements in ``DataFrame.drop_duplicates`` with integer dtypes (:issue:`10917`)
 - 4x improvement in ``timedelta`` string parsing (:issue:`6755`, :issue:`10426`)
 - 8x improvement in ``timedelta64`` and ``datetime64`` ops (:issue:`6755`)

pandas/core/groupby.py

@@ -2565,7 +2565,17 @@ def nunique(self, dropna=True):
         ids, _, _ = self.grouper.group_info
         val = self.obj.get_values()
 
-        sorter = np.lexsort((val, ids))
+        try:
+            sorter = np.lexsort((val, ids))
+        except TypeError:  # catches object dtypes
+            assert val.dtype == object, \
+                'val.dtype must be object, got %s' % val.dtype
+            val, _ = algos.factorize(val, sort=False)
+            sorter = np.lexsort((val, ids))
+            isnull = lambda a: a == -1
+        else:
+            isnull = com.isnull
+
         ids, val = ids[sorter], val[sorter]
 
         # group boundries are where group ids change

pandas/tests/test_groupby.py

@@ -5511,6 +5511,22 @@ def test_sort(x):
 
                 g.apply(test_sort)
 
+    def test_nunique_with_object(self):
+        # GH 11077
+        data = pd.DataFrame(
+            [[100, 1, 'Alice'],
+             [200, 2, 'Bob'],
+             [300, 3, 'Charlie'],
+             [-400, 4, 'Dan'],
+             [500, 5, 'Edith']],
+            columns=['amount', 'id', 'name']
+        )
+
+        result = data.groupby(['id', 'amount'])['name'].nunique()
+        index = MultiIndex.from_arrays([data.id, data.amount])
+        expected = pd.Series([1] * 5, name='name', index=index)
+        tm.assert_series_equal(result, expected)
+
 
 def assert_fp_equal(a, b):
     assert (np.abs(a - b) < 1e-12).all()