EHN: groupby missing data in index(pandas-dev#20519)

Author: HH

doc/source/whatsnew/v0.25.1.rst

@@ -85,7 +85,7 @@ Indexing
 - Bug in partial-string indexing returning a NumPy array rather than a ``Series`` when indexing with a scalar like ``.loc['2015']`` (:issue:`27516`)
 - Break reference cycle involving :class:`Index` and other index classes to allow garbage collection of index objects without running the GC. (:issue:`27585`, :issue:`27840`)
 - Fix regression in assigning values to a single column of a DataFrame with a ``MultiIndex`` columns (:issue:`27841`).
--
+- `IndexError` would not raised if group keys are nan value (:issue:`20519`)
 
 Missing
 ^^^^^^^

pandas/core/indexes/multi.py

@@ -1279,7 +1279,10 @@ def _get_grouper_for_level(self, mapper, level):
             # Remove unobserved levels from level_index
             level_index = level_index.take(uniques)
 
-        grouper = level_index.take(codes)
+        if not len(level_index):
+            grouper = level_index
+        else:
+            grouper = level_index.take(codes)
 
         return grouper, codes, level_index
 

pandas/tests/indexes/test_base.py

@@ -2240,6 +2240,30 @@ def test_groupby(self):
 
         tm.assert_dict_equal(result, expected)
 
+    def test_groupby_nan_index_value(self):
+        df = pd.DataFrame([["x", np.nan, 1]], columns=["A", "B", "C"]).set_index(
+            ["A", "B"]
+        )
+        result = df.groupby(level=["A", "B"]).C.sum()
+        result = np.asarray(result)
+
+        s = Series([])
+        s.name = "C"
+        expected = s.astype("int64")
+        expected = np.asarray(expected)
+        tm.assert_numpy_array_equal(result, expected)
+
+        df = pd.DataFrame(
+            [["x", np.nan, 1, 2], [None, "y", 3, 4]], columns=["A", "B", "C", "D"]
+        ).set_index(["A", "B", "C"])
+        result = df.groupby(level=["A", "B"]).D.sum()
+        s = Series([])
+        s.name = "D"
+        expected = s.astype("int64")
+        result = np.asarray(result)
+        expected = np.asarray(expected)
+        tm.assert_numpy_array_equal(result, expected)
+
     @pytest.mark.parametrize(
         "mi,expected",
         [