BUG: groupby.agg returns incorrect results for uint64 cols (#26310)

Author: Matias Heikkilä

doc/source/whatsnew/v0.25.0.rst

@@ -403,6 +403,7 @@ Groupby/Resample/Rolling
 - Bug in :meth:`pandas.core.groupby.GroupBy.idxmax` and :meth:`pandas.core.groupby.GroupBy.idxmin` with datetime column would return incorrect dtype (:issue:`25444`, :issue:`15306`)
 - Bug in :meth:`pandas.core.groupby.GroupBy.cumsum`, :meth:`pandas.core.groupby.GroupBy.cumprod`, :meth:`pandas.core.groupby.GroupBy.cummin` and :meth:`pandas.core.groupby.GroupBy.cummax` with categorical column having absent categories, would return incorrect result or segfault (:issue:`16771`)
 - Bug in :meth:`pandas.core.groupby.GroupBy.nth` where NA values in the grouping would return incorrect results (:issue:`26011`)
+- Bug in :meth:`pandas.core.groupby.GroupBy.agg` where incorrect results are returned for uint64 columns. (:issue:`26310`)
 
 
 Reshaping

pandas/core/dtypes/common.py

@@ -5,6 +5,7 @@
 
 from pandas._libs import algos, lib
 from pandas._libs.tslibs import conversion
+from pandas._typing import ArrayLike
 from pandas.compat import PY36
 
 from pandas.core.dtypes.dtypes import (
@@ -87,10 +88,10 @@ def ensure_categorical(arr):
     return arr
 
 
-def ensure_int64_or_float64(arr, copy=False):
+def ensure_int_or_float(arr: ArrayLike, copy=False) -> np.array:
     """
     Ensure that an dtype array of some integer dtype
-    has an int64 dtype if possible
+    has an int64 dtype if possible.
     If it's not possible, potentially because of overflow,
     convert the array to float64 instead.
 
@@ -107,9 +108,18 @@ def ensure_int64_or_float64(arr, copy=False):
     out_arr : The input array cast as int64 if
               possible without overflow.
               Otherwise the input array cast to float64.
+
+    Notes
+    -------
+    If the array is explicitly of type uint64 the type
+    will remain unchanged.
     """
     try:
         return arr.astype('int64', copy=copy, casting='safe')
+    except TypeError:
+        pass
+    try:
+        return arr.astype('uint64', copy=copy, casting='safe')
     except TypeError:
         return arr.astype('float64', copy=copy)
 

pandas/core/groupby/ops.py

@@ -17,7 +17,7 @@
 from pandas.util._decorators import cache_readonly
 
 from pandas.core.dtypes.common import (
-    ensure_float64, ensure_int64, ensure_int64_or_float64, ensure_object,
+    ensure_float64, ensure_int64, ensure_int_or_float, ensure_object,
     ensure_platform_int, is_bool_dtype, is_categorical_dtype, is_complex_dtype,
     is_datetime64_any_dtype, is_integer_dtype, is_numeric_dtype,
     is_timedelta64_dtype, needs_i8_conversion)
@@ -486,7 +486,7 @@ def _cython_operation(self, kind, values, how, axis, min_count=-1,
             if (values == iNaT).any():
                 values = ensure_float64(values)
             else:
-                values = ensure_int64_or_float64(values)
+                values = ensure_int_or_float(values)
         elif is_numeric and not is_complex_dtype(values):
             values = ensure_float64(values)
         else:

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -313,3 +313,16 @@ def test_order_aggregate_multiple_funcs():
     expected = pd.Index(['sum', 'max', 'mean', 'ohlc', 'min'])
 
     tm.assert_index_equal(result, expected)
+
+
+@pytest.mark.parametrize('dtype', [np.int64, np.uint64])
+@pytest.mark.parametrize('how', ['first', 'last', 'min',
+                                 'max', 'mean', 'median'])
+def test_uint64_type_handling(dtype, how):
+    # GH 26310
+    df = pd.DataFrame({'x': 6903052872240755750, 'y': [1, 2]})
+    expected = df.groupby('y').agg({'x': how})
+    df.x = df.x.astype(dtype)
+    result = df.groupby('y').agg({'x': how})
+    result.x = result.x.astype(np.int64)
+    tm.assert_frame_equal(result, expected, check_exact=True)