Backport PR pandas-dev#32121: REG: dont call func on empty input

Author: jbrockmendel

doc/source/whatsnew/v1.0.2.rst

@@ -21,6 +21,7 @@ Fixed regressions
 - Fixed regression in :meth:`rolling(..).corr() <pandas.core.window.Rolling.corr>` when using a time offset (:issue:`31789`)
 - Fixed regression where :func:`read_pickle` raised a ``UnicodeDecodeError`` when reading a py27 pickle with :class:`MultiIndex` column (:issue:`31988`).
 - Fixed regression in :class:`DataFrame` arithmetic operations with mis-matched columns (:issue:`31623`)
+- Fixed regression in :meth:`GroupBy.agg` calling a user-provided function an extra time on an empty input (:issue:`31760`)
 -
 
 .. ---------------------------------------------------------------------------

pandas/core/groupby/groupby.py

@@ -923,17 +923,10 @@ def _python_agg_general(self, func, *args, **kwargs):
 
             try:
                 # if this function is invalid for this dtype, we will ignore it.
-                func(obj[:0])
+                result, counts = self.grouper.agg_series(obj, f)
             except TypeError:
                 continue
-            except AssertionError:
-                raise
-            except Exception:
-                # Our function depends on having a non-empty argument
-                #  See test_groupby_agg_err_catching
-                pass
-
-            result, counts = self.grouper.agg_series(obj, f)
+
             assert result is not None
             key = base.OutputKey(label=name, position=idx)
             output[key] = self._try_cast(result, obj, numeric_only=True)

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -14,6 +14,18 @@
 from pandas.core.groupby.grouper import Grouping
 
 
+def test_groupby_agg_no_extra_calls():
+    # GH#31760
+    df = pd.DataFrame({"key": ["a", "b", "c", "c"], "value": [1, 2, 3, 4]})
+    gb = df.groupby("key")["value"]
+
+    def dummy_func(x):
+        assert len(x) != 0
+        return x.sum()
+
+    gb.agg(dummy_func)
+
+
 def test_agg_regression1(tsframe):
     grouped = tsframe.groupby([lambda x: x.year, lambda x: x.month])
     result = grouped.agg(np.mean)