BUG/df.agg-with-df-with-missing-values-results-in-IndexError

doc/source/whatsnew/v3.0.0.rst

@@ -39,6 +39,7 @@ Other enhancements
 - Users can globally disable any ``PerformanceWarning`` by setting the option ``mode.performance_warnings`` to ``False`` (:issue:`56920`)
 - :meth:`Styler.format_index_names` can now be used to format the index and column names (:issue:`48936` and :issue:`47489`)
 - :class:`.errors.DtypeWarning` improved to include column names when mixed data types are detected (:issue:`58174`)
+- :meth:`DataFrame.agg` now correctly handles missing values without raising an IndexError (:issue:`58810`)
 - :meth:`DataFrame.corrwith` now accepts ``min_periods`` as optional arguments, as in :meth:`DataFrame.corr` and :meth:`Series.corr` (:issue:`9490`)
 - :meth:`DataFrame.cummin`, :meth:`DataFrame.cummax`, :meth:`DataFrame.cumprod` and :meth:`DataFrame.cumsum` methods now have a ``numeric_only`` parameter (:issue:`53072`)
 - :meth:`DataFrame.fillna` and :meth:`Series.fillna` can now accept ``value=None``; for non-object dtype the corresponding NA value will be used (:issue:`57723`)

pandas/core/apply.py

@@ -1824,12 +1824,15 @@ def relabel_result(
             fun = [
                 com.get_callable_name(f) if not isinstance(f, str) else f for f in fun
             ]
-            col_idx_order = Index(s.index).get_indexer(fun)
-            s = s.iloc[col_idx_order]
+            col_idx_order = list(Index(s.index).get_indexer(fun))
+            col_idx_order = [i for i in col_idx_order if 0 <= i < len(s)]
+            if col_idx_order:
+                s = s.iloc[col_idx_order]
 
         # assign the new user-provided "named aggregation" as index names, and reindex
         # it based on the whole user-provided names.
-        s.index = reordered_indexes[idx : idx + len(fun)]
+        if len(s) > 0:
+            s.index = reordered_indexes[idx : idx + len(fun)]
         reordered_result_in_dict[col] = s.reindex(columns)
         idx = idx + len(fun)
     return reordered_result_in_dict

pandas/tests/groupby/aggregate/test_aggregate.py

@@ -62,6 +62,32 @@ def test_agg_ser_multi_key(df):
     tm.assert_series_equal(results, expected)
 
 
+def test_agg_with_missing_values():
+    # GH#58810
+    missing_df = DataFrame(
+        {
+            "nan": [np.nan, np.nan, np.nan, np.nan],
+            "na": [pd.NA, pd.NA, pd.NA, pd.NA],
+            "nat": [pd.NaT, pd.NaT, pd.NaT, pd.NaT],
+            "none": [None, None, None, None],
+            "values": [1, 2, 3, 4],
+        }
+    )
+
+    result = missing_df.agg(x=("nan", "min"), y=("na", "min"), z=("values", "sum"))
+
+    expected = DataFrame(
+        {
+            "nan": [np.nan, np.nan, np.nan],
+            "na": [np.nan, np.nan, np.nan],
+            "values": [np.nan, np.nan, 10.0],
+        },
+        index=["x", "y", "z"],
+    )
+
+    tm.assert_frame_equal(result, expected)
+
+
 def test_groupby_aggregation_mixed_dtype():
     # GH 6212
     expected = DataFrame(