BUG: Validate numeric_only parameter in groupby aggregations (pandas-dev#62842)

Co-authored-by: Zrahay <shubhangsinha4@gmail.com>

Author: 2 people

doc/source/whatsnew/v3.0.0.rst

@@ -1151,6 +1151,7 @@ Groupby/resample/rolling
 - Bug in :meth:`.DataFrameGroupBy.groups` and :meth:`.SeriesGroupby.groups` that would not respect groupby argument ``dropna`` (:issue:`55919`)
 - Bug in :meth:`.DataFrameGroupBy.median` where nat values gave an incorrect result. (:issue:`57926`)
 - Bug in :meth:`.DataFrameGroupBy.quantile` when ``interpolation="nearest"`` is inconsistent with :meth:`DataFrame.quantile` (:issue:`47942`)
+- Bug in :meth:`.DataFrameGroupBy` reductions where non-Boolean values were allowed for the ``numeric_only`` argument; passing a non-Boolean value will now raise (:issue:`62778`)
 - Bug in :meth:`.Resampler.interpolate` on a :class:`DataFrame` with non-uniform sampling and/or indices not aligning with the resulting resampled index would result in wrong interpolation (:issue:`21351`)
 - Bug in :meth:`.Series.rolling` when used with a :class:`.BaseIndexer` subclass and computing min/max (:issue:`46726`)
 - Bug in :meth:`DataFrame.ewm` and :meth:`Series.ewm` when passed ``times`` and aggregation functions other than mean (:issue:`51695`)

pandas/core/groupby/groupby.py

@@ -76,6 +76,7 @@ class providing the base-class of operations.
     ensure_dtype_can_hold_na,
 )
 from pandas.core.dtypes.common import (
+    is_bool,
     is_bool_dtype,
     is_float_dtype,
     is_hashable,
@@ -109,9 +110,7 @@ class providing the base-class of operations.
     SparseArray,
 )
 from pandas.core.arrays.string_ import StringDtype
-from pandas.core.arrays.string_arrow import (
-    ArrowStringArray,
-)
+from pandas.core.arrays.string_arrow import ArrowStringArray
 from pandas.core.base import (
     PandasObject,
     SelectionMixin,
@@ -1756,6 +1755,9 @@ def _cython_agg_general(
         # Note: we never get here with how="ohlc" for DataFrameGroupBy;
         #  that goes through SeriesGroupBy
 
+        if not is_bool(numeric_only):
+            raise ValueError("numeric_only accepts only Boolean values")
+
         data = self._get_data_to_aggregate(numeric_only=numeric_only, name=how)
 
         def array_func(values: ArrayLike) -> ArrayLike:

pandas/tests/groupby/test_reductions.py

@@ -1520,3 +1520,19 @@ def test_groupby_std_datetimelike():
     exp_ser = Series([td1 * 2, td1, td1, td1, td4], index=np.arange(5))
     expected = DataFrame({"A": exp_ser, "B": exp_ser, "C": exp_ser})
     tm.assert_frame_equal(result, expected)
+
+
+def test_mean_numeric_only_validates_bool():
+    # GH#62778
+
+    df = DataFrame({"A": range(5), "B": range(5)})
+
+    msg = "numeric_only accepts only Boolean values"
+    with pytest.raises(ValueError, match=msg):
+        df.groupby(["A"]).mean(["B"])
+
+    with pytest.raises(ValueError, match=msg):
+        df.groupby(["A"]).mean(numeric_only="True")
+
+    with pytest.raises(ValueError, match=msg):
+        df.groupby(["A"]).mean(numeric_only=1)