BUG: Fix SeriesGroupBy.quantile for nullable integers (#33138)

Author: dsaxton

doc/source/whatsnew/v1.1.0.rst

@@ -445,6 +445,7 @@ Groupby/resample/rolling
 - Bug in :meth:`DataFrameGroupby.transform` produces incorrect result with transformation functions (:issue:`30918`)
 - Bug in :meth:`GroupBy.count` causes segmentation fault when grouped-by column contains NaNs (:issue:`32841`)
 - Bug in :meth:`DataFrame.groupby` and :meth:`Series.groupby` produces inconsistent type when aggregating Boolean series (:issue:`32894`)
+- Bug in :meth:`SeriesGroupBy.quantile` raising on nullable integers (:issue:`33136`)
 - Bug in :meth:`SeriesGroupBy.first`, :meth:`SeriesGroupBy.last`, :meth:`SeriesGroupBy.min`, and :meth:`SeriesGroupBy.max` returning floats when applied to nullable Booleans (:issue:`33071`)
 - Bug in :meth:`DataFrameGroupBy.agg` with dictionary input losing ``ExtensionArray`` dtypes (:issue:`32194`)
 - Bug in :meth:`DataFrame.resample` where an ``AmbiguousTimeError`` would be raised when the resulting timezone aware :class:`DatetimeIndex` had a DST transition at midnight (:issue:`25758`)

pandas/core/groupby/groupby.py

@@ -44,7 +44,9 @@ class providing the base-class of operations.
 from pandas.core.dtypes.cast import maybe_cast_result
 from pandas.core.dtypes.common import (
     ensure_float,
+    is_bool_dtype,
     is_datetime64_dtype,
+    is_extension_array_dtype,
     is_integer_dtype,
     is_numeric_dtype,
     is_object_dtype,
@@ -1867,9 +1869,13 @@ def pre_processor(vals: np.ndarray) -> Tuple[np.ndarray, Optional[Type]]:
                 )
 
             inference = None
-            if is_integer_dtype(vals):
+            if is_integer_dtype(vals.dtype):
+                if is_extension_array_dtype(vals.dtype):
+                    vals = vals.to_numpy(dtype=float, na_value=np.nan)
                 inference = np.int64
-            elif is_datetime64_dtype(vals):
+            elif is_bool_dtype(vals.dtype) and is_extension_array_dtype(vals.dtype):
+                vals = vals.to_numpy(dtype=float, na_value=np.nan)
+            elif is_datetime64_dtype(vals.dtype):
                 inference = "datetime64[ns]"
                 vals = np.asarray(vals).astype(np.float)
 

pandas/tests/groupby/test_function.py

@@ -1519,6 +1519,30 @@ def test_quantile_missing_group_values_correct_results():
     tm.assert_frame_equal(result, expected)
 
 
+@pytest.mark.parametrize(
+    "values",
+    [
+        pd.array([1, 0, None] * 2, dtype="Int64"),
+        pd.array([True, False, None] * 2, dtype="boolean"),
+    ],
+)
+@pytest.mark.parametrize("q", [0.5, [0.0, 0.5, 1.0]])
+def test_groupby_quantile_nullable_array(values, q):
+    # https://github.com/pandas-dev/pandas/issues/33136
+    df = pd.DataFrame({"a": ["x"] * 3 + ["y"] * 3, "b": values})
+    result = df.groupby("a")["b"].quantile(q)
+
+    if isinstance(q, list):
+        idx = pd.MultiIndex.from_product((["x", "y"], q), names=["a", None])
+        true_quantiles = [0.0, 0.5, 1.0]
+    else:
+        idx = pd.Index(["x", "y"], name="a")
+        true_quantiles = [0.5]
+
+    expected = pd.Series(true_quantiles * 2, index=idx, name="b")
+    tm.assert_series_equal(result, expected)
+
+
 # pipe
 # --------------------------------