BUG: groupby raises on non-C-contiguous masks (#63148)

Author: rhshadrach

doc/source/whatsnew/v3.0.0.rst

@@ -1267,6 +1267,7 @@ Groupby/resample/rolling
 - Bug in :meth:`Series.resample` could raise when the date range ended shortly before a non-existent time. (:issue:`58380`)
 - Bug in :meth:`Series.resample` raising error when resampling non-nanosecond resolutions out of bounds for nanosecond precision (:issue:`57427`)
 - Bug in :meth:`Series.rolling.var` and :meth:`Series.rolling.std` computing incorrect results due to numerical instability. (:issue:`47721`, :issue:`52407`, :issue:`54518`, :issue:`55343`)
+- Bug in :meth:`DataFrame.groupby` methods when operating on NumPy-nullable data failing when the NA mask was not C-contiguous (:issue:`61031`)
 
 Reshaping
 ^^^^^^^^^

pandas/_libs/groupby.pyx

@@ -819,7 +819,7 @@ def group_prod(
     int64_t[::1] counts,
     ndarray[int64float_t, ndim=2] values,
     const intp_t[::1] labels,
-    const uint8_t[:, ::1] mask,
+    const uint8_t[:, :] mask,
     uint8_t[:, ::1] result_mask=None,
     Py_ssize_t min_count=0,
     bint skipna=True,
@@ -893,7 +893,7 @@ def group_var(
     const intp_t[::1] labels,
     Py_ssize_t min_count=-1,
     int64_t ddof=1,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
     bint is_datetimelike=False,
     str name="var",
@@ -998,7 +998,7 @@ def group_skew(
     int64_t[::1] counts,
     ndarray[float64_t, ndim=2] values,
     const intp_t[::1] labels,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
     bint skipna=True,
 ) -> None:
@@ -1086,7 +1086,7 @@ def group_kurt(
     int64_t[::1] counts,
     ndarray[float64_t, ndim=2] values,
     const intp_t[::1] labels,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
     bint skipna=True,
 ) -> None:
@@ -1180,7 +1180,7 @@ def group_mean(
     const intp_t[::1] labels,
     Py_ssize_t min_count=-1,
     bint is_datetimelike=False,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
     bint skipna=True,
 ) -> None:
@@ -1324,7 +1324,7 @@ def group_ohlc(
     ndarray[int64float_t, ndim=2] values,
     const intp_t[::1] labels,
     Py_ssize_t min_count=-1,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
 ) -> None:
     """
@@ -1870,7 +1870,7 @@ cdef group_min_max(
     Py_ssize_t min_count=-1,
     bint is_datetimelike=False,
     bint compute_max=True,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
     bint skipna=True,
 ):
@@ -1983,7 +1983,7 @@ def group_idxmin_idxmax(
     const intp_t[::1] labels,
     Py_ssize_t min_count=-1,
     bint is_datetimelike=False,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     str name="idxmin",
     bint skipna=True,
     uint8_t[:, ::1] result_mask=None,
@@ -2096,7 +2096,7 @@ def group_max(
     const intp_t[::1] labels,
     Py_ssize_t min_count=-1,
     bint is_datetimelike=False,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
     bint skipna=True,
 ) -> None:
@@ -2124,7 +2124,7 @@ def group_min(
     const intp_t[::1] labels,
     Py_ssize_t min_count=-1,
     bint is_datetimelike=False,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
     bint skipna=True,
 ) -> None:
@@ -2148,7 +2148,7 @@ def group_min(
 cdef group_cummin_max(
     numeric_t[:, ::1] out,
     ndarray[numeric_t, ndim=2] values,
-    const uint8_t[:, ::1] mask,
+    const uint8_t[:, :] mask,
     uint8_t[:, ::1] result_mask,
     const intp_t[::1] labels,
     int ngroups,
@@ -2264,7 +2264,7 @@ def group_cummin(
     const intp_t[::1] labels,
     int ngroups,
     bint is_datetimelike,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
     bint skipna=True,
 ) -> None:
@@ -2290,7 +2290,7 @@ def group_cummax(
     const intp_t[::1] labels,
     int ngroups,
     bint is_datetimelike,
-    const uint8_t[:, ::1] mask=None,
+    const uint8_t[:, :] mask=None,
     uint8_t[:, ::1] result_mask=None,
     bint skipna=True,
 ) -> None:

pandas/tests/groupby/test_all_methods.py

@@ -84,3 +84,22 @@ def test_dup_labels_output_shape(groupby_func, idx):
 
     assert result.shape == (1, 2)
     tm.assert_index_equal(result.columns, idx)
+
+
+def test_not_c_contiguous_mask(groupby_func):
+    # https://github.com/pandas-dev/pandas/issues/61031
+    if groupby_func == "corrwith":
+        # corrwith is deprecated
+        return
+    df = DataFrame({"a": [1, 1, 2], "b": [3, 4, 5]}, dtype="Int64")
+    reversed = DataFrame(
+        {"a": [2, 1, 1], "b": [5, 4, 3]}, dtype="Int64", index=[2, 1, 0]
+    )[::-1]
+    assert not reversed["b"].array._mask.flags["C_CONTIGUOUS"]
+    args = get_groupby_method_args(groupby_func, df)
+
+    gb_reversed = reversed.groupby("a")
+    result = getattr(gb_reversed, groupby_func)(*args)
+    gb = df.groupby("a")
+    expected = getattr(gb, groupby_func)(*args)
+    tm.assert_equal(result, expected)