Backport PR #39260: REGR: fix numpy accumulate ufuncs for DataFrame (#39273)

Co-authored-by: Joris Van den Bossche <[email protected]>

Author: meeseeksmachine

doc/source/whatsnew/v1.2.1.rst

@@ -32,6 +32,7 @@ Fixed regressions
 - Fixed regression in :meth:`DataFrame.replace` raising ``ValueError`` when :class:`DataFrame` has dtype ``bytes`` (:issue:`38900`)
 - Fixed regression in :meth:`Series.fillna` that raised ``RecursionError`` with ``datetime64[ns, UTC]`` dtype (:issue:`38851`)
 - Fixed regression in comparisons between ``NaT`` and ``datetime.date`` objects incorrectly returning ``True`` (:issue:`39151`)
+- Fixed regression in calling NumPy :func:`~numpy.ufunc.accumulate` ufuncs on DataFrames, e.g. ``np.maximum.accumulate(df)`` (:issue:`39259`)
 - Fixed regression in repr of float-like strings of an ``object`` dtype having trailing 0's truncated after the decimal (:issue:`38708`)
 - Fixed regression that raised ``AttributeError`` with PyArrow versions [0.16.0, 1.0.0) (:issue:`38801`)
 - Fixed regression in :func:`pandas.testing.assert_frame_equal` raising ``TypeError`` with ``check_like=True`` when :class:`Index` or columns have mixed dtype (:issue:`39168`)

pandas/core/arraylike.py

@@ -274,8 +274,14 @@ def reconstruct(result):
         result = getattr(ufunc, method)(*inputs, **kwargs)
     else:
         # ufunc(dataframe)
-        mgr = inputs[0]._mgr
-        result = mgr.apply(getattr(ufunc, method))
+        if method == "__call__":
+            # for np.<ufunc>(..) calls
+            mgr = inputs[0]._mgr
+            result = mgr.apply(getattr(ufunc, method))
+        else:
+            # otherwise specific ufunc methods (eg np.<ufunc>.accumulate(..))
+            # Those can have an axis keyword and thus can't be called block-by-block
+            result = getattr(ufunc, method)(np.asarray(inputs[0]), **kwargs)
 
     if ufunc.nout > 1:  # type: ignore[attr-defined]
         result = tuple(reconstruct(x) for x in result)

pandas/tests/frame/test_ufunc.py

@@ -105,6 +105,27 @@ def test_binary_frame_series_raises():
         np.logaddexp(df["A"], df)
 
 
+def test_unary_accumulate_axis():
+    # https://github.com/pandas-dev/pandas/issues/39259
+    df = pd.DataFrame({"a": [1, 3, 2, 4]})
+    result = np.maximum.accumulate(df)
+    expected = pd.DataFrame({"a": [1, 3, 3, 4]})
+    tm.assert_frame_equal(result, expected)
+
+    df = pd.DataFrame({"a": [1, 3, 2, 4], "b": [0.1, 4.0, 3.0, 2.0]})
+    result = np.maximum.accumulate(df)
+    # in theory could preserve int dtype for default axis=0
+    expected = pd.DataFrame({"a": [1.0, 3.0, 3.0, 4.0], "b": [0.1, 4.0, 4.0, 4.0]})
+    tm.assert_frame_equal(result, expected)
+
+    result = np.maximum.accumulate(df, axis=0)
+    tm.assert_frame_equal(result, expected)
+
+    result = np.maximum.accumulate(df, axis=1)
+    expected = pd.DataFrame({"a": [1.0, 3.0, 2.0, 4.0], "b": [1.0, 4.0, 3.0, 4.0]})
+    tm.assert_frame_equal(result, expected)
+
+
 def test_frame_outer_deprecated():
     df = pd.DataFrame({"A": [1, 2]})
     with tm.assert_produces_warning(FutureWarning):