From e631442400b0417c638d394d9d9af0e018cf366b Mon Sep 17 00:00:00 2001 From: Nitish Satyavolu Date: Mon, 2 Dec 2024 16:15:57 -0800 Subject: [PATCH] BUG: Maintain column order in table method rolling (#60465) * BUG: Maintain column order in table method rolling * BUG: Add bug description to whatsnew/v3.0.0.rst --- doc/source/whatsnew/v3.0.0.rst | 1 + pandas/core/window/rolling.py | 2 +- pandas/tests/window/test_numba.py | 32 +++++++++++++++++++++++++++++++ 3 files changed, 34 insertions(+), 1 deletion(-) diff --git a/doc/source/whatsnew/v3.0.0.rst b/doc/source/whatsnew/v3.0.0.rst index e73ee0dfbe67e..f4e7281ca0659 100644 --- a/doc/source/whatsnew/v3.0.0.rst +++ b/doc/source/whatsnew/v3.0.0.rst @@ -737,6 +737,7 @@ Groupby/resample/rolling - Bug in :meth:`DataFrameGroupBy.cumsum` and :meth:`DataFrameGroupBy.cumprod` where ``numeric_only`` parameter was passed indirectly through kwargs instead of passing directly. (:issue:`58811`) - Bug in :meth:`DataFrameGroupBy.cumsum` where it did not return the correct dtype when the label contained ``None``. (:issue:`58811`) - Bug in :meth:`DataFrameGroupby.transform` and :meth:`SeriesGroupby.transform` with a reducer and ``observed=False`` that coerces dtype to float when there are unobserved categories. (:issue:`55326`) +- Bug in :meth:`Rolling.apply` for ``method="table"`` where column order was not being respected due to the columns getting sorted by default. (:issue:`59666`) - Bug in :meth:`Rolling.apply` where the applied function could be called on fewer than ``min_period`` periods if ``method="table"``. (:issue:`58868`) - Bug in :meth:`Series.resample` could raise when the the date range ended shortly before a non-existent time. (:issue:`58380`) diff --git a/pandas/core/window/rolling.py b/pandas/core/window/rolling.py index b1c37ab48fa57..4446b21976069 100644 --- a/pandas/core/window/rolling.py +++ b/pandas/core/window/rolling.py @@ -269,7 +269,7 @@ def _create_data(self, obj: NDFrameT, numeric_only: bool = False) -> NDFrameT: """ # filter out the on from the object if self.on is not None and not isinstance(self.on, Index) and obj.ndim == 2: - obj = obj.reindex(columns=obj.columns.difference([self.on])) + obj = obj.reindex(columns=obj.columns.difference([self.on], sort=False)) if obj.ndim > 1 and numeric_only: obj = self._make_numeric_only(obj) return obj diff --git a/pandas/tests/window/test_numba.py b/pandas/tests/window/test_numba.py index d9ab4723a8f2c..120dbe788a23f 100644 --- a/pandas/tests/window/test_numba.py +++ b/pandas/tests/window/test_numba.py @@ -459,6 +459,38 @@ def f(x): ) tm.assert_frame_equal(result, expected) + def test_table_method_rolling_apply_col_order(self): + # GH#59666 + def f(x): + return np.nanmean(x[:, 0] - x[:, 1]) + + df = DataFrame( + { + "a": [1, 2, 3, 4, 5, 6], + "b": [6, 7, 8, 5, 6, 7], + } + ) + result = df.rolling(3, method="table", min_periods=0)[["a", "b"]].apply( + f, raw=True, engine="numba" + ) + expected = DataFrame( + { + "a": [-5, -5, -5, -3.66667, -2.33333, -1], + "b": [-5, -5, -5, -3.66667, -2.33333, -1], + } + ) + tm.assert_almost_equal(result, expected) + result = df.rolling(3, method="table", min_periods=0)[["b", "a"]].apply( + f, raw=True, engine="numba" + ) + expected = DataFrame( + { + "b": [5, 5, 5, 3.66667, 2.33333, 1], + "a": [5, 5, 5, 3.66667, 2.33333, 1], + } + ) + tm.assert_almost_equal(result, expected) + def test_table_method_rolling_weighted_mean(self, step): def weighted_mean(x): arr = np.ones((1, x.shape[1]))