From 298a75a25616fd0a56d16d08cbf5db0508abcc88 Mon Sep 17 00:00:00 2001 From: Deepak Cherian Date: Wed, 7 May 2025 11:52:26 -0600 Subject: [PATCH] Fix BinGrouper when labels is not specified Closes #10284 --- doc/whats-new.rst | 3 ++- xarray/groupers.py | 2 +- xarray/tests/test_groupby.py | 16 +++++++++++----- 3 files changed, 14 insertions(+), 7 deletions(-) diff --git a/doc/whats-new.rst b/doc/whats-new.rst index cc3bf5ca410..12d2e7ab0da 100644 --- a/doc/whats-new.rst +++ b/doc/whats-new.rst @@ -36,7 +36,8 @@ Deprecations Bug fixes ~~~~~~~~~ - +- Fix :py:class:`~xarray.groupers.BinGrouper` when ``labels`` is not specified (:issue:`10284`). + By `Deepak Cherian `_. Documentation ~~~~~~~~~~~~~ diff --git a/xarray/groupers.py b/xarray/groupers.py index 203acbe37c5..226f98256f7 100644 --- a/xarray/groupers.py +++ b/xarray/groupers.py @@ -413,7 +413,7 @@ def factorize(self, group: T_Group) -> EncodedGroups: # This seems silly, but it lets us have Pandas handle the complexity # of `labels`, `precision`, and `include_lowest`, even when group is a chunked array # Pandas ignores labels when IntervalIndex is passed - if not isinstance(self.bins, pd.IntervalIndex): + if self.labels is None or not isinstance(self.bins, pd.IntervalIndex): dummy, _ = self._cut(np.array([0]).astype(group.dtype)) full_index = dummy.categories else: diff --git a/xarray/tests/test_groupby.py b/xarray/tests/test_groupby.py index fd5f2f5d6d1..0f260eb381d 100644 --- a/xarray/tests/test_groupby.py +++ b/xarray/tests/test_groupby.py @@ -1042,10 +1042,12 @@ def test_groupby_math_bitshift() -> None: assert_equal(right_expected, right_actual) +@pytest.mark.parametrize( + "x_bins", ((0, 2, 4, 6), pd.IntervalIndex.from_breaks((0, 2, 4, 6), closed="left")) +) @pytest.mark.parametrize("use_flox", [True, False]) -def test_groupby_bins_cut_kwargs(use_flox: bool) -> None: +def test_groupby_bins_cut_kwargs(use_flox: bool, x_bins) -> None: da = xr.DataArray(np.arange(12).reshape(6, 2), dims=("x", "y")) - x_bins = (0, 2, 4, 6) with xr.set_options(use_flox=use_flox): actual = da.groupby_bins( @@ -1055,7 +1057,12 @@ def test_groupby_bins_cut_kwargs(use_flox: bool) -> None: np.array([[1.0, 2.0], [5.0, 6.0], [9.0, 10.0]]), dims=("x_bins", "y"), coords={ - "x_bins": ("x_bins", pd.IntervalIndex.from_breaks(x_bins, closed="left")) + "x_bins": ( + "x_bins", + x_bins + if isinstance(x_bins, pd.IntervalIndex) + else pd.IntervalIndex.from_breaks(x_bins, closed="left"), + ) }, ) assert_identical(expected, actual) @@ -1067,9 +1074,8 @@ def test_groupby_bins_cut_kwargs(use_flox: bool) -> None: assert_identical(expected, actual) with xr.set_options(use_flox=use_flox): - bins_index = pd.IntervalIndex.from_breaks(x_bins) labels = ["one", "two", "three"] - actual = da.groupby(x=BinGrouper(bins=bins_index, labels=labels)).sum() + actual = da.groupby(x=BinGrouper(bins=x_bins, labels=labels)).sum() assert actual.xindexes["x_bins"].index.equals(pd.Index(labels)) # type: ignore[attr-defined] pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.

Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy