Keep the original ordering of the coordinates (#4409)

* un-xfail the pint assert_allclose and assert_duckarray_equal tests

* update the required version of pint

* keep the order of the coordinates

* fix the groupby doctest

* keep the order of the dims in concat

* don't compute a set difference if we're filtering anyways

* sort names instead of potentially dropping items

* Apply suggestions from code review

* sort in DatasetCoordinates.to_dataset instead of in Dataset._copy_listed

* update whats-new.rst

* filter _variables instead of sorting _coord_name

Author: keewis

ci/requirements/py36-min-nep18.yml

@@ -10,7 +10,7 @@ dependencies:
   - distributed=2.9
   - numpy=1.17
   - pandas=0.25
-  - pint=0.13
+  - pint=0.15
   - pip
   - pytest
   - pytest-cov

doc/whats-new.rst

@@ -33,7 +33,7 @@ New Features
   now accept more than 1 dimension. (:pull:`4219`)
   By `Keisuke Fujii <https://github.com/fujiisoup>`_.
 - ``min_count`` can be supplied to reductions such as ``.sum`` when specifying
-  multiple dimension to reduce over. (:pull:`4356`) 
+  multiple dimension to reduce over. (:pull:`4356`)
   By `Maximilian Roos <https://github.com/max-sixty>`_.
 - :py:func:`xarray.cov` and :py:func:`xarray.corr` now handle missing values. (:pull:`4351`)
   By `Maximilian Roos <https://github.com/max-sixty>`_.
@@ -77,7 +77,7 @@ Bug fixes
   and :py:meth:`DataArray.str.wrap` (:issue:`4334`). By `Mathias Hauser <https://github.com/mathause>`_.
 - Fixed overflow issue causing incorrect results in computing means of :py:class:`cftime.datetime`
   arrays (:issue:`4341`). By `Spencer Clark <https://github.com/spencerkclark>`_.
-- Fixed :py:meth:`Dataset.coarsen`, :py:meth:`DataArray.coarsen` dropping attributes on original object (:issue:`4120`, :pull:`4360`). by `Julia Kent <https://github.com/jukent>`_.
+- Fixed :py:meth:`Dataset.coarsen`, :py:meth:`DataArray.coarsen` dropping attributes on original object (:issue:`4120`, :pull:`4360`). By `Julia Kent <https://github.com/jukent>`_.
 - fix the signature of the plot methods. (:pull:`4359`) By `Justus Magin <https://github.com/keewis>`_.
 - Fix :py:func:`xarray.apply_ufunc` with ``vectorize=True`` and ``exclude_dims`` (:issue:`3890`).
   By `Mathias Hauser <https://github.com/mathause>`_.
@@ -86,6 +86,8 @@ Bug fixes
   By `Jens Svensmark <https://github.com/jenssss>`_
 - Fix incorrect legend labels for :py:meth:`Dataset.plot.scatter` (:issue:`4126`).
   By `Peter Hausamann <https://github.com/phausamann>`_.
+- Avoid relying on :py:class:`set` objects for the ordering of the coordinates (:pull:`4409`)
+  By `Justus Magin <https://github.com/keewis>`_.
 - Fix indexing with datetime64 scalars with pandas 1.1 (:issue:`4283`).
   By `Stephan Hoyer <https://github.com/shoyer>`_ and
   `Justus Magin <https://github.com/keewis>`_.
@@ -99,6 +101,8 @@ Documentation
   By `Sander van Rijn <https://github.com/sjvrijn>`_
 - Update the contributing guide to use merges instead of rebasing and state
   that we squash-merge. (:pull:`4355`) By `Justus Magin <https://github.com/keewis>`_.
+- Make sure the examples from the docstrings actually work (:pull:`4408`).
+  By `Justus Magin <https://github.com/keewis>`_.
 - Updated Vectorized Indexing to a clearer example.
   By `Maximilian Roos <https://github.com/max-sixty>`_
 

xarray/core/concat.py

@@ -349,7 +349,11 @@ def _parse_datasets(
         all_coord_names.update(ds.coords)
         data_vars.update(ds.data_vars)
 
-        for dim in set(ds.dims) - dims:
+        # preserves ordering of dimensions
+        for dim in ds.dims:
+            if dim in dims:
+                continue
+
             if dim not in dim_coords:
                 dim_coords[dim] = ds.coords[dim].variable
         dims = dims | set(ds.dims)

xarray/core/coordinates.py

@@ -215,7 +215,9 @@ def __getitem__(self, key: Hashable) -> "DataArray":
 
     def to_dataset(self) -> "Dataset":
         """Convert these coordinates into a new Dataset"""
-        return self._data._copy_listed(self._names)
+
+        names = [name for name in self._data._variables if name in self._names]
+        return self._data._copy_listed(names)
 
     def _update_coords(
         self, coords: Dict[Hashable, Variable], indexes: Mapping[Hashable, pd.Index]

xarray/core/dataset.py

@@ -1142,7 +1142,11 @@ def _copy_listed(self, names: Iterable[Hashable]) -> "Dataset":
 
         dims = {k: self.dims[k] for k in needed_dims}
 
-        for k in self._coord_names:
+        # preserves ordering of coordinates
+        for k in self._variables:
+            if k not in self._coord_names:
+                continue
+
             if set(self.variables[k].dims) <= needed_dims:
                 variables[k] = self._variables[k]
                 coord_names.add(k)
@@ -5729,10 +5733,10 @@ def filter_by_attrs(self, **kwargs):
         <xarray.Dataset>
         Dimensions:         (time: 3, x: 2, y: 2)
         Coordinates:
-            reference_time  datetime64[ns] 2014-09-05
+            lon             (x, y) float64 -99.83 -99.32 -99.79 -99.23
             lat             (x, y) float64 42.25 42.21 42.63 42.59
           * time            (time) datetime64[ns] 2014-09-06 2014-09-07 2014-09-08
-            lon             (x, y) float64 -99.83 -99.32 -99.79 -99.23
+            reference_time  datetime64[ns] 2014-09-05
         Dimensions without coordinates: x, y
         Data variables:
             precipitation   (x, y, time) float64 5.68 9.256 0.7104 ... 7.992 4.615 7.805
@@ -5742,10 +5746,10 @@ def filter_by_attrs(self, **kwargs):
         <xarray.Dataset>
         Dimensions:         (time: 3, x: 2, y: 2)
         Coordinates:
-            reference_time  datetime64[ns] 2014-09-05
+            lon             (x, y) float64 -99.83 -99.32 -99.79 -99.23
             lat             (x, y) float64 42.25 42.21 42.63 42.59
           * time            (time) datetime64[ns] 2014-09-06 2014-09-07 2014-09-08
-            lon             (x, y) float64 -99.83 -99.32 -99.79 -99.23
+            reference_time  datetime64[ns] 2014-09-05
         Dimensions without coordinates: x, y
         Data variables:
             temperature     (x, y, time) float64 29.11 18.2 22.83 ... 18.28 16.15 26.63

xarray/tests/test_testing.py

@@ -70,12 +70,7 @@ def test_assert_allclose(obj1, obj2):
         pytest.param(
             quantity,
             id="pint",
-            marks=[
-                pytest.mark.skipif(not has_pint, reason="requires pint"),
-                pytest.mark.xfail(
-                    reason="inconsistencies in the return value of pint's implementation of eq"
-                ),
-            ],
+            marks=pytest.mark.skipif(not has_pint, reason="requires pint"),
         ),
     ),
 )
@@ -115,12 +110,7 @@ def test_assert_duckarray_equal_failing(duckarray, obj1, obj2):
         pytest.param(
             quantity,
             id="pint",
-            marks=[
-                pytest.mark.skipif(not has_pint, reason="requires pint"),
-                pytest.mark.xfail(
-                    reason="inconsistencies in the return value of pint's implementation of eq"
-                ),
-            ],
+            marks=pytest.mark.skipif(not has_pint, reason="requires pint"),
         ),
     ),
 )