anemoi-datasets 0.5.5__tar.gz → 0.5.6__tar.gz

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/CHANGELOG.md

@@ -8,8 +8,13 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 Please add your functional changes to the appropriate section in the PR.
 Keep it human-readable, your future self will thank you!
 
+## [Unreleased](https://github.com/ecmwf/anemoi-datasets/compare/0.5.5...HEAD)
 
-## [Unreleased](https://github.com/ecmwf/anemoi-datasets/compare/0.5.4...HEAD)
+## [0.5.5](https://github.com/ecmwf/anemoi-datasets/compare/0.5.4...0.5.5) - 2024-10-04
+
+### Changed
+
+- Allow for unknown coordinates when parsing CF input
 
 ## [Add support for (semi-)constant fields](https://github.com/ecmwf/anemoi-datasets/compare/0.5.1...0.5.2) - 2024-10-03
 

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: anemoi-datasets
-Version: 0.5.5
+Version: 0.5.6
 Summary: A package to hold various functions to support training of ML models on ECMWF data.
 Author-email: "European Centre for Medium-Range Weather Forecasts (ECMWF)" <software.support@ecmwf.int>
 License:                                  Apache License

anemoi_datasets-0.5.6/docs/building/filters/yaml/rename.yaml

@@ -0,0 +1,4 @@
+rename:
+  param:
+    from: "old"
+    to: "new"

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/docs/building/sources/netcdf.rst

@@ -4,3 +4,5 @@
 
 .. literalinclude:: yaml/netcdf.yaml
    :language: yaml
+
+.. include:: xarray-based.rst

anemoi_datasets-0.5.6/docs/building/sources/repeated_dates.rst

@@ -0,0 +1,39 @@
+################
+ repeated_dates
+################
+
+The `repeated_dates` source is used to repeat a single source multiple
+times, so that its data is present at multiple dates. A simple example
+of this is when you have source that contains a constant field, such as
+orography or bathymetry, that you want to have repeated at all the dates
+of the dataset.
+
+The generale format of the `repeated_dates` source is:
+
+.. literalinclude:: yaml/repeated_dates1.yaml
+   :language: yaml
+
+where ``source`` is any of the :ref:`operations <operations>` or
+:ref:`sources <sources>` described in the previous sections. The
+``mode`` parameter can be one of the following:
+
+**********
+ constant
+**********
+
+.. literalinclude:: yaml/repeated_dates2.yaml
+   :language: yaml
+
+*************
+ climatology
+*************
+
+.. literalinclude:: yaml/repeated_dates3.yaml
+   :language: yaml
+
+*********
+ closest
+*********
+
+.. literalinclude:: yaml/repeated_dates4.yaml
+   :language: yaml

anemoi_datasets-0.5.6/docs/building/sources/xarray-based.rst

@@ -0,0 +1,13 @@
+This source uses Xarray_ internally to access the data, and assumes that
+it follows the `CF conventions`_.
+
+You specify any valid xarray.open_dataset_ arguments in the source.
+
+.. literalinclude:: yaml/xarray-based.yaml
+   :language: yaml
+
+.. _cf conventions: http://cfconventions.org/
+
+.. _xarray: https://docs.xarray.dev/en/stable/index.html
+
+.. _xarray.open_dataset: https://docs.xarray.dev/en/stable/generated/xarray.open_dataset.html

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/docs/building/sources/xarray-kerchunk.rst

@@ -2,7 +2,7 @@
  xarray-kerchunk
 #################
 
-.. literalinclude:: xarray-kerchunk.yaml
+.. literalinclude:: yaml/xarray-kerchunk.yaml
    :language: yaml
 
 The code below is inspired by the `kerchunk tutorial`_, and makes use of

anemoi_datasets-0.5.6/docs/building/sources/yaml/xarray-based.yaml

@@ -0,0 +1,3 @@
+input:
+   xarray-based-source: # netcdf, zarr, opendap, etc.
+      group: mygroup

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/src/anemoi/datasets/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '0.5.5'
-__version_tuple__ = version_tuple = (0, 5, 5)
+__version__ = version = '0.5.6'
+__version_tuple__ = version_tuple = (0, 5, 6)

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/src/anemoi/datasets/create/functions/sources/xarray/__init__.py

@@ -42,7 +42,7 @@ def load_one(emoji, context, dates, dataset, options={}, flavour=None, **kwargs)
     We have seen this bug triggered when we run many clients in parallel, for example, when we create a new dataset using `xarray-zarr`.
     """
 
-    context.trace(emoji, dataset, options)
+    context.trace(emoji, dataset, options, kwargs)
 
     if isinstance(dataset, str) and ".zarr" in dataset:
         data = xr.open_zarr(name_to_zarr_store(dataset), **options)

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/src/anemoi/datasets/create/functions/sources/xarray/coordinates.py

@@ -244,3 +244,9 @@ class ScalarCoordinate(Coordinate):
     @property
     def mars_names(self):
         return (self.variable.name,)
+
+
+class UnsupportedCoordinate(Coordinate):
+    @property
+    def mars_names(self):
+        return (self.variable.name,)

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/src/anemoi/datasets/create/functions/sources/xarray/flavour.py

@@ -18,6 +18,7 @@ from .coordinates import LongitudeCoordinate
 from .coordinates import ScalarCoordinate
 from .coordinates import StepCoordinate
 from .coordinates import TimeCoordinate
+from .coordinates import UnsupportedCoordinate
 from .coordinates import XCoordinate
 from .coordinates import YCoordinate
 from .coordinates import is_scalar
@@ -157,11 +158,13 @@ class CoordinateGuesser:
         if c.shape in ((1,), tuple()):
             return ScalarCoordinate(c)
 
-        raise NotImplementedError(
+        LOG.warning(
             f"Coordinate {coord} not supported\n{axis=}, {name=},"
             f" {long_name=}, {standard_name=}, units\n\n{c}\n\n{type(c.values)} {c.shape}"
         )
 
+        return UnsupportedCoordinate(c)
+
     def grid(self, coordinates, variable):
         lat = [c for c in coordinates if c.is_lat]
         lon = [c for c in coordinates if c.is_lon]

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/src/anemoi_datasets.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: anemoi-datasets
-Version: 0.5.5
+Version: 0.5.6
 Summary: A package to hold various functions to support training of ML models on ECMWF data.
 Author-email: "European Centre for Medium-Range Weather Forecasts (ECMWF)" <software.support@ecmwf.int>
 License:                                  Apache License

{anemoi_datasets-0.5.5 → anemoi_datasets-0.5.6}/src/anemoi_datasets.egg-info/SOURCES.txt

@@ -57,6 +57,7 @@ docs/building/sources/netcdf.rst
 docs/building/sources/opendap.rst
 docs/building/sources/recentre.rst
 docs/building/sources/repeated_dates.rst
+docs/building/sources/xarray-based.rst
 docs/building/sources/xarray-kerchunk.py
 docs/building/sources/xarray-kerchunk.rst
 docs/building/sources/xarray-zarr.rst
@@ -78,6 +79,7 @@ docs/building/sources/yaml/repeated_dates1.yaml
 docs/building/sources/yaml/repeated_dates2.yaml
 docs/building/sources/yaml/repeated_dates3.yaml
 docs/building/sources/yaml/repeated_dates4.yaml
+docs/building/sources/yaml/xarray-based.yaml
 docs/building/sources/yaml/xarray-kerchunk.yaml
 docs/building/sources/yaml/xarray-zarr.yaml
 docs/building/sources/yaml/zenodo.yaml

anemoi_datasets-0.5.5/docs/building/sources/repeated_dates.rst

@@ -1,29 +0,0 @@
-################
- repeated_dates
-################
-
-The generale format of the `repeated_dates` source is:
-
-.. literalinclude:: yaml/repeated_dates1.yaml
-   :language: yaml
-
-**********
- constant
-**********
-
-.. literalinclude:: yaml/repeated_dates2.yaml
-   :language: yaml
-
-*************
- climatology
-*************
-
-.. literalinclude:: yaml/repeated_dates3.yaml
-   :language: yaml
-
-*********
- closest
-*********
-
-.. literalinclude:: yaml/repeated_dates4.yaml
-   :language: yaml