Merge branch 'mllam:main' into feat/prediction_constraints

CHANGELOG.md

@@ -20,12 +20,21 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 ### Fixed
 - Only print on rank 0 to avoid duplicates of all print statements.
 [\#103](https://github.com/mllam/neural-lam/pull/103) @simonkamuk @sadamov
+
+- Fix MLFlow exception import introduced in [\#77](https://github.com/mllam/neural-lam/pull/77).
+  [\#111](https://github.com/mllam/neural-lam/pull/111)
+  @observingClouds
+
 - Fix duplicate tensor copy to CPU [\#106](https://github.com/mllam/neural-lam/pull/106) @observingClouds
 
 ### Maintenance
 - update ci/cd testing setup to install torch version compatible with neural-lam
   dependencies [\#115](https://github.com/mllam/neural-lam/pull/115), @leifdenby
 
+- switch to new npyfiles MEPS and mdp DANRA test datasets which are coincident
+  in time and space (on cropped ~100x100 grid-point domain)
+  [\#110](https://github.com/mllam/neural-lam/pull/110), @leifdenby
+
 
 ## [v0.3.0](https://github.com/mllam/neural-lam/releases/tag/v0.3.0)
 

neural_lam/custom_loggers.py

@@ -49,7 +49,7 @@ def log_image(self, key, images, step=None):
             Step to log the image under. If None, logs under the key directly
         """
         # Third-party
-        import botocore
+        from botocore.exceptions import NoCredentialsError
         from PIL import Image
 
         if step is not None:
@@ -63,6 +63,6 @@ def log_image(self, key, images, step=None):
         img = Image.open(temporary_image)
         try:
             mlflow.log_image(img, f"{key}.png")
-        except botocore.exceptions.NoCredentialsError:
+        except NoCredentialsError:
             logger.error("Error logging image\nSet AWS credentials")
             sys.exit(1)

tests/datastore_examples/mdp/danra_100m_winds/README.md

@@ -0,0 +1,5 @@
+# Cropped DANRA test dataset
+
+The `danra.datastore.yaml` datastore config file in this directory points to a cropped version of DANRA. It was designed to be coincident in time and space with the npyfiles MEPS example dataset. The cropped domain is approximately 100x100 grid points centered on Copenhagen, Denmark. The time spans the first 2 weeks of April 2022.
+
+See https://github.com/mllam/mllam-testdata/tree/2025-02-05 for further details.

tests/datastore_examples/npyfilesmeps/README.md

@@ -0,0 +1,5 @@
+# Cropped DANRA test dataset
+
+The `meps_example_reduced/meps_example_reduced.datastore.yaml` datastore config file in this directory points to a cropped version of the MEPS April 2022 example dataset. It was designed to be coincident in time and space with the mdp DANRA example dataset. The cropped domain is approximately 100x100 grid points centered on Copenhagen, Denmark. The time spans the first 2 weeks of April 2022.
+
+See https://github.com/mllam/mllam-testdata/tree/2025-02-05 for further details.