climate-ref-core 0.6.4__tar.gz → 0.6.5__tar.gz

{climate_ref_core-0.6.4 → climate_ref_core-0.6.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: climate-ref-core
-Version: 0.6.4
+Version: 0.6.5
 Summary: Core library for the CMIP Rapid Evaluation Framework
 Author-email: Jared Lewis <jared.lewis@climate-resource.com>, Mika Pflueger <mika.pflueger@climate-resource.com>, Bouwe Andela <b.andela@esciencecenter.nl>, Jiwoo Lee <lee1043@llnl.gov>, Min Xu <xum1@ornl.gov>, Nathan Collier <collierno@ornl.gov>, Dora Hegedus <dora.hegedus@stfc.ac.uk>
 License-Expression: Apache-2.0

{climate_ref_core-0.6.4 → climate_ref_core-0.6.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "climate-ref-core"
-version = "0.6.4"
+version = "0.6.5"
 description = "Core library for the CMIP Rapid Evaluation Framework"
 readme = "README.md"
 authors = [

{climate_ref_core-0.6.4 → climate_ref_core-0.6.5}/src/climate_ref_core/constraints.py

@@ -200,17 +200,27 @@ class AddSupplementaryDataset:
         for facet, values in supplementary_facets.items():
             mask = supplementary_group[facet].isin(values)
             supplementary_group = supplementary_group[mask]
-
-        if not supplementary_group.empty and self.optional_matching_facets:
-            facets = list(self.matching_facets + self.optional_matching_facets)
+        if not supplementary_group.empty:
+            matching_facets = list(self.matching_facets)
+            facets = matching_facets + list(self.optional_matching_facets)
             datasets = group[facets].drop_duplicates()
             indices = set()
             for i in range(len(datasets)):
-                scores = (supplementary_group[facets] == datasets.iloc[i]).sum(axis=1)
-                matches = supplementary_group[scores == scores.max()]
-                # Select the latest version if there are multiple matches
-                matches = matches[matches["version"] == matches["version"].max()]
-                indices.add(matches.index[0])
+                dataset = datasets.iloc[i]
+                # Restrict the supplementary datasets to those that match the main dataset.
+                supplementaries = supplementary_group[
+                    (supplementary_group[matching_facets] == dataset[matching_facets]).all(1)
+                ]
+                if not supplementaries.empty:
+                    # Select the best matching supplementary dataset based on the optional matching facets.
+                    scores = (supplementaries[facets] == dataset).sum(axis=1)
+                    matches = supplementaries[scores == scores.max()]
+                    if "version" in facets:
+                        # Select the latest version if there are multiple matches
+                        matches = matches[matches["version"] == matches["version"].max()]
+                    # Select one match per dataset
+                    indices.add(matches.index[0])
+
             supplementary_group = supplementary_group.loc[list(indices)].drop_duplicates()
 
         return pd.concat([group, supplementary_group])

{climate_ref_core-0.6.4 → climate_ref_core-0.6.5}/tests/unit/test_constraints.py

@@ -60,6 +60,21 @@ class TestAddSupplementaryDataset:
                 ),
                 [0],
             ),
+            (
+                # Test that missing supplementary files are handled gracefully.
+                pd.DataFrame(
+                    {
+                        "variable_id": ["tas", "areacella", "areacella", "tas"],
+                        "source_id": ["X", "X", "X", "Y"],
+                        "grid_label": ["gn"] * 4,
+                        "table_id": ["Amon", "fx", "fx", "Amon"],
+                        "experiment_id": ["historical"] * 4,
+                        "member_id": ["r1i1p1f1", "r1i1p1f1", "r2i1p1f1", "r2i1p1f1"],
+                        "version": ["v20210316", "v20210316", "v20210317", "v20210317"],
+                    }
+                ),
+                [0, 3, 1],
+            ),
             (
                 # Test that the grid_label matches.
                 pd.DataFrame(
@@ -68,7 +83,7 @@ class TestAddSupplementaryDataset:
                         "source_id": ["ACCESS-ESM1-5"] * 3,
                         "grid_label": ["gn", "gn", "gr"],
                         "table_id": ["Amon", "fx", "fx"],
-                        "experiment_id": ["historical"] * 3,
+                        "experiment_id": ["historical", "piControl", "historical"],
                         "member_id": ["r1i1p1f1", "r2i1p1f1", "r1i1p1f1"],
                         "version": ["v20210316"] * 3,
                     }