climate-ref 0.5.0__py3-none-any.whl → 0.5.2__py3-none-any.whl

climate_ref/solver.py

@@ -25,21 +25,16 @@ from climate_ref.models import Provider as ProviderModel
 from climate_ref.models.execution import Execution
 from climate_ref.provider_registry import ProviderRegistry
 from climate_ref_core.constraints import apply_constraint
-from climate_ref_core.datasets import DatasetCollection, ExecutionDatasetCollection, SourceDatasetType
+from climate_ref_core.datasets import (
+    DatasetCollection,
+    ExecutionDatasetCollection,
+    Selector,
+    SourceDatasetType,
+)
 from climate_ref_core.diagnostics import DataRequirement, Diagnostic, ExecutionDefinition
 from climate_ref_core.exceptions import InvalidDiagnosticException
 from climate_ref_core.providers import DiagnosticProvider
 
-SelectorKey = tuple[tuple[str, str], ...]
-"""
-Type describing the key used to identify a group of datasets
-
-This is a tuple of tuples, where each inner tuple contains a metadata and dimension value
-that was used to group the datasets together.
-
-This SelectorKey type must be hashable, as it is used as a key in a dictionary.
-"""
-
 
 @frozen
 class DiagnosticExecution:
@@ -81,20 +76,14 @@ class DiagnosticExecution:
         return "__".join(key_values)
 
     @property
-    def selectors(self) -> dict[str, SelectorKey]:
+    def selectors(self) -> dict[str, Selector]:
         """
         Collection of selectors used to identify the datasets
 
         These are the key, value pairs that were selected during the initial group-by,
         for each data requirement.
         """
-        # The "value" of SourceType is used here so this can be stored in the db
-        s = {}
-        for source_type in SourceDatasetType.ordered():
-            if source_type not in self.datasets:
-                continue
-            s[source_type.value] = self.datasets[source_type].selector
-        return s
+        return self.datasets.selectors
 
     def build_execution_definition(self, output_root: pathlib.Path) -> ExecutionDefinition:
         """
@@ -107,6 +96,7 @@ class DiagnosticExecution:
         fragment = pathlib.Path() / self.provider.slug / self.diagnostic.slug / self.datasets.hash
 
         return ExecutionDefinition(
+            diagnostic=self.diagnostic,
             root_directory=output_root,
             output_directory=output_root / fragment,
             key=self.dataset_key,
@@ -116,7 +106,7 @@ class DiagnosticExecution:
 
 def extract_covered_datasets(
     data_catalog: pd.DataFrame, requirement: DataRequirement
-) -> dict[SelectorKey, pd.DataFrame]:
+) -> dict[Selector, pd.DataFrame]:
     """
     Determine the different diagnostic executions that should be performed with the current data catalog
     """
@@ -140,8 +130,8 @@ def extract_covered_datasets(
 
     for name, group in groups:
         if requirement.group_by is None:
-            assert len(groups) == 1  # noqa: S101
-            group_keys: SelectorKey = ()
+            assert len(groups) == 1
+            group_keys: Selector = ()
         else:
             group_keys = tuple(zip(requirement.group_by, name))
         constrained_group = _process_group_constraints(data_catalog, group, requirement)
@@ -238,12 +228,12 @@ def _solve_from_data_requirements(
             diagnostic=diagnostic,
             datasets=ExecutionDatasetCollection(
                 {
-                    key: DatasetCollection(
-                        datasets=dataset_groups[key][dataset_group_key],
-                        slug_column=get_dataset_adapter(key.value).slug_column,
-                        selector=dataset_group_key,
+                    source_type: DatasetCollection(
+                        datasets=dataset_groups[source_type][selector],
+                        slug_column=get_dataset_adapter(source_type.value).slug_column,
+                        selector=selector,
                     )
-                    for key, dataset_group_key in zip(dataset_groups.keys(), items)
+                    for source_type, selector in zip(dataset_groups.keys(), items)
                 }
             ),
         )
@@ -341,7 +331,7 @@ def solve_required_executions(
 
         # Use a transaction to make sure that the models
         # are created correctly before potentially executing out of process
-        with db.session.begin(nested=True):
+        with db.session.begin():
             diagnostic = (
                 db.session.query(DiagnosticModel)
                 .join(DiagnosticModel.provider)
@@ -386,8 +376,6 @@ def solve_required_executions(
                 execution.register_datasets(db, definition.datasets)
 
                 executor.run(
-                    provider=potential_execution.provider,
-                    diagnostic=potential_execution.diagnostic,
                     definition=definition,
                     execution=execution,
                 )

climate_ref/testing.py

@@ -10,7 +10,7 @@ from loguru import logger
 from climate_ref.config import Config
 from climate_ref.database import Database
 from climate_ref.executor import handle_execution_result
-from climate_ref.models import Execution
+from climate_ref.models import Execution, ExecutionGroup
 from climate_ref_core.dataset_registry import dataset_registry_manager, fetch_all_files
 from climate_ref_core.diagnostics import Diagnostic, ExecutionResult
 from climate_ref_core.pycmec.metric import CMECMetric
@@ -26,7 +26,7 @@ def _determine_test_directory() -> Path | None:
 
 
 TEST_DATA_DIR = _determine_test_directory()
-SAMPLE_DATA_VERSION = "v0.5.0"
+SAMPLE_DATA_VERSION = "v0.5.2"
 
 
 def fetch_sample_data(force_cleanup: bool = False, symlink: bool = False) -> None:
@@ -82,10 +82,16 @@ def validate_result(diagnostic: Diagnostic, config: Config, result: ExecutionRes
     This should only be used by the test suite as it will create a fake
     database entry for the diagnostic execution result.
     """
-    # Add a fake item in the Database
+    # Add a fake execution/execution group in the Database
     database = Database.from_config(config)
+    execution_group = ExecutionGroup(
+        diagnostic_id=1, key=result.definition.key, dirty=True, selectors=result.definition.datasets.selectors
+    )
+    database.session.add(execution_group)
+    database.session.flush()
+
     execution = Execution(
-        execution_group_id=1,
+        execution_group_id=execution_group.id,
         dataset_hash=result.definition.datasets.hash,
         output_fragment=str(result.definition.output_fragment()),
     )
@@ -96,9 +102,7 @@ def validate_result(diagnostic: Diagnostic, config: Config, result: ExecutionRes
 
     # Validate bundles
     metric_bundle = CMECMetric.load_from_json(result.to_output_path(result.metric_bundle_filename))
-    assert diagnostic.facets == tuple(metric_bundle.DIMENSIONS.root["json_structure"]), (
-        metric_bundle.DIMENSIONS.root["json_structure"]
-    )
+    assert diagnostic.facets == tuple(metric_bundle.DIMENSIONS.root["json_structure"])
     CMECOutput.load_from_json(result.to_output_path(result.output_bundle_filename))
 
     # Create a fake log file if one doesn't exist

{climate_ref-0.5.0.dist-info → climate_ref-0.5.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: climate-ref
-Version: 0.5.0
+Version: 0.5.2
 Summary: Application which runs 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: Apache-2.0
@@ -28,15 +28,21 @@ Requires-Dist: platformdirs>=4.3.6
 Requires-Dist: setuptools>=75.8.0
 Requires-Dist: sqlalchemy>=2.0.36
 Requires-Dist: tomlkit>=0.13.2
+Requires-Dist: tqdm>=4.67.1
 Requires-Dist: typer>=0.12.5
+Provides-Extra: aft-providers
+Requires-Dist: climate-ref-esmvaltool>=0.5.0; extra == 'aft-providers'
+Requires-Dist: climate-ref-ilamb>=0.5.0; extra == 'aft-providers'
+Requires-Dist: climate-ref-pmp>=0.5.0; extra == 'aft-providers'
 Provides-Extra: celery
 Requires-Dist: climate-ref-celery>=0.5.0; extra == 'celery'
-Provides-Extra: metrics
-Requires-Dist: climate-ref-esmvaltool>=0.5.0; extra == 'metrics'
-Requires-Dist: climate-ref-ilamb>=0.5.0; extra == 'metrics'
-Requires-Dist: climate-ref-pmp>=0.5.0; extra == 'metrics'
 Provides-Extra: postgres
+Requires-Dist: alembic-postgresql-enum>=1.7.0; extra == 'postgres'
 Requires-Dist: psycopg2-binary>=2.9.2; extra == 'postgres'
+Provides-Extra: providers
+Requires-Dist: climate-ref-esmvaltool>=0.5.0; extra == 'providers'
+Requires-Dist: climate-ref-ilamb>=0.5.0; extra == 'providers'
+Requires-Dist: climate-ref-pmp>=0.5.0; extra == 'providers'
 Description-Content-Type: text/markdown
 
 # Climate REF (Rapid Evaluation Framework)
@@ -62,7 +68,7 @@ pip install climate-ref
 If you want to use the diagnostic providers for the Assessment Fast Track, you can install them with:
 
 ```bash
-pip install climate-ref[metrics]
+pip install climate-ref[aft-providers]
 ```
 
 ## Quick Start

climate_ref-0.5.2.dist-info/RECORD

@@ -0,0 +1,47 @@
+climate_ref/__init__.py,sha256=OJl5EnjLyEoCQpa0zQ8edV8EcU2YxBJ0xjermIlm9Bw,820
+climate_ref/_config_helpers.py,sha256=-atI5FX7SukhLE_jz_rL-EHQ7s0YYqKu3dSFYWxSyMU,6632
+climate_ref/alembic.ini,sha256=WRvbwSIFuZ7hWNMnR2-yHPJAwYUnwhvRYBzkJhtpGdg,3535
+climate_ref/config.py,sha256=cOJOYXoxF3T73xoRIKZUZUOCCUAG12abKTCCRpQdfA8,16112
+climate_ref/constants.py,sha256=9RaNLgUSuQva7ki4eRW3TjOKeVP6T81QNiu0veB1zVk,111
+climate_ref/database.py,sha256=LJ6s5qSPJz4yaCzNjJZ-Mw71hquhnx0IKW32VulkuIs,7293
+climate_ref/provider_registry.py,sha256=0oVHQrnFenEQhCUqhrZAUnF6r83VCbXrQVbbo8Bh96c,4109
+climate_ref/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+climate_ref/solver.py,sha256=_QteO9AP1FR-P0W7WzwgntMh4VvpMAkhn02ikw-KDf8,13625
+climate_ref/testing.py,sha256=O36cliznD1sj04xmsqFgowCXC-CoVpfLFbSPfzZbshI,4105
+climate_ref/cli/__init__.py,sha256=1SjCNQ2fV5GtQX_TS77rNlf0h_ECGAup58WYGlcOTTs,4112
+climate_ref/cli/_utils.py,sha256=6bIb8zEVvzXyKpv8MG58T-T2L2jH-G8WNrOOGpz3uCw,1918
+climate_ref/cli/config.py,sha256=8I6CLdqKgTu6yaASy-qG0T839Fc0lDZtLSZ6YCc4wOY,520
+climate_ref/cli/datasets.py,sha256=4k5iSeft5klYKFPBPkmN9sw1RNT7WWp6eI2RPxPT-SM,7519
+climate_ref/cli/executions.py,sha256=sZXyVFYWML5mD7dE8xlsqyunsrwOIweTBDEUKCjXEpo,6798
+climate_ref/cli/providers.py,sha256=eS9IaQxW8zGxidr8TWt7thdMU5JH53u4T3xbcIe2C_E,2455
+climate_ref/cli/solve.py,sha256=1_7Y2Cs6pVCk8Yz1n_NuVhi7WdhfNbtPicbyT804ttE,656
+climate_ref/dataset_registry/obs4ref_reference.txt,sha256=1NodZd3tOS9Z1Afpb_Oq4obp4OGAFDSAwEl3FssPwAQ,251
+climate_ref/dataset_registry/sample_data.txt,sha256=ZQ-bPuBkwaChSYtEVFamg97qu-76oiOVEWn7l9HWYDc,14746
+climate_ref/datasets/__init__.py,sha256=PV3u5ZmhyfcHbKqySgwVA8m4-naZgxzydLXSBqdTGLM,1171
+climate_ref/datasets/base.py,sha256=sgfR548rLZRNPIaZKKXmGp8E_dyoAW1NONZnuVbFXa0,8286
+climate_ref/datasets/cmip6.py,sha256=Dhq97ow8OmTshDCaL7vfrwn83Nfi6SY8uxJHeY4ZDHk,6083
+climate_ref/datasets/obs4mips.py,sha256=PQhI3QKlYA9L2d_MpnlcVrUn4irMG7Iu-II8l1ncjUs,7032
+climate_ref/datasets/pmp_climatology.py,sha256=goHDc_3B2Wdiy_hmpERNvWDdDYZACPOyFDt3Du6nGc0,534
+climate_ref/datasets/utils.py,sha256=iLJO7h4G3DWsRe9hIC4qkIyi5_zIW1ZMw-FDASLujtM,359
+climate_ref/executor/__init__.py,sha256=DooN4jQudmLHyw24IfqNfWynfa1vEolLs-mZ7uY8O0k,604
+climate_ref/executor/local.py,sha256=W62scL2UTtBurhYQz9hVIHrYiq9-FeMKRdnajqiohN0,7753
+climate_ref/executor/result_handling.py,sha256=UxhOTTe1a1p1sU1mZuFTChvhz06CbjY_NFl9BuWYj48,7885
+climate_ref/executor/synchronous.py,sha256=o4TndsoKMu9AzJYLkusU9lRkgHCy6HcCP46tEs6o86U,1895
+climate_ref/migrations/README,sha256=xM5osYbyEbEFA2eh5kwary_oh-5VFWtDubA-vgWwvlE,935
+climate_ref/migrations/env.py,sha256=8GvBLhGTuQy6MKYMj7QszJEQ2LNewf1Z9kB9dBHQs9I,4375
+climate_ref/migrations/script.py.mako,sha256=MEqL-2qATlST9TAOeYgscMn1uy6HUS9NFvDgl93dMj8,635
+climate_ref/migrations/versions/2025-05-02T1418_341a4aa2551e_regenerate.py,sha256=S8Q4THCI4TPnlaQHgQJUCiNW5LAyQClaiTB-0dwhtXU,14050
+climate_ref/migrations/versions/2025-05-09T2032_03dbb4998e49_series_metric_value.py,sha256=s9nZ_l64pSF7sWN53rRPCQlqW_xHqR8tlWhU-ovmsME,2043
+climate_ref/models/__init__.py,sha256=rUDKRANeAEAHVOrzJVIZoZ99dDG5O4AGzHmOpC876Nc,801
+climate_ref/models/base.py,sha256=YMyovT2Z_tRv59zz6qC9YCCDodhO3x6OLnFdBtPJkho,1271
+climate_ref/models/dataset.py,sha256=Rpwrx0HqOJBHs4Sb4n6B0In__Uo0PqXSZKvZR-juGCg,7491
+climate_ref/models/diagnostic.py,sha256=YB6xzbEXdpz2j-Ddf19RV8mAiWBrkmtRmiAEUV3tl4Q,1762
+climate_ref/models/execution.py,sha256=lRCpaKLSR7rZbuoL94GW76tm9wLMsSDoIOA7bIa6xgY,9848
+climate_ref/models/metric_value.py,sha256=44OLcZz-qLx-p_9w7YWDKpD5S7Y9HyTKKsvSb77RBro,10190
+climate_ref/models/provider.py,sha256=RAE2qAAxwObu-72CdK4kt5ACMmKYEn07WJm7DU9hF28,990
+climate_ref-0.5.2.dist-info/METADATA,sha256=_VM9gflxr_w6CvvSP7ZBGK_xyIzF_K80nXhvmCtUhxA,4368
+climate_ref-0.5.2.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+climate_ref-0.5.2.dist-info/entry_points.txt,sha256=IaggEJlDIhoYWXdXJafacWbWtCcoEqUKceP1qD7_7vU,44
+climate_ref-0.5.2.dist-info/licenses/LICENCE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+climate_ref-0.5.2.dist-info/licenses/NOTICE,sha256=4qTlax9aX2-mswYJuVrLqJ9jK1IkN5kSBqfVvYLF3Ws,128
+climate_ref-0.5.2.dist-info/RECORD,,

climate_ref-0.5.0.dist-info/RECORD

@@ -1,44 +0,0 @@
-climate_ref/__init__.py,sha256=OJl5EnjLyEoCQpa0zQ8edV8EcU2YxBJ0xjermIlm9Bw,820
-climate_ref/_config_helpers.py,sha256=-atI5FX7SukhLE_jz_rL-EHQ7s0YYqKu3dSFYWxSyMU,6632
-climate_ref/alembic.ini,sha256=WRvbwSIFuZ7hWNMnR2-yHPJAwYUnwhvRYBzkJhtpGdg,3535
-climate_ref/config.py,sha256=QW1HOLajC2Gc5xZnrGQ8YLAver3BAlVBrfl1kVd_IyM,15072
-climate_ref/constants.py,sha256=rFk3XxNuP0lkzTvUneIhNLq16uadXsT45aUFIlSiBmg,111
-climate_ref/database.py,sha256=RCffNHbJcxxukN6PIOXBTW9TALE2rRsxU0chJHxyNK4,7257
-climate_ref/provider_registry.py,sha256=P35H4VFcsxJ8-Ly4Czwi_gelDU_nF5RiqSC-iBcx_Ws,4116
-climate_ref/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-climate_ref/solver.py,sha256=Hpb_3g-hYWopuBYyqaEtOgfuLOHfZpWbwP1rco802uE,14310
-climate_ref/testing.py,sha256=rUdtU8a4p2OV35IO87veW0mEB9C4Bqwe7BBQU6BILhs,3889
-climate_ref/cli/__init__.py,sha256=RSzaFkgwn1qWRBVbWlDKtNrIxLvQ2T7IWDBIqptpjjU,3658
-climate_ref/cli/_utils.py,sha256=6bIb8zEVvzXyKpv8MG58T-T2L2jH-G8WNrOOGpz3uCw,1918
-climate_ref/cli/config.py,sha256=8I6CLdqKgTu6yaASy-qG0T839Fc0lDZtLSZ6YCc4wOY,520
-climate_ref/cli/datasets.py,sha256=SLl88S3BxKPRbHy9OJ1ymhMnxDmkadFO_BZTIeLR0k8,7367
-climate_ref/cli/executions.py,sha256=6cnMxPK4ZydscUw_Mk9RMISNjP2Yr98BgsOsei8fQ7w,6799
-climate_ref/cli/providers.py,sha256=XVZQsZoEqiCBvgSmp6cNf0mCTxeq_Ycoc6DwVxWDYKg,2521
-climate_ref/cli/solve.py,sha256=D6rAivfm_yl1TTey_zc4KKwZ96LGGF8N1wHjcJ_0XpE,703
-climate_ref/dataset_registry/obs4ref_reference.txt,sha256=1NodZd3tOS9Z1Afpb_Oq4obp4OGAFDSAwEl3FssPwAQ,251
-climate_ref/dataset_registry/sample_data.txt,sha256=aKl9tfO4vknZ5X2mmdyxKOv-nyWhkPDXnpDoNLLTzE8,11892
-climate_ref/datasets/__init__.py,sha256=PV3u5ZmhyfcHbKqySgwVA8m4-naZgxzydLXSBqdTGLM,1171
-climate_ref/datasets/base.py,sha256=XplxCu4bfFmNHp2q8tHT26lB0RHv5swK0QqfUmuMO-c,8154
-climate_ref/datasets/cmip6.py,sha256=Dhq97ow8OmTshDCaL7vfrwn83Nfi6SY8uxJHeY4ZDHk,6083
-climate_ref/datasets/obs4mips.py,sha256=PQhI3QKlYA9L2d_MpnlcVrUn4irMG7Iu-II8l1ncjUs,7032
-climate_ref/datasets/pmp_climatology.py,sha256=goHDc_3B2Wdiy_hmpERNvWDdDYZACPOyFDt3Du6nGc0,534
-climate_ref/datasets/utils.py,sha256=iLJO7h4G3DWsRe9hIC4qkIyi5_zIW1ZMw-FDASLujtM,359
-climate_ref/executor/__init__.py,sha256=vUkE5Izfietvc57gA8LTdaD5IErKVebcE6qO7M7sCRo,9286
-climate_ref/executor/local.py,sha256=3icom02FCHiN0tIpsXR9tvn8-cQrUyoY-LlbHapbTx4,2920
-climate_ref/migrations/README,sha256=xM5osYbyEbEFA2eh5kwary_oh-5VFWtDubA-vgWwvlE,935
-climate_ref/migrations/env.py,sha256=b8om-LvFhVo_2BgaRsR8LcPQ-YcevjWikaWE6uhScAs,4213
-climate_ref/migrations/script.py.mako,sha256=MEqL-2qATlST9TAOeYgscMn1uy6HUS9NFvDgl93dMj8,635
-climate_ref/migrations/versions/2025-05-02T1418_341a4aa2551e_regenerate.py,sha256=349kbd58NdFHqqUAPDX1kR9RUOcxT2zXh9v9yg9-Je8,15533
-climate_ref/models/__init__.py,sha256=dFyqfhTffZz4m06xD4SyvRL9kIBRyVYetHwOxFGy4VM,713
-climate_ref/models/base.py,sha256=cMjNpGNU7pxRi9A5KXEmQIA9pvQDwqGCwo539yndpGY,1199
-climate_ref/models/dataset.py,sha256=Rpwrx0HqOJBHs4Sb4n6B0In__Uo0PqXSZKvZR-juGCg,7491
-climate_ref/models/diagnostic.py,sha256=YB6xzbEXdpz2j-Ddf19RV8mAiWBrkmtRmiAEUV3tl4Q,1762
-climate_ref/models/execution.py,sha256=lRCpaKLSR7rZbuoL94GW76tm9wLMsSDoIOA7bIa6xgY,9848
-climate_ref/models/metric_value.py,sha256=Sfjem65ih9g6WDpjGsiOphSjhYQ1ZAYUPZmsKyb_psU,6452
-climate_ref/models/provider.py,sha256=RAE2qAAxwObu-72CdK4kt5ACMmKYEn07WJm7DU9hF28,990
-climate_ref-0.5.0.dist-info/METADATA,sha256=pTjBsQveKvV8KGgvD9fy8LoxQ5CS-1ruBoFM4ReeLvY,4028
-climate_ref-0.5.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-climate_ref-0.5.0.dist-info/entry_points.txt,sha256=IaggEJlDIhoYWXdXJafacWbWtCcoEqUKceP1qD7_7vU,44
-climate_ref-0.5.0.dist-info/licenses/LICENCE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-climate_ref-0.5.0.dist-info/licenses/NOTICE,sha256=4qTlax9aX2-mswYJuVrLqJ9jK1IkN5kSBqfVvYLF3Ws,128
-climate_ref-0.5.0.dist-info/RECORD,,