climate-ref-ilamb 0.5.4__tar.gz → 0.6.0__tar.gz

{climate_ref_ilamb-0.5.4 → climate_ref_ilamb-0.6.0}/PKG-INFO

@@ -1,14 +1,15 @@
 Metadata-Version: 2.4
 Name: climate-ref-ilamb
-Version: 0.5.4
+Version: 0.6.0
 Summary: ILAMB diagnostic provider for the Rapid Evaluation Framework
-Author-email: Nathan Collier <nathaniel.collier@gmail.com>
-License: Apache-2.0
+Author-email: Nathan Collier <nathaniel.collier@gmail.com>, Jared Lewis <jared.lewis@climate-resource.com>
+License-Expression: Apache-2.0
 License-File: LICENCE
 License-File: NOTICE
-Classifier: Development Status :: 4 - Beta
+Classifier: Development Status :: 3 - Alpha
 Classifier: Intended Audience :: Developers
 Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: Python
 Classifier: Programming Language :: Python :: 3
@@ -18,8 +19,7 @@ Classifier: Programming Language :: Python :: 3.13
 Classifier: Topic :: Scientific/Engineering
 Requires-Python: >=3.11
 Requires-Dist: climate-ref-core
-Requires-Dist: ilamb3>=2025.4.28
-Requires-Dist: types-pyyaml>=6.0.12.20241230
+Requires-Dist: ilamb3>=2025.5.20
 Description-Content-Type: text/markdown
 
 # climate-ref-ilamb

climate_ref_ilamb-0.6.0/pyproject.toml

@@ -0,0 +1,32 @@
+[project]
+name = "climate-ref-ilamb"
+version = "0.6.0"
+description = "ILAMB diagnostic provider for the Rapid Evaluation Framework"
+readme = "README.md"
+authors = [
+  { name = "Nathan Collier", email = "nathaniel.collier@gmail.com" },
+  { name = "Jared Lewis", email = "jared.lewis@climate-resource.com" },
+]
+requires-python = ">=3.11"
+license = "Apache-2.0"
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Operating System :: OS Independent",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "Programming Language :: Python",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Topic :: Scientific/Engineering",
+  "License :: OSI Approved :: Apache Software License",
+]
+dependencies = ["climate-ref-core", "ilamb3>=2025.5.20"]
+
+[dependency-groups]
+dev = ["types-pyyaml>=6.0.12"]
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

{climate_ref_ilamb-0.5.4 → climate_ref_ilamb-0.6.0}/src/climate_ref_ilamb/__init__.py

@@ -10,9 +10,8 @@ import importlib.resources
 
 import yaml
 
-from climate_ref_core.dataset_registry import dataset_registry_manager
+from climate_ref_core.dataset_registry import DATASET_URL, dataset_registry_manager
 from climate_ref_core.providers import DiagnosticProvider
-from climate_ref_ilamb.datasets import ILAMB_DATA_VERSION
 from climate_ref_ilamb.standard import ILAMBStandard
 
 __version__ = importlib.metadata.version("climate-ref-ilamb")
@@ -22,27 +21,21 @@ provider = DiagnosticProvider("ILAMB", __version__)
 # Register some datasets
 dataset_registry_manager.register(
     "ilamb-test",
-    base_url="https://www.ilamb.org/ILAMB-Data/DATA",
+    base_url=DATASET_URL,
     package="climate_ref_ilamb.dataset_registry",
     resource="test.txt",
-    cache_name="ilamb3",
-    version=ILAMB_DATA_VERSION,
 )
 dataset_registry_manager.register(
     "ilamb",
-    base_url="https://www.ilamb.org/ILAMB-Data/DATA",
+    base_url=DATASET_URL,
     package="climate_ref_ilamb.dataset_registry",
     resource="ilamb.txt",
-    cache_name="ilamb3",
-    version=ILAMB_DATA_VERSION,
 )
 dataset_registry_manager.register(
     "iomb",
-    base_url="https://www.ilamb.org/ilamb3-data/",
+    base_url=DATASET_URL,
     package="climate_ref_ilamb.dataset_registry",
     resource="iomb.txt",
-    cache_name="ilamb3",
-    version=ILAMB_DATA_VERSION,
 )
 
 # Dynamically register ILAMB diagnostics

climate_ref_ilamb-0.6.0/src/climate_ref_ilamb/configure/ilamb.yaml

@@ -0,0 +1,59 @@
+registry: ilamb
+
+gpp-WECANN:
+  sources:
+    # TODO: Update to use the obs4REF equiv
+    gpp: ilamb/gpp/WECANN/gpp.nc
+  relationships:
+    pr: ilamb/pr/GPCPv2.3/pr.nc
+    tas: ilamb/tas/CRU4.02/tas.nc
+  variable_cmap: Greens
+
+gpp-FLUXNET2015:
+  sources:
+    gpp: ilamb/gpp/FLUXNET2015/gpp.nc
+  variable_cmap: Greens
+
+mrro-LORA:
+  sources:
+    # TODO: Update to use the obs4REF equiv
+    mrro: ilamb/mrro/LORA/LORA.nc
+  variable_cmap: Blues
+
+mrsos-WangMao:
+  sources:
+    mrsol: ilamb/mrsol/WangMao/mrsol_olc.nc
+  alternate_vars:
+  - mrsos
+  transform:
+  - select_depth:
+      value: 0
+  - soil_moisture_to_vol_fraction
+  variable_cmap: Blues
+
+cSoil-HWSD2:
+  sources:
+    cSoil: ilamb/cSoil/HWSD2/cSoil_fx_HWSD2_19600101-20220101.nc
+  variable_cmap: viridis
+
+lai-AVH15C1:
+  sources:
+    lai: ilamb/lai/AVH15C1/lai.nc
+  variable_cmap: Greens
+
+nbp-Hoffman:
+  analyses:
+  - nbp
+  sources:
+    # TODO: Update to use the obs4REF equiv
+    nbp: ilamb/nbp/HOFFMAN/nbp_1850-2010.nc
+
+snc-ESACCI:
+  sources:
+    snc: ilamb/snc/Snow-cci/snc_mon_Snow-cci_BE_gn_198201-201906.nc
+
+burntFractionAll-GFED:
+  sources:
+    burntArea: ilamb/burntFractionAll/GFED/burntArea.nc
+  alternate_vars:
+  - burntFractionAll

climate_ref_ilamb-0.6.0/src/climate_ref_ilamb/configure/iomb.yaml

@@ -0,0 +1,49 @@
+registry: iomb
+
+thetao-WOA2023-surface:
+  sources:
+    # TODO: Update to use the obs4REF equiv
+    thetao: ilamb/WOA/thetao_mon_WOA_A5B4_gn_200501-201412.nc
+  variable_cmap: Reds
+  transform:
+  - select_depth:
+      value: 0
+  alternate_vars:
+  - tos
+
+so-WOA2023-surface:
+  sources:
+    # TODO: Update to use the obs4REF equiv
+    so: ilamb/WOA/so_mon_WOA_A5B4_gn_200501-201412.nc
+  transform:
+  - select_depth:
+      value: 0
+  variable_cmap: YlGn
+  alternate_vars:
+  - sos
+
+amoc-RAPID:
+  analyses:
+  - timeseries
+  related_vars:
+  - msftmz
+  transform:
+  - msftmz_to_rapid
+  sources:
+    # TODO: Update to use the obs4REF equiv
+    amoc: ilamb/RAPID/amoc_mon_RAPID_BE_NA_200404-202302.nc
+
+ohc-NOAA:
+  sources:
+    ohc: ilamb/NOAA/ohc_yr_OHC_BE_gm_200506-202406.nc
+  related_vars:
+  - thetao
+  - volcello
+  transform:
+  - select_depth:
+      min: 0
+      max: 2000
+  - ocean_heat_content:
+      reference_year: 2005
+  analyses:
+  - accumulate

climate_ref_ilamb-0.6.0/src/climate_ref_ilamb/dataset_registry/ilamb.txt

@@ -0,0 +1,13 @@
+ilamb/cSoil/HWSD2/cSoil_fx_HWSD2_19600101-20220101.nc sha1:7138b0b53aa600878adf95e6aef65f4322a8e287
+ilamb/gpp/FLUXNET2015/gpp.nc sha1:16fd177e007caef2565687e2cd32884e20ef16e5
+ilamb/gpp/WECANN/gpp.nc sha1:6e864a6ae201195cdf995a3a81720188af441e13
+ilamb/lai/AVH15C1/lai.nc sha1:ccace4f84912d63acbb9ee09ee7b743412207a0d
+ilamb/mrro/LORA/LORA.nc sha1:72bb16787877591d0c54a36d74697d0d208f985a
+ilamb/mrsol/WangMao/mrsol_olc.nc sha1:24cbc9df69569bed3a39c20e499cfe4f911bd30e
+ilamb/regions/GlobalLand.nc sha1:2f987d44fdba6ad0e72d14d6a2fecb7e8df2a9c5
+ilamb/regions/Koppen_coarse.nc sha1:e464030db49f0295a6a22a81ca602b0f3c499b72
+ilamb/pr/GPCPv2.3/pr.nc sha1:e1b942863ec76a75aa972b6d75e2e08646741259
+ilamb/tas/CRU4.02/tas.nc sha1:2674da18a1a93483b50b1626e7a7ab741bf53d09
+ilamb/nbp/HOFFMAN/nbp_1850-2010.nc sha1:8350af00614d6afc6b70ad314aa499a9ece80ec2
+ilamb/snc/Snow-cci/snc_mon_Snow-cci_BE_gn_198201-201906.nc sha1:c0bfecd2f8b886e9301428d28bb6ff0507601be2
+ilamb/burntFractionAll/GFED/burntArea.nc sha1:cf9d73c6a8bfc594737c9ba6ca4df613df4a28ab

climate_ref_ilamb-0.6.0/src/climate_ref_ilamb/dataset_registry/iomb.txt

@@ -0,0 +1,4 @@
+ilamb/WOA/so_mon_WOA_A5B4_gn_200501-201412.nc sha1:831c42c3b2ba443c255150289a2c725d7f3e5838
+ilamb/WOA/thetao_mon_WOA_A5B4_gn_200501-201412.nc sha1:86d9056208291d76233e65b26c658c1fa54c3ea6
+ilamb/RAPID/amoc_mon_RAPID_BE_NA_200404-202302.nc sha1:3efe773e5c2a3c832977791ff7fd9cb9f473fe65
+ilamb/NOAA/ohc_yr_OHC_BE_gm_200506-202406.nc sha1:a918799d8e24e4f0015b9047a74d470ae9f0445c

climate_ref_ilamb-0.6.0/src/climate_ref_ilamb/dataset_registry/test.txt

@@ -0,0 +1,3 @@
+ilamb/test/Site/tas.nc sha1:3e757c9feadea581a92e6f4afb402b86168e113a
+ilamb/test/Grid/gpp.nc sha1:2688085f95fa13617b20c723c66b0009bd661847
+ilamb/test/Grid/pr.nc sha1:d667eb216939f5797d59b59cb4ade5ec31e67659

{climate_ref_ilamb-0.5.4 → climate_ref_ilamb-0.6.0}/src/climate_ref_ilamb/datasets.py

@@ -7,8 +7,6 @@ import pooch
 
 from climate_ref_core.datasets import DatasetCollection
 
-ILAMB_DATA_VERSION = "0.1"  # we don't really have data versions for the collection :/
-
 
 def registry_to_collection(registry: pooch.Pooch) -> DatasetCollection:
     """

climate_ref_ilamb-0.6.0/src/climate_ref_ilamb/standard.py

@@ -0,0 +1,294 @@
+from pathlib import Path
+from typing import Any
+
+import ilamb3  # type: ignore
+import ilamb3.regions as ilr  # type: ignore
+import matplotlib.pyplot as plt
+import pandas as pd
+import pooch
+from ilamb3 import run
+
+from climate_ref_core.constraints import AddSupplementaryDataset
+from climate_ref_core.dataset_registry import dataset_registry_manager
+from climate_ref_core.datasets import FacetFilter, SourceDatasetType
+from climate_ref_core.diagnostics import (
+    DataRequirement,
+    Diagnostic,
+    ExecutionDefinition,
+    ExecutionResult,
+)
+from climate_ref_core.pycmec.metric import CMECMetric
+from climate_ref_core.pycmec.output import CMECOutput
+from climate_ref_ilamb.datasets import (
+    registry_to_collection,
+)
+
+
+def format_cmec_output_bundle(
+    dataset: pd.DataFrame,
+    dimensions: list[str],
+    metadata_columns: list[str],
+    value_column: str = "value",
+) -> dict[str, Any]:
+    """
+    Create a CMEC output bundle for the dataset.
+
+    Parameters
+    ----------
+    dataset
+        Processed dataset
+    dimensions
+        The dimensions of the dataset (e.g., ["source_id", "member_id", "region"])
+    metadata_columns
+        The columns to be used as metadata (e.g., ["Description", "LongName"])
+    value_column
+        The column containing the values
+
+    Returns
+    -------
+        A CMEC output bundle ready to be written to disk
+    """
+    # Validate that all required columns exist
+    required_columns = set(dimensions) | {value_column} | set(metadata_columns)
+    missing_columns = required_columns - set(dataset.columns)
+    if missing_columns:
+        raise ValueError(f"Missing required columns: {missing_columns}")
+
+    # Build the dimensions section
+    dimensions_dict: dict[str, dict[str, dict[str, str]]] = {}
+
+    # For each dimension, create a dictionary of unique values and their metadata
+    for dim in dimensions:
+        unique_values = dataset[dim].unique()
+        dim_dict: dict[str, dict[str, str]] = {}
+
+        for val in unique_values:
+            # Get the row for this dimension value
+
+            dim_dict[str(val)] = {}
+
+            if dim == dimensions[-1]:
+                # If this is the last dimension, add the value column to the metadata
+
+                dim_dict[str(val)] = dataset[dataset[dim] == val].iloc[0][metadata_columns].to_dict()
+
+        dimensions_dict[dim] = dim_dict
+
+    # Build the results section - create nested structure based on dimensions
+    def nest_results(df: pd.DataFrame, dims: list[str]) -> dict[str, Any] | float:
+        if not dims:
+            return float(df[value_column].iloc[0].item())
+
+        current_dim = dims[0]
+        remaining_dims = dims[1:]
+
+        return {
+            str(group_name): nest_results(group_df, remaining_dims)
+            for group_name, group_df in df.groupby(current_dim)
+        }
+
+    results = nest_results(dataset, list(dimensions))
+
+    return {"DIMENSIONS": {"json_structure": list(dimensions), **dimensions_dict}, "RESULTS": results}
+
+
+def _build_cmec_bundle(df: pd.DataFrame) -> dict[str, Any]:
+    """
+    Build a CMEC bundle from information in the dataframe.
+
+    """
+    # TODO: Handle the reference data
+    # reference_df = df[df["source"] == "Reference"]
+    model_df = df[df["source"] != "Reference"]
+
+    # Source is formatted as "ACCESS-ESM1-5-r1i1p1f1-gn"
+    # This assumes that the member_id and grid_label are always the last two parts of the source string
+    # and don't contain '-'
+    extracted_source = model_df.source.str.extract(r"([\w-]+)-([\w\d]+)-([\w\d]+)")
+    model_df["source_id"] = extracted_source[0]
+    model_df["member_id"] = extracted_source[1]
+    model_df["grid_label"] = extracted_source[2]
+
+    # Strip out units from the name
+    # These are available in the attributes
+    extracted_source = model_df.name.str.extract(r"(.*)\s\[.*\]")
+    model_df["name"] = extracted_source[0]
+
+    model_df = model_df.rename(
+        columns={
+            "analysis": "metric",
+            "name": "statistic",
+        }
+    )
+
+    # Convert the value column to numeric, coercing errors to NaN
+    model_df["value"] = pd.to_numeric(model_df["value"], errors="coerce")
+
+    dimensions = ["experiment_id", "source_id", "member_id", "grid_label", "region", "metric", "statistic"]
+    attributes = ["type", "units"]
+
+    bundle = format_cmec_output_bundle(
+        model_df,
+        dimensions=dimensions,
+        metadata_columns=attributes,
+        value_column="value",
+    )
+
+    ilamb_regions = ilr.Regions()
+    for region, region_info in bundle["DIMENSIONS"]["region"].items():
+        if region == "None":
+            region_info["LongName"] = "None"
+            region_info["Description"] = "Reference data extents"
+            region_info["Generator"] = "N/A"
+        else:
+            region_info["LongName"] = ilamb_regions.get_name(region)
+            region_info["Description"] = ilamb_regions.get_name(region)
+            region_info["Generator"] = ilamb_regions.get_source(region)
+
+    return bundle
+
+
+def _form_bundles(df: pd.DataFrame) -> tuple[CMECMetric, CMECOutput]:
+    """
+    Create the output bundles (really a lift to make Ruff happy with the size of run()).
+    """
+    metric_bundle = _build_cmec_bundle(df)
+    output_bundle = CMECOutput.create_template()
+    return CMECMetric.model_validate(metric_bundle), CMECOutput.model_validate(output_bundle)
+
+
+def _set_ilamb3_options(registry: pooch.Pooch, registry_file: str) -> None:
+    """
+    Set options for ILAMB based on which registry file is being used.
+    """
+    ilamb3.conf.reset()
+    ilamb_regions = ilr.Regions()
+    if registry_file == "ilamb":
+        ilamb_regions.add_netcdf(registry.fetch("ilamb/regions/GlobalLand.nc"))
+        ilamb_regions.add_netcdf(registry.fetch("ilamb/regions/Koppen_coarse.nc"))
+        ilamb3.conf.set(regions=["global", "tropical"])
+
+
+def _load_csv_and_merge(output_directory: Path) -> pd.DataFrame:
+    """
+    Load individual csv scalar data and merge into a dataframe.
+    """
+    df = pd.concat(
+        [pd.read_csv(f, keep_default_na=False, na_values=["NaN"]) for f in output_directory.glob("*.csv")]
+    ).drop_duplicates(subset=["source", "region", "analysis", "name"])
+    return df
+
+
+class ILAMBStandard(Diagnostic):
+    """
+    Apply the standard ILAMB analysis with respect to a given reference dataset.
+    """
+
+    def __init__(
+        self,
+        registry_file: str,
+        metric_name: str,
+        sources: dict[str, str],
+        **ilamb_kwargs: Any,
+    ):
+        # Setup the diagnostic
+        if len(sources) != 1:
+            raise ValueError("Only single source ILAMB diagnostics have been implemented.")
+        self.variable_id = next(iter(sources.keys()))
+        if "sources" not in ilamb_kwargs:  # pragma: no cover
+            ilamb_kwargs["sources"] = sources
+        if "relationships" not in ilamb_kwargs:
+            ilamb_kwargs["relationships"] = {}
+        self.ilamb_kwargs = ilamb_kwargs
+
+        # REF stuff
+        self.name = metric_name
+        self.slug = self.name.lower().replace(" ", "-")
+        self.data_requirements = (
+            DataRequirement(
+                source_type=SourceDatasetType.CMIP6,
+                filters=(
+                    FacetFilter(
+                        facets={
+                            "variable_id": (
+                                self.variable_id,
+                                *ilamb_kwargs.get("relationships", {}).keys(),
+                                *ilamb_kwargs.get("alternate_vars", []),
+                                *ilamb_kwargs.get("related_vars", []),
+                            )
+                        }
+                    ),
+                    FacetFilter(facets={"frequency": ("mon",)}),
+                    FacetFilter(facets={"experiment_id": ("historical", "land-hist")}),
+                    # Exclude unneeded snc tables
+                    FacetFilter(facets={"table_id": ("ImonAnt", "ImonGre")}, keep=False),
+                ),
+                constraints=(
+                    AddSupplementaryDataset.from_defaults("areacella", SourceDatasetType.CMIP6),
+                    AddSupplementaryDataset.from_defaults("sftlf", SourceDatasetType.CMIP6),
+                )
+                if registry_file == "ilamb"
+                else (
+                    AddSupplementaryDataset.from_defaults("areacello", SourceDatasetType.CMIP6),
+                    AddSupplementaryDataset.from_defaults("sftof", SourceDatasetType.CMIP6),
+                ),
+                group_by=("experiment_id",),
+            ),
+        )
+        self.facets = (
+            "experiment_id",
+            "source_id",
+            "member_id",
+            "grid_label",
+            "region",
+            "metric",
+            "statistic",
+        )
+
+        # Setup ILAMB data and options
+        self.registry_file = registry_file
+        self.registry = dataset_registry_manager[self.registry_file]
+        self.ilamb_data = registry_to_collection(
+            dataset_registry_manager[self.registry_file],
+        )
+
+    def execute(self, definition: ExecutionDefinition) -> None:
+        """
+        Run the ILAMB standard analysis.
+        """
+        plt.rcParams.update({"figure.max_open_warning": 0})
+        _set_ilamb3_options(self.registry, self.registry_file)
+        ref_datasets = self.ilamb_data.datasets.set_index(self.ilamb_data.slug_column)
+        run.run_simple(
+            ref_datasets,
+            self.slug,
+            definition.datasets[SourceDatasetType.CMIP6].datasets,
+            definition.output_directory,
+            **self.ilamb_kwargs,
+        )
+
+    def build_execution_result(self, definition: ExecutionDefinition) -> ExecutionResult:
+        """
+        Build the diagnostic result after running ILAMB.
+
+        Parameters
+        ----------
+        definition
+            The definition of the diagnostic execution
+
+        Returns
+        -------
+            An execution result object
+        """
+        selectors = definition.datasets[SourceDatasetType.CMIP6].selector_dict()
+        _set_ilamb3_options(self.registry, self.registry_file)
+
+        df = _load_csv_and_merge(definition.output_directory)
+        # Add the selectors to the dataframe
+        for key, value in selectors.items():
+            df[key] = value
+        metric_bundle, output_bundle = _form_bundles(df)
+
+        return ExecutionResult.build_from_output_bundle(
+            definition, cmec_output_bundle=output_bundle, cmec_metric_bundle=metric_bundle
+        )

{climate_ref_ilamb-0.5.4 → climate_ref_ilamb-0.6.0}/tests/integration/test_diagnostics.py

@@ -4,8 +4,7 @@ from climate_ref_ilamb import provider as ilamb_provider
 from climate_ref_core.diagnostics import Diagnostic
 
 skipped_diagnostics = [
-    "csoil-hwsd2",  # Incorrect time spans
-    "nbp-hoffman",  # Incorrect time spans
+    "ohc-noaa",  # Missing sample data
 ]
 
 diagnostics = [
@@ -35,3 +34,4 @@ def test_build_results(diagnostic: Diagnostic, diagnostic_validation):
 
     definition = validator.get_regression_definition()
     validator.validate(definition)
+    validator.execution_regression.check(definition.key, definition.output_directory)

{climate_ref_ilamb-0.5.4 → climate_ref_ilamb-0.6.0}/tests/unit/test_standard_metrics.py

@@ -1,14 +1,17 @@
 import ilamb3
+import pandas as pd
 import pytest
 from climate_ref_ilamb.standard import ILAMBStandard, _set_ilamb3_options
+from climate_ref_pmp import provider as ilamb_provider
 
+from climate_ref.solver import solve_executions
 from climate_ref_core.dataset_registry import dataset_registry_manager
-from climate_ref_core.datasets import DatasetCollection
+from climate_ref_core.datasets import DatasetCollection, SourceDatasetType
 
 
 def test_standard_site(cmip6_data_catalog, definition_factory):
     diagnostic = ILAMBStandard(
-        registry_file="ilamb-test", metric_name="test-site-tas", sources={"tas": "test/Site/tas.nc"}
+        registry_file="ilamb-test", metric_name="test-site-tas", sources={"tas": "ilamb/test/Site/tas.nc"}
     )
     ds = (
         cmip6_data_catalog[
@@ -19,7 +22,10 @@ def test_standard_site(cmip6_data_catalog, definition_factory):
         .first()
     )
 
-    definition = definition_factory(diagnostic=diagnostic, cmip6=DatasetCollection(ds, "instance_id"))
+    definition = definition_factory(
+        diagnostic=diagnostic,
+        cmip6=DatasetCollection(ds, "instance_id", selector=(("experiment_id", "historical"),)),
+    )
     definition.output_directory.mkdir(parents=True, exist_ok=True)
 
     result = diagnostic.run(definition)
@@ -45,8 +51,8 @@ def test_standard_grid(cmip6_data_catalog, definition_factory):
     diagnostic = ILAMBStandard(
         registry_file="ilamb-test",
         metric_name="test-grid-gpp",
-        sources={"gpp": "test/Grid/gpp.nc"},
-        relationships={"pr": "test/Grid/pr.nc"},
+        sources={"gpp": "ilamb/test/Grid/gpp.nc"},
+        relationships={"pr": "ilamb/test/Grid/pr.nc"},
     )
     grp = cmip6_data_catalog[
         (cmip6_data_catalog["experiment_id"] == "historical")
@@ -54,7 +60,10 @@ def test_standard_grid(cmip6_data_catalog, definition_factory):
     ].groupby(["source_id", "member_id", "grid_label"])
     _, ds = next(iter(grp))
 
-    definition = definition_factory(diagnostic=diagnostic, cmip6=DatasetCollection(ds, "instance_id"))
+    definition = definition_factory(
+        diagnostic=diagnostic,
+        cmip6=DatasetCollection(ds, "instance_id", selector=(("experiment_id", "historical"),)),
+    )
     definition.output_directory.mkdir(parents=True, exist_ok=True)
 
     result = diagnostic.run(definition)
@@ -81,10 +90,56 @@ def test_standard_fail():
         ILAMBStandard(
             registry_file="ilamb-test",
             metric_name="test-fail",
-            sources={"gpp": "test/Grid/gpp.nc", "pr": "test/Grid/pr.nc"},
+            sources={"gpp": "ilamb/test/Grid/gpp.nc", "pr": "ilamb/test/Grid/pr.nc"},
         )
 
 
 def test_options():
     _set_ilamb3_options(dataset_registry_manager["ilamb"], "ilamb")
     assert set(["global", "tropical"]).issubset(ilamb3.conf["regions"])
+
+
+def test_expected_executions():
+    diagnostic = ILAMBStandard(
+        registry_file="ilamb",
+        metric_name="cSoil-HWSD2",
+        sources={"cSoil": "ilamb/cSoil/HWSD2/cSoil_fx_HWSD2_19600101-20220101.nc"},
+    )
+
+    # No Obs4MIPs datasets are used yet
+    data_catalog = {
+        SourceDatasetType.CMIP6: pd.DataFrame(
+            [
+                ["cSoil", "ACCESS-ESM1-5", "historical", "r1i1p1f1", "mon", "gn", "Amon", "v20191115"],
+                ["cSoil", "ACCESS-ESM1-5", "ssp119", "r1i1p1f1", "mon", "gn", "Amon", "v20191115"],
+                ["cSoil", "ACCESS-ESM1-5", "historical", "r2i1p1f1", "mon", "gn", "Amon", "v20191115"],
+                ["ts", "ACCESS-ESM1-5", "historical", "r1i1p1f1", "mon", "gn", "Amon", "v20191115"],
+                ["areacella", "ACCESS-ESM1-5", "fx", "r1i1p1f1", "mon", "gn", "Amon", "v20191115"],
+            ],
+            columns=(
+                "variable_id",
+                "source_id",
+                "experiment_id",
+                "member_id",
+                "frequency",
+                "grid_label",
+                "table_id",
+                "version",
+            ),
+        ),
+    }
+    executions = list(solve_executions(data_catalog, diagnostic, provider=ilamb_provider))
+    assert len(executions) == 1
+
+    # ts
+    assert executions[0].datasets[SourceDatasetType.CMIP6].selector == (("experiment_id", "historical"),)
+    assert executions[0].datasets[SourceDatasetType.CMIP6].datasets["variable_id"].tolist() == [
+        "cSoil",
+        "cSoil",
+        "areacella",
+    ]
+    assert executions[0].datasets[SourceDatasetType.CMIP6].datasets["member_id"].tolist() == [
+        "r1i1p1f1",
+        "r2i1p1f1",
+        "r1i1p1f1",
+    ]

climate_ref_ilamb-0.5.4/pyproject.toml

@@ -1,34 +0,0 @@
-[project]
-name = "climate-ref-ilamb"
-version = "0.5.4"
-description = "ILAMB diagnostic provider for the Rapid Evaluation Framework"
-readme = "README.md"
-authors = [{ name = "Nathan Collier", email = "nathaniel.collier@gmail.com" }]
-requires-python = ">=3.11"
-classifiers = [
-    "Development Status :: 4 - Beta",
-    "Intended Audience :: Developers",
-    "Operating System :: OS Independent",
-    "Intended Audience :: Science/Research",
-    "Programming Language :: Python",
-    "Programming Language :: Python :: 3",
-    "Programming Language :: Python :: 3.11",
-    "Programming Language :: Python :: 3.12",
-    "Programming Language :: Python :: 3.13",
-    "Topic :: Scientific/Engineering",
-]
-dependencies = [
-    "climate-ref-core",
-    "ilamb3>=2025.4.28",
-    "types-pyyaml>=6.0.12.20241230",
-]
-
-[project.license]
-text = "Apache-2.0"
-
-[tool.uv]
-dev-dependencies = []
-
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"

climate_ref_ilamb-0.5.4/src/climate_ref_ilamb/configure/ilamb.yaml

@@ -1,45 +0,0 @@
-registry: ilamb
-
-gpp-WECANN:
-  sources:
-    gpp: gpp/WECANN/gpp.nc
-  relationships:
-    pr: pr/GPCPv2.3/pr.nc
-    tas: tas/CRU4.02/tas.nc
-  variable_cmap: Greens
-
-gpp-FLUXNET2015:
-  sources:
-    gpp: gpp/FLUXNET2015/gpp.nc
-  variable_cmap: Greens
-
-mrro-LORA:
-  sources:
-    mrro: mrro/LORA/LORA.nc
-  variable_cmap: Blues
-
-mrsos-WangMao:
-  sources:
-    mrsol: mrsol/WangMao/mrsol_olc.nc
-  alternate_vars:
-  - mrsos
-  depth: 0.0
-  transform:
-  - soil_moisture_to_vol_fraction
-  variable_cmap: Blues
-
-cSoil-HWSD2:
-  sources:
-    cSoil: cSoil/HWSD2/hwsd2_cSoil.nc
-  variable_cmap: viridis
-
-lai-AVH15C1:
-  sources:
-    lai: lai/AVH15C1/lai.nc
-  variable_cmap: Greens
-
-nbp-Hoffman:
-  analyses:
-  - nbp
-  sources:
-    nbp: nbp/HOFFMAN/nbp_1850-2010.nc

climate_ref_ilamb-0.5.4/src/climate_ref_ilamb/configure/iomb.yaml

@@ -1,27 +0,0 @@
-registry: iomb
-
-thetao-WOA2023-surface:
-  sources:
-    thetao: WOA/thetao_mon_WOA_A5B4_gn_200501-201412.nc
-  variable_cmap: Reds
-  depth: 0.0
-  alternate_vars:
-  - tos
-
-so-WOA2023-surface:
-  sources:
-    so: WOA/so_mon_WOA_A5B4_gn_200501-201412.nc
-  variable_cmap: YlGn
-  depth: 0.0
-  alternate_vars:
-  - sos
-
-amoc-RAPID:
-  analyses:
-  - timeseries
-  alternate_vars:
-  - msftmz
-  transform:
-  - msftmz_to_rapid
-  sources:
-    amoc: RAPID/amoc_mon_RAPID_BE_NA_200404-202302.nc

climate_ref_ilamb-0.5.4/src/climate_ref_ilamb/dataset_registry/ilamb.txt

@@ -1,11 +0,0 @@
-cSoil/HWSD2/hwsd2_cSoil.nc sha1:9a6377e4c5ff457c08c194d2c376c46e003a4f84
-gpp/FLUXNET2015/gpp.nc sha1:16fd177e007caef2565687e2cd32884e20ef16e5
-gpp/WECANN/gpp.nc sha1:6e864a6ae201195cdf995a3a81720188af441e13
-lai/AVH15C1/lai.nc sha1:ccace4f84912d63acbb9ee09ee7b743412207a0d
-mrro/LORA/LORA.nc sha1:72bb16787877591d0c54a36d74697d0d208f985a
-mrsol/WangMao/mrsol_olc.nc sha1:24cbc9df69569bed3a39c20e499cfe4f911bd30e
-regions/GlobalLand.nc sha1:2f987d44fdba6ad0e72d14d6a2fecb7e8df2a9c5
-regions/Koppen_coarse.nc sha1:e464030db49f0295a6a22a81ca602b0f3c499b72
-pr/GPCPv2.3/pr.nc sha1:e1b942863ec76a75aa972b6d75e2e08646741259
-tas/CRU4.02/tas.nc sha1:2674da18a1a93483b50b1626e7a7ab741bf53d09
-nbp/HOFFMAN/nbp_1850-2010.nc sha1:8350af00614d6afc6b70ad314aa499a9ece80ec2

climate_ref_ilamb-0.5.4/src/climate_ref_ilamb/dataset_registry/iomb.txt

@@ -1,3 +0,0 @@
-WOA/so_mon_WOA_A5B4_gn_200501-201412.nc sha1:831c42c3b2ba443c255150289a2c725d7f3e5838
-WOA/thetao_mon_WOA_A5B4_gn_200501-201412.nc sha1:86d9056208291d76233e65b26c658c1fa54c3ea6
-RAPID/amoc_mon_RAPID_BE_NA_200404-202302.nc sha1:3efe773e5c2a3c832977791ff7fd9cb9f473fe65

climate_ref_ilamb-0.5.4/src/climate_ref_ilamb/dataset_registry/test.txt

@@ -1,3 +0,0 @@
-test/Site/tas.nc sha1:3e757c9feadea581a92e6f4afb402b86168e113a
-test/Grid/gpp.nc sha1:2688085f95fa13617b20c723c66b0009bd661847
-test/Grid/pr.nc sha1:d667eb216939f5797d59b59cb4ade5ec31e67659

climate_ref_ilamb-0.5.4/src/climate_ref_ilamb/standard.py

@@ -1,207 +0,0 @@
-from pathlib import Path
-from typing import Any
-
-import ilamb3  # type: ignore
-import ilamb3.regions as ilr  # type: ignore
-import matplotlib.pyplot as plt
-import pandas as pd
-import pooch
-from ilamb3 import run
-
-from climate_ref_core.dataset_registry import dataset_registry_manager
-from climate_ref_core.datasets import FacetFilter, SourceDatasetType
-from climate_ref_core.diagnostics import (
-    DataRequirement,
-    Diagnostic,
-    ExecutionDefinition,
-    ExecutionResult,
-)
-from climate_ref_core.pycmec.metric import CMECMetric
-from climate_ref_core.pycmec.output import CMECOutput
-from climate_ref_ilamb.datasets import (
-    registry_to_collection,
-)
-
-
-def _build_cmec_bundle(name: str, df: pd.DataFrame) -> dict[str, Any]:
-    """
-    Build a CMEC bundle from information in the dataframe.
-
-    TODO: Migrate to use pycmec when ready.
-    TODO: Add plots and html output.
-    """
-    ilamb_regions = ilr.Regions()
-    bundle = {
-        "DIMENSIONS": {
-            "json_structure": ["region", "model", "metric", "statistic"],
-            "region": {
-                r: {
-                    "LongName": "None" if r == "None" else ilamb_regions.get_name(r),
-                    "Description": "Reference data extents" if r == "None" else ilamb_regions.get_name(r),
-                    "Generator": "N/A" if r == "None" else ilamb_regions.get_source(r),
-                }
-                for r in df["region"].unique()
-            },
-            "model": {m: {"Description": m, "Source": m} for m in df["source"].unique() if m != "Reference"},
-            "metric": {
-                name: {
-                    "Name": name,
-                    "Abstract": "benchmark score",
-                    "URI": [
-                        "https://www.osti.gov/biblio/1330803",
-                        "https://doi.org/10.1029/2018MS001354",
-                    ],
-                    "Contact": "forrest AT climatemodeling.org",
-                }
-            },
-            "statistic": {s: {} for s in df["name"].unique()},
-        },
-        "RESULTS": {
-            r: {
-                m: {
-                    name: {
-                        s: float(
-                            df[(df["source"] == m) & (df["region"] == r) & (df["name"] == s)].iloc[0]["value"]
-                        )
-                        for s in df["name"].unique()
-                    }
-                }
-                for m in df["source"].unique()
-                if m != "Reference"
-            }
-            for r in df["region"].unique()
-        },
-    }
-    return bundle
-
-
-def _form_bundles(key: str, df: pd.DataFrame) -> tuple[CMECMetric, CMECOutput]:
-    """
-    Create the output bundles (really a lift to make Ruff happy with the size of run()).
-    """
-    metric_bundle = _build_cmec_bundle(key, df)
-    output_bundle = CMECOutput.create_template()
-    return CMECMetric.model_validate(metric_bundle), CMECOutput.model_validate(output_bundle)
-
-
-def _set_ilamb3_options(registry: pooch.Pooch, registry_file: str) -> None:
-    """
-    Set options for ILAMB based on which registry file is being used.
-    """
-    ilamb3.conf.reset()
-    ilamb_regions = ilr.Regions()
-    if registry_file == "ilamb":
-        ilamb_regions.add_netcdf(registry.fetch("regions/GlobalLand.nc"))
-        ilamb_regions.add_netcdf(registry.fetch("regions/Koppen_coarse.nc"))
-        ilamb3.conf.set(regions=["global", "tropical"])
-
-
-def _measure_facets(registry_file: str) -> list[str]:
-    """
-    Set options for ILAMB based on which registry file is being used.
-    """
-    if registry_file == "ilamb":
-        return ["areacella", "sftlf"]
-    return []
-
-
-def _load_csv_and_merge(output_directory: Path) -> pd.DataFrame:
-    """
-    Load individual csv scalar data and merge into a dataframe.
-    """
-    df = pd.concat(
-        [pd.read_csv(f, keep_default_na=False, na_values=["NaN"]) for f in output_directory.glob("*.csv")]
-    ).drop_duplicates(subset=["source", "region", "analysis", "name"])
-    return df
-
-
-class ILAMBStandard(Diagnostic):
-    """
-    Apply the standard ILAMB analysis with respect to a given reference dataset.
-    """
-
-    def __init__(
-        self,
-        registry_file: str,
-        metric_name: str,
-        sources: dict[str, str],
-        **ilamb_kwargs: Any,
-    ):
-        # Setup the diagnostic
-        if len(sources) != 1:
-            raise ValueError("Only single source ILAMB diagnostics have been implemented.")
-        self.variable_id = next(iter(sources.keys()))
-        if "sources" not in ilamb_kwargs:  # pragma: no cover
-            ilamb_kwargs["sources"] = sources
-        if "relationships" not in ilamb_kwargs:
-            ilamb_kwargs["relationships"] = {}
-        self.ilamb_kwargs = ilamb_kwargs
-
-        # REF stuff
-        self.name = metric_name
-        self.slug = self.name.lower().replace(" ", "-")
-        self.data_requirements = (
-            DataRequirement(
-                source_type=SourceDatasetType.CMIP6,
-                filters=(
-                    FacetFilter(
-                        facets={
-                            "variable_id": (
-                                self.variable_id,
-                                *ilamb_kwargs.get("relationships", {}).keys(),
-                                *ilamb_kwargs.get("alternate_vars", []),
-                                *_measure_facets(registry_file),
-                            )
-                        }
-                    ),
-                    FacetFilter(facets={"frequency": ("mon", "fx")}),
-                    FacetFilter(facets={"experiment_id": ("historical", "land-hist")}),
-                ),
-                group_by=("experiment_id",),
-            ),
-        )
-        self.facets = ("region", "model", "metric", "statistic")
-
-        # Setup ILAMB data and options
-        self.registry_file = registry_file
-        self.registry = dataset_registry_manager[self.registry_file]
-        self.ilamb_data = registry_to_collection(
-            dataset_registry_manager[self.registry_file],
-        )
-
-    def execute(self, definition: ExecutionDefinition) -> None:
-        """
-        Run the ILAMB standard analysis.
-        """
-        plt.rcParams.update({"figure.max_open_warning": 0})
-        _set_ilamb3_options(self.registry, self.registry_file)
-        ref_datasets = self.ilamb_data.datasets.set_index(self.ilamb_data.slug_column)
-        run.run_simple(
-            ref_datasets,
-            self.slug,
-            definition.datasets[SourceDatasetType.CMIP6].datasets,
-            definition.output_directory,
-            **self.ilamb_kwargs,
-        )
-
-    def build_execution_result(self, definition: ExecutionDefinition) -> ExecutionResult:
-        """
-        Build the diagnostic result after running ILAMB.
-
-        Parameters
-        ----------
-        definition
-            The definition of the diagnostic execution
-
-        Returns
-        -------
-            An execution result object
-        """
-        _set_ilamb3_options(self.registry, self.registry_file)
-
-        df = _load_csv_and_merge(definition.output_directory)
-        metric_bundle, output_bundle = _form_bundles(definition.key, df)
-
-        return ExecutionResult.build_from_output_bundle(
-            definition, cmec_output_bundle=output_bundle, cmec_metric_bundle=metric_bundle
-        )