climate-ref-pmp 0.5.5__tar.gz → 0.6.1__tar.gz

{climate_ref_pmp-0.5.5 → climate_ref_pmp-0.6.1}/PKG-INFO

@@ -1,9 +1,9 @@
 Metadata-Version: 2.4
 Name: climate-ref-pmp
-Version: 0.5.5
+Version: 0.6.1
 Summary: PMP diagnostic provider for the Rapid Evaluation Framework
-Author-email: Jiwoo Lee <jwlee@llnl.gov>
-License: Apache-2.0
+Author-email: Jiwoo Lee <jwlee@llnl.gov>, Jared Lewis <jared.lewis@climate-resource.com>
+License-Expression: Apache-2.0
 License-File: LICENCE
 License-File: NOTICE
 Classifier: Development Status :: 3 - Alpha

{climate_ref_pmp-0.5.5 → climate_ref_pmp-0.6.1}/pyproject.toml

@@ -1,11 +1,13 @@
 [project]
 name = "climate-ref-pmp"
-version = "0.5.5"
+version = "0.6.1"
 description = "PMP diagnostic provider for the Rapid Evaluation Framework"
 readme = "README.md"
 authors = [
-    { name = "Jiwoo Lee", email = "jwlee@llnl.gov" }
+    { name = "Jiwoo Lee", email = "jwlee@llnl.gov" },
+    { name = "Jared Lewis", email = "jared.lewis@climate-resource.com" },
 ]
+license = "Apache-2.0"
 requires-python = ">=3.11"
 classifiers = [
     "Development Status :: 3 - Alpha",
@@ -24,9 +26,6 @@ dependencies = [
     "climate-ref-core",
 ]
 
-[project.license]
-text = "Apache-2.0"
-
 [dependency-groups]
 dev = []
 

{climate_ref_pmp-0.5.5 → climate_ref_pmp-0.6.1}/src/climate_ref_pmp/__init__.py

@@ -6,7 +6,7 @@ import importlib.metadata
 
 from climate_ref_core.dataset_registry import DATASET_URL, dataset_registry_manager
 from climate_ref_core.providers import CondaDiagnosticProvider
-from climate_ref_pmp.diagnostics import AnnualCycle, ExtratropicalModesOfVariability
+from climate_ref_pmp.diagnostics import ENSO, AnnualCycle, ExtratropicalModesOfVariability
 
 __version__ = importlib.metadata.version("climate-ref-pmp")
 
@@ -14,6 +14,15 @@ __version__ = importlib.metadata.version("climate-ref-pmp")
 # PMP uses a conda environment to run the diagnostics
 provider = CondaDiagnosticProvider("PMP", __version__)
 
+# Annual cycle diagnostics and metrics
+provider.register(AnnualCycle())
+
+# ENSO diagnostics and metrics
+# provider.register(ENSO("ENSO_perf"))  # Assigned to ESMValTool
+provider.register(ENSO("ENSO_tel"))
+provider.register(ENSO("ENSO_proc"))
+
+# Extratropical modes of variability diagnostics and metrics
 provider.register(ExtratropicalModesOfVariability("PDO"))
 provider.register(ExtratropicalModesOfVariability("NPGO"))
 provider.register(ExtratropicalModesOfVariability("NAO"))
@@ -21,7 +30,6 @@ provider.register(ExtratropicalModesOfVariability("NAM"))
 provider.register(ExtratropicalModesOfVariability("PNA"))
 provider.register(ExtratropicalModesOfVariability("NPO"))
 provider.register(ExtratropicalModesOfVariability("SAM"))
-provider.register(AnnualCycle())
 
 
 dataset_registry_manager.register(

{climate_ref_pmp-0.5.5 → climate_ref_pmp-0.6.1}/src/climate_ref_pmp/diagnostics/__init__.py

@@ -1,9 +1,11 @@
 """PMP diagnostics."""
 
 from climate_ref_pmp.diagnostics.annual_cycle import AnnualCycle
+from climate_ref_pmp.diagnostics.enso import ENSO
 from climate_ref_pmp.diagnostics.variability_modes import ExtratropicalModesOfVariability
 
 __all__ = [
+    "ENSO",
     "AnnualCycle",
     "ExtratropicalModesOfVariability",
 ]

{climate_ref_pmp-0.5.5 → climate_ref_pmp-0.6.1}/src/climate_ref_pmp/diagnostics/annual_cycle.py

@@ -15,6 +15,44 @@ from climate_ref_core.pycmec.metric import remove_dimensions
 from climate_ref_pmp.pmp_driver import build_glob_pattern, build_pmp_command, process_json_result
 
 
+def make_data_requirement(variable_id: str, obs_source: str) -> tuple[DataRequirement, DataRequirement]:
+    """
+    Create a data requirement for the annual cycle diagnostic.
+
+    Parameters
+    ----------
+    variable_id : str
+        The variable ID to filter the data requirement.
+    obs_source : str
+        The observation source ID to filter the data requirement.
+
+    Returns
+    -------
+    DataRequirement
+        A DataRequirement object containing the necessary filters and groupings.
+    """
+    return (
+        DataRequirement(
+            source_type=SourceDatasetType.PMPClimatology,
+            filters=(FacetFilter(facets={"source_id": (obs_source,), "variable_id": (variable_id,)}),),
+            group_by=("variable_id", "source_id"),
+        ),
+        DataRequirement(
+            source_type=SourceDatasetType.CMIP6,
+            filters=(
+                FacetFilter(
+                    facets={
+                        "frequency": "mon",
+                        "experiment_id": ("amip", "historical", "hist-GHG", "piControl"),
+                        "variable_id": (variable_id,),
+                    }
+                ),
+            ),
+            group_by=("variable_id", "source_id", "experiment_id", "member_id", "grid_label"),
+        ),
+    )
+
+
 class AnnualCycle(CommandLineDiagnostic):
     """
     Calculate the annual cycle for a dataset
@@ -32,49 +70,20 @@ class AnnualCycle(CommandLineDiagnostic):
         "statistic",
         "season",
     )
+
     data_requirements = (
-        # Surface temperature
-        (
-            DataRequirement(
-                source_type=SourceDatasetType.PMPClimatology,
-                filters=(FacetFilter(facets={"source_id": ("ERA-5",), "variable_id": ("ts",)}),),
-                group_by=("variable_id", "source_id"),
-            ),
-            DataRequirement(
-                source_type=SourceDatasetType.CMIP6,
-                filters=(
-                    FacetFilter(
-                        facets={
-                            "frequency": "mon",
-                            "experiment_id": ("amip", "historical", "hist-GHG", "piControl"),
-                            "variable_id": ("ts",),
-                        }
-                    ),
-                ),
-                group_by=("variable_id", "source_id", "experiment_id", "member_id"),
-            ),
-        ),
-        # Precipitation
-        (
-            DataRequirement(
-                source_type=SourceDatasetType.PMPClimatology,
-                filters=(FacetFilter(facets={"source_id": ("GPCP-Monthly-3-2",), "variable_id": ("pr",)}),),
-                group_by=("variable_id", "source_id"),
-            ),
-            DataRequirement(
-                source_type=SourceDatasetType.CMIP6,
-                filters=(
-                    FacetFilter(
-                        facets={
-                            "frequency": "mon",
-                            "experiment_id": ("amip", "historical", "hist-GHG", "piControl"),
-                            "variable_id": ("pr",),
-                        }
-                    ),
-                ),
-                group_by=("variable_id", "source_id", "experiment_id", "member_id"),
-            ),
-        ),
+        make_data_requirement("ts", "ERA-5"),
+        make_data_requirement("uas", "ERA-5"),
+        make_data_requirement("vas", "ERA-5"),
+        make_data_requirement("psl", "ERA-5"),
+        make_data_requirement("pr", "GPCP-Monthly-3-2"),
+        make_data_requirement("rlds", "CERES-EBAF-4-2"),
+        make_data_requirement("rlus", "CERES-EBAF-4-2"),
+        make_data_requirement("rlut", "CERES-EBAF-4-2"),
+        make_data_requirement("rsds", "CERES-EBAF-4-2"),
+        make_data_requirement("rsdt", "CERES-EBAF-4-2"),
+        make_data_requirement("rsus", "CERES-EBAF-4-2"),
+        make_data_requirement("rsut", "CERES-EBAF-4-2"),
     )
 
     def __init__(self) -> None:

climate_ref_pmp-0.6.1/src/climate_ref_pmp/diagnostics/enso.py

@@ -0,0 +1,245 @@
+import json
+import os
+from collections.abc import Collection, Iterable
+from typing import Any
+
+from loguru import logger
+
+from climate_ref_core.constraints import AddSupplementaryDataset
+from climate_ref_core.datasets import DatasetCollection, FacetFilter, SourceDatasetType
+from climate_ref_core.diagnostics import (
+    CommandLineDiagnostic,
+    DataRequirement,
+    ExecutionDefinition,
+    ExecutionResult,
+)
+from climate_ref_pmp.pmp_driver import _get_resource, process_json_result
+
+
+class ENSO(CommandLineDiagnostic):
+    """
+    Calculate the ENSO performance metrics for a dataset
+    """
+
+    facets = ("source_id", "member_id", "grid_label", "experiment_id", "metric", "reference_datasets")
+
+    def __init__(self, metrics_collection: str, experiments: Collection[str] = ("historical",)) -> None:
+        self.name = metrics_collection
+        self.slug = metrics_collection.lower()
+        self.metrics_collection = metrics_collection
+        self.parameter_file = "pmp_param_enso.py"
+        self.obs_sources: tuple[str, ...]
+        self.model_variables: tuple[str, ...]
+
+        if metrics_collection == "ENSO_perf":  # pragma: no cover
+            self.model_variables = ("pr", "ts", "tauu")
+            self.obs_sources = ("GPCP-Monthly-3-2", "TropFlux-1-0", "HadISST-1-1")
+        elif metrics_collection == "ENSO_tel":
+            self.model_variables = ("pr", "ts")
+            self.obs_sources = ("GPCP-Monthly-3-2", "TropFlux-1-0", "HadISST-1-1")
+        elif metrics_collection == "ENSO_proc":
+            self.model_variables = ("ts", "tauu", "hfls", "hfss", "rlds", "rlus", "rsds", "rsus")
+            self.obs_sources = (
+                "GPCP-Monthly-3-2",
+                "TropFlux-1-0",
+                "HadISST-1-1",
+                "CERES-EBAF-4-2",
+            )
+        else:
+            raise ValueError(
+                f"Unknown metrics collection: {metrics_collection}. "
+                "Valid options are: ENSO_perf, ENSO_tel, ENSO_proc"
+            )
+
+        self.data_requirements = self._get_data_requirements(experiments)
+
+    def _get_data_requirements(
+        self,
+        experiments: Collection[str] = ("historical",),
+    ) -> tuple[DataRequirement, DataRequirement]:
+        filters = [
+            FacetFilter(
+                facets={
+                    "frequency": "mon",
+                    "experiment_id": tuple(experiments),
+                    "variable_id": self.model_variables,
+                }
+            )
+        ]
+
+        return (
+            DataRequirement(
+                source_type=SourceDatasetType.obs4MIPs,
+                filters=(
+                    FacetFilter(facets={"source_id": self.obs_sources, "variable_id": self.model_variables}),
+                ),
+                group_by=("activity_id",),
+            ),
+            DataRequirement(
+                source_type=SourceDatasetType.CMIP6,
+                filters=tuple(filters),
+                group_by=("source_id", "experiment_id", "member_id", "grid_label"),
+                constraints=(
+                    AddSupplementaryDataset.from_defaults("areacella", SourceDatasetType.CMIP6),
+                    AddSupplementaryDataset.from_defaults("sftlf", SourceDatasetType.CMIP6),
+                ),
+            ),
+        )
+
+    def build_cmd(self, definition: ExecutionDefinition) -> Iterable[str]:
+        """
+        Run the diagnostic on the given configuration.
+
+        Parameters
+        ----------
+        definition : ExecutionDefinition
+            The configuration to run the diagnostic on.
+
+        Returns
+        -------
+        :
+            The result of running the diagnostic.
+        """
+        mc_name = self.metrics_collection
+
+        # ------------------------------------------------
+        # Get the input datasets information for the model
+        # ------------------------------------------------
+        input_datasets = definition.datasets[SourceDatasetType.CMIP6]
+        input_selectors = input_datasets.selector_dict()
+        source_id = input_selectors["source_id"]
+        member_id = input_selectors["member_id"]
+        experiment_id = input_selectors["experiment_id"]
+        variable_ids = set(input_datasets["variable_id"].unique()) - {"areacella", "sftlf"}
+        mod_run = f"{source_id}_{member_id}"
+
+        # We only need one entry for the model run
+        dict_mod: dict[str, dict[str, Any]] = {mod_run: {}}
+
+        def extract_variable(dc: DatasetCollection, variable: str) -> list[str]:
+            return dc.datasets[input_datasets["variable_id"] == variable]["path"].to_list()  # type: ignore
+
+        # TO DO: Get the path to the files per variable
+        for variable in variable_ids:
+            list_files = extract_variable(input_datasets, variable)
+            list_areacella = extract_variable(input_datasets, "areacella")
+            list_sftlf = extract_variable(input_datasets, "sftlf")
+
+            if len(list_files) > 0:
+                dict_mod[mod_run][variable] = {
+                    "path + filename": list_files,
+                    "varname": variable,
+                    "path + filename_area": list_areacella,
+                    "areaname": "areacella",
+                    "path + filename_landmask": list_sftlf,
+                    "landmaskname": "sftlf",
+                }
+
+        # -------------------------------------------------------
+        # Get the input datasets information for the observations
+        # -------------------------------------------------------
+        reference_dataset = definition.datasets[SourceDatasetType.obs4MIPs]
+        reference_dataset_names = reference_dataset["source_id"].unique()
+
+        dict_obs: dict[str, dict[str, Any]] = {}
+
+        # TO DO: Get the path to the files per variable and per source
+        for obs_name in reference_dataset_names:
+            dict_obs[obs_name] = {}
+            for variable in variable_ids:
+                # Get the list of files for the current variable and observation source
+                list_files = reference_dataset.datasets[
+                    (reference_dataset["variable_id"] == variable)
+                    & (reference_dataset["source_id"] == obs_name)
+                ]["path"].to_list()
+                # If the list is not empty, add it to the dictionary
+                if len(list_files) > 0:
+                    dict_obs[obs_name][variable] = {
+                        "path + filename": list_files,
+                        "varname": variable,
+                    }
+
+        # Create input directory
+        dict_datasets = {
+            "model": dict_mod,
+            "observations": dict_obs,
+            "metricsCollection": mc_name,
+            "experiment_id": experiment_id,
+        }
+
+        # Create JSON file for dictDatasets
+        json_file = os.path.join(
+            definition.output_directory, f"input_{mc_name}_{source_id}_{experiment_id}_{member_id}.json"
+        )
+        with open(json_file, "w") as f:
+            json.dump(dict_datasets, f, indent=4)
+        logger.debug(f"JSON file created: {json_file}")
+
+        driver_file = _get_resource("climate_ref_pmp.drivers", "enso_driver.py", use_resources=True)
+        return [
+            "python",
+            driver_file,
+            "--metrics_collection",
+            mc_name,
+            "--experiment_id",
+            experiment_id,
+            "--input_json_path",
+            json_file,
+            "--output_directory",
+            str(definition.output_directory),
+        ]
+
+    def build_execution_result(self, definition: ExecutionDefinition) -> ExecutionResult:
+        """
+        Build a diagnostic result from the output of the PMP driver
+
+        Parameters
+        ----------
+        definition
+            Definition of the diagnostic execution
+
+        Returns
+        -------
+            Result of the diagnostic execution
+        """
+        input_datasets = definition.datasets[SourceDatasetType.CMIP6]
+        source_id = input_datasets["source_id"].unique()[0]
+        experiment_id = input_datasets["experiment_id"].unique()[0]
+        member_id = input_datasets["member_id"].unique()[0]
+        mc_name = self.metrics_collection
+        pattern = f"{mc_name}_{source_id}_{experiment_id}_{member_id}"
+
+        # Find the results files
+        results_files = list(definition.output_directory.glob(f"{pattern}_cmec.json"))
+        logger.debug(f"Results files: {results_files}")
+
+        if len(results_files) != 1:  # pragma: no cover
+            logger.warning(f"A single cmec output file not found: {results_files}")
+            return ExecutionResult.build_from_failure(definition)
+
+        # Find the other outputs
+        png_files = [definition.as_relative_path(f) for f in definition.output_directory.glob("*.png")]
+        data_files = [definition.as_relative_path(f) for f in definition.output_directory.glob("*.nc")]
+
+        cmec_output, cmec_metric = process_json_result(results_files[0], png_files, data_files)
+
+        input_selectors = definition.datasets[SourceDatasetType.CMIP6].selector_dict()
+        cmec_metric_bundle = cmec_metric.remove_dimensions(
+            [
+                "model",
+                "realization",
+            ],
+        ).prepend_dimensions(
+            {
+                "source_id": input_selectors["source_id"],
+                "member_id": input_selectors["member_id"],
+                "grid_label": input_selectors["grid_label"],
+                "experiment_id": input_selectors["experiment_id"],
+            }
+        )
+
+        return ExecutionResult.build_from_output_bundle(
+            definition,
+            cmec_output_bundle=cmec_output,
+            cmec_metric_bundle=cmec_metric_bundle,
+        )

{climate_ref_pmp-0.5.5 → climate_ref_pmp-0.6.1}/src/climate_ref_pmp/diagnostics/variability_modes.py

@@ -1,4 +1,6 @@
 from collections.abc import Iterable
+from pathlib import Path
+from typing import Any, Union
 
 from loguru import logger
 
@@ -37,10 +39,10 @@ class ExtratropicalModesOfVariability(CommandLineDiagnostic):
         self.name = f"Extratropical modes of variability: {mode_id}"
         self.slug = f"extratropical-modes-of-variability-{mode_id.lower()}"
 
-        def get_data_requirements(
+        def _get_data_requirements(
             obs_source: str,
             obs_variable: str,
-            cmip_variable: str,
+            model_variable: str,
             extra_experiments: str | tuple[str, ...] | list[str] = (),
         ) -> tuple[DataRequirement, DataRequirement]:
             filters = [
@@ -48,7 +50,7 @@ class ExtratropicalModesOfVariability(CommandLineDiagnostic):
                     facets={
                         "frequency": "mon",
                         "experiment_id": ("historical", "hist-GHG", "piControl", *extra_experiments),
-                        "variable_id": cmip_variable,
+                        "variable_id": model_variable,
                     }
                 )
             ]
@@ -64,17 +66,16 @@ class ExtratropicalModesOfVariability(CommandLineDiagnostic):
                 DataRequirement(
                     source_type=SourceDatasetType.CMIP6,
                     filters=tuple(filters),
-                    # TODO: remove unneeded variant_label
-                    group_by=("source_id", "experiment_id", "variant_label", "member_id"),
+                    group_by=("source_id", "experiment_id", "member_id", "grid_label"),
                 ),
             )
 
         if self.mode_id in self.ts_modes:
             self.parameter_file = "pmp_param_MoV-ts.py"
-            self.data_requirements = get_data_requirements("HadISST-1-1", "ts", "ts")
+            self.data_requirements = _get_data_requirements("HadISST-1-1", "ts", "ts")
         elif self.mode_id in self.psl_modes:
             self.parameter_file = "pmp_param_MoV-psl.py"
-            self.data_requirements = get_data_requirements("20CR", "psl", "psl", extra_experiments=("amip",))
+            self.data_requirements = _get_data_requirements("20CR", "psl", "psl", extra_experiments=("amip",))
         else:
             raise ValueError(
                 f"Unknown mode_id '{self.mode_id}'. Must be one of {self.ts_modes + self.psl_modes}"
@@ -172,6 +173,8 @@ class ExtratropicalModesOfVariability(CommandLineDiagnostic):
             logger.warning(f"A single cmec output file not found: {results_files}")
             return ExecutionResult.build_from_failure(definition)
 
+        clean_up_json(results_files[0])
+
         # Find the other outputs
         png_files = [definition.as_relative_path(f) for f in definition.output_directory.glob("*.png")]
         data_files = [definition.as_relative_path(f) for f in definition.output_directory.glob("*.nc")]
@@ -201,3 +204,63 @@ class ExtratropicalModesOfVariability(CommandLineDiagnostic):
             cmec_output_bundle=cmec_output_bundle,
             cmec_metric_bundle=cmec_metric_bundle,
         )
+
+
+def clean_up_json(json_file: Union[str, Path]) -> None:
+    """
+    Clean up the JSON file by removing unnecessary fields.
+
+    Parameters
+    ----------
+    json_file : str or Path
+        Path to the JSON file to clean up.
+    """
+    import json
+
+    with open(str(json_file)) as f:
+        data = json.load(f)
+
+    # Remove null values from the JSON data
+    data = remove_null_values(data)
+
+    with open(str(json_file), "w") as f:
+        json.dump(data, f, indent=4)
+
+    # Log the cleanup action
+    logger.debug(f"Cleaned up JSON file: {json_file}")
+    logger.info("JSON file cleaned up successfully.")
+
+
+def remove_null_values(data: Union[dict[Any, Any], list[Any], Any]) -> Union[dict[Any, Any], list[Any], Any]:
+    """
+    Recursively removes keys with null (None) values from a dictionary or list.
+
+    Parameters
+    ----------
+    data : dict, list, or Any
+        The JSON-like data structure to process. It can be a dictionary, a list,
+        or any other type of data.
+
+    Returns
+    -------
+    dict, list, or Any
+        A new data structure with null values removed. If the input is a dictionary,
+        keys with `None` values are removed. If the input is a list, items are
+        recursively processed to remove `None` values. For other types, the input
+        is returned unchanged.
+
+    Examples
+    --------
+    >>> data = {
+    ...     "key1": None,
+    ...     "key2": {"subkey1": 123, "subkey2": None},
+    ...     "key3": [None, 456, {"subkey3": None}],
+    ... }
+    >>> remove_null_values(data)
+    {'key2': {'subkey1': 123}, 'key3': [456, {}]}
+    """
+    if isinstance(data, dict):
+        return {key: remove_null_values(value) for key, value in data.items() if value is not None}
+    if isinstance(data, list):
+        return [remove_null_values(item) for item in data if item is not None]
+    return data