anemoi-datasets 0.5.27__py3-none-any.whl → 0.5.28__py3-none-any.whl

anemoi/datasets/create/__init__.py

@@ -865,7 +865,7 @@ class Load(Actor, HasRegistryMixin, HasStatisticTempMixin, HasElementForDataMixi
             # assert isinstance(group[0], datetime.datetime), type(group[0])
             LOG.debug(f"Building data for group {igroup}/{self.n_groups}")
 
-            result = self.input.select(group_of_dates=group)
+            result = self.input.select(argument=group)
             assert result.group_of_dates == group, (len(result.group_of_dates), len(group), group)
 
             # There are several groups.
@@ -1616,3 +1616,44 @@ def creator_factory(name: str, trace: str | None = None, **kwargs: Any) -> Any:
     )[name]
     LOG.debug(f"Creating {cls.__name__} with {kwargs}")
     return cls(**kwargs)
+
+
+def validate_config(config: Any) -> None:
+
+    import json
+
+    import jsonschema
+
+    def _tidy(d):
+        if isinstance(d, dict):
+            return {k: _tidy(v) for k, v in d.items()}
+
+        if isinstance(d, list):
+            return [_tidy(v) for v in d if v is not None]
+
+        # jsonschema does not support datetime.date
+        if isinstance(d, datetime.datetime):
+            return d.isoformat()
+
+        if isinstance(d, datetime.date):
+            return d.isoformat()
+
+        return d
+
+    # https://json-schema.org
+
+    with open(
+        os.path.join(
+            os.path.dirname(os.path.dirname(__file__)),
+            "schemas",
+            "recipe.json",
+        )
+    ) as f:
+        schema = json.load(f)
+
+    try:
+        jsonschema.validate(instance=_tidy(config), schema=schema)
+    except jsonschema.exceptions.ValidationError as e:
+        LOG.error("❌ Config validation failed (jsonschema):")
+        LOG.error(e.message)
+        raise

anemoi/datasets/create/config.py

@@ -279,6 +279,8 @@ class LoadersConfig(Config):
 
         self.output.order_by = normalize_order_by(self.output.order_by)
 
+        self.setdefault("dates", Config())
+
         self.dates["group_by"] = self.build.group_by
 
         ###########

anemoi/datasets/create/input/__init__.py

@@ -1,4 +1,4 @@
-# (C) Copyright 2024 Anemoi contributors.
+# (C) Copyright 2024-2025 Anemoi contributors.
 #
 # This software is licensed under the terms of the Apache Licence Version 2.0
 # which can be obtained at http://www.apache.org/licenses/LICENSE-2.0.
@@ -7,21 +7,15 @@
 # granted to it by virtue of its status as an intergovernmental organisation
 # nor does it submit to any jurisdiction.
 
-import logging
 from copy import deepcopy
+from functools import cached_property
+from typing import TYPE_CHECKING
 from typing import Any
 
-from anemoi.datasets.dates.groups import GroupOfDates
+from anemoi.datasets.create.input.context.field import FieldContext
 
-from .trace import trace_select
-
-LOG = logging.getLogger(__name__)
-
-
-class Context:
-    """Context for building input data."""
-
-    pass
+if TYPE_CHECKING:
+    from anemoi.datasets.create.input.action import Recipe
 
 
 class InputBuilder:
@@ -34,72 +28,58 @@ class InputBuilder:
         ----------
         config : dict
             Configuration dictionary.
-        data_sources : Union[dict, list]
+        data_sources : dict
             Data sources.
         **kwargs : Any
             Additional keyword arguments.
         """
         self.kwargs = kwargs
+        self.config = deepcopy(config)
+        self.data_sources = deepcopy(dict(data_sources=data_sources))
 
-        config = deepcopy(config)
-        if data_sources:
-            config = dict(
-                data_sources=dict(
-                    sources=data_sources,
-                    input=config,
-                )
-            )
-        self.config = config
-        self.action_path = ["input"]
-
-    @trace_select
-    def select(self, group_of_dates: GroupOfDates) -> Any:
-        """Select data based on the group of dates.
-
-        Parameters
-        ----------
-        group_of_dates : GroupOfDates
-            Group of dates to select data for.
-
-        Returns
-        -------
-        Any
-            Selected data.
-        """
-        from .action import ActionContext
+    @cached_property
+    def action(self) -> "Recipe":
+        """Returns the action object based on the configuration."""
+        from .action import Recipe
         from .action import action_factory
 
-        """This changes the context."""
-        context = ActionContext(**self.kwargs)
-        action = action_factory(self.config, context, self.action_path)
-        return action.select(group_of_dates)
-
-    def __repr__(self) -> str:
-        """Return a string representation of the InputBuilder.
-
-        Returns
-        -------
-        str
-            String representation.
-        """
-        from .action import ActionContext
-        from .action import action_factory
+        sources = action_factory(self.data_sources, "data_sources")
+        input = action_factory(self.config, "input")
 
-        context = ActionContext(**self.kwargs)
-        a = action_factory(self.config, context, self.action_path)
-        return repr(a)
+        return Recipe(input, sources)
 
-    def _trace_select(self, group_of_dates: GroupOfDates) -> str:
-        """Trace the select operation.
+    def select(self, argument) -> Any:
+        """Select data based on the group of dates.
 
         Parameters
         ----------
-        group_of_dates : GroupOfDates
+        argument : GroupOfDates
             Group of dates to select data for.
 
         Returns
         -------
-        str
-            Trace string.
+        Any
+            Selected data.
         """
-        return f"InputBuilder({group_of_dates})"
+        context = FieldContext(argument, **self.kwargs)
+        return context.create_result(self.action(context, argument))
+
+
+def build_input(config: dict, data_sources: dict | list, **kwargs: Any) -> InputBuilder:
+    """Build an InputBuilder instance.
+
+    Parameters
+    ----------
+    config : dict
+        Configuration dictionary.
+    data_sources : Union[dict, list]
+        Data sources.
+    **kwargs : Any
+        Additional keyword arguments.
+
+    Returns
+    -------
+    InputBuilder
+        An instance of InputBuilder.
+    """
+    return InputBuilder(config, data_sources, **kwargs)