anemoi-datasets 0.5.26__py3-none-any.whl → 0.5.27__py3-none-any.whl

anemoi/datasets/data/misc.py

@@ -15,11 +15,6 @@ import os
 from pathlib import PurePath
 from typing import TYPE_CHECKING
 from typing import Any
-from typing import Dict
-from typing import List
-from typing import Optional
-from typing import Tuple
-from typing import Union
 
 import numpy as np
 import zarr
@@ -33,7 +28,7 @@ if TYPE_CHECKING:
 LOG = logging.getLogger(__name__)
 
 
-def load_config() -> Dict[str, Any]:
+def load_config() -> dict[str, Any]:
     """Load the configuration settings.
 
     Returns
@@ -110,10 +105,10 @@ def round_datetime(d: np.datetime64, dates: NDArray[np.datetime64], up: bool) ->
 
 
 def _as_date(
-    d: Union[int, str, np.datetime64, datetime.date],
+    d: int | str | np.datetime64 | datetime.date,
     dates: NDArray[np.datetime64],
     last: bool,
-    frequency: Optional[datetime.timedelta] = None,
+    frequency: datetime.timedelta | None = None,
 ) -> np.datetime64:
     """Convert a date to a numpy datetime64 object, rounding to the nearest date in a list of dates.
 
@@ -221,8 +216,8 @@ def _as_date(
 
         if "-" in d and ":" in d:
             date, time = d.replace(" ", "T").split("T")
-            year, month, day = [int(_) for _ in date.split("-")]
-            hour, minute, second = [int(_) for _ in time.split(":")]
+            year, month, day = (int(_) for _ in date.split("-"))
+            hour, minute, second = (int(_) for _ in time.split(":"))
             return _as_date(
                 np.datetime64(f"{year:04}-{month:02}-{day:02}T{hour:02}:{minute:02}:{second:02}"),
                 dates,
@@ -258,9 +253,9 @@ def _as_date(
 
 
 def as_first_date(
-    d: Union[int, str, np.datetime64, datetime.date],
+    d: int | str | np.datetime64 | datetime.date,
     dates: NDArray[np.datetime64],
-    frequency: Optional[datetime.timedelta] = None,
+    frequency: datetime.timedelta | None = None,
 ) -> np.datetime64:
     """Convert a date to the first date in a list of dates.
 
@@ -282,9 +277,9 @@ def as_first_date(
 
 
 def as_last_date(
-    d: Union[int, str, np.datetime64, datetime.date],
+    d: int | str | np.datetime64 | datetime.date,
     dates: NDArray[np.datetime64],
-    frequency: Optional[datetime.timedelta] = None,
+    frequency: datetime.timedelta | None = None,
 ) -> np.datetime64:
     """Convert a date to the last date in a list of dates.
 
@@ -305,7 +300,7 @@ def as_last_date(
     return _as_date(d, dates, last=True, frequency=frequency)
 
 
-def _concat_or_join(datasets: List["Dataset"], kwargs: Dict[str, Any]) -> Tuple["Dataset", Dict[str, Any]]:
+def _concat_or_join(datasets: list["Dataset"], kwargs: dict[str, Any]) -> tuple["Dataset", dict[str, Any]]:
     """Concatenate or join datasets based on their date ranges.
 
     Parameters
@@ -317,7 +312,7 @@ def _concat_or_join(datasets: List["Dataset"], kwargs: Dict[str, Any]) -> Tuple[
 
     Returns
     -------
-    Tuple[Dataset, Dict[str, Any]]
+    tuple[Dataset, Dict[str, Any]]
         The concatenated or joined dataset and remaining arguments.
     """
     if "adjust" in kwargs:
@@ -339,12 +334,12 @@ def _concat_or_join(datasets: List["Dataset"], kwargs: Dict[str, Any]) -> Tuple[
     return Concat(datasets), kwargs
 
 
-def _open(a: Union[str, PurePath, Dict[str, Any], List[Any], Tuple[Any, ...]]) -> "Dataset":
+def _open(a: str | PurePath | dict[str, Any] | list[Any] | tuple[Any, ...]) -> "Dataset":
     """Open a dataset from various input types.
 
     Parameters
     ----------
-    a : Union[str, PurePath, Dict[str, Any], List[Any], Tuple[Any, ...]]
+    a : Union[str, PurePath, Dict[str, Any], List[Any], tuple[Any, ...]]
         The input to open.
 
     Returns
@@ -390,10 +385,10 @@ def _open(a: Union[str, PurePath, Dict[str, Any], List[Any], Tuple[Any, ...]]) -
 
 
 def _auto_adjust(
-    datasets: List["Dataset"],
-    kwargs: Dict[str, Any],
-    exclude: Optional[List[str]] = None,
-) -> Tuple[List["Dataset"], Dict[str, Any]]:
+    datasets: list["Dataset"],
+    kwargs: dict[str, Any],
+    exclude: list[str] | None = None,
+) -> tuple[list["Dataset"], dict[str, Any]]:
     """Automatically adjust datasets based on specified criteria.
 
     Parameters
@@ -407,7 +402,7 @@ def _auto_adjust(
 
     Returns
     -------
-    Tuple[List[Dataset], Dict[str, Any]]
+    tuple[List[Dataset], Dict[str, Any]]
         The adjusted datasets and remaining arguments.
     """
     if "adjust" not in kwargs:
@@ -620,7 +615,7 @@ def append_to_zarr(new_data: np.ndarray, new_dates: np.ndarray, zarr_path: str)
     # Re-open the zarr store to avoid root object accumulating memory.
     root = zarr.open(zarr_path, mode="a")
     # Convert new dates to strings (using str) regardless of input dtype.
-    new_dates = np.array(new_dates, dtype="datetime64[ns]")
+    new_dates = np.array(new_dates, dtype="datetime64[s]")
     dates_ds = root["dates"]
     old_len = dates_ds.shape[0]
     dates_ds.resize((old_len + len(new_dates),))
@@ -633,19 +628,19 @@ def append_to_zarr(new_data: np.ndarray, new_dates: np.ndarray, zarr_path: str)
     data_ds[old_shape[0] :] = new_data
 
 
-def process_date(date: Any, big_dataset: Any) -> Tuple[np.ndarray, np.ndarray]:
+def process_date(date: Any, big_dataset: "Dataset") -> tuple[np.ndarray, np.ndarray]:
     """Open the subset corresponding to the given date and return (date, subset).
 
     Parameters
     ----------
     date : Any
         The date to process.
-    big_dataset : Any
+    big_dataset : Dataset
         The dataset to process.
 
     Returns
     -------
-    Tuple[np.ndarray, np.ndarray]
+    tuple[np.ndarray, np.ndarray]
         The subset and the date.
     """
     print("Processing:", date, flush=True)
@@ -655,26 +650,24 @@ def process_date(date: Any, big_dataset: Any) -> Tuple[np.ndarray, np.ndarray]:
     return s, date
 
 
-def initialize_zarr_store(root: Any, big_dataset: Any, recipe: Dict[str, Any]) -> None:
+def initialize_zarr_store(root: Any, big_dataset: "Dataset") -> None:
     """Initialize the Zarr store with the given dataset and recipe.
 
     Parameters
     ----------
     root : Any
-        The root of the Zarr store.
-    big_dataset : Any
+        The root Zarr store.
+    big_dataset : Dataset
         The dataset to initialize the store with.
-    recipe : Dict[str, Any]
-        The recipe for initializing the store.
     """
-    ensembles = big_dataset.shape[1]
+    ensembles = big_dataset.shape[2]
     # Create or append to "dates" dataset.
     if "dates" not in root:
         full_length = len(big_dataset.dates)
         root.create_dataset("dates", data=np.array([], dtype="datetime64[s]"), chunks=(full_length,))
 
     if "data" not in root:
-        dims = (1, len(big_dataset.variables), ensembles, big_dataset.grids[0])
+        dims = (1, len(big_dataset.variables), ensembles, big_dataset.shape[-1])
         root.create_dataset(
             "data",
             shape=dims,
@@ -694,25 +687,28 @@ def initialize_zarr_store(root: Any, big_dataset: Any, recipe: Dict[str, Any]) -
     if "latitudes" not in root or "longitudes" not in root:
         root.create_dataset("latitudes", data=big_dataset.latitudes, compressor=None)
         root.create_dataset("longitudes", data=big_dataset.longitudes, compressor=None)
-
+    for k, v in big_dataset.metadata().items():
+        if k not in root.attrs:
+            root.attrs[k] = v
     # Set store-wide attributes if not already set.
-    if "frequency" not in root.attrs:
-        root.attrs["frequency"] = "10m"
-        root.attrs["resolution"] = "1km"
+    if "first_date" not in root.attrs:
+        root.attrs["first_date"] = big_dataset.metadata()["start_date"]
+        root.attrs["last_date"] = big_dataset.metadata()["end_date"]
+        root.attrs["resolution"] = big_dataset.resolution
         root.attrs["name_to_index"] = {k: i for i, k in enumerate(big_dataset.variables)}
-        root.attrs["ensemble_dimension"] = 1
+        root.attrs["ensemble_dimension"] = 2
         root.attrs["field_shape"] = big_dataset.field_shape
         root.attrs["flatten_grid"] = True
-        root.attrs["recipe"] = recipe
+        root.attrs["recipe"] = {}
 
 
-def _save_dataset(recipe: Dict[str, Any], zarr_path: str, n_workers: int = 1) -> None:
+def _save_dataset(dataset: "Dataset", zarr_path: str, n_workers: int = 1) -> None:
     """Incrementally create (or update) a Zarr store from an Anemoi dataset.
 
     Parameters
     ----------
-    recipe : Dict[str, Any]
-        The recipe for creating the dataset.
+    dataset : Dataset
+        anemoi-dataset opened from python to save to Zarr store
     zarr_path : str
         The path to the Zarr store.
     n_workers : int, optional
@@ -728,13 +724,13 @@ def _save_dataset(recipe: Dict[str, Any], zarr_path: str, n_workers: int = 1) ->
     """
     from concurrent.futures import ProcessPoolExecutor
 
-    full_ds = _open_dataset(recipe).mutate()
+    full_ds = dataset
     print("Opened full dataset.", flush=True)
 
     # Use ProcessPoolExecutor for parallel data extraction.
     # Workers return (date, subset) tuples.
     root = zarr.open(zarr_path, mode="a")
-    initialize_zarr_store(root, full_ds, recipe)
+    initialize_zarr_store(root, full_ds)
     print("Zarr store initialised.", flush=True)
 
     existing_dates = np.array(sorted(root["dates"]), dtype="datetime64[s]")

anemoi/datasets/data/missing.py

@@ -12,11 +12,6 @@ import datetime
 import logging
 from functools import cached_property
 from typing import Any
-from typing import Dict
-from typing import List
-from typing import Set
-from typing import Tuple
-from typing import Union
 
 import numpy as np
 from numpy.typing import NDArray
@@ -49,7 +44,7 @@ class MissingDates(Forwards):
         List of missing dates.
     """
 
-    def __init__(self, dataset: Dataset, missing_dates: List[Union[int, str]]) -> None:
+    def __init__(self, dataset: Dataset, missing_dates: list[int | str]) -> None:
         """Initializes the MissingDates class.
 
         Parameters
@@ -80,13 +75,13 @@ class MissingDates(Forwards):
                     self.missing_dates.append(date)
 
         n = self.forward._len
-        self._missing = set(i for i in self._missing if 0 <= i < n)
+        self._missing = {i for i in self._missing if 0 <= i < n}
         self.missing_dates = sorted(to_datetime(x) for x in self.missing_dates)
 
         assert len(self._missing), "No dates to force missing"
 
     @cached_property
-    def missing(self) -> Set[int]:
+    def missing(self) -> set[int]:
         """Returns the set of missing indices."""
         return self._missing.union(self.forward.missing)
 
@@ -148,7 +143,7 @@ class MissingDates(Forwards):
         raise MissingDateError(f"Date {self.forward.dates[n]} is missing (index={n})")
 
     @property
-    def reason(self) -> Dict[str, Any]:
+    def reason(self) -> dict[str, Any]:
         """Provides the reason for missing dates."""
         return {"missing_dates": self.missing_dates}
 
@@ -162,7 +157,7 @@ class MissingDates(Forwards):
         """
         return Node(self, [self.forward.tree()], **self.reason)
 
-    def forwards_subclass_metadata_specific(self) -> Dict[str, Any]:
+    def forwards_subclass_metadata_specific(self) -> dict[str, Any]:
         """Provides metadata specific to the subclass.
 
         Returns
@@ -184,7 +179,7 @@ class SkipMissingDates(Forwards):
         The expected access pattern.
     """
 
-    def __init__(self, dataset: Dataset, expected_access: Union[int, slice]) -> None:
+    def __init__(self, dataset: Dataset, expected_access: int | slice) -> None:
         """Initializes the SkipMissingDates class.
 
         Parameters
@@ -285,7 +280,7 @@ class SkipMissingDates(Forwards):
         return tuple(np.stack(_) for _ in result)
 
     @debug_indexing
-    def _get_slice(self, s: slice) -> Tuple[NDArray[Any], ...]:
+    def _get_slice(self, s: slice) -> tuple[NDArray[Any], ...]:
         """Retrieves a slice of items.
 
         Parameters
@@ -303,7 +298,7 @@ class SkipMissingDates(Forwards):
         return tuple(np.stack(_) for _ in result)
 
     @debug_indexing
-    def __getitem__(self, n: FullIndex) -> Tuple[NDArray[Any], ...]:
+    def __getitem__(self, n: FullIndex) -> tuple[NDArray[Any], ...]:
         """Retrieves the item at the given index.
 
         Parameters
@@ -339,7 +334,7 @@ class SkipMissingDates(Forwards):
         """
         return Node(self, [self.forward.tree()], expected_access=self.expected_access)
 
-    def forwards_subclass_metadata_specific(self) -> Dict[str, Any]:
+    def forwards_subclass_metadata_specific(self) -> dict[str, Any]:
         """Provides metadata specific to the subclass.
 
         Returns
@@ -404,7 +399,7 @@ class MissingDataset(Forwards):
         return self._dates
 
     @property
-    def missing(self) -> Set[int]:
+    def missing(self) -> set[int]:
         """Returns the set of missing indices."""
         return self._missing
 
@@ -436,7 +431,7 @@ class MissingDataset(Forwards):
         """
         return Node(self, [self.forward.tree()], start=self.start, end=self.end)
 
-    def forwards_subclass_metadata_specific(self) -> Dict[str, Any]:
+    def forwards_subclass_metadata_specific(self) -> dict[str, Any]:
         """Provides metadata specific to the subclass.
 
         Returns

anemoi/datasets/data/observations/__init__.py

@@ -10,8 +10,6 @@ import logging
 import os
 from functools import cached_property
 from typing import Any
-from typing import Dict
-from typing import Tuple
 
 import numpy as np
 from anemoi.utils.dates import frequency_to_timedelta
@@ -82,10 +80,8 @@ class ObservationsBase(Dataset):
         #    return [self.getitem(j) for j in i]
 
         raise ValueError(
-            (
-                f"Expected int, got {i} of type {type(i)}. Only int is supported to index "
-                "observations datasets. Please use a second [] to select part of the data [i][a,b,c]"
-            )
+            f"Expected int, got {i} of type {type(i)}. Only int is supported to index "
+            "observations datasets. Please use a second [] to select part of the data [i][a,b,c]"
         )
 
     @property
@@ -195,13 +191,11 @@ class ObservationsZarr(ObservationsBase):
 
         if len(self.forward) != len(self.dates):
             raise ValueError(
-                (
-                    f"Dates are not consistent with the number of items in the dataset. "
-                    f"The dataset contains {len(self.forward)} time windows. "
-                    f"This is not compatible with the "
-                    f"{len(self.dates)} requested dates with frequency={frequency_hours}"
-                    f"{self.dates[0]}, {self.dates[1]}, ..., {self.dates[-2]}, {self.dates[-1]} "
-                )
+                f"Dates are not consistent with the number of items in the dataset. "
+                f"The dataset contains {len(self.forward)} time windows. "
+                f"This is not compatible with the "
+                f"{len(self.dates)} requested dates with frequency={frequency_hours}"
+                f"{self.dates[0]}, {self.dates[1]}, ..., {self.dates[-2]}, {self.dates[-1]} "
             )
 
     @property
@@ -307,7 +301,7 @@ class ObservationsZarr(ObservationsBase):
         return f"Observations({os.path.basename(self.path)}, {self.dates[0]};{self.dates[-1]}, {len(self)})"
 
 
-def observations_factory(args: Tuple[Any, ...], kwargs: Dict[str, Any]) -> ObservationsBase:
+def observations_factory(args: tuple[Any, ...], kwargs: dict[str, Any]) -> ObservationsBase:
     observations = kwargs.pop("observations")
 
     if not isinstance(observations, dict):

anemoi/datasets/data/padded.py

@@ -12,8 +12,6 @@ import datetime
 import logging
 from functools import cached_property
 from typing import Any
-from typing import Dict
-from typing import Set
 
 import numpy as np
 from anemoi.utils.dates import frequency_to_timedelta
@@ -38,7 +36,7 @@ class Padded(Forwards):
     _after: int = 0
     _inside: int = 0
 
-    def __init__(self, dataset: Dataset, start: str, end: str, frequency: str, reason: Dict[str, Any]) -> None:
+    def __init__(self, dataset: Dataset, start: str, end: str, frequency: str, reason: dict[str, Any]) -> None:
         """Create a padded subset of a dataset.
 
         Attributes:
@@ -195,7 +193,7 @@ class Padded(Forwards):
         return (len(self.dates),) + self.dataset.shape[1:]
 
     @cached_property
-    def missing(self) -> Set[int]:
+    def missing(self) -> set[int]:
         raise NotImplementedError("Need to decide whether to include the added dates as missing or not")
         # return self.forward.missing
 
@@ -207,7 +205,7 @@ class Padded(Forwards):
         """
         return Node(self, [self.dataset.tree()], **self.reason)
 
-    def forwards_subclass_metadata_specific(self) -> Dict[str, Any]:
+    def forwards_subclass_metadata_specific(self) -> dict[str, Any]:
         """Get the metadata specific to the forwards subclass.
 
         Returns:

anemoi/datasets/data/records/backends/__init__.py

@@ -35,7 +35,7 @@ class Npz1Backend(Backend):
             return dict(np.load(f))
 
     def read_metadata(self):
-        with open(os.path.join(self.path, "metadata.json"), "r") as f:
+        with open(os.path.join(self.path, "metadata.json")) as f:
             return json.load(f)
 
     def read_statistics(self):
@@ -56,7 +56,7 @@ class Npz2Backend(Backend):
             return dict(np.load(f))
 
     def read_metadata(self):
-        with open(os.path.join(self.path, "metadata.json"), "r") as f:
+        with open(os.path.join(self.path, "metadata.json")) as f:
             return json.load(f)
 
     def read_statistics(self):

anemoi/datasets/data/rescale.py

@@ -12,11 +12,6 @@ import datetime
 import logging
 from functools import cached_property
 from typing import Any
-from typing import Dict
-from typing import List
-from typing import Optional
-from typing import Tuple
-from typing import Union
 
 import numpy as np
 from numpy.typing import NDArray
@@ -35,9 +30,7 @@ from .indexing import update_tuple
 LOG = logging.getLogger(__name__)
 
 
-def make_rescale(
-    variable: str, rescale: Union[Tuple[float, float], List[str], Dict[str, float]]
-) -> Tuple[float, float]:
+def make_rescale(variable: str, rescale: tuple[float, float] | list[str] | dict[str, float]) -> tuple[float, float]:
     """Create rescale parameters (scale and offset) based on the input rescale specification.
 
     Parameters
@@ -86,7 +79,7 @@ class Rescale(Forwards):
     """A class to apply rescaling to dataset variables."""
 
     def __init__(
-        self, dataset: Dataset, rescale: Dict[str, Union[Tuple[float, float], List[str], Dict[str, float]]]
+        self, dataset: Dataset, rescale: dict[str, tuple[float, float] | list[str] | dict[str, float]]
     ) -> None:
         """Initialize the Rescale object.
 
@@ -129,7 +122,7 @@ class Rescale(Forwards):
         """
         return Node(self, [self.forward.tree()], rescale=self.rescale)
 
-    def forwards_subclass_metadata_specific(self) -> Dict[str, Any]:
+    def forwards_subclass_metadata_specific(self) -> dict[str, Any]:
         """Get the metadata specific to the rescale subclass.
 
         Returns
@@ -204,7 +197,7 @@ class Rescale(Forwards):
         return data * self._a[0] + self._b[0]
 
     @cached_property
-    def statistics(self) -> Dict[str, NDArray[Any]]:
+    def statistics(self) -> dict[str, NDArray[Any]]:
         """Get the statistics of the rescaled data."""
         result = {}
         a = self._a.squeeze()
@@ -224,7 +217,7 @@ class Rescale(Forwards):
 
         return result
 
-    def statistics_tendencies(self, delta: Optional[datetime.timedelta] = None) -> Dict[str, NDArray[Any]]:
+    def statistics_tendencies(self, delta: datetime.timedelta | None = None) -> dict[str, NDArray[Any]]:
         """Get the tendencies of the statistics of the rescaled data.
 
         Parameters

anemoi/datasets/data/select.py

@@ -12,9 +12,6 @@ import datetime
 import logging
 from functools import cached_property
 from typing import Any
-from typing import Dict
-from typing import List
-from typing import Optional
 
 from numpy.typing import NDArray
 
@@ -37,7 +34,7 @@ LOG = logging.getLogger(__name__)
 class Select(Forwards):
     """Class to select a subset of variables from a dataset."""
 
-    def __init__(self, dataset: Dataset, indices: List[int], reason: Dict[str, Any]) -> None:
+    def __init__(self, dataset: Dataset, indices: list[int], reason: dict[str, Any]) -> None:
         """Initialize the Select class.
 
         Parameters
@@ -140,26 +137,26 @@ class Select(Forwards):
         return (len(self), len(self.indices)) + self.dataset.shape[2:]
 
     @cached_property
-    def variables(self) -> List[str]:
+    def variables(self) -> list[str]:
         """Get the variables of the dataset."""
         return [self.dataset.variables[i] for i in self.indices]
 
     @cached_property
-    def variables_metadata(self) -> Dict[str, Any]:
+    def variables_metadata(self) -> dict[str, Any]:
         """Get the metadata of the variables."""
         return {k: v for k, v in self.dataset.variables_metadata.items() if k in self.variables}
 
     @cached_property
-    def name_to_index(self) -> Dict[str, int]:
+    def name_to_index(self) -> dict[str, int]:
         """Get the mapping of variable names to indices."""
         return {k: i for i, k in enumerate(self.variables)}
 
     @cached_property
-    def statistics(self) -> Dict[str, NDArray[Any]]:
+    def statistics(self) -> dict[str, NDArray[Any]]:
         """Get the statistics of the dataset."""
         return {k: v[self.indices] for k, v in self.dataset.statistics.items()}
 
-    def statistics_tendencies(self, delta: Optional[datetime.timedelta] = None) -> Dict[str, NDArray[Any]]:
+    def statistics_tendencies(self, delta: datetime.timedelta | None = None) -> dict[str, NDArray[Any]]:
         """Get the statistical tendencies of the dataset.
 
         Parameters
@@ -176,7 +173,7 @@ class Select(Forwards):
             delta = self.frequency
         return {k: v[self.indices] for k, v in self.dataset.statistics_tendencies(delta).items()}
 
-    def metadata_specific(self, **kwargs: Any) -> Dict[str, Any]:
+    def metadata_specific(self, **kwargs: Any) -> dict[str, Any]:
         """Get the specific metadata of the dataset.
 
         Parameters
@@ -216,7 +213,7 @@ class Select(Forwards):
         """
         return Node(self, [self.dataset.tree()], **self.reason)
 
-    def forwards_subclass_metadata_specific(self) -> Dict[str, Any]:
+    def forwards_subclass_metadata_specific(self) -> dict[str, Any]:
         """Get the metadata specific to the subclass.
 
         Returns
@@ -231,7 +228,7 @@ class Select(Forwards):
 class Rename(Forwards):
     """Class to rename variables in a dataset."""
 
-    def __init__(self, dataset: Dataset, rename: Dict[str, str]) -> None:
+    def __init__(self, dataset: Dataset, rename: dict[str, str]) -> None:
         """Initialize the Rename class.
 
         Parameters
@@ -251,17 +248,17 @@ class Rename(Forwards):
         self.rename = rename
 
     @property
-    def variables(self) -> List[str]:
+    def variables(self) -> list[str]:
         """Get the renamed variables."""
         return self._variables
 
     @property
-    def variables_metadata(self) -> Dict[str, Any]:
+    def variables_metadata(self) -> dict[str, Any]:
         """Get the renamed variables metadata."""
         return self._variables_metadata
 
     @cached_property
-    def name_to_index(self) -> Dict[str, int]:
+    def name_to_index(self) -> dict[str, int]:
         """Get the mapping of renamed variable names to indices."""
         return {k: i for i, k in enumerate(self.variables)}
 
@@ -273,7 +270,7 @@ class Rename(Forwards):
         """
         return Node(self, [self.forward.tree()], rename=self.rename)
 
-    def forwards_subclass_metadata_specific(self) -> Dict[str, Any]:
+    def forwards_subclass_metadata_specific(self) -> dict[str, Any]:
         """Get the metadata specific to the subclass.
 
         Returns:

anemoi/datasets/data/statistics.py

@@ -12,9 +12,6 @@ import datetime
 import logging
 from functools import cached_property
 from typing import Any
-from typing import Dict
-from typing import Optional
-from typing import Set
 
 from numpy.typing import NDArray
 
@@ -56,11 +53,11 @@ class Statistics(Forwards):
             )
 
     @cached_property
-    def statistics(self) -> Dict[str, NDArray[Any]]:
+    def statistics(self) -> dict[str, NDArray[Any]]:
         """Get the statistics."""
         return self._statistic.statistics
 
-    def statistics_tendencies(self, delta: Optional[datetime.timedelta] = None) -> Dict[str, NDArray[Any]]:
+    def statistics_tendencies(self, delta: datetime.timedelta | None = None) -> dict[str, NDArray[Any]]:
         """Get the statistics tendencies.
 
         Parameters
@@ -77,7 +74,7 @@ class Statistics(Forwards):
             delta = self.frequency
         return self._statistic.statistics_tendencies(delta)
 
-    def forwards_subclass_metadata_specific(self) -> Dict[str, Any]:
+    def forwards_subclass_metadata_specific(self) -> dict[str, Any]:
         """Get the metadata specific to the forwards subclass.
 
         Returns
@@ -97,7 +94,7 @@ class Statistics(Forwards):
         """
         return Node(self, [self.forward.tree()])
 
-    def get_dataset_names(self, names: Set[str]) -> None:
+    def get_dataset_names(self, names: set[str]) -> None:
         """Get the dataset names.
 
         Parameters