pycontrails 0.51.2__cp310-cp310-win_amd64.whl → 0.52.1__cp310-cp310-win_amd64.whl

pycontrails/{core/datalib.py → datalib/_met_utils/metsource.py}

@@ -1,4 +1,4 @@
-"""Datalib utilities."""
+"""Met datalib definitions and utilities."""
 
 from __future__ import annotations
 
@@ -35,9 +35,6 @@ DEFAULT_CHUNKS: dict[str, int] = {"time": 1}
 #: Whether to open multi-file datasets in parallel
 OPEN_IN_PARALLEL: bool = False
 
-#: Whether to use file locking when opening multi-file datasets
-OPEN_WITH_LOCK: bool = False
-
 
 def parse_timesteps(time: TimeInput | None, freq: str | None = "1h") -> list[datetime]:
     """Parse time input into set of time steps.
@@ -741,5 +738,4 @@ class MetDataSource(abc.ABC):
         xr_kwargs.setdefault("engine", NETCDF_ENGINE)
         xr_kwargs.setdefault("chunks", DEFAULT_CHUNKS)
         xr_kwargs.setdefault("parallel", OPEN_IN_PARALLEL)
-        xr_kwargs.setdefault("lock", OPEN_WITH_LOCK)
         return xr.open_mfdataset(disk_paths, **xr_kwargs)

pycontrails/datalib/ecmwf/arco_era5.py

@@ -32,8 +32,9 @@ from typing import Any
 import xarray as xr
 from overrides import overrides
 
-from pycontrails.core import cache, datalib, met_var
+from pycontrails.core import cache, met_var
 from pycontrails.core.met import MetDataset
+from pycontrails.datalib._met_utils import metsource
 from pycontrails.datalib.ecmwf import common as ecmwf_common
 from pycontrails.datalib.ecmwf import variables as ecmwf_variables
 from pycontrails.datalib.ecmwf.model_levels import pressure_levels_at_model_levels
@@ -374,23 +375,23 @@ class ARCOERA5(ecmwf_common.ECMWFAPI):
 
     def __init__(
         self,
-        time: datalib.TimeInput,
-        variables: datalib.VariableInput,
-        pressure_levels: datalib.PressureLevelInput | None = None,
+        time: metsource.TimeInput,
+        variables: metsource.VariableInput,
+        pressure_levels: metsource.PressureLevelInput | None = None,
         grid: float = 0.25,
         cachestore: cache.CacheStore | None = __marker,  # type: ignore[assignment]
         n_jobs: int = 1,
         cleanup_metview_tempfiles: bool = True,
     ) -> None:
-        self.timesteps = datalib.parse_timesteps(time)
+        self.timesteps = metsource.parse_timesteps(time)
 
         if pressure_levels is None:
             self.pressure_levels = pressure_levels_at_model_levels(20_000.0, 50_000.0)
         else:
-            self.pressure_levels = datalib.parse_pressure_levels(pressure_levels)
+            self.pressure_levels = metsource.parse_pressure_levels(pressure_levels)
 
         self.paths = None
-        self.variables = datalib.parse_variables(variables, self.supported_variables)
+        self.variables = metsource.parse_variables(variables, self.supported_variables)
         self.grid = grid
         self.cachestore = cache.DiskCacheStore() if cachestore is self.__marker else cachestore
         self.n_jobs = max(1, n_jobs)

pycontrails/datalib/ecmwf/common.py

@@ -13,10 +13,11 @@ import pandas as pd
 import xarray as xr
 from overrides import overrides
 
-from pycontrails.core import datalib, met
+from pycontrails.core import met
+from pycontrails.datalib._met_utils import metsource
 
 
-class ECMWFAPI(datalib.MetDataSource):
+class ECMWFAPI(metsource.MetDataSource):
     """Abstract class for all ECMWF data accessed remotely through CDS / MARS."""
 
     @property

pycontrails/datalib/ecmwf/era5.py

@@ -19,8 +19,9 @@ import xarray as xr
 from overrides import overrides
 
 import pycontrails
-from pycontrails.core import cache, datalib
+from pycontrails.core import cache
 from pycontrails.core.met import MetDataset, MetVariable
+from pycontrails.datalib._met_utils import metsource
 from pycontrails.datalib.ecmwf.common import ECMWFAPI, CDSCredentialsNotFound
 from pycontrails.datalib.ecmwf.variables import PRESSURE_LEVEL_VARIABLES, SURFACE_VARIABLES
 from pycontrails.utils import dependencies, temp
@@ -49,16 +50,16 @@ class ERA5(ECMWFAPI):
 
     Parameters
     ----------
-    time : datalib.TimeInput | None
+    time : metsource.TimeInput | None
         The time range for data retrieval, either a single datetime or (start, end) datetime range.
         Input must be datetime-like or tuple of datetime-like
         (`datetime`, :class:`pd.Timestamp`, :class:`np.datetime64`)
         specifying the (start, end) of the date range, inclusive.
         Datafiles will be downloaded from CDS for each day to reduce requests.
         If None, ``paths`` must be defined and all time coordinates will be loaded from files.
-    variables : datalib.VariableInput
+    variables : metsource.VariableInput
         Variable name (i.e. "t", "air_temperature", ["air_temperature, relative_humidity"])
-    pressure_levels : datalib.PressureLevelInput, optional
+    pressure_levels : metsource.PressureLevelInput, optional
         Pressure levels for data, in hPa (mbar)
         Set to -1 for to download surface level parameters.
         Defaults to -1.
@@ -145,9 +146,9 @@ class ERA5(ECMWFAPI):
 
     def __init__(
         self,
-        time: datalib.TimeInput | None,
-        variables: datalib.VariableInput,
-        pressure_levels: datalib.PressureLevelInput = -1,
+        time: metsource.TimeInput | None,
+        variables: metsource.VariableInput,
+        pressure_levels: metsource.PressureLevelInput = -1,
         paths: str | list[str] | pathlib.Path | list[pathlib.Path] | None = None,
         timestep_freq: str | None = None,
         product_type: str = "reanalysis",
@@ -193,11 +194,11 @@ class ERA5(ECMWFAPI):
         if timestep_freq is None:
             timestep_freq = "1h" if product_type == "reanalysis" else "3h"
 
-        self.timesteps = datalib.parse_timesteps(time, freq=timestep_freq)
-        self.pressure_levels = datalib.parse_pressure_levels(
+        self.timesteps = metsource.parse_timesteps(time, freq=timestep_freq)
+        self.pressure_levels = metsource.parse_pressure_levels(
             pressure_levels, self.supported_pressure_levels
         )
-        self.variables = datalib.parse_variables(variables, self.supported_variables)
+        self.variables = metsource.parse_variables(variables, self.supported_variables)
 
         # ensemble_mean, etc - time is only available on the 0, 3, 6, etc
         if product_type.startswith("ensemble") and any(t.hour % 3 for t in self.timesteps):
@@ -482,7 +483,7 @@ class ERA5(ECMWFAPI):
 
             # open file, edit, and save for each hourly time step
             ds = stack.enter_context(
-                xr.open_dataset(cds_temp_filename, engine=datalib.NETCDF_ENGINE)
+                xr.open_dataset(cds_temp_filename, engine=metsource.NETCDF_ENGINE)
             )
 
             # run preprocessing before cache

pycontrails/datalib/ecmwf/era5_model_level.py

@@ -40,8 +40,9 @@ import pandas as pd
 import xarray as xr
 
 import pycontrails
-from pycontrails.core import cache, datalib
+from pycontrails.core import cache
 from pycontrails.core.met import MetDataset, MetVariable
+from pycontrails.datalib._met_utils import metsource
 from pycontrails.datalib.ecmwf.common import ECMWFAPI, CDSCredentialsNotFound
 from pycontrails.datalib.ecmwf.model_levels import pressure_levels_at_model_levels
 from pycontrails.datalib.ecmwf.variables import MODEL_LEVEL_VARIABLES
@@ -73,7 +74,7 @@ class ERA5ModelLevel(ECMWFAPI):
 
     Parameters
     ----------
-    time : datalib.TimeInput | None
+    time : metsource.TimeInput | None
         The time range for data retrieval, either a single datetime or (start, end) datetime range.
         Input must be datetime-like or tuple of datetime-like
         (:py:class:`datetime.datetime`, :class:`pandas.Timestamp`, :class:`numpy.datetime64`)
@@ -82,9 +83,9 @@ class ERA5ModelLevel(ECMWFAPI):
         for the nominal reanalysis and no larger than 1 day for ensemble members.
         This ensures that exactly one request is submitted per file on tape accessed.
         If None, ``paths`` must be defined and all time coordinates will be loaded from files.
-    variables : datalib.VariableInput
+    variables : metsource.VariableInput
         Variable name (i.e. "t", "air_temperature", ["air_temperature, specific_humidity"])
-    pressure_levels : datalib.PressureLevelInput, optional
+    pressure_levels : metsource.PressureLevelInput, optional
         Pressure levels for data, in hPa (mbar).
         To download surface-level parameters, use :class:`pycontrails.datalib.ecmwf.ERA5`.
         Defaults to pressure levels that match model levels at a nominal surface pressure.
@@ -123,9 +124,9 @@ class ERA5ModelLevel(ECMWFAPI):
 
     def __init__(
         self,
-        time: datalib.TimeInput,
-        variables: datalib.VariableInput,
-        pressure_levels: datalib.PressureLevelInput | None = None,
+        time: metsource.TimeInput,
+        variables: metsource.VariableInput,
+        pressure_levels: metsource.PressureLevelInput | None = None,
         timestep_freq: str | None = None,
         product_type: str = "reanalysis",
         grid: float | None = None,
@@ -186,18 +187,18 @@ class ERA5ModelLevel(ECMWFAPI):
         datasource_timestep_freq = "1h" if product_type == "reanalysis" else "3h"
         if timestep_freq is None:
             timestep_freq = datasource_timestep_freq
-        if not datalib.validate_timestep_freq(timestep_freq, datasource_timestep_freq):
+        if not metsource.validate_timestep_freq(timestep_freq, datasource_timestep_freq):
             msg = (
                 f"Product {self.product_type} has timestep frequency of {datasource_timestep_freq} "
                 f"and cannot support requested timestep frequency of {timestep_freq}."
             )
             raise ValueError(msg)
 
-        self.timesteps = datalib.parse_timesteps(time, freq=timestep_freq)
+        self.timesteps = metsource.parse_timesteps(time, freq=timestep_freq)
         if pressure_levels is None:
             pressure_levels = pressure_levels_at_model_levels(20_000.0, 50_000.0)
-        self.pressure_levels = datalib.parse_pressure_levels(pressure_levels)
-        self.variables = datalib.parse_variables(variables, self.pressure_level_variables)
+        self.pressure_levels = metsource.parse_pressure_levels(pressure_levels)
+        self.variables = metsource.parse_variables(variables, self.pressure_level_variables)
 
     def __repr__(self) -> str:
         base = super().__repr__()

pycontrails/datalib/ecmwf/hres.py

@@ -17,8 +17,9 @@ import xarray as xr
 from overrides import overrides
 
 import pycontrails
-from pycontrails.core import cache, datalib
+from pycontrails.core import cache
 from pycontrails.core.met import MetDataset, MetVariable
+from pycontrails.datalib._met_utils import metsource
 from pycontrails.datalib.ecmwf.common import ECMWFAPI
 from pycontrails.datalib.ecmwf.variables import PRESSURE_LEVEL_VARIABLES, SURFACE_VARIABLES
 from pycontrails.utils import dependencies, iteration, temp
@@ -120,7 +121,7 @@ class HRES(ECMWFAPI):
 
     Parameters
     ----------
-    time : datalib.TimeInput | None
+    time : metsource.TimeInput | None
         The time range for data retrieval, either a single datetime or (start, end) datetime range.
         Input must be a datetime-like or tuple of datetime-like
         (datetime, :class:`pandas.Timestamp`, :class:`numpy.datetime64`)
@@ -129,10 +130,10 @@ class HRES(ECMWFAPI):
         be assumed to be the nearest synoptic hour: 00, 06, 12, 18.
         All subsequent times will be downloaded for relative to :attr:`forecast_time`.
         If None, ``paths`` must be defined and all time coordinates will be loaded from files.
-    variables : datalib.VariableInput
+    variables : metsource.VariableInput
         Variable name (i.e. "air_temperature", ["air_temperature, relative_humidity"])
         See :attr:`pressure_level_variables` for the list of available variables.
-    pressure_levels : datalib.PressureLevelInput, optional
+    pressure_levels : metsource.PressureLevelInput, optional
         Pressure levels for data, in hPa (mbar)
         Set to -1 for to download surface level parameters.
         Defaults to -1.
@@ -241,9 +242,9 @@ class HRES(ECMWFAPI):
 
     def __init__(
         self,
-        time: datalib.TimeInput | None,
-        variables: datalib.VariableInput,
-        pressure_levels: datalib.PressureLevelInput = -1,
+        time: metsource.TimeInput | None,
+        variables: metsource.VariableInput,
+        pressure_levels: metsource.PressureLevelInput = -1,
         paths: str | list[str] | pathlib.Path | list[pathlib.Path] | None = None,
         cachepath: str | list[str] | pathlib.Path | list[pathlib.Path] | None = None,
         grid: float = 0.25,
@@ -277,13 +278,13 @@ class HRES(ECMWFAPI):
         if time is None and paths is None:
             raise ValueError("Time input is required when paths is None")
 
-        self.timesteps = datalib.parse_timesteps(time, freq="1h")
-        self.pressure_levels = datalib.parse_pressure_levels(
+        self.timesteps = metsource.parse_timesteps(time, freq="1h")
+        self.pressure_levels = metsource.parse_pressure_levels(
             pressure_levels, self.supported_pressure_levels
         )
-        self.variables = datalib.parse_variables(variables, self.supported_variables)
+        self.variables = metsource.parse_variables(variables, self.supported_variables)
 
-        self.grid = datalib.parse_grid(grid, [0.1, 0.25, 0.5, 1])  # lat/lon degree resolution
+        self.grid = metsource.parse_grid(grid, [0.1, 0.25, 0.5, 1])  # lat/lon degree resolution
 
         # "enfo" = ensemble forecast
         # "oper" = atmospheric model/HRES
@@ -309,12 +310,12 @@ class HRES(ECMWFAPI):
             if forecast_time_pd.hour % 6:
                 raise ValueError("Forecast hour must be on one of 00, 06, 12, 18")
 
-            self.forecast_time = datalib.round_hour(forecast_time_pd.to_pydatetime(), 6)
+            self.forecast_time = metsource.round_hour(forecast_time_pd.to_pydatetime(), 6)
 
         # if no specific forecast is requested, set the forecast time using timesteps
         elif self.timesteps:
             # round first element to the nearest 6 hour time (00, 06, 12, 18 UTC) for forecast_time
-            self.forecast_time = datalib.round_hour(self.timesteps[0], 6)
+            self.forecast_time = metsource.round_hour(self.timesteps[0], 6)
 
         # when no forecast_time or time input, forecast_time is defined in _open_and_cache
 

pycontrails/datalib/ecmwf/hres_model_level.py

@@ -28,8 +28,9 @@ import xarray as xr
 from overrides import overrides
 
 import pycontrails
-from pycontrails.core import cache, datalib
+from pycontrails.core import cache
 from pycontrails.core.met import MetDataset, MetVariable
+from pycontrails.datalib._met_utils import metsource
 from pycontrails.datalib.ecmwf.common import ECMWFAPI
 from pycontrails.datalib.ecmwf.model_levels import pressure_levels_at_model_levels
 from pycontrails.datalib.ecmwf.variables import MODEL_LEVEL_VARIABLES
@@ -70,7 +71,7 @@ class HRESModelLevel(ECMWFAPI):
 
     Parameters
     ----------
-    time : datalib.TimeInput
+    time : metsource.TimeInput
         The time range for data retrieval, either a single datetime or (start, end) datetime range.
         Input must be datetime-like or tuple of datetime-like
         (:py:class:`datetime.datetime`, :class:`pandas.Timestamp`, :class:`numpy.datetime64`)
@@ -80,9 +81,9 @@ class HRESModelLevel(ECMWFAPI):
         If ``forecast_time`` is unspecified, the forecast time will
         be assumed to be the nearest synoptic hour available in the operational archive (00 or 12).
         All subsequent times will be downloaded for relative to :attr:`forecast_time`.
-    variables : datalib.VariableInput
+    variables : metsource.VariableInput
         Variable name (i.e. "t", "air_temperature", ["air_temperature, specific_humidity"])
-    pressure_levels : datalib.PressureLevelInput, optional
+    pressure_levels : metsource.PressureLevelInput, optional
         Pressure levels for data, in hPa (mbar).
         To download surface-level parameters, use :class:`pycontrails.datalib.ecmwf.HRES`.
         Defaults to pressure levels that match model levels at a nominal surface pressure.
@@ -119,9 +120,9 @@ class HRESModelLevel(ECMWFAPI):
 
     def __init__(
         self,
-        time: datalib.TimeInput,
-        variables: datalib.VariableInput,
-        pressure_levels: datalib.PressureLevelInput | None = None,
+        time: metsource.TimeInput,
+        variables: metsource.VariableInput,
+        pressure_levels: metsource.PressureLevelInput | None = None,
         timestep_freq: str | None = None,
         grid: float | None = None,
         forecast_time: DatetimeLike | None = None,
@@ -165,15 +166,15 @@ class HRESModelLevel(ECMWFAPI):
             raise ValueError(msg)
         self.levels = levels
 
-        forecast_hours = datalib.parse_timesteps(time, freq="1h")
+        forecast_hours = metsource.parse_timesteps(time, freq="1h")
         if forecast_time is None:
-            self.forecast_time = datalib.round_hour(forecast_hours[0], 12)
+            self.forecast_time = metsource.round_hour(forecast_hours[0], 12)
         else:
             forecast_time_pd = pd.to_datetime(forecast_time)
             if (hour := forecast_time_pd.hour) % 12:
                 msg = f"Forecast hour must be one of 00 or 12 but is {hour:02d}."
                 raise ValueError(msg)
-            self.forecast_time = datalib.round_hour(forecast_time_pd.to_pydatetime(), 12)
+            self.forecast_time = metsource.round_hour(forecast_time_pd.to_pydatetime(), 12)
 
         last_step = (forecast_hours[-1] - self.forecast_time) / timedelta(hours=1)
         if last_step > LAST_STEP_6H:
@@ -188,7 +189,7 @@ class HRESModelLevel(ECMWFAPI):
         )
         if timestep_freq is None:
             timestep_freq = datasource_timestep_freq
-        if not datalib.validate_timestep_freq(timestep_freq, datasource_timestep_freq):
+        if not metsource.validate_timestep_freq(timestep_freq, datasource_timestep_freq):
             msg = (
                 f"Forecast out to step {last_step} "
                 f"has timestep frequency of {datasource_timestep_freq} "
@@ -196,15 +197,15 @@ class HRESModelLevel(ECMWFAPI):
             )
             raise ValueError(msg)
 
-        self.timesteps = datalib.parse_timesteps(time, freq=timestep_freq)
+        self.timesteps = metsource.parse_timesteps(time, freq=timestep_freq)
         if self.step_offset < 0:
             msg = f"Selected forecast time {self.forecast_time} is after first timestep."
             raise ValueError(msg)
 
         if pressure_levels is None:
             pressure_levels = pressure_levels_at_model_levels(20_000.0, 50_000.0)
-        self.pressure_levels = datalib.parse_pressure_levels(pressure_levels)
-        self.variables = datalib.parse_variables(variables, self.pressure_level_variables)
+        self.pressure_levels = metsource.parse_pressure_levels(pressure_levels)
+        self.variables = metsource.parse_variables(variables, self.pressure_level_variables)
 
     def __repr__(self) -> str:
         base = super().__repr__()

pycontrails/datalib/ecmwf/ifs.py

@@ -15,13 +15,14 @@ import pandas as pd
 import xarray as xr
 from overrides import overrides
 
-from pycontrails.core import datalib, met
+from pycontrails.core import met
+from pycontrails.datalib._met_utils import metsource
 from pycontrails.datalib.ecmwf.variables import ECMWF_VARIABLES
 from pycontrails.physics import constants
 from pycontrails.utils.types import DatetimeLike
 
 
-class IFS(datalib.MetDataSource):
+class IFS(metsource.MetDataSource):
     """
     ECMWF Integrated Forecasting System (IFS) data source.
 
@@ -31,16 +32,16 @@ class IFS(datalib.MetDataSource):
 
     Parameters
     ----------
-    time : datalib.TimeInput | None
+    time : metsource.TimeInput | None
         The time range for data retrieval, either a single datetime or (start, end) datetime range.
         Input must be a single datetime-like or tuple of datetime-like
         (datetime, :class:`pandas.Timestamp`, :class:`numpy.datetime64`)
         specifying the (start, end) of the date range, inclusive.
         If None, all time coordinates will be loaded.
-    variables : datalib.VariableInput
+    variables : metsource.VariableInput
         Variable name (i.e. "air_temperature", ["air_temperature, relative_humidity"])
         See :attr:`pressure_level_variables` for the list of available variables.
-    pressure_levels : datalib.PressureLevelInput, optional
+    pressure_levels : metsource.PressureLevelInput, optional
         Pressure level bounds for data (min, max), in hPa (mbar)
         Set to -1 for to download surface level parameters.
         Defaults to -1.
@@ -69,9 +70,9 @@ class IFS(datalib.MetDataSource):
 
     def __init__(
         self,
-        time: datalib.TimeInput | None,
-        variables: datalib.VariableInput,
-        pressure_levels: datalib.PressureLevelInput = -1,
+        time: metsource.TimeInput | None,
+        variables: metsource.VariableInput,
+        pressure_levels: metsource.PressureLevelInput = -1,
         paths: str | list[str] | pathlib.Path | list[pathlib.Path] | None = None,
         grid: float | None = None,
         forecast_path: str | pathlib.Path | None = None,
@@ -89,9 +90,9 @@ class IFS(datalib.MetDataSource):
         self.forecast_date = pd.to_datetime(forecast_date).to_pydatetime()
 
         # parse inputs
-        self.timesteps = datalib.parse_timesteps(time, freq="3h")
-        self.pressure_levels = datalib.parse_pressure_levels(pressure_levels, None)
-        self.variables = datalib.parse_variables(variables, self.supported_variables)
+        self.timesteps = metsource.parse_timesteps(time, freq="3h")
+        self.pressure_levels = metsource.parse_pressure_levels(pressure_levels, None)
+        self.variables = metsource.parse_variables(variables, self.supported_variables)
 
     def __repr__(self) -> str:
         base = super().__repr__()
@@ -221,8 +222,8 @@ class IFS(datalib.MetDataSource):
         LOG.debug(f"Loading IFS forecast date {date_str}")
 
         # load each dataset
-        xr_kwargs.setdefault("chunks", datalib.DEFAULT_CHUNKS)
-        xr_kwargs.setdefault("engine", datalib.NETCDF_ENGINE)
+        xr_kwargs.setdefault("chunks", metsource.DEFAULT_CHUNKS)
+        xr_kwargs.setdefault("engine", metsource.NETCDF_ENGINE)
         ds_full = xr.open_dataset(path_full, **xr_kwargs)
         ds_fl = xr.open_dataset(path_fl, **xr_kwargs)
         ds_surface = xr.open_dataset(path_surface, **xr_kwargs)

pycontrails/datalib/gfs/gfs.py

@@ -22,7 +22,8 @@ import xarray as xr
 from overrides import overrides
 
 import pycontrails
-from pycontrails.core import cache, datalib, met
+from pycontrails.core import cache, met
+from pycontrails.datalib._met_utils import metsource
 from pycontrails.datalib.gfs.variables import (
     PRESSURE_LEVEL_VARIABLES,
     SURFACE_VARIABLES,
@@ -43,12 +44,12 @@ logger = logging.getLogger(__name__)
 GFS_FORECAST_BUCKET = "noaa-gfs-bdp-pds"
 
 
-class GFSForecast(datalib.MetDataSource):
+class GFSForecast(metsource.MetDataSource):
     """GFS Forecast data access.
 
     Parameters
     ----------
-    time : `datalib.TimeInput`
+    time : `metsource.TimeInput`
         The time range for data retrieval, either a single datetime or (start, end) datetime range.
         Input must be a single datetime-like or tuple of datetime-like (datetime,
         :class:`pandas.Timestamp`, :class:`numpy.datetime64`)
@@ -56,10 +57,10 @@ class GFSForecast(datalib.MetDataSource):
         All times will be downloaded for a single forecast model run nearest to the start time
         (see :attr:`forecast_time`)
         If None, ``paths`` must be defined and all time coordinates will be loaded from files.
-    variables : `datalib.VariableInput`
+    variables : `metsource.VariableInput`
         Variable name (i.e. "temperature", ["temperature, relative_humidity"])
         See :attr:`pressure_level_variables` for the list of available variables.
-    pressure_levels : `datalib.PressureLevelInput`, optional
+    pressure_levels : `metsource.PressureLevelInput`, optional
         Pressure levels for data, in hPa (mbar)
         Set to [-1] for to download surface level parameters.
         Defaults to [-1].
@@ -132,9 +133,9 @@ class GFSForecast(datalib.MetDataSource):
 
     def __init__(
         self,
-        time: datalib.TimeInput | None,
-        variables: datalib.VariableInput,
-        pressure_levels: datalib.PressureLevelInput = -1,
+        time: metsource.TimeInput | None,
+        variables: metsource.VariableInput,
+        pressure_levels: metsource.PressureLevelInput = -1,
         paths: str | list[str] | pathlib.Path | list[pathlib.Path] | None = None,
         grid: float = 0.25,
         forecast_time: DatetimeLike | None = None,
@@ -175,13 +176,13 @@ class GFSForecast(datalib.MetDataSource):
         # 3 hourly for 0.5 and 1 degree grid
         # https://www.nco.ncep.noaa.gov/pmb/products/gfs/
         freq = "1h" if grid == 0.25 else "3h"
-        self.timesteps = datalib.parse_timesteps(time, freq=freq)
+        self.timesteps = metsource.parse_timesteps(time, freq=freq)
 
-        self.pressure_levels = datalib.parse_pressure_levels(
+        self.pressure_levels = metsource.parse_pressure_levels(
             pressure_levels, self.supported_pressure_levels
         )
-        self.variables = datalib.parse_variables(variables, self.supported_variables)
-        self.grid = datalib.parse_grid(grid, (0.25, 0.5, 1))
+        self.variables = metsource.parse_variables(variables, self.supported_variables)
+        self.grid = metsource.parse_grid(grid, (0.25, 0.5, 1))
 
         # note GFS allows unsigned requests (no credentials)
         # https://stackoverflow.com/questions/34865927/can-i-use-boto3-anonymously/34866092#34866092
@@ -195,12 +196,12 @@ class GFSForecast(datalib.MetDataSource):
             if forecast_time_pd.hour % 6:
                 raise ValueError("Forecast hour must be on one of 00, 06, 12, 18")
 
-            self.forecast_time = datalib.round_hour(forecast_time_pd.to_pydatetime(), 6)
+            self.forecast_time = metsource.round_hour(forecast_time_pd.to_pydatetime(), 6)
 
         # if no specific forecast is requested, set the forecast time using timesteps
         else:
             # round first element to the nearest 6 hour time (00, 06, 12, 18 UTC) for forecast_time
-            self.forecast_time = datalib.round_hour(self.timesteps[0], 6)
+            self.forecast_time = metsource.round_hour(self.timesteps[0], 6)
 
     def __repr__(self) -> str:
         base = super().__repr__()

pycontrails/datalib/goes.py

@@ -16,7 +16,7 @@ from __future__ import annotations
 
 import datetime
 import enum
-import io
+import tempfile
 from collections.abc import Iterable
 
 import numpy as np
@@ -35,7 +35,7 @@ except ModuleNotFoundError as exc:
         name="goes module",
         package_name="cartopy",
         module_not_found_error=exc,
-        pycontrails_optional_package="goes",
+        pycontrails_optional_package="sat",
     )
 
 try:
@@ -45,7 +45,7 @@ except ModuleNotFoundError as exc:
         name="goes module",
         package_name="gcsfs",
         module_not_found_error=exc,
-        pycontrails_optional_package="goes",
+        pycontrails_optional_package="sat",
     )
 
 
@@ -535,7 +535,7 @@ class GOES:
             da_dict = {}
             for rpath, init_bytes in data.items():
                 channel = _extract_channel_from_rpath(rpath)
-                ds = xr.open_dataset(io.BytesIO(init_bytes), engine="h5netcdf")
+                ds = _load_via_tempfile(init_bytes)
 
                 da = ds["CMI"]
                 da = da.expand_dims(band_id=ds["band_id"].values)
@@ -551,7 +551,7 @@ class GOES:
                 da = xr.concat(da_dict.values(), dim="band_id")
 
         else:
-            ds = xr.open_dataset(io.BytesIO(data), engine="h5netcdf")
+            ds = _load_via_tempfile(data)
             da = ds["CMI"]
             da = da.expand_dims(band_id=ds["band_id"].values)
 
@@ -564,6 +564,13 @@ class GOES:
         return da
 
 
+def _load_via_tempfile(data: bytes) -> xr.Dataset:
+    """Load xarray dataset via temporary file."""
+    with tempfile.NamedTemporaryFile(buffering=0) as tmp:
+        tmp.write(data)
+        return xr.load_dataset(tmp.name)
+
+
 def _concat_c02(ds1: XArrayType, ds2: XArrayType) -> XArrayType:
     """Concatenate two datasets with C01 and C02 data."""
     # Average the C02 data to the C01 resolution