sdf-xarray 0.2.6__cp311-cp311-win_amd64.whl → 0.3.2__cp311-cp311-win_amd64.whl

sdf_xarray/__init__.py

@@ -1,13 +1,17 @@
+import contextlib
 import os
 import re
 from collections import Counter, defaultdict
 from collections.abc import Callable, Iterable
+from importlib.metadata import version
 from itertools import product
+from os import PathLike as os_PathLike
 from pathlib import Path
 from typing import ClassVar
 
 import numpy as np
 import xarray as xr
+from packaging.version import Version
 from xarray.backends import AbstractDataStore, BackendArray, BackendEntrypoint
 from xarray.backends.file_manager import CachingFileManager
 from xarray.backends.locks import ensure_lock
@@ -15,12 +19,24 @@ from xarray.core import indexing
 from xarray.core.utils import close_on_error, try_read_magic_number_from_path
 from xarray.core.variable import Variable
 
-# NOTE: Do not delete this line, otherwise the "epoch" accessor will not be
-# imported when the user imports sdf_xarray
+# NOTE: Do not delete these lines, otherwise the "epoch" dataset and dataarray
+# accessors will not be imported when the user imports sdf_xarray
+import sdf_xarray.dataset_accessor
 import sdf_xarray.plotting  # noqa: F401
 
+# NOTE: This attempts to initialise with the "pint" accessor if the user
+# has installed the package
+with contextlib.suppress(ImportError):
+    import pint_xarray  # noqa: F401
+
 from .sdf_interface import Constant, SDFFile  # type: ignore  # noqa: PGH003
 
+# TODO Remove this once the new kwarg options are fully implemented
+if Version(version("xarray")) >= Version("2025.8.0"):
+    xr.set_options(use_new_combine_kwarg_defaults=True)
+
+PathLike = str | os_PathLike
+
 
 def _rename_with_underscore(name: str) -> str:
     """A lot of the variable names have spaces, forward slashes and dashes in them, which
@@ -51,14 +67,69 @@ def _process_latex_name(variable_name: str) -> str:
     return variable_name
 
 
-def combine_datasets(path_glob: Iterable | str, **kwargs) -> xr.Dataset:
-    """Combine all datasets using a single time dimension"""
+def _resolve_glob(path_glob: PathLike | Iterable[PathLike]):
+    """
+    Normalise input path_glob into a sorted list of absolute, resolved Path objects.
+    """
+
+    try:
+        p = Path(path_glob)
+        paths = list(p.parent.glob(p.name)) if p.name == "*.sdf" else list(p)
+    except TypeError:
+        paths = list({Path(p) for p in path_glob})
+
+    paths = sorted(p.resolve() for p in paths)
+    if not paths:
+        raise FileNotFoundError(f"No files matched pattern or input: {path_glob!r}")
+    return paths
+
+
+def purge_unselected_data_vars(ds: xr.Dataset, data_vars: list[str]) -> xr.Dataset:
+    """
+    If the user has exclusively requested only certain variables be
+    loaded in then we purge all other variables and dimensions
+    """
+    existing_data_vars = set(ds.data_vars.keys())
+    vars_to_keep = set(data_vars) & existing_data_vars
+    vars_to_drop = existing_data_vars - vars_to_keep
+    ds = ds.drop_vars(vars_to_drop)
+
+    existing_dims = set(ds.sizes)
+    dims_to_keep = set()
+    for var in vars_to_keep:
+        dims_to_keep.update(ds[var].coords._names)
+        dims_to_keep.update(ds[var].dims)
+
+    coords_to_drop = existing_dims - dims_to_keep
+    return ds.drop_dims(coords_to_drop)
+
+
+def combine_datasets(
+    path_glob: Iterable | str, data_vars: list[str], **kwargs
+) -> xr.Dataset:
+    """
+    Combine all datasets using a single time dimension, optionally extract
+    data from only the listed data_vars
+    """
+
+    if data_vars is not None:
+        return xr.open_mfdataset(
+            path_glob,
+            join="outer",
+            coords="different",
+            compat="no_conflicts",
+            combine="nested",
+            concat_dim="time",
+            preprocess=SDFPreprocess(data_vars=data_vars),
+            **kwargs,
+        )
 
     return xr.open_mfdataset(
         path_glob,
-        data_vars="minimal",
-        coords="minimal",
-        compat="override",
+        data_vars="all",
+        coords="different",
+        compat="no_conflicts",
+        join="outer",
         preprocess=SDFPreprocess(),
         **kwargs,
     )
@@ -70,6 +141,7 @@ def open_mfdataset(
     separate_times: bool = False,
     keep_particles: bool = False,
     probe_names: list[str] | None = None,
+    data_vars: list[str] | None = None,
 ) -> xr.Dataset:
     """Open a set of EPOCH SDF files as one `xarray.Dataset`
 
@@ -101,25 +173,34 @@ def open_mfdataset(
         If ``True``, also load particle data (this may use a lot of memory!)
     probe_names :
         List of EPOCH probe names
+    data_vars :
+        List of data vars to load in (If not specified loads in all variables)
     """
 
-    # TODO: This is not very robust, look at how xarray.open_mfdataset does it
-    if isinstance(path_glob, str):
-        path_glob = Path().glob(path_glob)
-
-    # Coerce to list because we might need to use the sequence multiple times
-    path_glob = sorted(list(path_glob))  # noqa: C414
+    path_glob = _resolve_glob(path_glob)
 
     if not separate_times:
         return combine_datasets(
-            path_glob, keep_particles=keep_particles, probe_names=probe_names
+            path_glob,
+            data_vars=data_vars,
+            keep_particles=keep_particles,
+            probe_names=probe_names,
         )
 
-    time_dims, var_times_map = make_time_dims(path_glob)
-    all_dfs = [
-        xr.open_dataset(f, keep_particles=keep_particles, probe_names=probe_names)
-        for f in path_glob
-    ]
+    _, var_times_map = make_time_dims(path_glob)
+
+    all_dfs = []
+    for f in path_glob:
+        ds = xr.open_dataset(f, keep_particles=keep_particles, probe_names=probe_names)
+
+        # If the data_vars are specified then only load them in and disregard the rest.
+        # If there are no remaining data variables then skip adding the dataset to list
+        if data_vars is not None:
+            ds = purge_unselected_data_vars(ds, data_vars)
+            if not ds.data_vars:
+                continue
+
+        all_dfs.append(ds)
 
     for df in all_dfs:
         for da in df:
@@ -136,7 +217,11 @@ def open_mfdataset(
                 )
 
     return xr.combine_by_coords(
-        all_dfs, data_vars="minimal", combine_attrs="drop_conflicts"
+        all_dfs,
+        coords="different",
+        combine_attrs="drop_conflicts",
+        join="outer",
+        compat="no_conflicts",
     )
 
 
@@ -490,10 +575,43 @@ class SDFEntrypoint(BackendEntrypoint):
 
 
 class SDFPreprocess:
-    """Preprocess SDF files for xarray ensuring matching job ids and sets time dimension"""
+    """Preprocess SDF files for xarray ensuring matching job ids and sets
+    time dimension.
+
+    This class is used as a 'preprocess' function within ``xr.open_mfdataset``. It
+    performs three main duties on each individual file's Dataset:
+
+    1. Checks for a **matching job ID** across all files to ensure dataset consistency.
+    2. **Filters** the Dataset to keep only the variables specified in `data_vars`
+       and their required coordinates.
+    3. **Expands dimensions** to include a single 'time' coordinate, preparing the
+       Dataset for concatenation.
+
+    EPOCH can output variables at different intervals, so some SDF files
+    may not contain the requested variable. We combine this data into one
+    dataset by concatenating across the time dimension.
 
-    def __init__(self):
+    The combination is performed using ``join="outer"`` (in the calling ``open_mfdataset`` function),
+    meaning that the final combined dataset will contain the variable across the
+    entire time span, with NaNs filling the time steps where the variable was absent in
+    the individual file.
+
+    With large SDF files, this filtering method will save on memory consumption when
+    compared to loading all variables from all files before concatenation.
+
+    Parameters
+    ----------
+    data_vars :
+        A list of data variables to load in (If not specified loads
+        in all variables)
+    """
+
+    def __init__(
+        self,
+        data_vars: list[str] | None = None,
+    ):
         self.job_id: int | None = None
+        self.data_vars = data_vars
 
     def __call__(self, ds: xr.Dataset) -> xr.Dataset:
         if self.job_id is None:
@@ -504,17 +622,23 @@ class SDFPreprocess:
                 f"Mismatching job ids (got {ds.attrs['jobid1']}, expected {self.job_id})"
             )
 
-        ds = ds.expand_dims(time=[ds.attrs["time"]])
+        # If the user has exclusively requested only certain variables be
+        # loaded in then we purge all other variables and coordinates
+        if self.data_vars:
+            ds = purge_unselected_data_vars(ds, self.data_vars)
+
+        time_val = ds.attrs.get("time", np.nan)
+        ds = ds.expand_dims(time=[time_val])
         ds = ds.assign_coords(
             time=(
                 "time",
-                [ds.attrs["time"]],
+                [time_val],
                 {"units": "s", "long_name": "Time", "full_name": "time"},
             )
         )
         # Particles' spartial coordinates also evolve in time
         for coord, value in ds.coords.items():
             if value.attrs.get("point_data", False):
-                ds.coords[coord] = value.expand_dims(time=[ds.attrs["time"]])
+                ds.coords[coord] = value.expand_dims(time=[time_val])
 
         return ds

sdf_xarray/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '0.2.6'
-__version_tuple__ = version_tuple = (0, 2, 6)
+__version__ = version = '0.3.2'
+__version_tuple__ = version_tuple = (0, 3, 2)
 
-__commit_id__ = commit_id = 'g67411803b'
+__commit_id__ = commit_id = 'g331520e50'

sdf_xarray/dataset_accessor.py

@@ -0,0 +1,73 @@
+from typing import Union
+
+import xarray as xr
+
+
+@xr.register_dataset_accessor("epoch")
+class EpochAccessor:
+    def __init__(self, xarray_obj: xr.Dataset):
+        # The xarray object is the Dataset, which we store as self._ds
+        self._ds = xarray_obj
+
+    def rescale_coords(
+        self,
+        multiplier: float,
+        unit_label: str,
+        coord_names: Union[str, list[str]],
+    ) -> xr.Dataset:
+        """
+        Rescales specified X and Y coordinates in the Dataset by a given multiplier
+        and updates the unit label attribute.
+
+        Parameters
+        ----------
+        multiplier : float
+            The factor by which to multiply the coordinate values (e.g., 1e6 for meters to microns).
+        unit_label : str
+            The new unit label for the coordinates (e.g., "µm").
+        coord_names : str or list of str
+            The name(s) of the coordinate variable(s) to rescale.
+            If a string, only that coordinate is rescaled.
+            If a list, all listed coordinates are rescaled.
+
+        Returns
+        -------
+        xr.Dataset
+            A new Dataset with the updated and rescaled coordinates.
+
+        Examples
+        --------
+        # Convert X, Y, and Z from meters to microns
+        >>> ds_in_microns = ds.epoch.rescale_coords(1e6, "µm", coord_names=["X_Grid", "Y_Grid", "Z_Grid"])
+
+        # Convert only X to millimeters
+        >>> ds_in_mm = ds.epoch.rescale_coords(1000, "mm", coord_names="X_Grid")
+        """
+
+        ds = self._ds
+        new_coords = {}
+
+        if isinstance(coord_names, str):
+            # Convert single string to a list
+            coords_to_process = [coord_names]
+        elif isinstance(coord_names, list):
+            # Use the provided list
+            coords_to_process = coord_names
+        else:
+            coords_to_process = list(coord_names)
+
+        for coord_name in coords_to_process:
+            if coord_name not in ds.coords:
+                raise ValueError(
+                    f"Coordinate '{coord_name}' not found in the Dataset. Cannot rescale."
+                )
+
+            coord_original = ds[coord_name]
+
+            coord_rescaled = coord_original * multiplier
+            coord_rescaled.attrs = coord_original.attrs.copy()
+            coord_rescaled.attrs["units"] = unit_label
+
+            new_coords[coord_name] = coord_rescaled
+
+        return ds.assign_coords(new_coords)

{sdf_xarray-0.2.6.dist-info → sdf_xarray-0.3.2.dist-info}/METADATA

@@ -1,8 +1,8 @@
 Metadata-Version: 2.4
 Name: sdf-xarray
-Version: 0.2.6
+Version: 0.3.2
 Summary: Provides a backend for xarray to read SDF files as created by the EPOCH plasma PIC code.
-Author-Email: Peter Hill <peter.hill@york.ac.uk>, Joel Adams <joel.adams@york.ac.uk>, Shaun Doherty <shaun.doherty@york.ac.uk>
+Author-Email: Peter Hill <peter.hill@york.ac.uk>, Joel Adams <joel.adams@york.ac.uk>, Shaun Doherty <shaun.doherty@york.ac.uk>, Chris Herdman <chris.herdman@york.ac.uk>
 License-Expression: BSD-3-Clause
 Classifier: Development Status :: 5 - Production/Stable
 Classifier: Intended Audience :: Science/Research
@@ -61,6 +61,9 @@ sdf-xarray provides a backend for [xarray](https://xarray.dev) to read SDF files
 [EPOCH](https://epochpic.github.io) using the [SDF-C](https://github.com/epochpic/SDF_C) library.
 Part of [BEAM](#broad-epoch-analysis-modules-beam) (Broad EPOCH Analysis Modules).
 
+> [!IMPORTANT]
+> To install this package make sure you are using one of the Python versions listed above.
+
 ## Installation
 
 Install from PyPI with:

{sdf_xarray-0.2.6.dist-info → sdf_xarray-0.3.2.dist-info}/RECORD

@@ -6,19 +6,20 @@ include/SDFC_14.4.7/sdf_list_type.h,sha256=Quu8v0-SEsQuJpGtEZnm09tAyXqWNitx0sXl5
 include/SDFC_14.4.7/sdf_vector_type.h,sha256=dbKjhzRRsvhzrnTwVjtVlvnuisEnRMKY-vvdm94ok_Q,1595
 include/SDFC_14.4.7/stack_allocator.h,sha256=L7U9vmGiVSw3VQLIv9EzTaVq7JbFxs9aNonKStTkUSg,1335
 include/SDFC_14.4.7/uthash.h,sha256=rIyy_-ylY6S_7WaZCCC3VtvXaC9q37rFyA0f1U9xc4w,63030
-lib/SDFC_14.4.7/sdfc.lib,sha256=Xtb83Kznp6ErvWjqaOQC9e5zRgj821Z2A5TcxYDqPOM,350158
+lib/SDFC_14.4.7/sdfc.lib,sha256=2X2DUE3jjnJGQOI2wQFQLidt_6vFdzEizuQHMEFoMqc,350158
 lib/SDFC_14.4.7/SDFCConfig.cmake,sha256=IOA1eusC-KvUK4LNTEiOAmEdaPH1ZvNvbYPgiG1oZio,802
 lib/SDFC_14.4.7/SDFCConfigVersion.cmake,sha256=pN7Qqyf04s3izw7PYQ0XK6imvmhaVegSdR_nEl3Ok_o,2830
 lib/SDFC_14.4.7/SDFCTargets-release.cmake,sha256=G4zdx5PyjePigeD_a6rmZAxbk7L8Nf0klUnV78Lm2fI,828
 lib/SDFC_14.4.7/SDFCTargets.cmake,sha256=OVt1Gm8n7Ew4fiTmA9yHoef3vIIGwsXUZfqeG9p9Bys,4152
-sdf_xarray/__init__.py,sha256=-RXoKffu5dD54-t5qmapiAJ9ODN-w0OmXDal88e-KKE,19816
-sdf_xarray/_version.py,sha256=tKK1XlQrBwni5QwVI5KGGYkfGy_9gVAaKgRzYVdjGSI,746
+sdf_xarray/__init__.py,sha256=obgAD4Aecvvpd8GkxLIAiIagSaY0bFVP2Q397N48_5g,24201
+sdf_xarray/_version.py,sha256=bmLiJYnZTISDv_NDGANk6QDMSY0XTk0CwXXKhbOvW3Y,746
 sdf_xarray/csdf.pxd,sha256=ADPjAuHsodAvdOz96Z_XlFF7VL3KmVaXcTifWDP3rK0,4205
+sdf_xarray/dataset_accessor.py,sha256=TvnVMBefnT1d94Bkllhd-__O3ittzpaVjZKfze-3WQ4,2484
 sdf_xarray/plotting.py,sha256=PnbEspR4XkA5SHkpoFKA2G7BYj5J3mVgR1TEeGol6Vw,7041
-sdf_xarray/sdf_interface.cp311-win_amd64.pyd,sha256=Z-Ze_0XmYq04SD_ftp56rCdofmPF9nQlBd7sgZSYYW0,356864
+sdf_xarray/sdf_interface.cp311-win_amd64.pyd,sha256=_nUbBNxen8g_lr9nLGmHxtq51QN3oGfDh_E2DRO7KZ4,356864
 sdf_xarray/sdf_interface.pyx,sha256=PFC6upg14OZBqiGInLgBoxztIIKBk-HOh3WC9Ro4YUw,11975
-sdf_xarray-0.2.6.dist-info/METADATA,sha256=tiVT3h4nUdTgmGJsSKbymdlWjDNbVw8pnr5ccxNy5cQ,7475
-sdf_xarray-0.2.6.dist-info/WHEEL,sha256=RKWfL8d6R7y9dzb5_AyhPLMoBaKZaDpOTwy7YMg9zGI,106
-sdf_xarray-0.2.6.dist-info/entry_points.txt,sha256=gP7BIQpXNg6vIf7S7p-Rw_EJZTC1X50BsVTkK7dA7g0,57
-sdf_xarray-0.2.6.dist-info/licenses/LICENCE,sha256=aHWuyELjtzIL1jTXFHTbI3tr9vyVyhnw3I9_QYPdEX8,1515
-sdf_xarray-0.2.6.dist-info/RECORD,,
+sdf_xarray-0.3.2.dist-info/METADATA,sha256=xvADFsOdsd5EzaZbVYGOUgmEMe4RzrTDF9IbyijadqE,7624
+sdf_xarray-0.3.2.dist-info/WHEEL,sha256=oXhHG6ewLm-FNdEna2zwgy-K0KEl4claZ1ztR4VTx0I,106
+sdf_xarray-0.3.2.dist-info/entry_points.txt,sha256=gP7BIQpXNg6vIf7S7p-Rw_EJZTC1X50BsVTkK7dA7g0,57
+sdf_xarray-0.3.2.dist-info/licenses/LICENCE,sha256=aHWuyELjtzIL1jTXFHTbI3tr9vyVyhnw3I9_QYPdEX8,1515
+sdf_xarray-0.3.2.dist-info/RECORD,,

{sdf_xarray-0.2.6.dist-info → sdf_xarray-0.3.2.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: scikit-build-core 0.11.5
+Generator: scikit-build-core 0.11.6
 Root-Is-Purelib: false
 Tag: cp311-cp311-win_amd64