Merge branch 'main' into namedarray-parallelcompat

andersy005 · web-flow · commit ebf02527ab95 · 2023-10-26T12:37:02.000-07:00
diff --git a/doc/conf.py b/doc/conf.py
@@ -231,6 +231,7 @@
     # canonical_url="",
     repository_url="https://github.com/pydata/xarray",
     repository_branch="main",
+    navigation_with_keys=False,  # pydata/pydata-sphinx-theme#1492
     path_to_docs="doc",
     use_edit_page_button=True,
     use_repository_button=True,
diff --git a/doc/examples/apply_ufunc_vectorize_1d.ipynb b/doc/examples/apply_ufunc_vectorize_1d.ipynb
@@ -11,7 +11,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This example will illustrate how to conveniently apply an unvectorized function `func` to xarray objects using `apply_ufunc`. `func` expects 1D numpy arrays and returns a 1D numpy array. Our goal is to coveniently apply this function along a dimension of xarray objects that may or may not wrap dask arrays with a signature.\n",
+    "This example will illustrate how to conveniently apply an unvectorized function `func` to xarray objects using `apply_ufunc`. `func` expects 1D numpy arrays and returns a 1D numpy array. Our goal is to conveniently apply this function along a dimension of xarray objects that may or may not wrap dask arrays with a signature.\n",
     "\n",
     "We will illustrate this using `np.interp`: \n",
     "\n",
diff --git a/doc/internals/how-to-create-custom-index.rst b/doc/internals/how-to-create-custom-index.rst
@@ -1,5 +1,7 @@
 .. currentmodule:: xarray
 
+.. _internals.custom indexes:
+
 How to create a custom index
 ============================
 
diff --git a/doc/internals/index.rst b/doc/internals/index.rst
@@ -19,9 +19,10 @@ The pages in this section are intended for:
    :hidden:
 
    internal-design
+   interoperability
    duck-arrays-integration
    chunked-arrays
    extending-xarray
-   zarr-encoding-spec
    how-to-add-new-backend
    how-to-create-custom-index
+   zarr-encoding-spec
diff --git a/doc/internals/internal-design.rst b/doc/internals/internal-design.rst
@@ -59,9 +59,9 @@ which is used as the basic building block behind xarray's
 - ``data``: The N-dimensional array (typically a NumPy or Dask array) storing
   the Variable's data. It must have the same number of dimensions as the length
   of ``dims``.
-- ``attrs``: An ordered dictionary of metadata associated with this array. By
+- ``attrs``: A dictionary of metadata associated with this array. By
   convention, xarray's built-in operations never use this metadata.
-- ``encoding``: Another ordered dictionary used to store information about how
+- ``encoding``: Another dictionary used to store information about how
   these variable's data is represented on disk. See :ref:`io.encoding` for more
   details.
 
@@ -95,7 +95,7 @@ all of which are implemented by forwarding on to the underlying ``Variable`` obj
 
 In addition, a :py:class:`~xarray.DataArray` stores additional ``Variable`` objects stored in a dict under the private ``_coords`` attribute,
 each of which is referred to as a "Coordinate Variable". These coordinate variable objects are only allowed to have ``dims`` that are a subset of the data variable's ``dims``,
-and each dim has a specific length. This means that the full :py:attr:`~xarray.DataArray.sizes` of the dataarray can be represented by a dictionary mapping dimension names to integer sizes.
+and each dim has a specific length. This means that the full :py:attr:`~xarray.DataArray.size` of the dataarray can be represented by a dictionary mapping dimension names to integer sizes.
 The underlying data variable has this exact same size, and the attached coordinate variables have sizes which are some subset of the size of the data variable.
 Another way of saying this is that all coordinate variables must be "alignable" with the data variable.
 
@@ -124,7 +124,7 @@ The :py:class:`~xarray.Dataset` class is a generalization of the :py:class:`~xar
 Internally all data variables and coordinate variables are stored under a single ``variables`` dict, and coordinates are
 specified by storing their names in a private ``_coord_names`` dict.
 
-The dataset's dimensions are the set of all dims present across any variable, but (similar to in dataarrays) coordinate
+The dataset's ``dims`` are the set of all dims present across any variable, but (similar to in dataarrays) coordinate
 variables cannot have a dimension that is not present on any data variable.
 
 When a data variable or coordinate variable is accessed, a new ``DataArray`` is again constructed from all compatible
diff --git a/doc/internals/interoperability.rst b/doc/internals/interoperability.rst
@@ -0,0 +1,45 @@
+.. _interoperability:
+
+Interoperability of Xarray
+==========================
+
+Xarray is designed to be extremely interoperable, in many orthogonal ways.
+Making xarray as flexible as possible is the common theme of most of the goals on our :ref:`roadmap`.
+
+This interoperability comes via a set of flexible abstractions into which the user can plug in. The current full list is:
+
+- :ref:`Custom file backends <add_a_backend>` via the :py:class:`~xarray.backends.BackendEntrypoint` system,
+- Numpy-like :ref:`"duck" array wrapping <internals.duckarrays>`, which supports the `Python Array API Standard <https://data-apis.org/array-api/latest/>`_,
+- :ref:`Chunked distributed array computation <internals.chunkedarrays>` via the :py:class:`~xarray.core.parallelcompat.ChunkManagerEntrypoint` system,
+- Custom :py:class:`~xarray.Index` objects for :ref:`flexible label-based lookups <internals.custom indexes>`,
+- Extending xarray objects with domain-specific methods via :ref:`custom accessors <internals.accessors>`.
+
+.. warning::
+
+    One obvious way in which xarray could be more flexible is that whilst subclassing xarray objects is possible, we
+    currently don't support it in most transformations, instead recommending composition over inheritance. See the
+    :ref:`internal design page <internal design.subclassing>` for the rationale and look at the corresponding `GH issue <https://github.com/pydata/xarray/issues/3980>`_
+    if you're interested in improving support for subclassing!
+
+.. note::
+
+    If you think there is another way in which xarray could become more generically flexible then please
+    tell us your ideas by `raising an issue to request the feature <https://github.com/pydata/xarray/issues/new/choose>`_!
+
+
+Whilst xarray was originally designed specifically to open ``netCDF4`` files as :py:class:`numpy.ndarray` objects labelled by :py:class:`pandas.Index` objects,
+it is entirely possible today to:
+
+- lazily open an xarray object directly from a custom binary file format (e.g. using ``xarray.open_dataset(path, engine='my_custom_format')``,
+- handle the data as any API-compliant numpy-like array type (e.g. sparse or GPU-backed),
+- distribute out-of-core computation across that array type in parallel (e.g. via :ref:`dask`),
+- track the physical units of the data through computations (e.g via `pint-xarray <https://pint-xarray.readthedocs.io/en/stable/>`_),
+- query the data via custom index logic optimized for specific applications (e.g. an :py:class:`~xarray.Index` object backed by a KDTree structure),
+- attach domain-specific logic via accessor methods (e.g. to understand geographic Coordinate Reference System metadata),
+- organize hierarchical groups of xarray data in a :py:class:`~datatree.DataTree` (e.g. to treat heterogenous simulation and observational data together during analysis).
+
+All of these features can be provided simultaneously, using libaries compatible with the rest of the scientific python ecosystem.
+In this situation xarray would be essentially a thin wrapper acting as pure-python framework, providing a common interface and
+separation of concerns via various domain-agnostic abstractions.
+
+Most of the remaining pages in the documentation of xarray's internals describe these various types of interoperability in more detail.
diff --git a/doc/user-guide/io.rst b/doc/user-guide/io.rst
@@ -819,7 +819,7 @@ with ``mode='a'`` on a Dataset containing the new variables, passing in an
 existing Zarr store or path to a Zarr store.
 
 To resize and then append values along an existing dimension in a store, set
-``append_dim``. This is a good option if data always arives in a particular
+``append_dim``. This is a good option if data always arrives in a particular
 order, e.g., for time-stepping a simulation:
 
 .. ipython:: python
diff --git a/doc/whats-new.rst b/doc/whats-new.rst
@@ -137,6 +137,8 @@ Bug fixes
 Documentation
 ~~~~~~~~~~~~~
 
+- Added page on the interoperability of xarray objects.
+  (:pull:`7992`) By `Tom Nicholas <https://github.com/TomNicholas>`_.
 - Added xarray-regrid to the list of xarray related projects (:pull:`8272`).
   By `Bart Schilperoort <https://github.com/BSchilperoort>`_.
 
diff --git a/xarray/backends/common.py b/xarray/backends/common.py
@@ -247,7 +247,7 @@ def sync(self, compute=True, chunkmanager_store_kwargs=None):
             chunkmanager = get_chunked_array_type(*self.sources)
 
             # TODO: consider wrapping targets with dask.delayed, if this makes
-            # for any discernible difference in perforance, e.g.,
+            # for any discernible difference in performance, e.g.,
             # targets = [dask.delayed(t) for t in self.targets]
 
             if chunkmanager_store_kwargs is None:
diff --git a/xarray/core/accessor_dt.py b/xarray/core/accessor_dt.py
@@ -601,7 +601,7 @@ class CombinedDatetimelikeAccessor(
     DatetimeAccessor[T_DataArray], TimedeltaAccessor[T_DataArray]
 ):
     def __new__(cls, obj: T_DataArray) -> CombinedDatetimelikeAccessor:
-        # CombinedDatetimelikeAccessor isn't really instatiated. Instead
+        # CombinedDatetimelikeAccessor isn't really instantiated. Instead
         # we need to choose which parent (datetime or timedelta) is
         # appropriate. Since we're checking the dtypes anyway, we'll just
         # do all the validation here.
diff --git a/xarray/core/computation.py b/xarray/core/computation.py
@@ -409,7 +409,7 @@ def _unpack_dict_tuples(
 
 def _check_core_dims(signature, variable_args, name):
     """
-    Chcek if an arg has all the core dims required by the signature.
+    Check if an arg has all the core dims required by the signature.
 
     Slightly awkward design, of returning the error message. But we want to
     give a detailed error message, which requires inspecting the variable in
diff --git a/xarray/core/groupby.py b/xarray/core/groupby.py
@@ -989,7 +989,7 @@ def _flox_reduce(
             if kwargs["func"] not in ["sum", "prod"]:
                 raise TypeError("Received an unexpected keyword argument 'min_count'")
             elif kwargs["min_count"] is None:
-                # set explicitly to avoid unncessarily accumulating count
+                # set explicitly to avoid unnecessarily accumulating count
                 kwargs["min_count"] = 0
 
         # weird backcompat
diff --git a/xarray/core/missing.py b/xarray/core/missing.py
@@ -678,7 +678,7 @@ def interp_func(var, x, new_x, method: InterpOptions, kwargs):
 
     Notes
     -----
-    This requiers scipy installed.
+    This requires scipy installed.
 
     See Also
     --------
@@ -724,7 +724,7 @@ def interp_func(var, x, new_x, method: InterpOptions, kwargs):
             for i in range(new_x[0].ndim)
         }
 
-        # if useful, re-use localize for each chunk of new_x
+        # if useful, reuse localize for each chunk of new_x
         localize = (method in ["linear", "nearest"]) and new_x0_chunks_is_not_none
 
         # scipy.interpolate.interp1d always forces to float.
diff --git a/xarray/core/types.py b/xarray/core/types.py
@@ -62,7 +62,7 @@
     _DTypeLikeNested = Any  # TODO: wait for support for recursive types
 
     # Xarray requires a Mapping[Hashable, dtype] in many places which
-    # conflics with numpys own DTypeLike (with dtypes for fields).
+    # conflicts with numpys own DTypeLike (with dtypes for fields).
     # https://numpy.org/devdocs/reference/typing.html#numpy.typing.DTypeLike
     # This is a copy of this DTypeLike that allows only non-Mapping dtypes.
     DTypeLikeSave = Union[
diff --git a/xarray/namedarray/core.py b/xarray/namedarray/core.py
@@ -270,7 +270,7 @@ def __init__(
     def __init_subclass__(cls, **kwargs: Any) -> None:
         if NamedArray in cls.__bases__ and (cls._new == NamedArray._new):
             # Type hinting does not work for subclasses unless _new is
-            # overriden with the correct class.
+            # overridden with the correct class.
             raise TypeError(
                 "Subclasses of `NamedArray` must override the `_new` method."
             )
diff --git a/xarray/tests/test_concat.py b/xarray/tests/test_concat.py
@@ -622,7 +622,7 @@ def test_concat_errors(self):
             concat([data, data], "new_dim", data_vars=["not_found"])
 
         with pytest.raises(ValueError, match=r"global attributes not"):
-            # call deepcopy seperately to get unique attrs
+            # call deepcopy separately to get unique attrs
             data0 = deepcopy(split_data[0])
             data1 = deepcopy(split_data[1])
             data1.attrs["foo"] = "bar"
diff --git a/xarray/tests/test_formatting.py b/xarray/tests/test_formatting.py
@@ -497,7 +497,7 @@ def test_array_repr_variable(self) -> None:
     def test_array_repr_recursive(self) -> None:
         # GH:issue:7111
 
-        # direct recurion
+        # direct recursion
         var = xr.Variable("x", [0, 1])
         var.attrs["x"] = var
         formatting.array_repr(var)
diff --git a/xarray/tests/test_plot.py b/xarray/tests/test_plot.py
@@ -2768,7 +2768,7 @@ def test_datetime_hue(self) -> None:
     def test_facetgrid_hue_style(self) -> None:
         ds2 = self.ds.copy()
 
-        # Numbers plots as continous:
+        # Numbers plots as continuous:
         g = ds2.plot.scatter(x="A", y="B", row="row", col="col", hue="hue")
         assert isinstance(g._mappables[-1], mpl.collections.PathCollection)
 
diff --git a/xarray/util/generate_ops.py b/xarray/util/generate_ops.py
@@ -121,7 +121,7 @@ def {method}(self, *args: Any, **kwargs: Any) -> Self:
 # We need to add "# type: ignore[override]"
 # Keep an eye out for:
 # https://discuss.python.org/t/make-type-hints-for-eq-of-primitives-less-strict/34240
-# The type ignores might not be neccesary anymore at some point.
+# The type ignores might not be necessary anymore at some point.
 #
 # We require a "hack" to tell type checkers that e.g. Variable + DataArray = DataArray
 # In reality this returns NotImplementes, but this is not a valid type in python 3.9.
