fix typos (using codespell) (pydata#6316)

mathause · web-flow · commit cdab326bab0c · 2022-03-02T14:57:29.000+01:00
* fix typos (using codespell)

* revert 'split'
diff --git a/doc/examples/ROMS_ocean_model.ipynb b/doc/examples/ROMS_ocean_model.ipynb
@@ -77,7 +77,7 @@
     "ds = xr.tutorial.open_dataset(\"ROMS_example.nc\", chunks={\"ocean_time\": 1})\n",
     "\n",
     "# This is a way to turn on chunking and lazy evaluation. Opening with mfdataset, or\n",
-    "# setting the chunking in the open_dataset would also achive this.\n",
+    "# setting the chunking in the open_dataset would also achieve this.\n",
     "ds"
    ]
   },
diff --git a/doc/gallery/plot_colorbar_center.py b/doc/gallery/plot_colorbar_center.py
@@ -38,6 +38,6 @@
 ax4.set_title("Celsius: center=False")
 ax4.set_ylabel("")
 
-# Mke it nice
+# Make it nice
 plt.tight_layout()
 plt.show()
diff --git a/doc/internals/how-to-add-new-backend.rst b/doc/internals/how-to-add-new-backend.rst
@@ -317,7 +317,7 @@ grouped in three types of indexes
 :py:class:`~xarray.core.indexing.OuterIndexer` and
 :py:class:`~xarray.core.indexing.VectorizedIndexer`.
 This implies that the implementation of the method ``__getitem__`` can be tricky.
-In oder to simplify this task, Xarray provides a helper function,
+In order to simplify this task, Xarray provides a helper function,
 :py:func:`~xarray.core.indexing.explicit_indexing_adapter`, that transforms
 all the input  ``indexer`` types (`basic`, `outer`, `vectorized`) in a tuple
 which is interpreted correctly by your backend.
@@ -426,7 +426,7 @@ The ``OUTER_1VECTOR`` indexing shall supports number, slices and at most one
 list. The behaviour with the list shall be the same of ``OUTER`` indexing.
 
 If you support more complex indexing as `explicit indexing` or
-`numpy indexing`, you can have a look to the implemetation of Zarr backend and Scipy backend,
+`numpy indexing`, you can have a look to the implementation of Zarr backend and Scipy backend,
 currently available in :py:mod:`~xarray.backends` module.
 
 .. _RST preferred_chunks:
diff --git a/doc/internals/zarr-encoding-spec.rst b/doc/internals/zarr-encoding-spec.rst
@@ -14,7 +14,7 @@ for the storage of the NetCDF data model in Zarr; see
 discussion.
 
 First, Xarray can only read and write Zarr groups. There is currently no support
-for reading / writting individual Zarr arrays. Zarr groups are mapped to
+for reading / writing individual Zarr arrays. Zarr groups are mapped to
 Xarray ``Dataset`` objects.
 
 Second, from Xarray's point of view, the key difference between
diff --git a/doc/roadmap.rst b/doc/roadmap.rst
@@ -112,7 +112,7 @@ A cleaner model would be to elevate ``indexes`` to an explicit part of
 xarray's data model, e.g., as attributes on the ``Dataset`` and
 ``DataArray`` classes. Indexes would need to be propagated along with
 coordinates in xarray operations, but will no longer would need to have
-a one-to-one correspondance with coordinate variables. Instead, an index
+a one-to-one correspondence with coordinate variables. Instead, an index
 should be able to refer to multiple (possibly multidimensional)
 coordinates that define it. See `GH
 1603 <https://github.com/pydata/xarray/issues/1603>`__ for full details
diff --git a/doc/user-guide/time-series.rst b/doc/user-guide/time-series.rst
@@ -101,7 +101,7 @@ You can also select a particular time by indexing with a
 
     ds.sel(time=datetime.time(12))
 
-For more details, read the pandas documentation and the section on `Indexing Using Datetime Components <datetime_component_indexing>`_ (i.e. using the ``.dt`` acessor).
+For more details, read the pandas documentation and the section on `Indexing Using Datetime Components <datetime_component_indexing>`_ (i.e. using the ``.dt`` accessor).
 
 .. _dt_accessor:
 
diff --git a/doc/whats-new.rst b/doc/whats-new.rst
@@ -138,7 +138,7 @@ Bug fixes
   By `Michael Delgado <https://github.com/delgadom>`_.
 - `dt.season <https://docs.xarray.dev/en/stable/generated/xarray.DataArray.dt.season.html>`_  can now handle NaN and NaT.  (:pull:`5876`).
   By `Pierre Loicq <https://github.com/pierreloicq>`_.
-- Determination of zarr chunks handles empty lists for encoding chunks or variable chunks that occurs in certain cirumstances (:pull:`5526`). By `Chris Roat <https://github.com/chrisroat>`_.
+- Determination of zarr chunks handles empty lists for encoding chunks or variable chunks that occurs in certain circumstances (:pull:`5526`). By `Chris Roat <https://github.com/chrisroat>`_.
 
 Internal Changes
 ~~~~~~~~~~~~~~~~
@@ -706,7 +706,7 @@ Breaking changes
   By `Alessandro Amici <https://github.com/alexamici>`_.
 - Functions that are identities for 0d data return the unchanged data
   if axis is empty. This ensures that Datasets where some variables do
-  not have the averaged dimensions are not accidentially changed
+  not have the averaged dimensions are not accidentally changed
   (:issue:`4885`, :pull:`5207`).
   By `David Schwörer <https://github.com/dschwoerer>`_.
 - :py:attr:`DataArray.coarsen` and :py:attr:`Dataset.coarsen` no longer support passing ``keep_attrs``
@@ -1419,7 +1419,7 @@ New Features
 Enhancements
 ~~~~~~~~~~~~
 - Performance improvement of :py:meth:`DataArray.interp` and :py:func:`Dataset.interp`
-  We performs independant interpolation sequentially rather than interpolating in
+  We performs independent interpolation sequentially rather than interpolating in
   one large multidimensional space. (:issue:`2223`)
   By `Keisuke Fujii <https://github.com/fujiisoup>`_.
 - :py:meth:`DataArray.interp` now support interpolations over chunked dimensions (:pull:`4155`). By `Alexandre Poux <https://github.com/pums974>`_.
@@ -2770,7 +2770,7 @@ Breaking changes
   - ``Dataset.T`` has been removed as a shortcut for :py:meth:`Dataset.transpose`.
     Call :py:meth:`Dataset.transpose` directly instead.
   - Iterating over a ``Dataset`` now includes only data variables, not coordinates.
-    Similarily, calling ``len`` and ``bool`` on a ``Dataset`` now
+    Similarly, calling ``len`` and ``bool`` on a ``Dataset`` now
     includes only data variables.
   - ``DataArray.__contains__`` (used by Python's ``in`` operator) now checks
     array data, not coordinates.
@@ -3908,7 +3908,7 @@ Bug fixes
   (:issue:`1606`).
   By `Joe Hamman <https://github.com/jhamman>`_.
 
-- Fix bug when using ``pytest`` class decorators to skiping certain unittests.
+- Fix bug when using ``pytest`` class decorators to skipping certain unittests.
   The previous behavior unintentionally causing additional tests to be skipped
   (:issue:`1531`). By `Joe Hamman <https://github.com/jhamman>`_.
 
@@ -5656,7 +5656,7 @@ Bug fixes
 - Several bug fixes related to decoding time units from netCDF files
   (:issue:`316`, :issue:`330`). Thanks Stefan Pfenninger!
 - xray no longer requires ``decode_coords=False`` when reading datasets with
-  unparseable coordinate attributes (:issue:`308`).
+  unparsable coordinate attributes (:issue:`308`).
 - Fixed ``DataArray.loc`` indexing with ``...`` (:issue:`318`).
 - Fixed an edge case that resulting in an error when reindexing
   multi-dimensional variables (:issue:`315`).
diff --git a/xarray/backends/common.py b/xarray/backends/common.py
@@ -160,7 +160,7 @@ def sync(self, compute=True):
             import dask.array as da
 
             # TODO: consider wrapping targets with dask.delayed, if this makes
-            # for any discernable difference in perforance, e.g.,
+            # for any discernible difference in perforance, e.g.,
             # targets = [dask.delayed(t) for t in self.targets]
 
             delayed_store = da.store(
diff --git a/xarray/backends/file_manager.py b/xarray/backends/file_manager.py
@@ -204,7 +204,7 @@ def _acquire_with_cache_info(self, needs_lock=True):
                     kwargs["mode"] = self._mode
                 file = self._opener(*self._args, **kwargs)
                 if self._mode == "w":
-                    # ensure file doesn't get overriden when opened again
+                    # ensure file doesn't get overridden when opened again
                     self._mode = "a"
                 self._cache[self._key] = file
                 return file, False
diff --git a/xarray/backends/pseudonetcdf_.py b/xarray/backends/pseudonetcdf_.py
@@ -105,7 +105,7 @@ class PseudoNetCDFBackendEntrypoint(BackendEntrypoint):
     available = has_pseudonetcdf
 
     # *args and **kwargs are not allowed in open_backend_dataset_ kwargs,
-    # unless the open_dataset_parameters are explicity defined like this:
+    # unless the open_dataset_parameters are explicitly defined like this:
     open_dataset_parameters = (
         "filename_or_obj",
         "mask_and_scale",
diff --git a/xarray/backends/zarr.py b/xarray/backends/zarr.py
@@ -179,7 +179,7 @@ def _determine_zarr_chunks(enc_chunks, var_chunks, ndim, name, safe_chunks):
 
 
 def _get_zarr_dims_and_attrs(zarr_obj, dimension_key):
-    # Zarr arrays do not have dimenions. To get around this problem, we add
+    # Zarr arrays do not have dimensions. To get around this problem, we add
     # an attribute that specifies the dimension. We have to hide this attribute
     # when we send the attributes to the user.
     # zarr_obj can be either a zarr group or zarr array
diff --git a/xarray/convert.py b/xarray/convert.py
@@ -235,7 +235,7 @@ def _iris_cell_methods_to_str(cell_methods_obj):
 
 
 def _name(iris_obj, default="unknown"):
-    """Mimicks `iris_obj.name()` but with different name resolution order.
+    """Mimics `iris_obj.name()` but with different name resolution order.
 
     Similar to iris_obj.name() method, but using iris_obj.var_name first to
     enable roundtripping.
diff --git a/xarray/core/accessor_str.py b/xarray/core/accessor_str.py
@@ -456,7 +456,7 @@ def cat(
             Strings or array-like of strings to concatenate elementwise with
             the current DataArray.
         sep : str or array-like of str, default: "".
-            Seperator to use between strings.
+            Separator to use between strings.
             It is broadcast in the same way as the other input strings.
             If array-like, its dimensions will be placed at the end of the output array dimensions.
 
@@ -539,7 +539,7 @@ def join(
             Only one dimension is allowed at a time.
             Optional for 0D or 1D DataArrays, required for multidimensional DataArrays.
         sep : str or array-like, default: "".
-            Seperator to use between strings.
+            Separator to use between strings.
             It is broadcast in the same way as the other input strings.
             If array-like, its dimensions will be placed at the end of the output array dimensions.
 
diff --git a/xarray/core/combine.py b/xarray/core/combine.py
@@ -135,7 +135,7 @@ def _infer_concat_order_from_coords(datasets):
                 order = rank.astype(int).values - 1
 
                 # Append positions along extra dimension to structure which
-                # encodes the multi-dimensional concatentation order
+                # encodes the multi-dimensional concatenation order
                 tile_ids = [
                     tile_id + (position,) for tile_id, position in zip(tile_ids, order)
                 ]
diff --git a/xarray/core/computation.py b/xarray/core/computation.py
@@ -1941,7 +1941,7 @@ def unify_chunks(*objects: T_Xarray) -> tuple[T_Xarray, ...]:
         for obj in objects
     ]
 
-    # Get argumets to pass into dask.array.core.unify_chunks
+    # Get arguments to pass into dask.array.core.unify_chunks
     unify_chunks_args = []
     sizes: dict[Hashable, int] = {}
     for ds in datasets:
diff --git a/xarray/core/concat.py b/xarray/core/concat.py
@@ -455,7 +455,7 @@ def _dataset_concat(
     if (dim in coord_names or dim in data_names) and dim not in dim_names:
         datasets = [ds.expand_dims(dim) for ds in datasets]
 
-    # determine which variables to concatentate
+    # determine which variables to concatenate
     concat_over, equals, concat_dim_lengths = _calc_concat_over(
         datasets, dim, dim_names, data_vars, coords, compat
     )
diff --git a/xarray/core/dataarray.py b/xarray/core/dataarray.py
@@ -2584,7 +2584,7 @@ def interpolate_na(
         )
 
     def ffill(self, dim: Hashable, limit: int = None) -> DataArray:
-        """Fill NaN values by propogating values forward
+        """Fill NaN values by propagating values forward
 
         *Requires bottleneck.*
 
@@ -2609,7 +2609,7 @@ def ffill(self, dim: Hashable, limit: int = None) -> DataArray:
         return ffill(self, dim, limit=limit)
 
     def bfill(self, dim: Hashable, limit: int = None) -> DataArray:
-        """Fill NaN values by propogating values backward
+        """Fill NaN values by propagating values backward
 
         *Requires bottleneck.*
 
diff --git a/xarray/core/dataset.py b/xarray/core/dataset.py
@@ -379,7 +379,7 @@ def _check_chunks_compatibility(var, chunks, preferred_chunks):
 
 
 def _get_chunk(var, chunks):
-    # chunks need to be explicity computed to take correctly into accout
+    # chunks need to be explicitly computed to take correctly into account
     # backend preferred chunking
     import dask.array as da
 
@@ -1529,7 +1529,7 @@ def __setitem__(self, key: Hashable | list[Hashable] | Mapping, value) -> None:
                 except Exception as e:
                     if processed:
                         raise RuntimeError(
-                            "An error occured while setting values of the"
+                            "An error occurred while setting values of the"
                             f" variable '{name}'. The following variables have"
                             f" been successfully updated:\n{processed}"
                         ) from e
@@ -1976,7 +1976,7 @@ def to_zarr(
             metadata for existing stores (falling back to non-consolidated).
         append_dim : hashable, optional
             If set, the dimension along which the data will be appended. All
-            other dimensions on overriden variables must remain the same size.
+            other dimensions on overridden variables must remain the same size.
         region : dict, optional
             Optional mapping from dimension names to integer slices along
             dataset dimensions to indicate the region of existing zarr array(s)
@@ -2001,7 +2001,7 @@ def to_zarr(
             Set False to override this restriction; however, data may become corrupted
             if Zarr arrays are written in parallel. This option may be useful in combination
             with ``compute=False`` to initialize a Zarr from an existing
-            Dataset with aribtrary chunk structure.
+            Dataset with arbitrary chunk structure.
         storage_options : dict, optional
             Any additional parameters for the storage backend (ignored for local
             paths).
@@ -4930,7 +4930,7 @@ def interpolate_na(
         return new
 
     def ffill(self, dim: Hashable, limit: int = None) -> Dataset:
-        """Fill NaN values by propogating values forward
+        """Fill NaN values by propagating values forward
 
         *Requires bottleneck.*
 
@@ -4956,7 +4956,7 @@ def ffill(self, dim: Hashable, limit: int = None) -> Dataset:
         return new
 
     def bfill(self, dim: Hashable, limit: int = None) -> Dataset:
-        """Fill NaN values by propogating values backward
+        """Fill NaN values by propagating values backward
 
         *Requires bottleneck.*
 
diff --git a/xarray/core/merge.py b/xarray/core/merge.py
@@ -587,7 +587,7 @@ def merge_core(
     Parameters
     ----------
     objects : list of mapping
-        All values must be convertable to labeled arrays.
+        All values must be convertible to labeled arrays.
     compat : {"identical", "equals", "broadcast_equals", "no_conflicts", "override"}, optional
         Compatibility checks to use when merging variables.
     join : {"outer", "inner", "left", "right"}, optional
diff --git a/xarray/core/missing.py b/xarray/core/missing.py
@@ -573,7 +573,7 @@ def _localize(var, indexes_coords):
 
 def _floatize_x(x, new_x):
     """Make x and new_x float.
-    This is particulary useful for datetime dtype.
+    This is particularly useful for datetime dtype.
     x, new_x: tuple of np.ndarray
     """
     x = list(x)
@@ -624,7 +624,7 @@ def interp(var, indexes_coords, method, **kwargs):
     kwargs["bounds_error"] = kwargs.get("bounds_error", False)
 
     result = var
-    # decompose the interpolation into a succession of independant interpolation
+    # decompose the interpolation into a succession of independent interpolation
     for indexes_coords in decompose_interp(indexes_coords):
         var = result
 
@@ -731,7 +731,7 @@ def interp_func(var, x, new_x, method, kwargs):
             for i in range(new_x[0].ndim)
         }
 
-        # if usefull, re-use localize for each chunk of new_x
+        # if useful, re-use localize for each chunk of new_x
         localize = (method in ["linear", "nearest"]) and (new_x[0].chunks is not None)
 
         # scipy.interpolate.interp1d always forces to float.
@@ -825,7 +825,7 @@ def _dask_aware_interpnd(var, *coords, interp_func, interp_kwargs, localize=True
 
 
 def decompose_interp(indexes_coords):
-    """Decompose the interpolation into a succession of independant interpolation keeping the order"""
+    """Decompose the interpolation into a succession of independent interpolation keeping the order"""
 
     dest_dims = [
         dest[1].dims if dest[1].ndim > 0 else [dim]
diff --git a/xarray/core/rolling.py b/xarray/core/rolling.py
@@ -33,7 +33,7 @@
 Returns
 -------
 reduced : same type as caller
-    New object with `{name}` applied along its rolling dimnension.
+    New object with `{name}` applied along its rolling dimension.
 """
 
 
@@ -767,7 +767,7 @@ def __init__(self, obj, windows, boundary, side, coord_func):
             exponential window along (e.g. `time`) to the size of the moving window.
         boundary : 'exact' | 'trim' | 'pad'
             If 'exact', a ValueError will be raised if dimension size is not a
-            multiple of window size. If 'trim', the excess indexes are trimed.
+            multiple of window size. If 'trim', the excess indexes are trimmed.
             If 'pad', NA will be padded.
         side : 'left' or 'right' or mapping from dimension to 'left' or 'right'
         coord_func : mapping from coordinate name to func.
diff --git a/xarray/core/variable.py b/xarray/core/variable.py
@@ -700,7 +700,7 @@ def _broadcast_indexes_outer(self, key):
         return dims, OuterIndexer(tuple(new_key)), None
 
     def _nonzero(self):
-        """Equivalent numpy's nonzero but returns a tuple of Varibles."""
+        """Equivalent numpy's nonzero but returns a tuple of Variables."""
         # TODO we should replace dask's native nonzero
         # after https://github.com/dask/dask/issues/1076 is implemented.
         nonzeros = np.nonzero(self.data)
diff --git a/xarray/tests/test_backends.py b/xarray/tests/test_backends.py
@@ -1937,7 +1937,7 @@ def test_chunk_encoding_with_dask(self):
             with self.roundtrip(ds_chunk4) as actual:
                 assert (4,) == actual["var1"].encoding["chunks"]
 
-        # TODO: remove this failure once syncronized overlapping writes are
+        # TODO: remove this failure once synchronized overlapping writes are
         # supported by xarray
         ds_chunk4["var1"].encoding.update({"chunks": 5})
         with pytest.raises(NotImplementedError, match=r"named 'var1' would overlap"):
@@ -2255,7 +2255,7 @@ def test_write_region_mode(self, mode):
 
     @requires_dask
     def test_write_preexisting_override_metadata(self):
-        """Metadata should be overriden if mode="a" but not in mode="r+"."""
+        """Metadata should be overridden if mode="a" but not in mode="r+"."""
         original = Dataset(
             {"u": (("x",), np.zeros(10), {"variable": "original"})},
             attrs={"global": "original"},
@@ -2967,7 +2967,7 @@ def test_open_fileobj(self):
                 with pytest.raises(TypeError, match="not a valid NetCDF 3"):
                     open_dataset(f, engine="scipy")
 
-            # TOOD: this additional open is required since scipy seems to close the file
+            # TODO: this additional open is required since scipy seems to close the file
             # when it fails on the TypeError (though didn't when we used
             # `raises_regex`?). Ref https://github.com/pydata/xarray/pull/5191
             with open(tmp_file, "rb") as f:
diff --git a/xarray/tests/test_calendar_ops.py b/xarray/tests/test_calendar_ops.py
@@ -161,7 +161,7 @@ def test_convert_calendar_errors():
     with pytest.raises(ValueError, match="Argument `align_on` must be specified"):
         convert_calendar(src_nl, "360_day")
 
-    # Standard doesn't suuport year 0
+    # Standard doesn't support year 0
     with pytest.raises(
         ValueError, match="Source time coordinate contains dates with year 0"
     ):
diff --git a/xarray/tests/test_coarsen.py b/xarray/tests/test_coarsen.py
diff --git a/xarray/tests/test_computation.py b/xarray/tests/test_computation.py
diff --git a/xarray/tests/test_dask.py b/xarray/tests/test_dask.py
diff --git a/xarray/tests/test_dataarray.py b/xarray/tests/test_dataarray.py
diff --git a/xarray/tests/test_dataset.py b/xarray/tests/test_dataset.py
diff --git a/xarray/tests/test_interp.py b/xarray/tests/test_interp.py
diff --git a/xarray/tests/test_missing.py b/xarray/tests/test_missing.py
diff --git a/xarray/tests/test_plot.py b/xarray/tests/test_plot.py

Original file line number	Diff line number	Diff line change
`@@ -77,7 +77,7 @@`
`77`	`77`	`"ds = xr.tutorial.open_dataset(\"ROMS_example.nc\", chunks={\"ocean_time\": 1})\n",`
`78`	`78`	`"\n",`
`79`	`79`	`"# This is a way to turn on chunking and lazy evaluation. Opening with mfdataset, or\n",`
`80`		`- "# setting the chunking in the open_dataset would also achive this.\n",`
	`80`	`+ "# setting the chunking in the open_dataset would also achieve this.\n",`
`81`	`81`	`"ds"`
`82`	`82`	`]`
`83`	`83`	`},`