Repository navigation
Expand file tree
/
Copy pathcommon.py
More file actions
2120 lines (1804 loc) · 73.8 KB
/
Copy pathcommon.py
File metadata and controls
2120 lines (1804 loc) · 73.8 KB
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
from __future__ import annotations
import datetime
import warnings
from collections.abc import Callable, Hashable, Iterable, Iterator, Mapping
from contextlib import suppress
from html import escape
from textwrap import dedent
from typing import TYPE_CHECKING, Any, Concatenate, ParamSpec, TypeVar, Union, overload
import numpy as np
import pandas as pd
from xarray.core import dtypes, duck_array_ops, formatting, formatting_html
from xarray.core.indexing import BasicIndexer, ExplicitlyIndexed
from xarray.core.options import OPTIONS, _get_keep_attrs
from xarray.core.types import ResampleCompatible
from xarray.core.utils import (
Frozen,
either_dict_or_kwargs,
is_scalar,
)
from xarray.namedarray.core import _raise_if_any_duplicate_dimensions
from xarray.namedarray.parallelcompat import get_chunked_array_type, guess_chunkmanager
from xarray.namedarray.pycompat import is_chunked_array
try:
import cftime
except ImportError:
cftime = None
# Used as a sentinel value to indicate all dimensions
ALL_DIMS = ...
if TYPE_CHECKING:
from numpy.typing import DTypeLike
from xarray.computation.rolling_exp import RollingExp
from xarray.core.dataarray import DataArray
from xarray.core.dataset import Dataset
from xarray.core.indexes import Index
from xarray.core.resample import Resample
from xarray.core.types import (
DatetimeLike,
DTypeLikeSave,
ScalarOrArray,
Self,
SideOptions,
T_Chunks,
T_DataWithCoords,
T_Variable,
)
from xarray.core.variable import Variable
from xarray.groupers import Resampler
DTypeMaybeMapping = Union[DTypeLikeSave, Mapping[Any, DTypeLikeSave]]
T_Resample = TypeVar("T_Resample", bound="Resample")
C = TypeVar("C")
T = TypeVar("T")
P = ParamSpec("P")
class ImplementsArrayReduce:
__slots__ = ()
@classmethod
def _reduce_method(cls, func: Callable, include_skipna: bool, numeric_only: bool):
if include_skipna:
def wrapped_func(self, dim=None, axis=None, skipna=None, **kwargs):
return self.reduce(
func=func, dim=dim, axis=axis, skipna=skipna, **kwargs
)
else:
def wrapped_func(self, dim=None, axis=None, **kwargs): # type: ignore[misc]
return self.reduce(func=func, dim=dim, axis=axis, **kwargs)
return wrapped_func
_reduce_extra_args_docstring = dedent(
"""\
dim : str or sequence of str, optional
Dimension(s) over which to apply `{name}`.
axis : int or sequence of int, optional
Axis(es) over which to apply `{name}`. Only one of the 'dim'
and 'axis' arguments can be supplied. If neither are supplied, then
`{name}` is calculated over axes."""
)
_cum_extra_args_docstring = dedent(
"""\
dim : str or sequence of str, optional
Dimension over which to apply `{name}`.
axis : int or sequence of int, optional
Axis over which to apply `{name}`. Only one of the 'dim'
and 'axis' arguments can be supplied."""
)
class ImplementsDatasetReduce:
__slots__ = ()
@classmethod
def _reduce_method(cls, func: Callable, include_skipna: bool, numeric_only: bool):
if include_skipna:
def wrapped_func(self, dim=None, skipna=None, **kwargs):
return self.reduce(
func=func,
dim=dim,
skipna=skipna,
numeric_only=numeric_only,
**kwargs,
)
else:
def wrapped_func(self, dim=None, **kwargs): # type: ignore[misc]
return self.reduce(
func=func, dim=dim, numeric_only=numeric_only, **kwargs
)
return wrapped_func
_reduce_extra_args_docstring = dedent(
"""
dim : str or sequence of str, optional
Dimension(s) over which to apply `{name}`. By default `{name}` is
applied over all dimensions.
"""
).strip()
_cum_extra_args_docstring = dedent(
"""
dim : str or sequence of str, optional
Dimension over which to apply `{name}`.
axis : int or sequence of int, optional
Axis over which to apply `{name}`. Only one of the 'dim'
and 'axis' arguments can be supplied.
"""
).strip()
class AbstractArray:
"""Shared base class for DataArray and Variable."""
__slots__ = ()
def __bool__(self: Any) -> bool:
return bool(self.values)
def __float__(self: Any) -> float:
return float(self.values)
def __int__(self: Any) -> int:
return int(self.values)
def __complex__(self: Any) -> complex:
return complex(self.values)
def __array__(
self: Any, dtype: DTypeLike | None = None, /, *, copy: bool | None = None
) -> np.ndarray:
if not copy:
if np.lib.NumpyVersion(np.__version__) >= "2.0.0":
copy = None
elif np.lib.NumpyVersion(np.__version__) <= "1.28.0":
copy = False
else:
# 2.0.0 dev versions, handle cases where copy may or may not exist
try:
np.array([1]).__array__(copy=None)
copy = None
except TypeError:
copy = False
return np.array(self.values, dtype=dtype, copy=copy)
def __repr__(self) -> str:
return formatting.array_repr(self)
def _repr_html_(self):
if OPTIONS["display_style"] == "text":
return f"<pre>{escape(repr(self))}</pre>"
return formatting_html.array_repr(self)
def __format__(self: Any, format_spec: str = "") -> str:
if format_spec != "":
if self.shape == ():
# Scalar values might be ok use format_spec with instead of repr:
return self.data.__format__(format_spec)
else:
# TODO: If it's an array the formatting.array_repr(self) should
# take format_spec as an input. If we'd only use self.data we
# lose all the information about coords for example which is
# important information:
raise NotImplementedError(
"Using format_spec is only supported"
f" when shape is (). Got shape = {self.shape}."
)
else:
return self.__repr__()
def _iter(self: Any) -> Iterator[Any]:
for n in range(len(self)):
yield self[n]
def __iter__(self: Any) -> Iterator[Any]:
if self.ndim == 0:
raise TypeError("iteration over a 0-d array")
return self._iter()
@overload
def get_axis_num(self, dim: str) -> int: ... # type: ignore [overload-overlap]
@overload
def get_axis_num(self, dim: Iterable[Hashable]) -> tuple[int, ...]: ...
@overload
def get_axis_num(self, dim: Hashable) -> int: ...
def get_axis_num(self, dim: Hashable | Iterable[Hashable]) -> int | tuple[int, ...]:
"""Return axis number(s) corresponding to dimension(s) in this array.
Parameters
----------
dim : str or iterable of str
Dimension name(s) for which to lookup axes.
Returns
-------
int or tuple of int
Axis number or numbers corresponding to the given dimensions.
"""
if not isinstance(dim, str) and isinstance(dim, Iterable):
return tuple(self._get_axis_num(d) for d in dim)
else:
return self._get_axis_num(dim)
def _get_axis_num(self: Any, dim: Hashable) -> int:
_raise_if_any_duplicate_dimensions(self.dims)
try:
return self.dims.index(dim)
except ValueError as err:
raise ValueError(
f"{dim!r} not found in array dimensions {self.dims!r}"
) from err
@property
def sizes(self: Any) -> Mapping[Hashable, int]:
"""Ordered mapping from dimension names to lengths.
Immutable.
See Also
--------
Dataset.sizes
"""
return Frozen(dict(zip(self.dims, self.shape, strict=True)))
class AttrAccessMixin:
"""Mixin class that allows getting keys with attribute access"""
__slots__ = ()
def __init_subclass__(cls, **kwargs):
"""Verify that all subclasses explicitly define ``__slots__``. If they don't,
raise error in the core xarray module and a FutureWarning in third-party
extensions.
"""
if not hasattr(object.__new__(cls), "__dict__"):
pass
elif cls.__module__.startswith("xarray."):
raise AttributeError(f"{cls.__name__} must explicitly define __slots__")
else:
cls.__setattr__ = cls._setattr_dict
warnings.warn(
f"xarray subclass {cls.__name__} should explicitly define __slots__",
FutureWarning,
stacklevel=2,
)
super().__init_subclass__(**kwargs)
@property
def _attr_sources(self) -> Iterable[Mapping[Hashable, Any]]:
"""Places to look-up items for attribute-style access"""
yield from ()
@property
def _item_sources(self) -> Iterable[Mapping[Hashable, Any]]:
"""Places to look-up items for key-autocompletion"""
yield from ()
def __getattr__(self, name: str) -> Any:
if name not in {"__dict__", "__setstate__"}:
# this avoids an infinite loop when pickle looks for the
# __setstate__ attribute before the xarray object is initialized
for source in self._attr_sources:
with suppress(KeyError):
return source[name]
raise AttributeError(
f"{type(self).__name__!r} object has no attribute {name!r}"
)
# This complicated two-method design boosts overall performance of simple operations
# - particularly DataArray methods that perform a _to_temp_dataset() round-trip - by
# a whopping 8% compared to a single method that checks hasattr(self, "__dict__") at
# runtime before every single assignment. All of this is just temporary until the
# FutureWarning can be changed into a hard crash.
def _setattr_dict(self, name: str, value: Any) -> None:
"""Deprecated third party subclass (see ``__init_subclass__`` above)"""
object.__setattr__(self, name, value)
if name in self.__dict__:
# Custom, non-slotted attr, or improperly assigned variable?
warnings.warn(
f"Setting attribute {name!r} on a {type(self).__name__!r} object. Explicitly define __slots__ "
"to suppress this warning for legitimate custom attributes and "
"raise an error when attempting variables assignments.",
FutureWarning,
stacklevel=2,
)
def __setattr__(self, name: str, value: Any) -> None:
"""Objects with ``__slots__`` raise AttributeError if you try setting an
undeclared attribute. This is desirable, but the error message could use some
improvement.
"""
try:
object.__setattr__(self, name, value)
except AttributeError as e:
# Don't accidentally shadow custom AttributeErrors, e.g.
# DataArray.dims.setter
if str(e) != f"{type(self).__name__!r} object has no attribute {name!r}":
raise
raise AttributeError(
f"cannot set attribute {name!r} on a {type(self).__name__!r} object. Use __setitem__ style"
"assignment (e.g., `ds['name'] = ...`) instead of assigning variables."
) from e
def __dir__(self) -> list[str]:
"""Provide method name lookup and completion. Only provide 'public'
methods.
"""
extra_attrs = {
item
for source in self._attr_sources
for item in source
if isinstance(item, str)
}
return sorted(set(dir(type(self))) | extra_attrs)
def _ipython_key_completions_(self) -> list[str]:
"""Provide method for the key-autocompletions in IPython.
See https://ipython.readthedocs.io/en/stable/config/integrating.html#tab-completion
For the details.
"""
items = {
item
for source in self._item_sources
for item in source
if isinstance(item, str)
}
return list(items)
class TreeAttrAccessMixin(AttrAccessMixin):
"""Mixin class that allows getting keys with attribute access"""
# TODO: Ensure ipython tab completion can include both child datatrees and
# variables from Dataset objects on relevant nodes.
__slots__ = ()
def __init_subclass__(cls, **kwargs):
"""This method overrides the check from ``AttrAccessMixin`` that ensures
``__dict__`` is absent in a class, with ``__slots__`` used instead.
``DataTree`` has some dynamically defined attributes in addition to those
defined in ``__slots__``. (GH9068)
"""
if not hasattr(object.__new__(cls), "__dict__"):
pass
def get_squeeze_dims(
xarray_obj,
dim: Hashable | Iterable[Hashable] | None = None,
axis: int | Iterable[int] | None = None,
) -> list[Hashable]:
"""Get a list of dimensions to squeeze out."""
if dim is not None and axis is not None:
raise ValueError("cannot use both parameters `axis` and `dim`")
if dim is None and axis is None:
return [d for d, s in xarray_obj.sizes.items() if s == 1]
if isinstance(dim, Iterable) and not isinstance(dim, str):
dim = list(dim)
elif dim is not None:
dim = [dim]
else:
assert axis is not None
if isinstance(axis, int):
axis = [axis]
axis = list(axis)
if any(not isinstance(a, int) for a in axis):
raise TypeError("parameter `axis` must be int or iterable of int.")
alldims = list(xarray_obj.sizes.keys())
dim = [alldims[a] for a in axis]
if any(xarray_obj.sizes[k] > 1 for k in dim):
raise ValueError(
"cannot select a dimension to squeeze out which has length greater than one"
)
return dim
class DataWithCoords(AttrAccessMixin):
"""Shared base class for Dataset and DataArray."""
_close: Callable[[], None] | None
_indexes: dict[Hashable, Index]
__slots__ = ("_close",)
def squeeze(
self,
dim: Hashable | Iterable[Hashable] | None = None,
drop: bool = False,
axis: int | Iterable[int] | None = None,
) -> Self:
"""Return a new object with squeezed data.
Parameters
----------
dim : None or Hashable or iterable of Hashable, optional
Selects a subset of the length one dimensions. If a dimension is
selected with length greater than one, an error is raised. If
None, all length one dimensions are squeezed.
drop : bool, default: False
If ``drop=True``, drop squeezed coordinates instead of making them
scalar.
axis : None or int or iterable of int, optional
Like dim, but positional.
Returns
-------
squeezed : same type as caller
This object, but with with all or a subset of the dimensions of
length 1 removed.
See Also
--------
numpy.squeeze
"""
dims = get_squeeze_dims(self, dim, axis)
return self.isel(dict.fromkeys(dims, 0), drop=drop)
def clip(
self,
min: ScalarOrArray | None = None,
max: ScalarOrArray | None = None,
*,
keep_attrs: bool | None = None,
) -> Self:
"""
Return an array whose values are limited to ``[min, max]``.
At least one of max or min must be given.
Parameters
----------
min : None or Hashable, optional
Minimum value. If None, no lower clipping is performed.
max : None or Hashable, optional
Maximum value. If None, no upper clipping is performed.
keep_attrs : bool or None, optional
If True, the attributes (`attrs`) will be copied from
the original object to the new one. If False, the new
object will be returned without attributes.
Returns
-------
clipped : same type as caller
This object, but with with values < min are replaced with min,
and those > max with max.
See Also
--------
numpy.clip : equivalent function
"""
from xarray.computation.apply_ufunc import apply_ufunc
if keep_attrs is None:
# When this was a unary func, the default was True, so retaining the
# default.
keep_attrs = _get_keep_attrs(default=True)
return apply_ufunc(
duck_array_ops.clip, self, min, max, keep_attrs=keep_attrs, dask="allowed"
)
def get_index(self, key: Hashable) -> pd.Index:
"""Get an index for a dimension, with fall-back to a default RangeIndex"""
if key not in self.dims:
raise KeyError(key)
try:
return self._indexes[key].to_pandas_index()
except KeyError:
return pd.Index(range(self.sizes[key]), name=key)
def _calc_assign_results(
self: C, kwargs: Mapping[Any, T | Callable[[C], T]]
) -> dict[Hashable, T]:
return {k: v(self) if callable(v) else v for k, v in kwargs.items()}
def assign_coords(
self,
coords: Mapping | None = None,
**coords_kwargs: Any,
) -> Self:
"""Assign new coordinates to this object.
Returns a new object with all the original data in addition to the new
coordinates.
Parameters
----------
coords : mapping of dim to coord, optional
A mapping whose keys are the names of the coordinates and values are the
coordinates to assign. The mapping will generally be a dict or
:class:`Coordinates`.
* If a value is a standard data value — for example, a ``DataArray``,
scalar, or array — the data is simply assigned as a coordinate.
* If a value is callable, it is called with this object as the only
parameter, and the return value is used as new coordinate variables.
* A coordinate can also be defined and attached to an existing dimension
using a tuple with the first element the dimension name and the second
element the values for this new coordinate.
**coords_kwargs : optional
The keyword arguments form of ``coords``.
One of ``coords`` or ``coords_kwargs`` must be provided.
Returns
-------
assigned : same type as caller
A new object with the new coordinates in addition to the existing
data.
Examples
--------
Convert `DataArray` longitude coordinates from 0-359 to -180-179:
>>> da = xr.DataArray(
... np.random.rand(4),
... coords=[np.array([358, 359, 0, 1])],
... dims="lon",
... )
>>> da
<xarray.DataArray (lon: 4)> Size: 32B
array([0.5488135 , 0.71518937, 0.60276338, 0.54488318])
Coordinates:
* lon (lon) int64 32B 358 359 0 1
>>> da.assign_coords(lon=(((da.lon + 180) % 360) - 180))
<xarray.DataArray (lon: 4)> Size: 32B
array([0.5488135 , 0.71518937, 0.60276338, 0.54488318])
Coordinates:
* lon (lon) int64 32B -2 -1 0 1
The function also accepts dictionary arguments:
>>> da.assign_coords({"lon": (((da.lon + 180) % 360) - 180)})
<xarray.DataArray (lon: 4)> Size: 32B
array([0.5488135 , 0.71518937, 0.60276338, 0.54488318])
Coordinates:
* lon (lon) int64 32B -2 -1 0 1
New coordinate can also be attached to an existing dimension:
>>> lon_2 = np.array([300, 289, 0, 1])
>>> da.assign_coords(lon_2=("lon", lon_2))
<xarray.DataArray (lon: 4)> Size: 32B
array([0.5488135 , 0.71518937, 0.60276338, 0.54488318])
Coordinates:
* lon (lon) int64 32B 358 359 0 1
lon_2 (lon) int64 32B 300 289 0 1
Note that the same result can also be obtained with a dict e.g.
>>> _ = da.assign_coords({"lon_2": ("lon", lon_2)})
Note the same method applies to `Dataset` objects.
Convert `Dataset` longitude coordinates from 0-359 to -180-179:
>>> temperature = np.linspace(20, 32, num=16).reshape(2, 2, 4)
>>> precipitation = 2 * np.identity(4).reshape(2, 2, 4)
>>> ds = xr.Dataset(
... data_vars=dict(
... temperature=(["x", "y", "time"], temperature),
... precipitation=(["x", "y", "time"], precipitation),
... ),
... coords=dict(
... lon=(["x", "y"], [[260.17, 260.68], [260.21, 260.77]]),
... lat=(["x", "y"], [[42.25, 42.21], [42.63, 42.59]]),
... time=pd.date_range("2014-09-06", periods=4),
... reference_time=pd.Timestamp("2014-09-05"),
... ),
... attrs=dict(description="Weather-related data"),
... )
>>> ds
<xarray.Dataset> Size: 360B
Dimensions: (x: 2, y: 2, time: 4)
Coordinates:
lon (x, y) float64 32B 260.2 260.7 260.2 260.8
lat (x, y) float64 32B 42.25 42.21 42.63 42.59
* time (time) datetime64[us] 32B 2014-09-06 ... 2014-09-09
reference_time datetime64[us] 8B 2014-09-05
Dimensions without coordinates: x, y
Data variables:
temperature (x, y, time) float64 128B 20.0 20.8 21.6 ... 30.4 31.2 32.0
precipitation (x, y, time) float64 128B 2.0 0.0 0.0 0.0 ... 0.0 0.0 2.0
Attributes:
description: Weather-related data
>>> ds.assign_coords(lon=(((ds.lon + 180) % 360) - 180))
<xarray.Dataset> Size: 360B
Dimensions: (x: 2, y: 2, time: 4)
Coordinates:
lon (x, y) float64 32B -99.83 -99.32 -99.79 -99.23
lat (x, y) float64 32B 42.25 42.21 42.63 42.59
* time (time) datetime64[us] 32B 2014-09-06 ... 2014-09-09
reference_time datetime64[us] 8B 2014-09-05
Dimensions without coordinates: x, y
Data variables:
temperature (x, y, time) float64 128B 20.0 20.8 21.6 ... 30.4 31.2 32.0
precipitation (x, y, time) float64 128B 2.0 0.0 0.0 0.0 ... 0.0 0.0 2.0
Attributes:
description: Weather-related data
See Also
--------
Dataset.assign
Dataset.swap_dims
Dataset.set_coords
"""
from xarray.core.coordinates import Coordinates
coords_combined = either_dict_or_kwargs(coords, coords_kwargs, "assign_coords")
data = self.copy(deep=False)
results: Coordinates | dict[Hashable, Any]
if isinstance(coords, Coordinates):
results = coords
else:
results = self._calc_assign_results(coords_combined)
data.coords.update(results)
return data
def assign_attrs(self, *args: Any, **kwargs: Any) -> Self:
"""Assign new attrs to this object.
Returns a new object equivalent to ``self.attrs.update(*args, **kwargs)``.
Parameters
----------
*args
positional arguments passed into ``attrs.update``.
**kwargs
keyword arguments passed into ``attrs.update``.
Examples
--------
>>> dataset = xr.Dataset({"temperature": [25, 30, 27]})
>>> dataset
<xarray.Dataset> Size: 24B
Dimensions: (temperature: 3)
Coordinates:
* temperature (temperature) int64 24B 25 30 27
Data variables:
*empty*
>>> new_dataset = dataset.assign_attrs(
... units="Celsius", description="Temperature data"
... )
>>> new_dataset
<xarray.Dataset> Size: 24B
Dimensions: (temperature: 3)
Coordinates:
* temperature (temperature) int64 24B 25 30 27
Data variables:
*empty*
Attributes:
units: Celsius
description: Temperature data
# Attributes of the new dataset
>>> new_dataset.attrs
{'units': 'Celsius', 'description': 'Temperature data'}
Returns
-------
assigned : same type as caller
A new object with the new attrs in addition to the existing data.
See Also
--------
Dataset.assign
"""
out = self.copy(deep=False)
out.attrs.update(*args, **kwargs)
return out
@overload
def pipe(
self,
func: Callable[Concatenate[Self, P], T],
*args: P.args,
**kwargs: P.kwargs,
) -> T: ...
@overload
def pipe(
self,
func: tuple[Callable[..., T], str],
*args: Any,
**kwargs: Any,
) -> T: ...
def pipe(
self,
func: Callable[Concatenate[Self, P], T] | tuple[Callable[P, T], str],
*args: P.args,
**kwargs: P.kwargs,
) -> T:
"""
Apply ``func(self, *args, **kwargs)``
This method replicates the pandas method of the same name.
Parameters
----------
func : callable
function to apply to this xarray object (Dataset/DataArray).
``args``, and ``kwargs`` are passed into ``func``.
Alternatively a ``(callable, data_keyword)`` tuple where
``data_keyword`` is a string indicating the keyword of
``callable`` that expects the xarray object.
*args
positional arguments passed into ``func``.
**kwargs
a dictionary of keyword arguments passed into ``func``.
Returns
-------
object : Any
the return type of ``func``.
Notes
-----
Use ``.pipe`` when chaining together functions that expect
xarray or pandas objects, e.g., instead of writing
.. code:: python
f(g(h(ds), arg1=a), arg2=b, arg3=c)
You can write
.. code:: python
(ds.pipe(h).pipe(g, arg1=a).pipe(f, arg2=b, arg3=c))
If you have a function that takes the data as (say) the second
argument, pass a tuple indicating which keyword expects the
data. For example, suppose ``f`` takes its data as ``arg2``:
.. code:: python
(ds.pipe(h).pipe(g, arg1=a).pipe((f, "arg2"), arg1=a, arg3=c))
Examples
--------
>>> x = xr.Dataset(
... {
... "temperature_c": (
... ("lat", "lon"),
... 20 * np.random.rand(4).reshape(2, 2),
... ),
... "precipitation": (("lat", "lon"), np.random.rand(4).reshape(2, 2)),
... },
... coords={"lat": [10, 20], "lon": [150, 160]},
... )
>>> x
<xarray.Dataset> Size: 96B
Dimensions: (lat: 2, lon: 2)
Coordinates:
* lat (lat) int64 16B 10 20
* lon (lon) int64 16B 150 160
Data variables:
temperature_c (lat, lon) float64 32B 10.98 14.3 12.06 10.9
precipitation (lat, lon) float64 32B 0.4237 0.6459 0.4376 0.8918
>>> def adder(data, arg):
... return data + arg
...
>>> def div(data, arg):
... return data / arg
...
>>> def sub_mult(data, sub_arg, mult_arg):
... return (data * mult_arg) - sub_arg
...
>>> x.pipe(adder, 2)
<xarray.Dataset> Size: 96B
Dimensions: (lat: 2, lon: 2)
Coordinates:
* lat (lat) int64 16B 10 20
* lon (lon) int64 16B 150 160
Data variables:
temperature_c (lat, lon) float64 32B 12.98 16.3 14.06 12.9
precipitation (lat, lon) float64 32B 2.424 2.646 2.438 2.892
>>> x.pipe(adder, arg=2)
<xarray.Dataset> Size: 96B
Dimensions: (lat: 2, lon: 2)
Coordinates:
* lat (lat) int64 16B 10 20
* lon (lon) int64 16B 150 160
Data variables:
temperature_c (lat, lon) float64 32B 12.98 16.3 14.06 12.9
precipitation (lat, lon) float64 32B 2.424 2.646 2.438 2.892
>>> (
... x.pipe(adder, arg=2)
... .pipe(div, arg=2)
... .pipe(sub_mult, sub_arg=2, mult_arg=2)
... )
<xarray.Dataset> Size: 96B
Dimensions: (lat: 2, lon: 2)
Coordinates:
* lat (lat) int64 16B 10 20
* lon (lon) int64 16B 150 160
Data variables:
temperature_c (lat, lon) float64 32B 10.98 14.3 12.06 10.9
precipitation (lat, lon) float64 32B 0.4237 0.6459 0.4376 0.8918
See Also
--------
pandas.DataFrame.pipe
"""
if isinstance(func, tuple):
# Use different var when unpacking function from tuple because the type
# signature of the unpacked function differs from the expected type
# signature in the case where only a function is given, rather than a tuple.
# This makes type checkers happy at both call sites below.
f, target = func
if target in kwargs:
raise ValueError(
f"{target} is both the pipe target and a keyword argument"
)
kwargs[target] = self
return f(*args, **kwargs)
return func(self, *args, **kwargs)
def rolling_exp(
self: T_DataWithCoords,
window: Mapping[Any, int] | None = None,
window_type: str = "span",
**window_kwargs,
) -> RollingExp[T_DataWithCoords]:
"""
Exponentially-weighted moving window.
Similar to EWM in pandas
Requires the optional Numbagg dependency.
Parameters
----------
window : mapping of hashable to int, optional
A mapping from the name of the dimension to create the rolling
exponential window along (e.g. `time`) to the size of the moving window.
window_type : {"span", "com", "halflife", "alpha"}, default: "span"
The format of the previously supplied window. Each is a simple
numerical transformation of the others. Described in detail:
https://pandas.pydata.org/pandas-docs/stable/reference/api/pandas.DataFrame.ewm.html
**window_kwargs : optional
The keyword arguments form of ``window``.
One of window or window_kwargs must be provided.
See Also
--------
core.rolling_exp.RollingExp
"""
if "keep_attrs" in window_kwargs:
warnings.warn(
"Passing ``keep_attrs`` to ``rolling_exp`` has no effect. Pass"
" ``keep_attrs`` directly to the applied function, e.g."
" ``rolling_exp(...).mean(keep_attrs=False)``.",
stacklevel=2,
)
window = either_dict_or_kwargs(window, window_kwargs, "rolling_exp")
from xarray.computation.rolling_exp import RollingExp
return RollingExp(self, window, window_type)
def _resample(
self,
resample_cls: type[T_Resample],
indexer: Mapping[Hashable, ResampleCompatible | Resampler] | None,
skipna: bool | None,
closed: SideOptions | None,
label: SideOptions | None,
offset: pd.Timedelta | datetime.timedelta | str | None,
origin: str | DatetimeLike,
restore_coord_dims: bool | None,
**indexer_kwargs: ResampleCompatible | Resampler,
) -> T_Resample:
"""Returns a Resample object for performing resampling operations.
Handles both downsampling and upsampling. The resampled
dimension must be a datetime-like coordinate. If any intervals
contain no values from the original object, they will be given
the value ``NaN``.
Parameters
----------
indexer : {dim: freq}, optional
Mapping from the dimension name to resample frequency [1]_. The
dimension must be datetime-like.
skipna : bool, optional
Whether to skip missing values when aggregating in downsampling.
closed : {"left", "right"}, optional
Side of each interval to treat as closed.
label : {"left", "right"}, optional
Side of each interval to use for labeling.
origin : {'epoch', 'start', 'start_day', 'end', 'end_day'}, pd.Timestamp, datetime.datetime, np.datetime64, or cftime.datetime, default 'start_day'
The datetime on which to adjust the grouping. The timezone of origin
must match the timezone of the index.
If a datetime is not used, these values are also supported:
- 'epoch': `origin` is 1970-01-01
- 'start': `origin` is the first value of the timeseries
- 'start_day': `origin` is the first day at midnight of the timeseries
- 'end': `origin` is the last value of the timeseries
- 'end_day': `origin` is the ceiling midnight of the last day
offset : pd.Timedelta, datetime.timedelta, or str, default is None
An offset timedelta added to the origin.
restore_coord_dims : bool, optional
If True, also restore the dimension order of multi-dimensional
coordinates.
**indexer_kwargs : {dim: freq}
The keyword arguments form of ``indexer``.
One of indexer or indexer_kwargs must be provided.
Returns
-------
resampled : same type as caller
This object resampled.
Examples
--------
Downsample monthly time-series data to seasonal data:
>>> da = xr.DataArray(
... np.linspace(0, 11, num=12),
... coords=[
... pd.date_range(
... "1999-12-15",
... periods=12,
... freq=pd.DateOffset(months=1),
... )
... ],
... dims="time",
... )
>>> da
<xarray.DataArray (time: 12)> Size: 96B
array([ 0., 1., 2., 3., 4., 5., 6., 7., 8., 9., 10., 11.])
Coordinates:
* time (time) datetime64[us] 96B 1999-12-15 2000-01-15 ... 2000-11-15
>>> da.resample(time="QS-DEC").mean()
<xarray.DataArray (time: 4)> Size: 32B
array([ 1., 4., 7., 10.])
Coordinates:
* time (time) datetime64[us] 32B 1999-12-01 2000-03-01 ... 2000-09-01
Upsample monthly time-series data to daily data:
>>> da.resample(time="1D").interpolate("linear") # +doctest: ELLIPSIS