Skip to content
Navigation Menu
{{ message }}
-
-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Expand file tree
/
Copy pathtutorial.py
More file actions
389 lines (326 loc) · 12.6 KB
/
Copy pathtutorial.py
File metadata and controls
389 lines (326 loc) · 12.6 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
"""
Useful for:
* users learning xarray
* building tutorials in the documentation.
"""
from __future__ import annotations
import os
import pathlib
import sys
from typing import TYPE_CHECKING
import numpy as np
from xarray.backends.api import open_dataset as _open_dataset
from xarray.backends.api import open_datatree as _open_datatree
from xarray.core.dataarray import DataArray
from xarray.core.dataset import Dataset
from xarray.core.datatree import DataTree
if TYPE_CHECKING:
from xarray.backends.api import T_Engine
_default_cache_dir_name = "xarray_tutorial_data"
base_url = "https://github.com/pydata/xarray-data"
version = "master"
def _construct_cache_dir(path):
import pooch
if isinstance(path, os.PathLike):
path = os.fspath(path)
elif path is None:
path = pooch.os_cache(_default_cache_dir_name)
return path
external_urls: dict = {}
file_formats = {
"air_temperature": 3,
"air_temperature_gradient": 4,
"ASE_ice_velocity": 4,
"basin_mask": 4,
"ersstv5": 4,
"rasm": 3,
"ROMS_example": 4,
"tiny": 3,
"eraint_uvz": 3,
}
def _check_netcdf_engine_installed(name):
version = file_formats.get(name)
if version == 3:
try:
import scipy # noqa: F401
except ImportError:
try:
import netCDF4
except ImportError as err:
raise ImportError(
f"opening tutorial dataset {name} requires either scipy or "
"netCDF4 to be installed."
) from err
if version == 4:
try:
import h5netcdf # noqa: F401
except ImportError:
try:
import netCDF4 # noqa: F401
except ImportError as err:
raise ImportError(
f"opening tutorial dataset {name} requires either h5netcdf "
"or netCDF4 to be installed."
) from err
# idea borrowed from Seaborn
def open_dataset(
name: str,
cache: bool = True,
cache_dir: str | os.PathLike | None = None,
*,
engine: T_Engine = None,
**kws,
) -> Dataset:
"""
Open a dataset from the online repository (requires internet).
If a local copy is found then always use that to avoid network traffic.
Available datasets:
* ``"air_temperature"``: NCEP reanalysis subset
* ``"air_temperature_gradient"``: NCEP reanalysis subset with approximate x,y gradients
* ``"basin_mask"``: Dataset with ocean basins marked using integers
* ``"ASE_ice_velocity"``: MEaSUREs InSAR-Based Ice Velocity of the Amundsen Sea Embayment, Antarctica, Version 1
* ``"rasm"``: Output of the Regional Arctic System Model (RASM)
* ``"ROMS_example"``: Regional Ocean Model System (ROMS) output
* ``"tiny"``: small synthetic dataset with a 1D data variable
* ``"era5-2mt-2019-03-uk.grib"``: ERA5 temperature data over the UK
* ``"eraint_uvz"``: data from ERA-Interim reanalysis, monthly averages of upper level data
* ``"ersstv5"``: NOAA's Extended Reconstructed Sea Surface Temperature monthly averages
Parameters
----------
name : str
Name of the file containing the dataset.
e.g. 'air_temperature'
cache_dir : path-like, optional
The directory in which to search for and write cached data.
cache : bool, optional
If True, then cache data locally for use on subsequent calls
**kws : dict, optional
Passed to xarray.open_dataset
See Also
--------
tutorial.load_dataset
open_dataset
load_dataset
"""
try:
import pooch
except ImportError as e:
raise ImportError(
"tutorial.open_dataset depends on pooch to download and manage datasets."
" To proceed please install pooch."
) from e
logger = pooch.get_logger()
logger.setLevel("WARNING")
cache_dir = _construct_cache_dir(cache_dir)
if name in external_urls:
url = external_urls[name]
else:
path = pathlib.Path(name)
if not path.suffix:
# process the name
default_extension = ".nc"
if engine is None:
_check_netcdf_engine_installed(name)
path = path.with_suffix(default_extension)
elif path.suffix == ".grib":
if engine is None:
engine = "cfgrib"
try:
import cfgrib # noqa: F401
except ImportError as e:
raise ImportError(
"Reading this tutorial dataset requires the cfgrib package."
) from e
url = f"{base_url}/raw/{version}/{path.name}"
headers = {"User-Agent": f"xarray {sys.modules['xarray'].__version__}"}
downloader = pooch.HTTPDownloader(headers=headers)
# retrieve the file
filepath = pooch.retrieve(
url=url, known_hash=None, path=cache_dir, downloader=downloader
)
ds = _open_dataset(filepath, engine=engine, **kws)
if not cache:
ds = ds.load()
pathlib.Path(filepath).unlink()
return ds
def load_dataset(*args, **kwargs) -> Dataset:
"""
Open, load into memory, and close a dataset from the online repository
(requires internet).
If a local copy is found then always use that to avoid network traffic.
Available datasets:
* ``"air_temperature"``: NCEP reanalysis subset
* ``"air_temperature_gradient"``: NCEP reanalysis subset with approximate x,y gradients
* ``"basin_mask"``: Dataset with ocean basins marked using integers
* ``"rasm"``: Output of the Regional Arctic System Model (RASM)
* ``"ROMS_example"``: Regional Ocean Model System (ROMS) output
* ``"tiny"``: small synthetic dataset with a 1D data variable
* ``"era5-2mt-2019-03-uk.grib"``: ERA5 temperature data over the UK
* ``"eraint_uvz"``: data from ERA-Interim reanalysis, monthly averages of upper level data
* ``"ersstv5"``: NOAA's Extended Reconstructed Sea Surface Temperature monthly averages
Parameters
----------
name : str
Name of the file containing the dataset.
e.g. 'air_temperature'
cache_dir : path-like, optional
The directory in which to search for and write cached data.
cache : bool, optional
If True, then cache data locally for use on subsequent calls
**kws : dict, optional
Passed to xarray.open_dataset
See Also
--------
tutorial.open_dataset
open_dataset
load_dataset
"""
with open_dataset(*args, **kwargs) as ds:
return ds.load()
def scatter_example_dataset(*, seed: int | None = None) -> Dataset:
"""
Create an example dataset.
Parameters
----------
seed : int, optional
Seed for the random number generation.
"""
rng = np.random.default_rng(seed)
A = DataArray(
np.zeros([3, 11, 4, 4]),
dims=["x", "y", "z", "w"],
coords={
"x": np.arange(3),
"y": np.linspace(0, 1, 11),
"z": np.arange(4),
"w": 0.1 * rng.standard_normal(4),
},
)
B = 0.1 * A.x**2 + A.y**2.5 + 0.1 * A.z * A.w
A = -0.1 * A.x + A.y / (5 + A.z) + A.w
ds = Dataset({"A": A, "B": B})
ds["w"] = ["one", "two", "three", "five"]
ds.x.attrs["units"] = "xunits"
ds.y.attrs["units"] = "yunits"
ds.z.attrs["units"] = "zunits"
ds.w.attrs["units"] = "wunits"
ds.A.attrs["units"] = "Aunits"
ds.B.attrs["units"] = "Bunits"
return ds
def open_datatree(
name: str,
cache: bool = True,
cache_dir: str | os.PathLike | None = None,
*,
engine: T_Engine = None,
**kws,
) -> DataTree:
"""
Open a dataset as a `DataTree` from the online repository (requires internet).
If a local copy is found then always use that to avoid network traffic.
Available datasets:
* ``"imerghh_730"``: GPM IMERG Final Precipitation L3 Half Hourly 0.1 degree x 0.1 degree V07 from 2021-08-29T07:30:00.000Z
* ``"imerghh_830"``: GPM IMERG Final Precipitation L3 Half Hourly 0.1 degree x 0.1 degree V07 from 2021-08-29T08:30:00.000Z
* ``"air_temperature"``: NCEP reanalysis subset
* ``"air_temperature_gradient"``: NCEP reanalysis subset with approximate x,y gradients
* ``"basin_mask"``: Dataset with ocean basins marked using integers
* ``"ASE_ice_velocity"``: MEaSUREs InSAR-Based Ice Velocity of the Amundsen Sea Embayment, Antarctica, Version 1
* ``"rasm"``: Output of the Regional Arctic System Model (RASM)
* ``"ROMS_example"``: Regional Ocean Model System (ROMS) output
* ``"tiny"``: small synthetic dataset with a 1D data variable
* ``"era5-2mt-2019-03-uk.grib"``: ERA5 temperature data over the UK
* ``"eraint_uvz"``: data from ERA-Interim reanalysis, monthly averages of upper level data
* ``"ersstv5"``: NOAA's Extended Reconstructed Sea Surface Temperature monthly averages
Parameters
----------
name : str
Name of the file containing the dataset.
e.g. 'air_temperature'
cache_dir : path-like, optional
The directory in which to search for and write cached data.
cache : bool, optional
If True, then cache data locally for use on subsequent calls
**kws : dict, optional
Passed to xarray.open_dataset
See Also
--------
tutorial.load_datatree
open_datatree
"""
try:
import pooch
except ImportError as e:
raise ImportError(
"tutorial.open_dataset depends on pooch to download and manage datasets."
" To proceed please install pooch."
) from e
logger = pooch.get_logger()
logger.setLevel("WARNING")
cache_dir = _construct_cache_dir(cache_dir)
if name in external_urls:
url = external_urls[name]
else:
path = pathlib.Path(name)
if not path.suffix:
# process the name
default_extension = ".nc"
if engine is None:
_check_netcdf_engine_installed(name)
path = path.with_suffix(default_extension)
elif path.suffix == ".grib":
if engine is None:
engine = "cfgrib"
try:
import cfgrib # noqa: F401
except ImportError as e:
raise ImportError(
"Reading this tutorial dataset requires the cfgrib package."
) from e
url = f"{base_url}/raw/{version}/{path.name}"
headers = {"User-Agent": f"xarray {sys.modules['xarray'].__version__}"}
downloader = pooch.HTTPDownloader(headers=headers)
# retrieve the file
filepath = pooch.retrieve(
url=url, known_hash=None, path=cache_dir, downloader=downloader
)
ds = _open_datatree(filepath, engine=engine, **kws)
if not cache:
ds = ds.load()
pathlib.Path(filepath).unlink()
return ds
def load_datatree(*args, **kwargs) -> DataTree:
"""
Open, load into memory (as a `DataTree`), and close a dataset from the online repository
(requires internet).
If a local copy is found then always use that to avoid network traffic.
Available datasets:
* ``"imerghh_730"``: GPM IMERG Final Precipitation L3 Half Hourly 0.1 degree x 0.1 degree V07 from 2021-08-29T07:30:00.000Z
* ``"imerghh_830"``: GPM IMERG Final Precipitation L3 Half Hourly 0.1 degree x 0.1 degree V07 from 2021-08-29T08:30:00.000Z
* ``"air_temperature"``: NCEP reanalysis subset
* ``"air_temperature_gradient"``: NCEP reanalysis subset with approximate x,y gradients
* ``"basin_mask"``: Dataset with ocean basins marked using integers
* ``"ASE_ice_velocity"``: MEaSUREs InSAR-Based Ice Velocity of the Amundsen Sea Embayment, Antarctica, Version 1
* ``"rasm"``: Output of the Regional Arctic System Model (RASM)
* ``"ROMS_example"``: Regional Ocean Model System (ROMS) output
* ``"tiny"``: small synthetic dataset with a 1D data variable
* ``"era5-2mt-2019-03-uk.grib"``: ERA5 temperature data over the UK
* ``"eraint_uvz"``: data from ERA-Interim reanalysis, monthly averages of upper level data
* ``"ersstv5"``: NOAA's Extended Reconstructed Sea Surface Temperature monthly averages
Parameters
----------
name : str
Name of the file containing the dataset.
e.g. 'air_temperature'
cache_dir : path-like, optional
The directory in which to search for and write cached data.
cache : bool, optional
If True, then cache data locally for use on subsequent calls
**kws : dict, optional
Passed to xarray.open_datatree
See Also
--------
tutorial.open_datatree
open_datatree
"""
with open_datatree(*args, **kwargs) as ds:
return ds.load()
You can’t perform that action at this time.