-
-
Notifications
You must be signed in to change notification settings - Fork 52
/
api.py
490 lines (396 loc) · 15.8 KB
/
api.py
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
# -*- coding: utf-8 -*-
# Copyright (c) 2018-2021, earthobservations developers.
# Distributed under the MIT License. See LICENSE for more info.
import logging
from datetime import datetime
from enum import Enum
from io import StringIO
from typing import Dict, Generator, Optional, Tuple, Union
from urllib.parse import urljoin
import pandas as pd
import requests
from requests import HTTPError
from wetterdienst.core.scalar.request import ScalarRequestCore
from wetterdienst.core.scalar.result import StationsResult, ValuesResult
from wetterdienst.core.scalar.values import ScalarValuesCore
from wetterdienst.metadata.columns import Columns
from wetterdienst.metadata.period import Period, PeriodType
from wetterdienst.metadata.provider import Provider
from wetterdienst.metadata.resolution import Resolution, ResolutionType
from wetterdienst.metadata.timezone import Timezone
from wetterdienst.provider.dwd.forecast.access import KMLReader
from wetterdienst.provider.dwd.forecast.metadata import (
DwdForecastDate,
DwdMosmixParameter,
DwdMosmixType,
)
from wetterdienst.provider.dwd.forecast.metadata.field_types import INTEGER_PARAMETERS
from wetterdienst.provider.dwd.forecast.metadata.unit import (
DwdMosmixUnitOrigin,
DwdMosmixUnitSI,
)
from wetterdienst.provider.dwd.metadata.column_names import DwdColumns
from wetterdienst.provider.dwd.metadata.constants import (
DWD_MOSMIX_L_SINGLE_PATH,
DWD_MOSMIX_S_PATH,
DWD_SERVER,
)
from wetterdienst.provider.dwd.metadata.datetime import DatetimeFormat
from wetterdienst.util.cache import metaindex_cache
from wetterdienst.util.enumeration import parse_enumeration_from_template
from wetterdienst.util.geo import convert_dm_to_dd
from wetterdienst.util.network import list_remote_files_fsspec
log = logging.getLogger(__name__)
class DwdMosmixDataset(Enum):
SMALL = "small"
LARGE = "large"
class DwdMosmixValues(ScalarValuesCore):
"""
Fetch weather forecast data (KML/MOSMIX_S dataset).
Parameters
----------
station_id : List
- If None, data for all stations is returned.
- If not None, station_ids are a list of station ids for which data is desired.
parameter: List
- If None, data for all parameters is returned.
- If not None, list of parameters, per MOSMIX definition, see
https://www.dwd.de/DE/leistungen/opendata/help/schluessel_datenformate/kml/mosmix_elemente_pdf.pdf?__blob=publicationFile&v=2 # noqa:E501,B950
"""
_tz = Timezone.GERMANY
_data_tz = Timezone.UTC
_has_quality = False
@property
def _tidy(self) -> bool:
return self.stations.tidy
_irregular_parameters = tuple()
_integer_parameters = INTEGER_PARAMETERS
_string_parameters = tuple()
def _create_humanized_parameters_mapping(self) -> Dict[str, str]:
"""Method for creation of parameter name mappings based on
self._parameter_base"""
hcnm = {
parameter.value: parameter.name.lower()
for parameter in self.stations.stations._parameter_base[
self.stations.stations.mosmix_type.name
]
}
return hcnm
def __init__(self, stations: StationsResult) -> None:
""""""
super(DwdMosmixValues, self).__init__(stations=stations)
parameter_base = self.stations.stations._parameter_base
dataset_accessor = self.stations.stations._dataset_accessor
parameter_ = []
for parameter, dataset in self.stations.parameter:
if parameter == dataset:
parameter = [par.value for par in parameter_base[dataset_accessor]]
parameter_.extend(parameter)
else:
parameter_.append(parameter.value)
self.kml = KMLReader(
station_ids=self.stations.station_id.tolist(),
parameters=parameter_,
)
# TODO: add __eq__ and __str__
@property
def metadata(self) -> pd.DataFrame:
""" Wrapper for forecast metadata """
return self.stations.df
def query(self) -> Generator[ValuesResult, None, None]:
"""Replace collect data method as all information is read once from kml file"""
for forecast_df in self._collect_station_parameter():
forecast_df = self._coerce_meta_fields(forecast_df)
forecast_df = self._coerce_parameter_types(forecast_df)
if self.stations.humanize:
forecast_df = self._humanize(forecast_df)
result = ValuesResult(stations=self.stations, df=forecast_df)
yield result
def _collect_station_parameter(self) -> Generator[pd.DataFrame, None, None]:
"""Wrapper of read_mosmix to collect forecast data (either latest or for
defined dates)"""
if self.stations.start_issue == DwdForecastDate.LATEST:
df = next(self.read_mosmix(self.stations.stations.start_issue))
df[Columns.QUALITY.value] = pd.NA
yield df
else:
for date in pd.date_range(
self.stations.stations.start_issue,
self.stations.stations.end_issue,
freq=self.stations.frequency.value,
):
try:
df = next(self.read_mosmix(date))
df[Columns.QUALITY.value] = pd.NA
yield df
except IndexError as e:
log.warning(e)
continue
def read_mosmix(
self, date: Union[datetime, DwdForecastDate]
) -> Generator[pd.DataFrame, None, None]:
"""
Manage data acquisition for a given date that is used to filter the found files
on the MOSMIX path of the DWD server.
:param date: datetime or enumeration for latest MOSMIX forecast
:return: DWDMosmixResult with gathered information
"""
for df_forecast in self._read_mosmix(date):
df_forecast = df_forecast.rename(
columns={
"station_id": DwdColumns.STATION_ID.value,
"datetime": DwdColumns.DATE.value,
}
)
if self.stations.tidy:
df_forecast = df_forecast.melt(
id_vars=[
DwdColumns.STATION_ID.value,
DwdColumns.DATE.value,
],
var_name=DwdColumns.PARAMETER.value,
value_name=DwdColumns.VALUE.value,
)
yield df_forecast
def _read_mosmix(
self, date: Union[DwdForecastDate, datetime]
) -> Generator[pd.DataFrame, None, None]:
"""Wrapper that either calls read_mosmix_s or read_mosmix_l depending on
defined period type"""
if self.stations.stations.mosmix_type == DwdMosmixType.SMALL:
yield from self.read_mosmix_small(date)
else:
yield from self.read_mosmix_large(date)
def read_mosmix_small(
self, date: Union[DwdForecastDate, datetime]
) -> Generator[Tuple[pd.DataFrame, pd.DataFrame], None, None]:
"""Reads single MOSMIX-S file with all stations and returns every forecast that
matches with one of the defined station ids."""
url = urljoin(DWD_SERVER, DWD_MOSMIX_S_PATH)
file_url = self.get_url_for_date(url, date)
self.kml.read(file_url)
for forecast in self.kml.get_forecasts():
yield forecast
def read_mosmix_large(
self, date: Union[DwdForecastDate, datetime]
) -> Generator[Tuple[pd.DataFrame, pd.DataFrame], None, None]:
"""Reads multiple MOSMIX-L files with one per each station and returns a
forecast per file."""
url = urljoin(DWD_SERVER, DWD_MOSMIX_L_SINGLE_PATH)
for station_id in self.stations.station_id:
station_url = f"{url}{station_id}/kml"
try:
file_url = self.get_url_for_date(station_url, date)
except HTTPError:
log.warning(f"Files for {station_id} do not exist on the server")
continue
self.kml.read(file_url)
yield next(self.kml.get_forecasts())
@staticmethod
def get_url_for_date(url: str, date: Union[datetime, DwdForecastDate]) -> str:
"""
Method to get a file url based on the MOSMIX-S/MOSMIX-L url and the date that is
used for filtering.
Args:
url: MOSMIX-S/MOSMIX-L path on the dwd server
date: date used for filtering of the available files
Returns:
file url based on the filtering
"""
urls = list_remote_files_fsspec(url, recursive=False)
if date == DwdForecastDate.LATEST:
try:
url = list(filter(lambda url_: "LATEST" in url_.upper(), urls))[0]
return url
except IndexError as e:
raise IndexError(f"Unable to find LATEST file within {url}") from e
df_urls = pd.DataFrame({"URL": urls})
df_urls[DwdColumns.DATE.value] = df_urls["URL"].apply(
lambda url_: url_.split("/")[-1].split("_")[2].replace(".kmz", "")
)
df_urls = df_urls[df_urls[DwdColumns.DATE.value] != "LATEST"]
df_urls[DwdColumns.DATE.value] = pd.to_datetime(
df_urls[DwdColumns.DATE.value], format=DatetimeFormat.YMDH.value
)
df_urls = df_urls.loc[df_urls[DwdColumns.DATE.value] == date]
if df_urls.empty:
raise IndexError(f"Unable to find {date} file within {url}")
return df_urls["URL"].item()
class DwdMosmixRequest(ScalarRequestCore):
""" Implementation of sites for MOSMIX forecast sites """
provider = Provider.DWD
_url = (
"https://www.dwd.de/DE/leistungen/met_verfahren_mosmix/"
"mosmix_stationskatalog.cfg?view=nasPublication"
)
_colspecs = [
(0, 5),
(6, 11),
(12, 17),
(18, 22),
(23, 44),
(45, 51),
(52, 58),
(59, 64),
(65, 71),
(72, 76),
]
_columns = [
Columns.STATION_ID.value,
Columns.ICAO_ID.value,
Columns.FROM_DATE.value,
Columns.TO_DATE.value,
Columns.HEIGHT.value,
Columns.LATITUDE.value,
Columns.LONGITUDE.value,
Columns.NAME.value,
Columns.STATE.value,
]
_tz = Timezone.GERMANY
_parameter_base = DwdMosmixParameter
_values = DwdMosmixValues
_resolution_type = ResolutionType.FIXED
_resolution_base = None
_period_type = PeriodType.FIXED
_period_base = None
_has_datasets = True
_unique_dataset = True
_dataset_base = DwdMosmixDataset
_origin_unit_tree = DwdMosmixUnitOrigin
_si_unit_tree = DwdMosmixUnitSI
@property
def _dataset_accessor(self) -> str:
return self.mosmix_type.name
@classmethod
def _setup_discover_filter(cls, filter_):
filter_ = pd.Series(filter_).apply(
parse_enumeration_from_template, args=(cls._dataset_base,)
).tolist() or [*cls._dataset_base]
return filter_
_base_columns = [
Columns.STATION_ID.value,
Columns.ICAO_ID.value,
Columns.FROM_DATE.value,
Columns.TO_DATE.value,
Columns.HEIGHT.value,
Columns.LATITUDE.value,
Columns.LONGITUDE.value,
Columns.NAME.value,
Columns.STATE.value,
]
@staticmethod
def adjust_datetime(datetime_: datetime) -> datetime:
"""
Adjust datetime to MOSMIX release frequency, which is required for MOSMIX-L
that is only released very 6 hours (3, 9, 15, 21). Datetime is floored
to closest release time e.g. if hour is 14, it will be rounded to 9
Args:
datetime_: datetime that is adjusted
Returns:
adjusted datetime with floored hour
"""
regular_date = datetime_ + pd.offsets.DateOffset(hour=3)
if regular_date > datetime_:
regular_date -= pd.Timedelta(hours=6)
delta_hours = (datetime_.hour - regular_date.hour) % 6
datetime_adjusted = datetime_ - pd.Timedelta(hours=delta_hours)
return datetime_adjusted
def __init__(
self,
parameter: Optional[Tuple[Union[str, DwdMosmixParameter], ...]],
mosmix_type: Union[str, DwdMosmixType],
start_issue: Optional[
Union[str, datetime, DwdForecastDate]
] = DwdForecastDate.LATEST,
end_issue: Optional[Union[str, datetime]] = None,
start_date: Optional[Union[str, datetime]] = None,
end_date: Optional[Union[str, datetime]] = None,
humanize: bool = True,
tidy: bool = True,
si_units: bool = True,
) -> None:
self.mosmix_type = parse_enumeration_from_template(mosmix_type, DwdMosmixType)
super().__init__(
parameter=parameter,
start_date=start_date,
end_date=end_date,
resolution=Resolution.HOURLY,
period=Period.FUTURE,
si_units=si_units,
)
# Parse issue date if not set to fixed "latest" string
if start_issue is DwdForecastDate.LATEST and end_issue:
log.info(
"end_issue will be ignored as 'latest' was selected for issue date"
)
if start_issue is not DwdForecastDate.LATEST:
if not start_issue and not end_issue:
start_issue = DwdForecastDate.LATEST
elif not end_issue:
end_issue = start_issue
elif not start_issue:
start_issue = end_issue
start_issue = pd.to_datetime(start_issue, infer_datetime_format=True).floor(
"1H"
)
end_issue = pd.to_datetime(end_issue, infer_datetime_format=True).floor(
"1H"
)
# Shift start date and end date to 3, 9, 15, 21 hour format
if mosmix_type == DwdMosmixType.LARGE:
start_issue = self.adjust_datetime(start_issue)
end_issue = self.adjust_datetime(end_issue)
# TODO: this should be replaced by the freq property in the main class
if self.mosmix_type == DwdMosmixType.SMALL:
self.resolution = Resolution.HOURLY
else:
self.resolution = Resolution.HOUR_6
self.start_issue = start_issue
self.end_issue = end_issue
self.humanize = humanize
self.tidy = tidy
@property
def issue_start(self):
""" Required for typing """
return self.issue_start
@property
def issue_end(self):
""" Required for typing """
return self.issue_end
@metaindex_cache.cache_on_arguments()
def _all(self) -> pd.DataFrame:
""" Create meta data DataFrame from available station list """
# TODO: Cache payload with FSSPEC
payload = requests.get(self._url, headers={"User-Agent": ""})
df = pd.read_fwf(
StringIO(payload.text),
skiprows=4,
skip_blank_lines=True,
colspecs=self._colspecs,
na_values=["----"],
header=None,
dtype="str",
)
df = df[
(df.iloc[:, 0] != "=====")
& (df.iloc[:, 0] != "TABLE")
& (df.iloc[:, 0] != "clu")
]
df = df.iloc[:, [2, 3, 4, 5, 6, 7]]
df.columns = [
Columns.STATION_ID.value,
Columns.ICAO_ID.value,
Columns.NAME.value,
Columns.LATITUDE.value,
Columns.LONGITUDE.value,
Columns.HEIGHT.value,
]
# Convert coordinates from degree minutes to decimal degrees
df[Columns.LATITUDE.value] = (
df[Columns.LATITUDE.value].astype(float).apply(convert_dm_to_dd)
)
df[Columns.LONGITUDE.value] = (
df[Columns.LONGITUDE.value].astype(float).apply(convert_dm_to_dd)
)
df = df.reindex(columns=self._columns)
return df.copy()