weatherdb 1.1.0__py3-none-any.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (77) hide show
  1. docker/Dockerfile +30 -0
  2. docker/docker-compose.yaml +58 -0
  3. docker/docker-compose_test.yaml +24 -0
  4. docker/start-docker-test.sh +6 -0
  5. docs/requirements.txt +10 -0
  6. docs/source/Changelog.md +2 -0
  7. docs/source/License.rst +7 -0
  8. docs/source/Methode.md +161 -0
  9. docs/source/_static/custom.css +8 -0
  10. docs/source/_static/favicon.ico +0 -0
  11. docs/source/_static/logo.png +0 -0
  12. docs/source/api/api.rst +15 -0
  13. docs/source/api/cli.rst +8 -0
  14. docs/source/api/weatherDB.broker.rst +10 -0
  15. docs/source/api/weatherDB.config.rst +7 -0
  16. docs/source/api/weatherDB.db.rst +23 -0
  17. docs/source/api/weatherDB.rst +22 -0
  18. docs/source/api/weatherDB.station.rst +56 -0
  19. docs/source/api/weatherDB.stations.rst +46 -0
  20. docs/source/api/weatherDB.utils.rst +22 -0
  21. docs/source/conf.py +137 -0
  22. docs/source/index.rst +33 -0
  23. docs/source/setup/Configuration.md +127 -0
  24. docs/source/setup/Hosting.md +9 -0
  25. docs/source/setup/Install.md +49 -0
  26. docs/source/setup/Quickstart.md +183 -0
  27. docs/source/setup/setup.rst +12 -0
  28. weatherdb/__init__.py +24 -0
  29. weatherdb/_version.py +1 -0
  30. weatherdb/alembic/README.md +8 -0
  31. weatherdb/alembic/alembic.ini +80 -0
  32. weatherdb/alembic/config.py +9 -0
  33. weatherdb/alembic/env.py +100 -0
  34. weatherdb/alembic/script.py.mako +26 -0
  35. weatherdb/alembic/versions/V1.0.0_initial_database_creation.py +898 -0
  36. weatherdb/alembic/versions/V1.0.2_more_charachters_for_settings+term_station_ma_raster.py +88 -0
  37. weatherdb/alembic/versions/V1.0.5_fix-ma-raster-values.py +152 -0
  38. weatherdb/alembic/versions/V1.0.6_update-views.py +22 -0
  39. weatherdb/broker.py +667 -0
  40. weatherdb/cli.py +214 -0
  41. weatherdb/config/ConfigParser.py +663 -0
  42. weatherdb/config/__init__.py +5 -0
  43. weatherdb/config/config_default.ini +162 -0
  44. weatherdb/db/__init__.py +3 -0
  45. weatherdb/db/connections.py +374 -0
  46. weatherdb/db/fixtures/RichterParameters.json +34 -0
  47. weatherdb/db/models.py +402 -0
  48. weatherdb/db/queries/get_quotient.py +155 -0
  49. weatherdb/db/views.py +165 -0
  50. weatherdb/station/GroupStation.py +710 -0
  51. weatherdb/station/StationBases.py +3108 -0
  52. weatherdb/station/StationET.py +111 -0
  53. weatherdb/station/StationP.py +807 -0
  54. weatherdb/station/StationPD.py +98 -0
  55. weatherdb/station/StationT.py +164 -0
  56. weatherdb/station/__init__.py +13 -0
  57. weatherdb/station/constants.py +21 -0
  58. weatherdb/stations/GroupStations.py +519 -0
  59. weatherdb/stations/StationsBase.py +1021 -0
  60. weatherdb/stations/StationsBaseTET.py +30 -0
  61. weatherdb/stations/StationsET.py +17 -0
  62. weatherdb/stations/StationsP.py +128 -0
  63. weatherdb/stations/StationsPD.py +24 -0
  64. weatherdb/stations/StationsT.py +21 -0
  65. weatherdb/stations/__init__.py +11 -0
  66. weatherdb/utils/TimestampPeriod.py +369 -0
  67. weatherdb/utils/__init__.py +3 -0
  68. weatherdb/utils/dwd.py +350 -0
  69. weatherdb/utils/geometry.py +69 -0
  70. weatherdb/utils/get_data.py +285 -0
  71. weatherdb/utils/logging.py +126 -0
  72. weatherdb-1.1.0.dist-info/LICENSE +674 -0
  73. weatherdb-1.1.0.dist-info/METADATA +765 -0
  74. weatherdb-1.1.0.dist-info/RECORD +77 -0
  75. weatherdb-1.1.0.dist-info/WHEEL +5 -0
  76. weatherdb-1.1.0.dist-info/entry_points.txt +2 -0
  77. weatherdb-1.1.0.dist-info/top_level.txt +3 -0
@@ -0,0 +1,710 @@
1
+ # libraries
2
+ import logging
3
+ from datetime import datetime
4
+ from pathlib import Path
5
+ import warnings
6
+ import zipfile
7
+ from packaging import version
8
+ import pandas as pd
9
+
10
+ from ..utils.TimestampPeriod import TimestampPeriod
11
+ from .StationBases import StationBase, AGG_TO
12
+ from . import StationP, StationT, StationET
13
+
14
+ # set settings
15
+ # ############
16
+ __all__ = ["GroupStation"]
17
+ log = logging.getLogger(__name__)
18
+
19
+ # class definition
20
+ ##################
21
+ class GroupStation(object):
22
+ """A class to group all possible parameters of one station.
23
+
24
+ So if you want to create the input files for a simulation, where you need T, ET and N, use this class to download the data for one station.
25
+ """
26
+
27
+ def __init__(self, id, error_if_missing=True, **kwargs):
28
+ self.id = id
29
+ self.station_parts = []
30
+ self._error_if_missing = error_if_missing
31
+ for StatClass in [StationP, StationT, StationET]:
32
+ try:
33
+ self.station_parts.append(
34
+ StatClass(id=id, **kwargs)
35
+ )
36
+ except Exception as e:
37
+ if error_if_missing:
38
+ raise e
39
+ self.paras_available = [stat._para for stat in self.station_parts]
40
+
41
+ def _check_paras(self, paras):
42
+ if isinstance(paras, str) and paras != "all":
43
+ paras = [paras,]
44
+
45
+ if isinstance(paras, str) and (paras == "all"):
46
+ return self.paras_available
47
+ else:
48
+ paras_new = []
49
+ for para in paras:
50
+ if para in self.paras_available:
51
+ paras_new.append(para)
52
+ elif self._error_if_missing:
53
+ raise ValueError(
54
+ f"The parameter {para} you asked for is not available for station {self.id}")
55
+ return paras_new
56
+
57
+ @staticmethod
58
+ def _check_kinds(kinds):
59
+ # type cast kinds
60
+ if isinstance(kinds, str):
61
+ kinds = [kinds]
62
+ else:
63
+ kinds = kinds.copy()
64
+ return kinds
65
+
66
+ def get_available_paras(self, short=False):
67
+ """Get the possible parameters for this station.
68
+
69
+ Parameters
70
+ ----------
71
+ short : bool, optional
72
+ Should the short name of the parameters be returned.
73
+ The default is "long".
74
+
75
+ Returns
76
+ -------
77
+ list of str
78
+ A list of the long parameter names that are possible for this station to get.
79
+ """
80
+ paras = []
81
+ attr_name = "_para" if short else "_para_long"
82
+ for stat in self.station_parts:
83
+ paras.append(getattr(stat, attr_name))
84
+
85
+ return paras
86
+
87
+ def get_filled_period(self, kinds="best", from_meta=True, join_how="inner"):
88
+ """Get the combined filled period for all 3 stations.
89
+
90
+ This is the maximum possible timerange for these stations.
91
+
92
+ Parameters
93
+ ----------
94
+ kind : str
95
+ The data kind to look for filled period.
96
+ Must be a column in the timeseries DB.
97
+ Must be one of "raw", "qc", "filled", "adj".
98
+ If "best" is given, then depending on the parameter of the station the best kind is selected.
99
+ For Precipitation this is "corr" and for the other this is "filled".
100
+ For the precipitation also "qn" and "corr" are valid.
101
+ from_meta : bool, optional
102
+ Should the period be from the meta table?
103
+ If False: the period is returned from the timeserie. In this case this function is only a wrapper for .get_period_meta.
104
+ The default is True.
105
+ join_how : str, optional
106
+ How should the different periods get joined.
107
+ If "inner" then the minimal period that is inside of all the filled_periods is returned.
108
+ If "outer" then the maximal possible period is returned.
109
+ The default is "inner".
110
+
111
+ Returns
112
+ -------
113
+ TimestampPeriod
114
+ The maximum filled period for the 3 parameters for this station.
115
+ """
116
+ kinds = self._check_kinds(kinds)
117
+ for kind in ["filled_by", "adj"]:
118
+ if kind in kinds:
119
+ kinds.remove(kind)
120
+
121
+ # get filled_period
122
+ for kind in kinds:
123
+ for stat in self.station_parts:
124
+ new_filled_period = stat.get_filled_period(
125
+ kind=kind, from_meta=from_meta)
126
+
127
+ if "filled_period" not in locals():
128
+ filled_period = new_filled_period.copy()
129
+ else:
130
+ filled_period = filled_period.union(
131
+ new_filled_period, how=join_how)
132
+
133
+ return filled_period
134
+
135
+ def get_df(self, period=(None, None), kinds="best", paras="all",
136
+ agg_to="day", nas_allowed=True, add_na_share=False,
137
+ add_t_min=False, add_t_max=False, **kwargs):
138
+ """Get a DataFrame with the corresponding data.
139
+
140
+ Parameters
141
+ ----------
142
+ period : TimestampPeriod or (tuple or list of datetime.datetime or None), optional
143
+ The minimum and maximum Timestamp for which to get the timeseries.
144
+ If None is given, the maximum or minimal possible Timestamp is taken.
145
+ The default is (None, None).
146
+ kinds : str or list of str
147
+ The data kind to look for filled period.
148
+ Must be a column in the timeseries DB.
149
+ Must be one of "raw", "qc", "filled", "adj", "filled_by", "best"("corr" for N and "filled" for T and ET).
150
+ If "best" is given, then depending on the parameter of the station the best kind is selected.
151
+ For Precipitation this is "corr" and for the other this is "filled".
152
+ For the precipitation also "qn" and "corr" are valid.
153
+ agg_to : str, optional
154
+ To what aggregation level should the timeseries get aggregated to.
155
+ The minimum aggregation for Temperatur and ET is daily and for the precipitation it is 10 minutes.
156
+ If a smaller aggregation is selected the minimum possible aggregation for the respective parameter is returned.
157
+ So if 10 minutes is selected, than precipitation is returned in 10 minuets and T and ET as daily.
158
+ The default is "10 min".
159
+ nas_allowed : bool, optional
160
+ Should NAs be allowed?
161
+ If True, then the maximum possible period is returned, even if there are NAs in the timeserie.
162
+ If False, then the minimal filled period is returned.
163
+ The default is True.
164
+ paras : list of str or str, optional
165
+ Give the parameters for which to get the meta information.
166
+ Can be "n", "t", "et" or "all".
167
+ If "all", then every available station parameter is returned.
168
+ The default is "all"
169
+ add_na_share : bool, optional
170
+ Should one or several columns be added to the Dataframe with the share of NAs in the data.
171
+ This is especially important, when the stations data get aggregated, because the aggregation doesn't make sense if there are a lot of NAs in the original data.
172
+ If True, one column per asked kind is added with the respective share of NAs, if the aggregation step is not the smallest.
173
+ The "kind"_na_share column is in percentage.
174
+ The default is False.
175
+ add_t_min : bool, optional
176
+ Should the minimal temperature value get added?
177
+ The default is False.
178
+ add_t_max : bool, optional
179
+ Should the maximal temperature value get added?
180
+ The default is False.
181
+
182
+ Returns
183
+ -------
184
+ pd.Dataframe
185
+ A DataFrame with the timeseries for this station and the given period.
186
+ """
187
+ paras = self._check_paras(paras)
188
+
189
+ # download dataframes
190
+ dfs = []
191
+ for stat in self.station_parts:
192
+ if stat._para in paras:
193
+ # check if min and max for temperature should get added
194
+ use_kinds = kinds.copy()
195
+ if stat._para == "t":
196
+ if isinstance(use_kinds, str):
197
+ use_kinds=[use_kinds]
198
+ if "best" in use_kinds:
199
+ use_kinds.insert(use_kinds.index("best"), "filled")
200
+ use_kinds.remove("best")
201
+ for k in ["raw", "filled"]:
202
+ if k in use_kinds:
203
+ if add_t_max:
204
+ use_kinds.insert(
205
+ use_kinds.index(k)+1,
206
+ f"{k}_max")
207
+ if add_t_min:
208
+ use_kinds.insert(
209
+ use_kinds.index(k)+1,
210
+ f"{k}_min")
211
+
212
+ # get the data from station object
213
+ df = stat.get_df(
214
+ period=period,
215
+ kinds=use_kinds,
216
+ agg_to=agg_to,
217
+ nas_allowed=nas_allowed,
218
+ add_na_share=add_na_share,
219
+ **kwargs)
220
+ df = df.rename(dict(zip(
221
+ df.columns,
222
+ [stat._para.upper() + "_" + col for col in df.columns])),
223
+ axis=1)
224
+ dfs.append(df)
225
+
226
+ # concat the dfs
227
+ if len(dfs) > 1:
228
+ df_all = pd.concat(dfs, axis=1)
229
+ elif len(dfs) == 1 :
230
+ df_all = dfs[0]
231
+ else:
232
+ raise ValueError("No timeserie was found for {paras} and Station {stid}".format(
233
+ paras=", ".join(paras),
234
+ stid=self.id))
235
+
236
+ return df_all
237
+
238
+ @classmethod
239
+ def get_meta_explanation(cls, infos="all"):
240
+ """Get the explanations of the available meta fields.
241
+
242
+ Parameters
243
+ ----------
244
+ infos : list or string, optional
245
+ The infos you wish to get an explanation for.
246
+ If "all" then all the available information get returned.
247
+ The default is "all"
248
+
249
+ Returns
250
+ -------
251
+ pd.Series
252
+ a pandas Series with the information names as index and the explanation as values.
253
+ """
254
+ return StationBase.get_meta_explanation(infos=infos)
255
+
256
+ def get_max_period(self, kinds, nas_allowed=False):
257
+ """Get the maximum available period for this stations timeseries.
258
+
259
+ If nas_allowed is True, then the maximum range of the timeserie is returned.
260
+ Else the minimal filled period is returned
261
+
262
+ Parameters
263
+ ----------
264
+ kinds : str or list of str
265
+ The data kinds to update.
266
+ Must be a column in the timeseries DB.
267
+ Must be one of "raw", "qc", "filled", "adj".
268
+ For the precipitation also "qn" and "corr" are valid.
269
+ nas_allowed : bool, optional
270
+ Should NAs be allowed?
271
+ If True, then the maximum possible period is returned, even if there are NAs in the timeserie.
272
+ If False, then the minimal filled period is returned.
273
+ The default is False.
274
+
275
+ Returns
276
+ -------
277
+ utils.TimestampPeriod
278
+ The maximum Timestamp Period
279
+ """
280
+ kinds = self._check_kinds(kinds)
281
+ max_period = None
282
+ for stat in self.station_parts:
283
+ max_period_i = stat.get_max_period(
284
+ kinds=kinds, nas_allowed=nas_allowed)
285
+ if max_period is None:
286
+ max_period = max_period_i
287
+ else:
288
+ max_period = max_period.union(
289
+ max_period_i,
290
+ how="outer" if nas_allowed else "inner")
291
+
292
+ return max_period
293
+
294
+ def get_meta(self, paras="all", **kwargs):
295
+ """Get the meta information for every parameter of this station.
296
+
297
+ Parameters
298
+ ----------
299
+ paras : list of str or str, optional
300
+ Give the parameters for which to get the meta information.
301
+ Can be "n", "t", "et" or "all".
302
+ If "all", then every available station parameter is returned.
303
+ The default is "all"
304
+ **kwargs : dict, optional
305
+ The optional keyword arguments are handed to the single Station get_meta methods. Can be e.g. "info".
306
+
307
+ Returns
308
+ -------
309
+ dict
310
+ dict with the information.
311
+ there is one subdict per parameter.
312
+ If only one parameter is asked for, then there is no subdict, but only a single value.
313
+ """
314
+ paras = self._check_paras(paras)
315
+
316
+ for stat in self.station_parts:
317
+ if stat._para in paras:
318
+ meta_para = stat.get_meta(**kwargs)
319
+ if "meta_all" not in locals():
320
+ meta_all = {stat._para:meta_para}
321
+ else:
322
+ meta_all.update({stat._para:meta_para})
323
+ return meta_all
324
+
325
+ def get_geom(self, crs=None):
326
+ """Get the point geometry of the station.
327
+
328
+ Parameters
329
+ ----------
330
+ crs: str, int or None, optional
331
+ The coordinate reference system of the geometry.
332
+ If None, then the geometry is returned in WGS84 (EPSG:4326).
333
+ If string, then it should be in a pyproj readable format.
334
+ If int, then it should be the EPSG code.
335
+ The default is None.
336
+
337
+ Returns
338
+ -------
339
+ shapely.geometries.Point
340
+ The location of the station as shapely Point in the given coordinate reference system.
341
+ """
342
+ return self.station_parts[0].get_geom(crs=crs)
343
+
344
+ def get_name(self):
345
+ return self.station_parts[0].get_name()
346
+
347
+ def create_roger_ts(self, dir, period=(None, None),
348
+ kind="best", r_r0=1, add_t_min=False, add_t_max=False,
349
+ do_toolbox_format=False,
350
+ **kwargs):
351
+ """Create the timeserie files for roger as csv.
352
+
353
+ This is only a wrapper function for create_ts with some standard settings.
354
+
355
+ Parameters
356
+ ----------
357
+ dir : pathlib like object or zipfile.ZipFile
358
+ The directory or Zipfile to store the timeseries in.
359
+ If a zipfile is given a folder with the statiopns ID is added to the filepath.
360
+ period : TimestampPeriod like object, optional
361
+ The period for which to get the timeseries.
362
+ If (None, None) is entered, then the maximal possible period is computed.
363
+ The default is (None, None)
364
+ kind : str
365
+ The data kind to look for filled period.
366
+ Must be a column in the timeseries DB.
367
+ Must be one of "raw", "qc", "filled", "adj".
368
+ If "best" is given, then depending on the parameter of the station the best kind is selected.
369
+ For Precipitation this is "corr" and for the other this is "filled".
370
+ For the precipitation also "qn" and "corr" are valid.
371
+ r_r0 : int or float, list of int or float or None, optional
372
+ Should the ET timeserie contain a column with R/R0.
373
+ If None, then no column is added.
374
+ If int or float, then a R/R0 column is appended with this number as standard value.
375
+ If list of int or floats, then the list should have the same length as the ET-timeserie and is appanded to the Timeserie.
376
+ If pd.Series, then the index should be a timestamp index. The serie is then joined to the ET timeserie.
377
+ The default is 1.
378
+ add_t_min=False : bool, optional
379
+ Schould the minimal temperature value get added?
380
+ The default is False.
381
+ add_t_max=False : bool, optional
382
+ Schould the maximal temperature value get added?
383
+ The default is False.
384
+ do_toolbox_format : bool, optional
385
+ Should the timeseries be saved in the RoGeR toolbox format? (have a look at the RoGeR examples in https://github.com/Hydrology-IFH/roger)
386
+ The default is False.
387
+ **kwargs:
388
+ additional parameters for Station.get_df
389
+
390
+ Raises
391
+ ------
392
+ Warning
393
+ If there are NAs in the timeseries or the period got changed.
394
+ """
395
+ if do_toolbox_format:
396
+ return self.create_ts(
397
+ dir=dir, period=period, kinds=kind,
398
+ agg_to="10 min", r_r0=r_r0, split_date=True,
399
+ nas_allowed=False,
400
+ add_t_min=add_t_min, add_t_max=add_t_max,
401
+ file_names={"N":"PREC.txt", "T":"TA.txt", "ET":"PET.txt"},
402
+ col_names={"N":"PREC", "ET":"PET",
403
+ "T":"TA", "T_min":"TA_min", "T_max":"TA_max",
404
+ "Jahr":"YYYY", "Monat":"MM", "Tag":"DD",
405
+ "Stunde":"hh", "Minute":"mm"},
406
+ add_meta=False,
407
+ keep_date_parts=True,
408
+ **kwargs)
409
+ else:
410
+ return self.create_ts(
411
+ dir=dir, period=period, kinds=kind,
412
+ agg_to="10 min", r_r0=r_r0, split_date=True,
413
+ nas_allowed=False,
414
+ add_t_min=add_t_min, add_t_max=add_t_max,
415
+ **kwargs)
416
+
417
+ def create_ts(self, dir, period=(None, None),
418
+ kinds="best", paras="all",
419
+ agg_to="10 min", r_r0=None, split_date=False,
420
+ nas_allowed=True, add_na_share=False,
421
+ add_t_min=False, add_t_max=False,
422
+ add_meta=True, file_names={}, col_names={},
423
+ keep_date_parts=False,
424
+ **kwargs):
425
+ """Create the timeserie files as csv.
426
+
427
+ Parameters
428
+ ----------
429
+ dir : pathlib like object or zipfile.ZipFile
430
+ The directory or Zipfile to store the timeseries in.
431
+ If a zipfile is given a folder with the statiopns ID is added to the filepath.
432
+ period : TimestampPeriod like object, optional
433
+ The period for which to get the timeseries.
434
+ If (None, None) is entered, then the maximal possible period is computed.
435
+ The default is (None, None)
436
+ kinds : str or list of str
437
+ The data kinds to look for filled period.
438
+ Must be a column in the timeseries DB.
439
+ Must be one of "raw", "qc", "filled", "adj", "filled_by", "filled_share", "best".
440
+ If "best" is given, then depending on the parameter of the station the best kind is selected.
441
+ For precipitation this is "corr" and for the other this is "filled".
442
+ For the precipitation also "qn" and "corr" are valid.
443
+ If only one kind is asked for, then the columns get renamed to only have the parameter name as column name.
444
+ paras : list of str or str, optional
445
+ Give the parameters for which to get the meta information.
446
+ Can be "n", "t", "et" or "all".
447
+ If "all", then every available station parameter is returned.
448
+ The default is "all"
449
+ agg_to : str, optional
450
+ To what aggregation level should the timeseries get aggregated to.
451
+ The minimum aggregation for Temperatur and ET is daily and for the precipitation it is 10 minutes.
452
+ If a smaller aggregation is selected the minimum possible aggregation for the respective parameter is returned.
453
+ So if 10 minutes is selected, than precipitation is returned in 10 minuets and T and ET as daily.
454
+ The default is "10 min".
455
+ r_r0 : int or float or None or pd.Series or list, optional
456
+ Should the ET timeserie contain a column with R/R0.
457
+ If None, then no column is added.
458
+ If int, then a R/R0 column is appended with this number as standard value.
459
+ If list of int or floats, then the list should have the same length as the ET-timeserie and is appanded to the Timeserie.
460
+ If pd.Series, then the index should be a timestamp index. The serie is then joined to the ET timeserie.
461
+ The default is None.
462
+ split_date : bool, optional
463
+ Should the timestamp get splitted into parts, so one column for year, one for month etc.?
464
+ If False the timestamp is saved in one column as string.
465
+ nas_allowed : bool, optional
466
+ Should NAs be allowed?
467
+ If True, then the maximum possible period is returned, even if there are NAs in the timeserie.
468
+ If False, then the minimal filled period is returned.
469
+ The default is True.
470
+ add_na_share : bool, optional
471
+ Should one or several columns be added to the Dataframe with the share of NAs in the data.
472
+ This is especially important, when the stations data get aggregated, because the aggregation doesn't make sense if there are a lot of NAs in the original data.
473
+ If True, one column per asked kind is added with the respective share of NAs, if the aggregation step is not the smallest.
474
+ The "kind"_na_share column is in percentage.
475
+ The default is False.
476
+ add_t_min=False : bool, optional
477
+ Should the minimal temperature value get added?
478
+ The default is False.
479
+ add_t_max=False : bool, optional
480
+ Should the maximal temperature value get added?
481
+ The default is False.
482
+ add_meta : bool, optional
483
+ Should station Meta information like name and Location (lat, long) be added to the file?
484
+ The default is True.
485
+ file_names : dict, optional
486
+ A dictionary with the file names for the different parameters.
487
+ e.g.{"N":"PREC.txt", "T":"TA.txt", "ET":"ET.txt"}
488
+ If an empty dictionary is given, then the standard names are used.
489
+ The default is {}.
490
+ col_names : dict, optional
491
+ A dictionary with the column names for the different parameters.
492
+ e.g.{"N":"PREC", "T":"TA", "ET":"ET", "Jahr":"YYYY", "Monat":"MM", "Tag":"DD", "Stunde":"HH", "Minute":"MN"}
493
+ If an empty dictionary is given, then the standard names are used.
494
+ The default is {}.
495
+ keep_date_parts : bool, optional
496
+ only used if split_date is True.
497
+ Should the date parts that are not needed, e.g. hour value for daily timeseries, be kept?
498
+ If False, then the columns that are not needed are dropped.
499
+ The default is False.
500
+ **kwargs:
501
+ additional parameters for Station.get_df
502
+
503
+ Raises
504
+ ------
505
+ Warning
506
+ If there are NAs in the timeseries and nas_allowed is False
507
+ or the period got changed.
508
+ """
509
+ # check directory
510
+ dir = self._check_dir(dir)
511
+
512
+ # type cast kinds
513
+ kinds = self._check_kinds(kinds)
514
+ paras = self._check_paras(paras)
515
+
516
+ # get the period
517
+ if not ("_skip_period_check" in kwargs and kwargs["_skip_period_check"]):
518
+ period = TimestampPeriod._check_period(period).expand_to_timestamp()
519
+ period_filled = self.get_filled_period(
520
+ kinds=kinds,
521
+ join_how="outer" if nas_allowed else "inner")
522
+
523
+ if period.is_empty():
524
+ period = period_filled
525
+ else:
526
+ period_new = period_filled.union(
527
+ period,
528
+ how="inner")
529
+ if period_new != period:
530
+ warnings.warn(
531
+ f"The Period for Station {self.id} got changed from {str(period)} to {str(period_new)}.")
532
+ period = period_new
533
+ if "_skip_period_check" in kwargs:
534
+ del kwargs["_skip_period_check"]
535
+
536
+ # prepare loop
537
+ name_suffix = "_{stid:0>5}.txt".format(stid=self.id)
538
+ x, y = self.get_geom().coords.xy
539
+ name = self.get_name() + " (ID: {stid})".format(stid=self.id)
540
+ do_zip = isinstance(dir, zipfile.ZipFile)
541
+
542
+ for para in paras:
543
+ # get the timeserie
544
+ df = self.get_df(
545
+ period=period, kinds=kinds,
546
+ paras=[para], agg_to=agg_to,
547
+ nas_allowed=nas_allowed,
548
+ add_na_share=add_na_share,
549
+ add_t_min=add_t_min, add_t_max=add_t_max,
550
+ _skip_period_check=True,
551
+ **kwargs)
552
+
553
+ # rename columns
554
+ if len(kinds)==1 or ("filled_by" in kinds and len(kinds)==2):
555
+ if len(kinds)==1:
556
+ colname_base = [col for col in df.columns if len(col.split("_"))==2][0]
557
+ else:
558
+ colname_base = f"{para.upper()}_" + kinds[1-(kinds.index("filled_by"))]
559
+ df.rename(
560
+ {colname_base: para.upper(),
561
+ f"{colname_base}_min": f"{para.upper()}_min",
562
+ f"{colname_base}_max": f"{para.upper()}_max",},
563
+ axis=1, inplace=True)
564
+ else:
565
+ df.rename(
566
+ dict(zip(df.columns,
567
+ [col.replace(f"{para}_", f"{para.upper()}_")
568
+ for col in df.columns])),
569
+ axis=1, inplace=True)
570
+
571
+ # check for NAs
572
+ filled_cols = [col for col in df.columns if "filled_by" in col]
573
+ if not nas_allowed and df.drop(filled_cols, axis=1).isna().sum().sum() > 0:
574
+ warnings.warn("There were NAs in the timeserie for Station {stid}.".format(
575
+ stid=self.id))
576
+
577
+ # special operations for et
578
+ if para == "et" and r_r0 is not None:
579
+ if isinstance(r_r0, int) or isinstance(r_r0, float):
580
+ df = df.join(
581
+ pd.Series([r_r0]*len(df), name="R/R0", index=df.index))
582
+ elif isinstance(r_r0, pd.Series):
583
+ df = df.join(r_r0.rename("R_R0"))
584
+ elif isinstance(r_r0, list):
585
+ df = df.join(
586
+ pd.Series(r_r0, name="R/R0", index=df.index))
587
+
588
+ # create tables
589
+ if split_date:
590
+ n_parts = 5 if keep_date_parts else AGG_TO[agg_to]["split"][para]
591
+ df = self._split_date(df.index)\
592
+ .iloc[:, 0:n_parts]\
593
+ .join(df)
594
+ else:
595
+ df.reset_index(inplace=True)
596
+
597
+ # rename columns if user asked for
598
+ df.rename(col_names, axis=1, inplace=True)
599
+
600
+ # create header
601
+ if add_meta:
602
+ header = f"Name: {name}{"\t" * (len(df.columns)-1)}\n" +\
603
+ f"Lat: {y[0]} ,Lon: {x[0]}{"\t" * (len(df.columns)-1)}\n"
604
+ else:
605
+ header = ""
606
+
607
+ # get file name
608
+ if para.upper() in file_names:
609
+ file_name = file_names[para.upper()]
610
+ elif para in file_names:
611
+ file_name = file_names[para]
612
+ else:
613
+ file_name = para.upper() + name_suffix
614
+
615
+ # write table out
616
+ if version.parse(pd.__version__) > version.parse("1.5.0"):
617
+ to_csv_kwargs = dict(lineterminator="\n")
618
+ else:
619
+ to_csv_kwargs = dict(line_terminator="\n")
620
+ str_df = header + df.to_csv(
621
+ sep="\t", decimal=".", index=False, **to_csv_kwargs)
622
+
623
+ if do_zip:
624
+ dir.writestr(f"{self.id}/{file_name}", str_df)
625
+ else:
626
+ with open(dir.joinpath(file_name), "w") as f:
627
+ f.write(str_df)
628
+
629
+ @staticmethod
630
+ def _check_dir(dir):
631
+ """Checks if a directors is valid and empty.
632
+
633
+ If not existing the directory is created.
634
+
635
+ Parameters
636
+ ----------
637
+ dir : pathlib object or zipfile.ZipFile
638
+ The directory to check.
639
+
640
+ Raises
641
+ ------
642
+ ValueError
643
+ If the directory is not empty.
644
+ ValueError
645
+ If the directory is not valid. E.G. it is a file path.
646
+ """
647
+ # check types
648
+ if isinstance(dir, str):
649
+ dir = Path(dir)
650
+
651
+ # check directory
652
+ if isinstance(dir, Path):
653
+ if dir.is_dir():
654
+ if len(list(dir.iterdir())) > 0:
655
+ raise ValueError(
656
+ "The given directory '{dir}' is not empty.".format(
657
+ dir=str(dir)))
658
+ elif dir.suffix == "":
659
+ dir.mkdir()
660
+ else:
661
+ raise ValueError(
662
+ "The given directory '{dir}' is not a directory.".format(
663
+ dir=dir))
664
+ elif not isinstance(dir, zipfile.ZipFile):
665
+ raise ValueError(
666
+ "The given directory '{dir}' is not a directory or zipfile.".format(
667
+ dir=dir))
668
+
669
+ return dir
670
+
671
+ @staticmethod
672
+ def _split_date(dates):
673
+ """
674
+ Split datetime into parts.
675
+
676
+ Parameters
677
+ ----------
678
+ dates : pandas.DatetimeIndex or list of (datetime.dateime or pandas.Timestamp) or
679
+ pandas.DataFrame of (datetime.datetime or pandas.Timestamp)
680
+ The datetime's to split.
681
+
682
+ Returns
683
+ -------
684
+ pandas.DataFrame
685
+ A DataFrame with 5 columns (Jahr, Monat, Tag, Stunde, Minute).
686
+ """
687
+ # if dates is not a list make it a list
688
+ if isinstance(dates, datetime) or isinstance(dates, pd.Timestamp):
689
+ dates = pd.DatetimeIndex([dates])
690
+ index = range(0, len(dates))
691
+
692
+ elif isinstance(dates, pd.DatetimeIndex):
693
+ index = dates
694
+ else:
695
+ index = range(0, len(dates))
696
+
697
+ # check if date is datetime or Timestamp:
698
+ if not (isinstance(dates[0], pd.Timestamp) or
699
+ isinstance(dates[0], datetime)):
700
+ raise ValueError("Error: The given date is not in a datetime or " +
701
+ "Timestamp format.")
702
+
703
+ return pd.DataFrame(
704
+ {"Jahr": dates.year,
705
+ "Monat": dates.month,
706
+ "Tag": dates.day,
707
+ "Stunde": dates.hour,
708
+ "Minute": dates.minute},
709
+ dtype=int,
710
+ index=index)