Newer
Older
Data manager for PermaSense data. Initially created for the paper "A decade of detailed observations (2008--2018) in steep
bedrock permafrost at Matterhorn Hoernligrat (Zermatt, CH)"
Script to perform the experiments
Copyright (c) 201, Swiss Federal Institute of Technology (ETH Zurich)
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
* Neither the name of the copyright holder nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
@author: Samuel Weber, Jan Beutel and Matthias Meyer
usage: manage_GSNdata.py [-h] [--gsn2raw GSN2RAW] [--load LOAD]
[--filter FILTER] [--clean CLEAN]
[--aggregationInterval AGGREGATIONINTERVAL]
[--export2csv EXPORT2CSV]
[--sanityPlot SANITYPLOT] [--gsn2img GSN2IMG]
[--nImg NIMG] [-p PATH] [-y1 YEARBEGIN]
[-m1 MONTHBEGIN] [-d1 DAYBEGIN] [-y2 YEAREND]
[-m2 MONTHEND] [-d2 DAYEND]
optional arguments:
-h, --help show this help message and exit
--gsn2raw GSN2RAW Get raw data from GSN and store locally (step1,
default: True)
--load LOAD Load locally stored data (step2, default: True)
--filter FILTER Filter data (according reference values, step3,
default: True)
--clean CLEAN Clean data manually (step4, default: True)
Aggregate data over timewindows of X minutes (step5,
default: 60)
--export2csv EXPORT2CSV
Export data in yearly csv files (step6, default: True)
--sanityPlot SANITYPLOT
Plot for sanity check (step7, default: True)
--gsn2img GSN2IMG Downlod images from GSN and convert NEF to JPEG
(default: True)
--nImg NIMG Number of images to download and convert (default: 10)
-p PATH, --path PATH Relative path for the data output (default: ./data)
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
'''
def main():
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
## SETUP PYTHON ENVIRONMENT
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
# Load functions
import sys
import socket
import argparse
import os as os
import numpy as np
import pandas as pd
import datetime as dt
import matplotlib as mpl
# For proper plotting on server
if socket.gethostname() == 'tik43x':
mpl.use('Agg')
import matplotlib.pyplot as plt
# faster plotting
import matplotlib.style as mplstyle
mplstyle.use('fast')
# remove matplotlib warning
from pandas.plotting import register_matplotlib_converters
register_matplotlib_converters()
# Load functions in relative path
sys.path.append('~/permasense/')
from permasense.GSNdata import get_GSNdata, save_data, load_data, filter_data, clean_data, get_GSNimg
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
## ASSIGN ARGUMENTS TO VARIABLES
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
args = parseArguments()
# Define path to data
PATH_DATA = args.path
# Define time range
TBEG = dt.datetime(args.yearBegin,args.monthBegin,args.dayBegin)
TEND = dt.datetime(args.yearEnd,args.monthEnd,args.dayEnd)
# Get raw data from GSN (step1) and produce derived data product (step2 - step7)
GSN2RAW = args.gsn2raw
LOAD = args.load
FILTER = args.filter
CLEAN = args.clean
AGGREGATION_INTERVAL = args.aggregationInterval
EXPORT2CSV = args.export2csv
SANITY_PLOT = args.sanityPlot
if FILTER | CLEAN | EXPORT2CSV | SANITY_PLOT:
LOAD = True
# Get high-resolution images (.NEF) and convert to .JPG
GSN2IMG = args.gsn2img
N_IMG = args.nImg
KEEP_NEF = False
# max number of images to download
DOWNLOAD_LIMIT = 30000
#DOWNLOAD_MAX_SIZE = 20000
DOWNLOAD_MAX_SIZE = 1000000
RESIZE = False
#resize_w, resize_h = 356, 536
RESIZE_WIDTH = 712
RESIZE_HEIGHT = 1072
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
## DICTIONARIES ASSIGNING 'VIRTUAL_SENSOR' TO 'POSITION'
## ## ## ## ## ## ## ## ## ## ## 'resistivity_fracture', ## ## ## ## ## ## ## ## ## ## ## ## ## ##
DEPO_VS = {
# 'AD01': {'displacement', 'temperature_rock'}, #OK
# 'AD02': {'displacement'}, #OK
# 'AD03': {'displacement'}, #OK
# 'AD04': {'displacement', 'temperature_rock'}, #OK
# 'AD05': {'displacement'}, #OK
# 'AD06': {'displacement', 'temperature_rock'}, #OK
# 'AD07': {'temperature_rock'}, #OK
# 'AD08': {'temperature_rock'}, #OK
# 'AD09': {'temperature_rock'}, #OK
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
# 'DH00': {'RD01': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, # OK
# 'DH05': {'DI55': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, # OK
# 'DH06': {'RA01': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #000deg, OK
# 'DH07': {'DI57': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, # OK
# 'DH09': {'RA02': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #000deg, OK
# 'DH12': {'BH03': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, # OK
# 'DH15': {'DI02': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #225/131/281/246deg, OK
# 'DH17': {'DI07': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #105/277/321/334deg, OK
# 'DH21': {'LS01': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #110deg, OK
# 'DH23': {'LS04': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #225deg, OK
# 'DH25': {'BH07': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #240deg, OK
# 'DH27': {'BH09': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #130deg, OK
# 'DH29': {'ST02': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #004deg, OK
# 'DH31': {'ST05': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #124deg, OK
# 'DH33': {'GU02': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #335deg, OK
# 'DH35': {'GU03': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #010deg, OK
# 'DH39': {'RG01': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, # OK
# 'DH41': {'GG52': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, # OK
# 'DH43': {'GG01': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #325deg, OK
# 'DH44': {'GG02': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #205/041deg OK
# 'DH55': {'BH10': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #280/270/294/312deg OK
# 'DH56': {'RL01': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #309deg OK
# 'DH57': {'GU04': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #014deg, OK
# 'DH62': {'BH12': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #140deg, OK
# 'DH63': {'BH13': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #090/000deg, OK
# 'DH64': {'LS05': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #318/330deg, OK
# 'DH66': {'GG66': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, #, OK
# 'DH67': {'GG67': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, #, OK
# 'DH70': {'RA03': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #000deg, OK
# 'DH81': {'RAND': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, #, OK
# 'DH82': {'WYS1': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #170deg, OK
# 'DH83': {'LS11': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #262deg, OK
# 'DH84': {'LS12': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #006deg, OK
# 'DH86': {'DI03': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #000deg, OK
# 'DH87': {'DI04': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #000deg, OK
# 'DH88': {'LS06': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #000deg, OK
# #'DH89': {'SA01': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #000deg
# #'DH91': {'SATT': {'gps_differential__batch__daily','gps_differential__rtklib__daily'}}, #
# 'DH13': {'DH13': {'vaisalawxt520prec', 'vaisalawxt520windpth'}}, #
# 'DH42': {'DH42': {'vaisalawxt520prec', 'vaisalawxt520windpth'}}, #
# 'DH68': {'DH68': {'vaisalawxt520prec', 'vaisalawxt520windpth'}}, #
# 'DH69': {'DH69': {'vaisalawxt520prec', 'vaisalawxt520windpth'}}, #
# 'DH73': {'DH73': {'radiometer__conv'}}, #
# 'PE01': {'DIS1': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'PE02': {'DIS2': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'PE03': {'RIT1': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'PE04': {'GRU1': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'PE05': {'JAE1': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'PE06': {'SCH1': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'PE07': {'MUA1': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'PE08': {'LAR1': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'PE09': {'LAR2': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'PE10': {'COR1': {'gps_differential__batch__daily','gps_differential__rtklib__daily','gps_inclinometer'}}, #, OK
# 'JJ01': {'resistivity_rock', 'temperature_rock'}, #OK
# 'JJ02': {'resistivity_rock', 'temperature_rock'}, #OK
# 'JJ03': {'resistivity_rock', 'temperature_rock'}, #OK
# 'JJ04': {'resistivity_rock', 'temperature_rock'}, #OK
# 'JJ05': {'resistivity_rock', 'temperature_rock'}, #OK
# 'JJ06': {'resistivity_rock', 'temperature_rock'}, #OK
# 'JJ07': {'resistivity_rock', 'temperature_rock'}, #OK
# 'JJ08': {'temperature_fracture'}, #OK
# 'JJ09': {'resistivity_rock', 'temperature_rock'}, #OK
# 'JJ10': {'temperature_fracture'}, #OK
# 'JJ13': {'temperature_rock'}, #
# 'JJ14': {'temperature_rock'}, #
# 'JJ18': {'temperature_rock'}, #
# 'JJ22': {'temperature_rock'}, #
# 'JJ25': {'temperature_rock'}, #
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
'MH01': {'MH01': {'displacement', 'temperature_fracture', 'temperature_rock'}}, #ok
'MH02': {'MH02': {'displacement', 'temperature_fracture', 'temperature_rock'}}, #ok
'MH03': {'MH03': {'displacement', 'temperature_fracture', 'temperature_rock'}}, #ok
'MH04': {'MH04': {'displacement', 'temperature_fracture', 'temperature_rock'}}, #ok
'MH05': {'MH05': {'resistivity_fracture', 'temperature_fracture'}}, #ok but resistivity
'MH06': {'MH06': {'displacement', 'temperature_rock'}}, #ok
'MH07': {'MH07': {'resistivity_fracture', 'temperature_fracture'}}, #ok but resistivity
'MH08': {'MH08': {'displacement', 'temperature_rock'}}, #ok
'MH09': {'MH09': {'displacement', 'temperature_fracture'}}, #ok
'MH10': {'MH10': {'resistivity_rock', 'temperature_rock'}}, #ok but resistivity
'MH11': {'MH11': {'resistivity_rock', 'temperature_rock'}}, #ok but resistivity_rock
'MH12': {'MH12': {'resistivity_rock', 'temperature_rock'}}, #ok but resistivity
'MH18': {'MH18': {'displacement'}}, #ok
'MH20': {'MH20': {'displacement'}}, #ok
'MH21': {'MH21': {'displacement'}}, #ok
'MH22': {'MH22': {'displacement'}}, #ok
'MH27': {'MH27': {'temperature_rock'}}, #ok
'MH30': {'MH30': {'temperature_rock'}}, #ok
'MH46': {'MH46': {'temperature_rock'}}, #ok
'MH47': {'MH47': {'temperature_rock'}}, #ok
'MH15': {'MH15': {'radiometer__conv'}}, #ok
'MH25': {'MH25': {'vaisalawxt520prec', 'vaisalawxt520windpth'}}, #ok
'MH33': {'MH33': {'gps_differential__batch__daily', 'gps_differential__rtklib__daily', 'gps_inclinometer'}}, #ok
'MH34': {'MH34': {'gps_differential__batch__daily', 'gps_differential__rtklib__daily', 'gps_inclinometer'}}, #ok
'MH35': {'MH35': {'gps_differential__batch__daily', 'gps_differential__rtklib__daily', 'gps_inclinometer'}}, #ok
'MH40': {'MH40': {'gps_differential__batch__daily', 'gps_differential__rtklib__daily'}}, #ok
'MH42': {'MH42': {'gps_differential__batch__daily', 'gps_differential__rtklib__daily'}}, #ok
'MH43': {'MH43': {'gps_differential__batch__daily', 'gps_differential__rtklib__daily'}},
}
DEPO_GPS = ['MH33', 'MH34', 'MH35', 'MH40', 'MH42', 'MH43']
DEPO_IMG = {
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
}
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
## Create PATH_DATA if it does not exist yet
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
os.makedirs(PATH_DATA, exist_ok=True)
os.makedirs(PATH_DATA + '/gnss_data_raw', exist_ok=True)
os.makedirs(PATH_DATA + '/gnss_derived_data_products', exist_ok=True)
os.makedirs(PATH_DATA + '/timelapse_images', exist_ok=True)
os.makedirs(PATH_DATA + '/timeseries_data_raw', exist_ok=True)
os.makedirs(PATH_DATA + '/timeseries_derived_data_products', exist_ok=True)
os.makedirs(PATH_DATA + '/timeseries_sanity_plots', exist_ok=True)
os.makedirs(PATH_DATA + '/timeseries_sanity_plots/' + 'channelwise', exist_ok=True)
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
## GSN timeseries data
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
# Loop through keys (depo) in dictionary DEPO_VS
for depo, depo_line in DEPO_VS.items():
print(depo)
print(depo_line)
for label in depo_line:
print('Working on data of label {:s} and depo {:s}.'.format(label, depo))
if depo[0:2] == 'JJ':
deployment = 'jungfraujoch'
elif depo[0:2] == 'AD':
deployment = 'adm'
elif depo[0:2] == 'MH':
deployment = 'matterhorn'
elif depo[0:2] == 'DH':
deployment = 'dirruhorn'
elif depo[0:2] == 'PE':
deployment = 'permos'
position = int(depo[2:4])
#print(depo)
#print(deployment)
#print(label)
#print("\n")
# Loop through values for a given key of dictionary DEPO_VS
#print(sorted(list(DEPO_VS[depo])))
#for vsensor in sorted(list(DEPO_VS[depo])):
for vsensor in sorted(list(depo_line[label])):
print(label, depo, deployment, vsensor, position)
# Step 1: Query data from GSN server and save it locally
if GSN2RAW:
print('Data from position {:s} and virtual sensor {:s} is imported (gsn query) as pd.DataFrame and stored as csv-file.'.format(depo,vsensor))
print('Time interval: ',TBEG, ' to ', TEND)
df = get_GSNdata(deployment, position, vsensor, TBEG, TEND, download_max_size = DOWNLOAD_MAX_SIZE)
if len(df) > 1:
print('Saving raw data')
#debug dtypes
#df.info(verbose=True)
#print(df)
if vsensor == 'gps_differential__batch__daily':
save_data(df, PATH_DATA + '/gnss_data_raw/', label, vsensor, deployment, file_type='csv')
save_data(df, PATH_DATA + '/gnss_data_raw/', label, vsensor, deployment, yearly=True, iso=True, file_type='csv')
elif vsensor == 'gps_differential__rtklib__daily':
save_data(df, PATH_DATA + '/gnss_data_raw/', label, vsensor, deployment, file_type='csv')
save_data(df, PATH_DATA + '/gnss_data_raw/', label, vsensor, deployment, yearly=True, iso=True, file_type='csv')
else:
save_data(df, PATH_DATA + '/timeseries_data_raw/', label, vsensor, deployment, file_type='csv')
save_data(df, PATH_DATA + '/timeseries_data_raw/', label, vsensor, deployment, yearly=True, iso=True, file_type='csv')
#debug dtypes
#df.info(verbose=True)
#print(df.describe())
#print(df)
print()
# Loop through values for a given key of dictionary DEPO_VS but without GPS
DEPO_VS_but_DEPO_GPS = list(vs for vs in sorted(list(depo_line[label])) if vs != 'gps_differential__batch__daily')
#print(DEPO_VS_but_DEPO_GPS)
#DEPO_VS_but_DEPO_GPS = list(vs for vs in sorted(list(DEPO_VS_but_DEPO_GPS)) if vs != 'gps_differential__rtklib__daily')
#print(DEPO_VS_but_DEPO_GPS)
#print(sorted(list(DEPO_VS[depo])))
#for vsensor in sorted(list(DEPO_VS[depo])):
for vsensor in DEPO_VS_but_DEPO_GPS:
#print(vsensor)
df={}
#print(df)
# Step 2: Load data
if LOAD:
print('Loading data', label, depo, deployment, vsensor)
#debug dtypes
#df.info(verbose=True)
if vsensor == 'gps_differential__batch__daily':
df = load_data(PATH_DATA + '/gnss_data_raw/', label, vsensor, file_type='csv')
df_raw = df.copy()
elif vsensor == 'gps_differential__rtklib__daily':
df = load_data(PATH_DATA + '/gnss_data_raw/', label, vsensor, file_type='csv')
df_raw = df.copy()
else:
df = load_data(PATH_DATA + '/timeseries_data_raw/', label, vsensor, file_type='csv')
df_raw = df.copy()
# Step 3 (optional): Filter data (according to reference values)
if FILTER:
print('Filtering data', label, depo, deployment, vsensor)
#debug dtypes
#df.info(verbose=True)
df = filter_data(df, depo)
df_filt = df.copy()
# Step 4 (optional): Clean data manually
if CLEAN:
print('Cleaning data', label, depo, deployment, vsensor)
try:
df = clean_data(df, depo, vsensor)
except Exception as i:
print('An issue with data cleaning raised - please check the data', i)
pass
df_filt_clean = df.copy()
# Step 5 (optional): Aggregate data
if AGGREGATION_INTERVAL > 0:
print('Aggregating data', label, depo, deployment, vsensor)
try:
if vsensor == 'vaisalawxt520prec':
f = {'position':'mean', 'device_id':'mean', 'rain_accumulation':'sum', 'rain_duration':'sum', 'rain_intensity':'mean', 'rain_peak_intensity':'max', 'hail_accumulation':'sum', 'hail_duration':'sum', 'hail_intensity':'mean', 'hail_peak_intensity':'mean'}
df = df.groupby(pd.Grouper(freq=str(AGGREGATION_INTERVAL) + 'Min')).agg(f)
elif vsensor == 'vaisalawxt520windpth':
f = {'position':'mean', 'device_id':'mean', 'wind_direction_minimum':'min', 'wind_direction_average':'mean', 'wind_direction_maximum':'max', 'wind_speed_minimum':'min', 'wind_speed_average':'mean', 'wind_speed_maximum':'max', 'temp_air':'mean', 'temp_internal':'mean', 'relative_humidity':'mean', 'air_pressure':'mean'}
df = df.groupby(pd.Grouper(freq=str(AGGREGATION_INTERVAL) + 'Min')).agg(f)
elif vsensor == 'gps_differential__batch__daily':
print('Copying GPS data, no aggregation.')
# df = df
elif vsensor == 'gps_differential__rtklib__daily':
print('Copying GPS data, no aggregation.')
# df = df
else:
df = df.groupby(pd.Grouper(freq=str(AGGREGATION_INTERVAL) + 'Min')).aggregate(np.mean)
#df = df.groupby(pd.TimeGrouper(freq=str(AGGREGATION_INTERVAL) + 'Min')).aggregate(np.median)
except:
print('There was an issue with time aggregation')
pass
df_agg = df.copy()
#df_agg.info(verbose=True)
#print(df_agg)
#df.info(verbose=True)
#print(df)
# Step 6: Export to csv
if EXPORT2CSV:
print('Exporting data', label, depo, deployment, vsensor)
for col in ['position', 'device_id', 'ref1', 'ref2', 'ref3', 'ref4', 'ref5', 'ref6']:
try:
df_csv = df.drop([col], axis=1, inplace=False)
except:
pass
try:
if vsensor == 'gps_differential__batch__daily':
save_data(df_csv, PATH_DATA + '/gnss_derived_data_products/', label, vsensor, deployment, yearly=True, iso=True, file_type='csv', float_format=4)
elif vsensor == 'gps_differential__rtklib__daily':
save_data(df_csv, PATH_DATA + '/gnss_derived_data_products/', label, vsensor, deployment, yearly=True, iso=True, file_type='csv', float_format=4)
else:
save_data(df_csv, PATH_DATA + '/timeseries_derived_data_products/', label, vsensor, deployment, yearly=True, iso=True, file_type='csv', float_format=4)
except:
pass
# Step 7: Plot for sanity check
if SANITY_PLOT:
print('Plotting data', label, depo, deployment, vsensor)
for i, col in enumerate(df_agg):
if col not in ['device_id', 'device_type', 'position', 'label', 'ref1', 'ref2', 'ref3', 'ref4', 'ref5', 'ref6', 'sd_e', 'sd_n', 'sd_h', 'version', 'reference_label', 'processing_time', 'ratio_of_fixed_ambiguities']:
#print(col)
#plt.figure(figsize=(24/2.54, 18/2.54), facecolor='w', edgecolor='k')
plt.figure(figsize=(40/2.54, 18/2.54), facecolor='w', edgecolor='k')
plt.plot(df_raw[col][~df_raw[col].isnull()] , color='C0')
plt.plot(df_filt[col], color='C1')
plt.plot(df_filt_clean[col], color='C2')
plt.plot(df_agg[col], color='C3')
plt.title(' Label: {:s} \n Deployment: {:s} \n Position: {:s} \n VSENSOR: {:s}\n VARIABLE: {:s}'.format(label, deployment,depo,vsensor,col), loc='left')
diff = df_agg[col].max() - df_agg[col].min()
try:
plt.ylim([df_agg[col].min() - diff/10, df_agg[col].max() + diff/10])
except:
pass
plt.legend(['raw','+ filtered', '+ cleaned', '+ aggregated'], loc="upper left")
##print(mpl.rcParams['agg.path.chunksize'])
mpl.rcParams['agg.path.chunksize'] = 10000
plt.savefig('{:s}/timeseries_sanity_plots/channelwise/{:s}_{:s}_{:s}.png'.format(PATH_DATA , label, vsensor, col), dpi=200)
# plt.close('all')
mpl.rcParams['agg.path.chunksize'] = 0
#plt.figure(figsize=(24/2.54, 18/2.54), facecolor='w', edgecolor='k')
fig = plt.figure(figsize=(40/2.54, 18/2.54), facecolor='w', edgecolor='k')
plt.subplots_adjust(left=0.05, right=0.95, bottom=0.05, top=0.85) # left=0.125, right=0.9, bottom=0.1, top=0.9, wspace=0.2, hspace=0.2
for i, col in enumerate(df_agg):
if col not in ['device_id', 'device_type', 'position', 'label', 'ref1', 'ref2', 'ref3', 'ref4', 'ref5', 'ref6', 'sd_e', 'sd_n', 'sd_h', 'version', 'reference_label', 'processing_time', 'ratio_of_fixed_ambiguities']:
#print(df_agg[col])
if ~df_agg[col].isnull().all():
plt.plot(df_agg[col], label=col)
#print(p1)
#print(col)
plt.title(' Label: {:s} \n Deployment: {:s} \n Position: {:s} \n VSENSOR: {:s}\n All channels'.format(label,deployment,depo,vsensor), loc='left')
# any legend location is too slow
# #plt.legend()
plt.legend(loc="upper left")
if deployment == 'matterhorn':
plt.xlim([TBEG, TEND])
#plt.tight_layout()
#if fig.get_axes(): # Do stuff when the figure isn't empty.
plt.savefig('{:s}/timeseries_sanity_plots/{:s}_{:s}_all.png'.format(PATH_DATA , label, vsensor), dpi=300)
# plt.close('all')
print()
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
## GSN images
## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ## ##
print(GSN2IMG)
if GSN2IMG:
# Loop through keys (depo) in dictionary DEPO_IMG
for depo in DEPO_IMG:
if depo[0:2] == 'MH':
deployment = 'matterhorn'
position = int(depo[2:4])
# Loop through values for a given key of dictionary DEPO_IMG
for vsensor in list(DEPO_IMG[depo]):
print(deployment, position, vsensor, TBEG, TEND)
df = get_GSNimg(PATH_DATA + '/timelapse_images/', deployment, position, vsensor, TBEG, TEND, n_img = N_IMG, keep_nef = KEEP_NEF, download_limit = DOWNLOAD_LIMIT, download_max_size = DOWNLOAD_MAX_SIZE, resize = RESIZE, resize_w = RESIZE_WIDTH, resize_h = RESIZE_HEIGHT)
def parseArguments():
import argparse
import datetime as dt
def true_or_false(arg):
ua = str(arg).upper()
if 'TRUE'.startswith(ua):
return True
elif 'FALSE'.startswith(ua):
return False
else:
pass #error condition maybe?
# Create argument parser
parser = argparse.ArgumentParser()
# Positional (mandatory) arguments
#parser.add_argument("positionalArgument1", help="Positional argument 1", type=float)
# Optional arguments
parser.add_argument("--gsn2raw", help="Get raw data from GSN and store locally (step1, default: %(default)s)", type=true_or_false, default=True)
parser.add_argument("--load", help="Load locally stored data (step2, default: %(default)s)", type=true_or_false, default=True)
parser.add_argument("--filter", help="Filter data (according reference values, step3, default: %(default)s)", type=true_or_false, default=True)
parser.add_argument("--clean", help="Clean data manually (step4, default: %(default)s)", type=true_or_false, default=True)
parser.add_argument("--aggregationInterval", help="Aggregate data over timewindows of X minutes (step5, default: %(default)s)", type=int, default=60)
parser.add_argument("--export2csv", help="Export data in yearly csv files (step6, default: %(default)s)", type=true_or_false, default=True)
parser.add_argument("--sanityPlot", help="Plot for sanity check (step7, default: %(default)s)", type=true_or_false, default=True)
parser.add_argument("--gsn2img", help="Downlod images from GSN and convert NEF to JPEG (default: %(default)s)", type=true_or_false, default=True)
parser.add_argument("--nImg", help="Number of images to download and convert (default: %(default)s)", type=int, default=10)
parser.add_argument("-p", "--path", help="Relative path for the data output (default: %(default)s)", type=str, default='./data')
parser.add_argument("-y1", "--yearBegin", help="Year begin (default: %(default)s)", type=int, default=2008)
parser.add_argument("-m1", "--monthBegin", help="Month begin (default: %(default)s)", type=int, default=1)
parser.add_argument("-d1", "--dayBegin", help="Day begin (default: %(default)s)", type=int, default=1)
parser.add_argument("-y2", "--yearEnd", help="Year end (default: today)", type=int, default=dt.datetime.now().year)
parser.add_argument("-m2", "--monthEnd", help="Month end (default: today)", type=int, default=dt.datetime.now().month)
parser.add_argument("-d2", "--dayEnd", help="Day end (default: today)", type=int, default=dt.datetime.now().day)