This repository has been archived by the owner on Jun 1, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 13
/
9_collaborator_data.yml
317 lines (268 loc) · 13.6 KB
/
9_collaborator_data.yml
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
target_default: 9_collaborator_data
packages:
- sf
- tidyverse
- lwgeom
- smoothr
- geojsonio
- geojsonsf
- ggplot2
- reticulate
sources:
- 1_network/src/calc_distance_functions.R
- 1_network/src/geo_fabric_functions.R
- 2_observations/src/data_munge_functions.R
- 9_collaborator_data/src/makerspace_geojson.R
- 9_collaborator_data/src/write_functions.R
- 9_collaborator_data/src/psu_site_selection.R
- 9_collaborator_data/src/subset_sntemp.R
- 9_collaborator_data/src/reservoir_inouts.R
targets:
9_collaborator_data:
depends:
- 9_collaborator_data/mkrsp/delaware_sites_summary.geojson.ind
- 9_collaborator_data/umn/network_subset.rds.ind
- 9_collaborator_data/umn/distance_matrix.rds.ind
- 9_collaborator_data/umn/distance_matrix.npz.ind
- 9_collaborator_data/umn/distance_matrix_subset.npz.ind
- 9_collaborator_data/umn/obs_temp_full.csv.ind
- 9_collaborator_data/umn/obs_temp_subset.csv.ind
- 9_collaborator_data/umn/obs_flow_full.csv.ind
- 9_collaborator_data/umn/obs_flow_subset.csv.ind
#- 9_collaborator_data/psu/highly_observed_sites.csv.ind
#- 9_collaborator_data/psu/highly_observed_map.png
#- 9_collaborator_data/psu/highly_obs_distance_matrix.csv.ind
#- 9_collaborator_data/psu/highly_obs_distance_heatmap.png
#- 9_collaborator_data/psu/sntemp_preds_aggregated.feather.ind
#- 9_collaborator_data/psu/temp_obs_high_obs_sites.csv.ind
#- 9_collaborator_data/psu/flow_obs_high_obs_sites.csv.ind
- 9_collaborator_data/res/res_io_obs.feather
- 9_collaborator_data/res/res_io_sntemp.feather
##### Makerspace #####
# generate file to load for map (http://delaware-basin-test-website.s3-website-us-west-2.amazonaws.com/)
9_collaborator_data/mkrsp/delaware_sites_summary.rds.ind:
command: generate_site_summary(
out_ind = target_name,
dat_ind = '2_observations/out/all_drb_temp_obs.rds.ind',
crosswalk_ind = '2_observations/out/crosswalk_site_reach.rds.ind')
# convert summary to geojson
9_collaborator_data/mkrsp/delaware_sites_summary.geojson.ind:
command: generate_site_geojson(summary_ind = '9_collaborator_data/mkrsp/delaware_sites_summary.rds.ind', out_ind = target_name)
###### University of Minnesota #####
# also should include:
# 1_network/out/network.rds
# 2_observations/out/basin_temp_data.rds
# subset network segments and then distance matrix to only those reaches whose outlets match up with
# SNTemp prediction points, because these are the reaches we'll have SNTemp driver data for, and
# for the purpose of the neural networks, the distance matrix is the only representation of network
# connectivity, so once we have it correct (by doing the network corrections in 1_network)
# we can safely subset to only the sntemp segments and still have a connected network. This effectively
# treats the reaches that were split into 2 reaches as now being 1 reach again (appropriate because
# that's what the inputs from SNTemp into the NN will describe).
9_collaborator_data/umn/sntemp_segs.rds:
command: select_sntemp_subsegs(
network_ind = '1_network/out/network.rds.ind',
out_rds = target_name)
9_collaborator_data/umn/distance_matrix.rds.ind:
command: subset_dist_to_subsegs(
subsegs_rds = '9_collaborator_data/umn/sntemp_segs.rds',
dist_ind = '1_network/out/subseg_distance_matrix.rds.ind',
out_ind = target_name)
# networks and distance matrices
# npy version of distance matrix - this target seems to rebuild a few times if given the chance. huh.
9_collaborator_data/umn/distance_matrix.npz.ind:
command: save_dist_matrices(
dist_mat_ind = '9_collaborator_data/umn/distance_matrix.rds.ind',
out_ind = target_name)
9_collaborator_data/umn/network_subset.rds.ind:
command: make_subnetwork(
out_ind = target_name,
lower_reach = I('2748_1'),
network_ind = '1_network/out/network.rds.ind',
distance_ind = '1_network/out/subseg_distance_matrix.rds.ind',
summary_ind = '9_collaborator_data/mkrsp/delaware_sites_summary.rds.ind')
9_collaborator_data/umn/network_subset_lordville.rds.ind:
command: make_subnetwork(
out_ind = target_name,
lower_reach = I('139_1'),
network_ind = '1_network/out/network.rds.ind',
distance_ind = '1_network/out/subseg_distance_matrix.rds.ind',
summary_ind = '9_collaborator_data/mkrsp/delaware_sites_summary.rds.ind')
# create distance matrix of subset
9_collaborator_data/umn/network_subset_sntemp_segs.rds:
command: select_sntemp_subsegs(
network_ind = '9_collaborator_data/umn/network_subset.rds.ind',
out_rds = target_name)
9_collaborator_data/umn/network_lordville_sntemp_segs.rds:
command: select_sntemp_subsegs(
network_ind = '9_collaborator_data/umn/network_subset_lordville.rds.ind',
out_rds = target_name)
9_collaborator_data/umn/distance_matrix_subset.rds.ind:
command: subset_dist_to_subsegs(
subsegs_rds = '9_collaborator_data/umn/network_subset_sntemp_segs.rds',
dist_ind = '1_network/out/subseg_distance_matrix.rds.ind',
out_ind = target_name)
9_collaborator_data/umn/distance_matrix_lordville.rds.ind:
command: subset_dist_to_subsegs(
subsegs_rds = '9_collaborator_data/umn/network_lordville_sntemp_segs.rds',
dist_ind = '1_network/out/subseg_distance_matrix.rds.ind',
out_ind = target_name)
# npy version of distance matrix_subset
9_collaborator_data/umn/distance_matrix_subset.npz.ind:
command: save_dist_matrices(dist_mat_ind = '9_collaborator_data/umn/distance_matrix_subset.rds.ind', out_ind = target_name)
# temp data
9_collaborator_data/umn/obs_temp_full.csv.ind:
command: write_to_csv(dat_ind = '2_observations/out/obs_temp_drb.rds.ind', out_ind = target_name)
9_collaborator_data/umn/obs_temp_subset.csv.ind:
command: filter_subset(
dat_ind = '2_observations/out/obs_temp_drb.rds.ind',
subnet_ind = '9_collaborator_data/umn/network_subset.rds.ind',
out_ind = target_name)
9_collaborator_data/umn/obs_temp_subset_lordville.csv.ind:
command: filter_subset(
dat_ind = '2_observations/out/obs_temp_drb.rds.ind',
subnet_ind = '9_collaborator_data/umn/network_subset_lordville.rds.ind',
out_ind = target_name)
# flow_data
9_collaborator_data/umn/obs_flow_full.csv.ind:
command: write_to_csv(dat_ind = '2_observations/out/obs_flow_drb.rds.ind', out_ind = target_name)
9_collaborator_data/umn/obs_flow_subset.csv.ind:
command: filter_subset(
dat_ind = '2_observations/out/obs_flow_drb.rds.ind',
subnet_ind = '9_collaborator_data/umn/network_subset.rds.ind',
out_ind = target_name)
9_collaborator_data/umn/obs_temp_subset.zarr.tar.ind:
command: write_zarr_tarfile(dat_ind = '9_collaborator_data/umn/obs_temp_subset.csv.ind', out_ind = target_name)
depends: '9_collaborator_data/src/write_functions_py.py'
9_collaborator_data/umn/obs_temp_full.zarr.tar.ind:
command: write_zarr_tarfile(dat_ind = '9_collaborator_data/umn/obs_temp_full.csv.ind', out_ind = target_name)
depends: '9_collaborator_data/src/write_functions_py.py'
9_collaborator_data/umn/obs_flow_subset.zarr.tar.ind:
command: write_zarr_tarfile(dat_ind = '9_collaborator_data/umn/obs_flow_subset.csv.ind', out_ind = target_name)
depends: '9_collaborator_data/src/write_functions_py.py'
9_collaborator_data/umn/obs_flow_full.zarr.tar.ind:
command: write_zarr_tarfile(dat_ind = '9_collaborator_data/umn/obs_flow_full.csv.ind', out_ind = target_name)
depends: '9_collaborator_data/src/write_functions_py.py'
9_collaborator_data/umn/uncal_sntemp_input_output.zarr.tar.ind:
command: write_zarr_tarfile(dat_ind = '3_predictions/out/uncal_sntemp_input_output.feather.ind', out_ind = target_name)
depends: '9_collaborator_data/src/write_functions_py.py'
9_collaborator_data/umn/obs_flow_subset_lordville.csv.ind:
command: filter_subset(
dat_ind = '2_observations/out/obs_flow_drb.rds.ind',
subnet_ind = '9_collaborator_data/umn/network_subset_lordville.rds.ind',
out_ind = target_name)
# reservoir metadata
9_collaborator_data/umn/reservoir_features.csv.ind:
command: get_res_features(dat_ind = '1_network/out/subseg_reservoir_mapping.rds.ind', out_ind = target_name)
#### Penn State ####
9_collaborator_data/psu/highly_observed_sites.rds:
command: filter_sites(
out_file = target_name,
dat_ind = '2_observations/out/obs_temp_drb.rds.ind',
geo_dat = I('1_network/in/GeospatialFabric_National.gdb'),
years = I(2),
obs_per_year = I(150),
min_drainage = I(100),
max_drainage = I(10000))
9_collaborator_data/psu/highly_observed_sites.csv.ind:
command: write_sites(dat = '9_collaborator_data/psu/highly_observed_sites.rds', out_ind = target_name)
9_collaborator_data/psu/highly_observed_map.png:
command: map_highly_obs(
out_file = target_name,
cross_ind = '2_observations/out/crosswalk_site_reach.rds.ind',
network_ind = '1_network/out/network.rds.ind',
dat = '9_collaborator_data/psu/highly_observed_sites.rds',
title = I('Sites with >=2 years with >150 obs'))
9_collaborator_data/psu/highly_obs_distance_matrix.rds.ind:
command: subset_dist_to_subsegs(
subsegs_rds = '9_collaborator_data/psu/highly_observed_sites.rds',
dist_ind = '1_network/out/subseg_distance_matrix.rds.ind',
out_ind = target_name)
# this target builds a few times for some reason
9_collaborator_data/psu/highly_obs_distance_matrix.csv.ind:
command: write_distance(
out_ind = target_name,
dat_ind = '9_collaborator_data/psu/highly_obs_distance_matrix.rds.ind',
dist_type = I('updown'))
9_collaborator_data/psu/highly_obs_distance_heatmap.png:
command: dist_heatmap2(
out_file = target_name,
dist_ind = '9_collaborator_data/psu/highly_obs_distance_matrix.rds.ind',
dist_type = I('updown'),
labels = I('subseg_id'),
title = I('Full Network - Upstream & Downstream'))
9_collaborator_data/psu/prms_azrh.csv:
command: download.file(
destfile = target_name,
url = I('https://raw.githubusercontent.com/nhm-params-v10-usgs/nhmparamdb_v10_CONUS/434d5da5c4f5a1184d4bd07839322ab1bcb4c3c5/azrh.csv'))
9_collaborator_data/psu/high_obs_upstream_sites.csv:
command: get_upstream_sites(
out_file = target_name,
dist_ind = '1_network/out/subseg_distance_matrix.rds.ind',
network_ind = '1_network/out/network.rds.ind',
sites = '9_collaborator_data/psu/highly_observed_sites.rds',
azrh_file = '9_collaborator_data/psu/prms_azrh.csv',
geo_dat = I('1_network/in/GeospatialFabric_National.gdb'))
9_collaborator_data/psu/sntemp_preds_high_obs_sites.feather:
command: subset_sntemp_preds(
out_file = target_name,
sub_net_file = '9_collaborator_data/psu/high_obs_upstream_sites.csv',
full_data_ind = '3_predictions/in/uncal_sntemp_input_output.feather.ind')
9_collaborator_data/psu/sntemp_preds_aggregated.feather.ind:
command: aggregate_sntemp_preds(
ind_file = target_name,
sub_net_file ='9_collaborator_data/psu/high_obs_upstream_sites.csv',
subset_data_file = '9_collaborator_data/psu/sntemp_preds_high_obs_sites.feather')
9_collaborator_data/psu/temp_obs_high_obs_sites.csv.ind:
command: filter_obs(
dat_ind = '2_observations/out/obs_temp_drb.rds.ind',
subset = '9_collaborator_data/psu/highly_observed_sites.rds',
out_ind = target_name)
9_collaborator_data/psu/flow_obs_high_obs_sites.csv.ind:
command: filter_obs(
dat_ind = '2_observations/out/obs_flow_drb.rds.ind',
subset = '9_collaborator_data/psu/highly_observed_sites.rds',
out_ind = target_name)
# data for Amy McHugh and Jon Janowicz
9_collaborator_data/usgs/sntemp_pred_obs_subset.csv:
command: filter_sntemp_obs(
sntemp_ind = '3_predictions/in/uncal_sntemp_input_output.feather.ind',
flow_ind = '2_observations/out/obs_flow_drb.rds.ind',
temp_ind = '2_observations/out/obs_temp_drb.rds.ind',
network_ind = '1_network/out/network.rds.ind',
out_file = target_name)
#### Reservoirs ####
# Hand-code the IDs at the outflows of the reservoirs of interest.
# The two Pepacton sites are both along the same outflow route, but
# one site is really close to the reservoir (01417000), and the
# other is a little downstream (01417500). They differ in data
# availability (see 9_collaborator_data/res/pep_io_*.png, created
# as a side effect of building 9_collaborator_data/res/res_io_obs.feather),
# but those plots show that 01417000 is pretty good since 1980, so we
# actually just drop 01417500 and go with 01417000 in res_io_obs.feather.
res_outflow_ids:
command: list(
Cannonsville = I('01425000'),
Pepacton = I(c('01417000', '01417500')))
# Find sites with lots of flow and/or temp data on inflows to each reservoir.
# This algorithm uses NLDI and hence currently only locates NWIS sites, overlooking
# any other relevant sites in WQP
res_inflow_ids:
command: find_inout_obs_sites(
res_outflow_ids = res_outflow_ids,
flow_ind = '2_observations/in/daily_flow.rds.ind',
temp_ind = '2_observations/out/all_drb_temp_obs.rds.ind',
min_obs_flow = I(1000),
min_obs_temp = I(50),
max_dist_km = I(100))
9_collaborator_data/res/res_io_obs.feather.ind:
command: get_inout_obs_all(
target_name,
res_inflow_ids,
res_outflow_ids,
flow_ind = '2_observations/in/daily_flow.rds.ind',
temp_ind = '2_observations/out/all_drb_temp_obs.rds.ind')
9_collaborator_data/res/res_io_sntemp.feather.ind:
command: get_inout_sntemp_all(
out_ind = target_name,
sntemp_ind = '3_predictions/out/uncal_sntemp_input_output.feather.ind')