-
Notifications
You must be signed in to change notification settings - Fork 0
/
untitled0.py
252 lines (214 loc) · 8.66 KB
/
untitled0.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
# -*- coding: utf-8 -*-
"""
@author: bav@geus.dk
tip list:
%matplotlib inline
%matplotlib qt
import pdb; pdb.set_trace()
"""
import matplotlib.pyplot as plt
import pandas as pd
import os
import matplotlib
matplotlib.use('Agg')
import tocgen
new_version = 'aws-l3-dev'
old_version = 'V19'
if old_version == 'aws-l3':
path_old = '../aws-l3/level_3/'
else:
path_old = 'C:/Users/bav/Downloads/'+old_version+'/hour/'
if 'thredds' in new_version:
path_new = 'C:/Users/bav/GitHub/PROMICE data/thredds-dev/level_3_sites/'
df_meta = pd.read_csv(path_new+'../AWS_latest_locations.csv')
df_meta2 = pd.read_csv(path_new+'../AWS_stations_metadata.csv')
elif 'dev' in new_version:
path_new = 'C:/Users/bav/GitHub/PROMICE data/aws-l3-dev/stations/'
df_meta = pd.read_csv(path_new+'../AWS_latest_locations.csv')
df_meta2 = pd.read_csv(path_new+'../AWS_stations_metadata.csv')
else:
path_new = '../aws-l3/'
df_meta = pd.read_csv(path_new+'/AWS_latest_locations.csv')
df_meta2 = pd.read_csv(path_new+'/AWS_metadata.csv')
path_new = '../aws-l3/level_3/'
# path_new = 'C:/Users/bav/Downloads/V15/hour/'
# path_new = 'https://thredds.geus.dk/thredds/fileServer/aws_l3_station_csv/level_3/'
# path_new = 'https://thredds.geus.dk/thredds/fileServer/aws_l3_time_csv/level_3/hour/'
# path_new = 'https://thredds.geus.dk/thredds/dodsC/aws_l3_time_netcdf/level_3/hour/'
from datetime import date
today = date.today().strftime("%Y%m%d")
filename = 'plot_compilations/'+old_version+'_versus_'+new_version+'.md' #'_'+today+'.md'
figure_folder='figures/'+old_version+'_versus_'+new_version #+'_'+today
try:
os.mkdir(figure_folder)
except:
pass
f = open(filename, "w")
def Msg(txt):
f = open(filename, "a")
print(txt)
f.write(txt + "\n")
Msg('# Comparison of data '+new_version+' to '+old_version+' (old).')
plt.close('all')
#%%
import toml
import xarray as xr
import numpy as np
for station in ['CP1']: #
# for station in np.unique(pd.concat((df_meta.stid,df_meta2.station_id))):
Msg('## '+station)
# if path_new == 'aws-l3-dev':
# config_path = '../aws-l0/metadata/station_configurations/'+station+'.toml'
# with open(config_path, 'r') as file:
# data = toml.load(file) # Load the TOML file
# station_save=station
# station = data.get("station_site") # Get the station site
file = path_new+station+'_hour.csv'
try:
df_new = pd.read_csv(file, index_col=0, parse_dates=True)
except:
file = path_new+station+'/'+station+'_hour.csv'
if os.path.isfile(file):
df_new = pd.read_csv(file, index_col=0, parse_dates=True)
else:
Msg('No new file for this station')
continue
# df_new = pd.read_csv('../aws-l3/'+station+'_hour.csv', index_col=0, parse_dates=True)
# df_new = pd.read_csv(
# 'https://thredds.geus.dk/thredds/fileServer/aws_l3_station_csv/level_3/'+station+'/'+station+'_hour.csv',
# index_col=0, parse_dates=True)
# if not os.path.isfile(path_old+'/'+station+'_hour.csv'):
# Msg(path_old+'/'+station+'_hour.csv cannot be found in old data')
# continue
# if path_l3 == 'aws-l3-dev':
# station = station_save
df_old = pd.DataFrame()
df_old['time'] = df_new.index.values
file = path_old+station+'/'+station+'_hour.csv'
if not os.path.isfile(file):
file = path_old+station+'_hour.csv'
if not os.path.isfile(file):
Msg('cannot find old file for '+station)
if os.path.isfile(file):
print(file)
df_old = pd.read_csv(file)
df_old.time = pd.to_datetime(df_old.time, utc=True)
df_old = df_old.set_index('time')
Msg('Variables in new file:\n'+ ', '.join(df_new.columns.values))
Msg('\nNew variables not in old files:\n'+ ', '.join(
[v for v in df_new.columns if v not in df_old.columns]
))
Msg('\nOld variables removed from new files:\n'+ ', '.join(
[v for v in df_old.columns if v not in df_new.columns]
))
Msg(' ')
var_list = df_new.columns.values
var_list_list = [var_list[i:i+5] for i in range(0, len(var_list), 5)]
# var_list_list = [
# ['gps_lat','gps_lon','gps_alt'],
# ['dlr','ulr','t_rad'],
# ['dsr','usr'],
# ['rh_u','rh_l','rh_u_cor','rh_l_cor']
# ]
for k, var_list in enumerate(var_list_list):
fig, ax_list = plt.subplots(len(var_list),1,sharex=True, figsize=(13,13))
if len(var_list)==1:
ax_list = [ax_list]
for var, ax in zip(var_list, ax_list):
ax.set_ylabel(var)
try:
ax.plot(df_old[var].index, df_old[var].values,
marker='^',linestyle='None', label=old_version,
alpha=0.7, color='tab:blue')
except:
print(var,'not in old data')
ax.plot(df_new[var].index, df_new[var].values,
marker='.',markeredgecolor='None', linestyle='None',
label=new_version, alpha=0.7,
color='tab:orange')
ax.legend()
ax.grid()
plt.suptitle('%s %i/%i'%(station, k+1, len(var_list_list)))
fig.savefig(figure_folder+'/%s_%i.png'%(station,k), dpi =120)
Msg('![%s](../%s/%s_%i.png)'%(station, figure_folder, station,k))
Msg(' ')
tocgen.processFile(filename, filename[:-3]+"_toc.md")
f.close()
# os.remove(filename)
# os.rename(filename[:-3]+"_toc.md", filename)
# if __name__ == '__main__':
# main()
# %% scatter version
figure_folder='figures/'+old_version+'_versus_'+new_version +'_scatter'
filename = 'plot_compilations/'+old_version+'_versus_'+new_version+'_scatter.md' #'_'+today+'.md'
try:
os.mkdir(figure_folder)
except:
pass
f = open(filename, "w")
def Msg(txt):
f = open(filename, "a")
print(txt)
f.write(txt + "\n")
import xarray as xr
import numpy as np
for station in [station]: #
# for station in np.unique(pd.concat((df_meta.stid,df_meta2.station_id))):
Msg('## '+station)
file = path_new+station+'_hour.csv'
try:
df_new = pd.read_csv(file, index_col=0, parse_dates=True)
except:
file = path_new+station+'/'+station+'_hour.csv'
if os.path.isfile(file):
df_new = pd.read_csv(file, index_col=0, parse_dates=True)
else:
Msg('No new file for this station')
continue
try:
file = path_old+station+'/'+station+'_hour.csv'
df_old = pd.read_csv(file)
except:
file = path_old+station+'_hour.csv'
if os.path.isfile(file):
df_old = pd.read_csv(file, index_col=0, parse_dates=True)
else:
Msg('No old file for this station')
continue
Msg('Variables in new file:\n'+ ', '.join(df_new.columns.values))
Msg('\nNew variables not in old files:\n'+ ', '.join(
[v for v in df_new.columns if v not in df_old.columns]
))
Msg('\nOld variables removed from new files:\n'+ ', '.join(
[v for v in df_old.columns if v not in df_new.columns]
))
Msg(' ')
var_list = df_new.columns.intersection(df_old.columns)
var_list = [v for v in var_list if df_new[v].notnull().any() and df_old[v].notnull().any()]
var_list_list = [var_list[i:i+9] for i in range(0, len(var_list), 9)]
# var_list_list = [['gps_lat','gps_lon','gps_alt'],
# ['dlr','ulr','t_rad'],
# ['rh_u','rh_l','rh_u_cor','rh_l_cor']]
for k, var_list in enumerate(var_list_list):
fig, ax_list = plt.subplots(3,3, figsize=(15,15))
ax_list = ax_list.flatten()
if len(var_list)==1:
fig, ax_list = plt.subplots(1,1, figsize=(15,15))
ax_list = [ax_list]
for var, ax in zip(var_list, ax_list):
ax.set_xlabel(var +' old')
ax.set_ylabel(var +' new')
try:
msk = df_old[var].index.intersection(df_new[var].index)
ax.plot(df_old.loc[msk, var].values, df_new.loc[msk,var].values,
marker='.',markeredgecolor='None', linestyle='None',
label='_nolegend_', alpha=0.7, c='k')
except:
print('error',var)
ax.grid()
plt.suptitle('%s %i/%i'%(station, k+1, len(var_list_list)))
fig.savefig(figure_folder+'/%s_%i.png'%(station,k), dpi =120)
Msg('![%s](../%s/%s_%i.png)'%(station, figure_folder, station,k))
Msg(' ')
tocgen.processFile(filename, filename[:-3]+"_toc.md")
f.close()