| 1 |
#!/usr/bin/env python |
|---|
| 2 |
# Last modified: Time-stamp: <2008-02-15 10:51:00 jcleary> |
|---|
| 3 |
""" |
|---|
| 4 |
how to parse data, and assert what data and info goes into |
|---|
| 5 |
creating and updating monthly netcdf files |
|---|
| 6 |
|
|---|
| 7 |
Texas Weather Instruments - Weather Processing System (WPS) met data |
|---|
| 8 |
delimited ASCII file like: |
|---|
| 9 |
year mon day hhmm epoch tmean hmean wsmean wdmean barom dewPt wchill rrmean rday rmonth rterm |
|---|
| 10 |
|
|---|
| 11 |
parser : output delimited ASCII file from onsite perl script |
|---|
| 12 |
creator : lat, lon, time, air_temp, humidity, wspd, wdir, air_pressure, |
|---|
| 13 |
dew_temp, wchill, rainfall_rate, rainfall_day, rainfall_month, rainfall_term |
|---|
| 14 |
updater : time, air_temp, humidity, wspd, wdir, air_pressure, |
|---|
| 15 |
dew_temp, wchill, rainfall_rate, rainfall_day, rainfall_month, rainfall_term |
|---|
| 16 |
|
|---|
| 17 |
Examples |
|---|
| 18 |
-------- |
|---|
| 19 |
|
|---|
| 20 |
>> (parse, create, update) = load_processors('proc_jpier_ascii_met') |
|---|
| 21 |
or |
|---|
| 22 |
>> si = get_config(cn+'.sensor_info') |
|---|
| 23 |
>> (parse, create, update) = load_processors(si['met']['proc_module']) |
|---|
| 24 |
|
|---|
| 25 |
>> lines = load_data(filename) |
|---|
| 26 |
>> data = parse(platform_info, sensor_info, lines) |
|---|
| 27 |
>> create(platform_info, sensor_info, data) or |
|---|
| 28 |
>> update(platform_info, sensor_info, data) |
|---|
| 29 |
|
|---|
| 30 |
""" |
|---|
| 31 |
|
|---|
| 32 |
from raw2proc import * |
|---|
| 33 |
from procutil import * |
|---|
| 34 |
from ncutil import * |
|---|
| 35 |
import time |
|---|
| 36 |
|
|---|
| 37 |
now_dt = datetime.utcnow() |
|---|
| 38 |
now_dt.replace(microsecond=0) |
|---|
| 39 |
|
|---|
| 40 |
def parser(platform_info, sensor_info, lines): |
|---|
| 41 |
""" |
|---|
| 42 |
parse and assign met data from JPIER TWS WPS text file |
|---|
| 43 |
|
|---|
| 44 |
""" |
|---|
| 45 |
|
|---|
| 46 |
i = 0 |
|---|
| 47 |
|
|---|
| 48 |
# drop header row from incoming lines list |
|---|
| 49 |
if lines[0].startswith('year',0,5): |
|---|
| 50 |
print "... Header row present, skipping ..." |
|---|
| 51 |
del lines[0] |
|---|
| 52 |
|
|---|
| 53 |
|
|---|
| 54 |
# sort file by fields 0-5 |
|---|
| 55 |
lines.sort() |
|---|
| 56 |
|
|---|
| 57 |
|
|---|
| 58 |
for line in lines: |
|---|
| 59 |
# split line and parse float and integers |
|---|
| 60 |
tws = [] |
|---|
| 61 |
# data row looks like: |
|---|
| 62 |
# 2008 1 1 0000 1199163600 17.2 84.8 0.00 0 1015.10 14.4 17.2 1729.1 0.0 0.0 1031.5 |
|---|
| 63 |
|
|---|
| 64 |
sw = re.split('\s+', line) |
|---|
| 65 |
for s in sw: |
|---|
| 66 |
m = re.search(REAL_RE_STR, s) |
|---|
| 67 |
if m: |
|---|
| 68 |
tws.append(float(m.groups()[0])) |
|---|
| 69 |
# assign specific fields |
|---|
| 70 |
n = len(tws) |
|---|
| 71 |
|
|---|
| 72 |
# get sample datetime in UTC from data |
|---|
| 73 |
# use epoch tws[4] to get time in UTC |
|---|
| 74 |
sample_str = '%04d-%02d-%02d %02d:%02d:00' % tuple(time.gmtime(float(tws[4]))[0:5]) |
|---|
| 75 |
sample_dt = scanf_datetime(sample_str, fmt='%Y-%m-%d %H:%M:%S') |
|---|
| 76 |
|
|---|
| 77 |
air_temp = tws[5] # Air Temperature (deg F) |
|---|
| 78 |
humidity = tws[6] # Humidity (%) |
|---|
| 79 |
dew_temp = tws[10] # Dew Point (deg F) |
|---|
| 80 |
air_pressure = tws[9] # Air Pressure (Tmean, sec) |
|---|
| 81 |
wspd = tws[7] # Mean Wind Speed (knots) |
|---|
| 82 |
wdir = tws[8] # Mean Wind Direction (deg from N) |
|---|
| 83 |
wchill = tws[11] # Wind Chill (deg F) |
|---|
| 84 |
rainfall_rate = tws[12] # Rainfall Rate () |
|---|
| 85 |
rainfall_day = tws[13] # Rainfall amount last 24 hours (in) |
|---|
| 86 |
rainfall_month = tws[14] # Rainfall amount last month (in) |
|---|
| 87 |
rainfall_term = tws[15] # Rainfall amount since installation (in) |
|---|
| 88 |
|
|---|
| 89 |
# set up dict of data if first line |
|---|
| 90 |
if i==0: |
|---|
| 91 |
data = { |
|---|
| 92 |
'dt' : numpy.array(numpy.ones((len(lines),), dtype=object)*numpy.nan), |
|---|
| 93 |
'time' : numpy.array(numpy.ones((len(lines),), dtype=long)*numpy.nan), |
|---|
| 94 |
'air_temp' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 95 |
'humidity' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 96 |
'dew_temp' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 97 |
'air_pressure' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 98 |
'wspd' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 99 |
'wdir' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 100 |
'wchill' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 101 |
'rainfall_rate' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 102 |
'rainfall_day' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 103 |
'rainfall_month' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 104 |
'rainfall_term' : numpy.array(numpy.ones((len(lines)), dtype=float)*numpy.nan), |
|---|
| 105 |
} |
|---|
| 106 |
|
|---|
| 107 |
data['dt'][i] = sample_dt # sample datetime |
|---|
| 108 |
data['time'][i] = dt2es(sample_dt) # sample time in epoch seconds |
|---|
| 109 |
data['air_temp'][i] = air_temp |
|---|
| 110 |
data['humidity'][i] = humidity |
|---|
| 111 |
data['dew_temp'][i] = dew_temp |
|---|
| 112 |
data['air_pressure'][i] = air_pressure |
|---|
| 113 |
data['wspd'][i] = wspd |
|---|
| 114 |
data['wdir'][i] = wdir |
|---|
| 115 |
data['wchill'][i] = wchill |
|---|
| 116 |
data['rainfall_rate'][i] = rainfall_rate |
|---|
| 117 |
data['rainfall_day'][i] = rainfall_day |
|---|
| 118 |
data['rainfall_month'][i] = rainfall_month |
|---|
| 119 |
data['rainfall_term'][i] = rainfall_term |
|---|
| 120 |
i = i+1 |
|---|
| 121 |
|
|---|
| 122 |
return data |
|---|
| 123 |
|
|---|
| 124 |
def creator(platform_info, sensor_info, data): |
|---|
| 125 |
# |
|---|
| 126 |
# |
|---|
| 127 |
title_str = sensor_info['description']+' at '+ platform_info['location'] |
|---|
| 128 |
global_atts = { |
|---|
| 129 |
'title' : title_str, |
|---|
| 130 |
'institution' : 'Unversity of North Carolina at Chapel Hill (UNC-CH)', |
|---|
| 131 |
'institution_url' : 'http://nccoos.org', |
|---|
| 132 |
'institution_dods_url' : 'http://nccoos.org', |
|---|
| 133 |
'metadata_url' : 'http://nccoos.org', |
|---|
| 134 |
'references' : 'http://nccoos.org', |
|---|
| 135 |
'contact' : 'Jesse Cleary (jcleary@email.unc.edu)', |
|---|
| 136 |
# |
|---|
| 137 |
'source' : 'TWS Met station observation', |
|---|
| 138 |
'history' : 'raw2proc using ' + sensor_info['process_module'], |
|---|
| 139 |
'comment' : 'File created using pycdf'+pycdfVersion()+' and numpy '+pycdfArrayPkg(), |
|---|
| 140 |
# conventions |
|---|
| 141 |
'Conventions' : 'CF-1.0; SEACOOS-CDL-v2.0', |
|---|
| 142 |
# SEACOOS CDL codes |
|---|
| 143 |
'format_category_code' : 'fixed-point', |
|---|
| 144 |
'institution_code' : platform_info['institution'], |
|---|
| 145 |
'platform_code' : platform_info['id'], |
|---|
| 146 |
'package_code' : sensor_info['id'], |
|---|
| 147 |
# institution specific |
|---|
| 148 |
'project' : 'North Carolina Coastal Ocean Observing System (NCCOOS)', |
|---|
| 149 |
'project_url' : 'http://nccoos.org', |
|---|
| 150 |
# timeframe of data contained in file yyyy-mm-dd HH:MM:SS |
|---|
| 151 |
'start_date' : data['dt'][0].strftime("%Y-%m-%d %H:%M:%S"), |
|---|
| 152 |
'end_date' : data['dt'][-1].strftime("%Y-%m-%d %H:%M:%S"), |
|---|
| 153 |
'release_date' : now_dt.strftime("%Y-%m-%d %H:%M:%S"), |
|---|
| 154 |
# |
|---|
| 155 |
'creation_date' : now_dt.strftime("%Y-%m-%d %H:%M:%S"), |
|---|
| 156 |
'modification_date' : now_dt.strftime("%Y-%m-%d %H:%M:%S"), |
|---|
| 157 |
'process_level' : 'level1', |
|---|
| 158 |
# |
|---|
| 159 |
# must type match to data (e.g. fillvalue is real if data is real) |
|---|
| 160 |
'_FillValue' : -99999., |
|---|
| 161 |
} |
|---|
| 162 |
|
|---|
| 163 |
var_atts = { |
|---|
| 164 |
# coordinate variables |
|---|
| 165 |
'time' : {'short_name': 'time', |
|---|
| 166 |
'long_name': 'Sample Time', |
|---|
| 167 |
'standard_name': 'time', |
|---|
| 168 |
'units': 'seconds since 1970-1-1 00:00:00 -0', # UTC |
|---|
| 169 |
'axis': 'T', |
|---|
| 170 |
}, |
|---|
| 171 |
'lat' : {'short_name': 'lat', |
|---|
| 172 |
'long_name': 'Latitude in Decimal Degrees', |
|---|
| 173 |
'standard_name': 'latitude', |
|---|
| 174 |
'reference':'geographic coordinates', |
|---|
| 175 |
'units': 'degrees_north', |
|---|
| 176 |
'valid_range':(-90.,90.), |
|---|
| 177 |
'axis': 'Y', |
|---|
| 178 |
}, |
|---|
| 179 |
'lon' : {'short_name': 'lon', |
|---|
| 180 |
'long_name': 'Longtitude in Decimal Degrees', |
|---|
| 181 |
'standard_name': 'longtitude', |
|---|
| 182 |
'reference':'geographic coordinates', |
|---|
| 183 |
'units': 'degrees_east', |
|---|
| 184 |
'valid_range':(-180.,180.), |
|---|
| 185 |
'axis': 'Y', |
|---|
| 186 |
}, |
|---|
| 187 |
'z' : {'short_name': 'z', |
|---|
| 188 |
'long_name': 'Height', |
|---|
| 189 |
'standard_name': 'height', |
|---|
| 190 |
'reference':'zero at sea-surface', |
|---|
| 191 |
'positive': 'up', |
|---|
| 192 |
'units': 'm', |
|---|
| 193 |
'axis': 'Z', |
|---|
| 194 |
}, |
|---|
| 195 |
# data variables |
|---|
| 196 |
|
|---|
| 197 |
'air_temp' : {'short_name': 'air_temp', |
|---|
| 198 |
'long_name': 'Air Temperature', |
|---|
| 199 |
'standard_name': 'air_temperature', |
|---|
| 200 |
'units': 'degrees Celsius', |
|---|
| 201 |
}, |
|---|
| 202 |
'humidity' : {'short_name': 'humidity', |
|---|
| 203 |
'long_name': 'Humidity', |
|---|
| 204 |
'standard_name': 'humidity', |
|---|
| 205 |
'units': '%', |
|---|
| 206 |
}, |
|---|
| 207 |
'dew_temp' : {'short_name': 'dew_temp', |
|---|
| 208 |
'long_name': 'Dew Temperature', |
|---|
| 209 |
'standard_name': 'dew_temp', |
|---|
| 210 |
'units': 'degrees Celsius', |
|---|
| 211 |
}, |
|---|
| 212 |
'air_pressure' : {'short_name': 'air_pressure', |
|---|
| 213 |
'long_name': 'Air Pressure at Barometer Height', |
|---|
| 214 |
'standard_name': 'air_pressure', |
|---|
| 215 |
'units': 'hPa', |
|---|
| 216 |
}, |
|---|
| 217 |
'wspd' : {'short_name': 'wspd', |
|---|
| 218 |
'long_name': 'Wind Speed', |
|---|
| 219 |
'standard_name': 'wind_speed', |
|---|
| 220 |
'units': 'm s-1', |
|---|
| 221 |
'can_be_normalized': '?', |
|---|
| 222 |
}, |
|---|
| 223 |
'wdir' : {'short_name': 'wdir', |
|---|
| 224 |
'long_name': 'Wind Direction from', |
|---|
| 225 |
'standard_name': 'wind_from_direction', |
|---|
| 226 |
'reference': 'clockwise from True North', |
|---|
| 227 |
'valid_range': '0., 360', |
|---|
| 228 |
'units': 'degrees', |
|---|
| 229 |
}, |
|---|
| 230 |
'wchill' : {'short_name': 'wchill', |
|---|
| 231 |
'long_name': 'Wind Chill', |
|---|
| 232 |
'standard_name': 'wind_chill', |
|---|
| 233 |
'units': 'degrees Celsius', |
|---|
| 234 |
}, |
|---|
| 235 |
'rainfall_rate' : {'short_name': 'rR', |
|---|
| 236 |
'long_name': 'Rainfall Rate', |
|---|
| 237 |
'standard_name': 'rainfall_rate', |
|---|
| 238 |
'units': 'mm hr-1', |
|---|
| 239 |
}, |
|---|
| 240 |
'rainfall_day' : {'short_name': 'rD', |
|---|
| 241 |
'long_name': 'Rainfall Day', |
|---|
| 242 |
'standard_name': 'rainfall_day', |
|---|
| 243 |
'units': 'mm', |
|---|
| 244 |
}, |
|---|
| 245 |
'rainfall_month' : {'short_name': 'rM', |
|---|
| 246 |
'long_name': 'Rainfall Month', |
|---|
| 247 |
'standard_name': 'rainfall_month', |
|---|
| 248 |
'units': 'mm', |
|---|
| 249 |
}, |
|---|
| 250 |
'rainfall_term' : {'short_name': 'rT', |
|---|
| 251 |
'long_name': 'Rainfall Term', |
|---|
| 252 |
'standard_name': 'rainfall_term', |
|---|
| 253 |
'units': 'mm', |
|---|
| 254 |
}, |
|---|
| 255 |
} |
|---|
| 256 |
# integer values |
|---|
| 257 |
ntime=NC.UNLIMITED |
|---|
| 258 |
nlat=1 |
|---|
| 259 |
nlon=1 |
|---|
| 260 |
nz=1 |
|---|
| 261 |
|
|---|
| 262 |
# dimension names use tuple so order of initialization is maintained |
|---|
| 263 |
dim_inits = ( |
|---|
| 264 |
('ntime', NC.UNLIMITED), |
|---|
| 265 |
('nlat', 1), |
|---|
| 266 |
('nlon', 1), |
|---|
| 267 |
('nz', 1) |
|---|
| 268 |
) |
|---|
| 269 |
|
|---|
| 270 |
# using tuple of tuples so order of initialization is maintained |
|---|
| 271 |
# using dict for attributes order of init not important |
|---|
| 272 |
# use dimension names not values |
|---|
| 273 |
# (varName, varType, (dimName1, [dimName2], ...)) |
|---|
| 274 |
var_inits = ( |
|---|
| 275 |
# coordinate variables |
|---|
| 276 |
('time', NC.INT, ('ntime',)), |
|---|
| 277 |
('lat', NC.FLOAT, ('nlat',)), |
|---|
| 278 |
('lon', NC.FLOAT, ('nlon',)), |
|---|
| 279 |
('z', NC.FLOAT, ('nz',)), |
|---|
| 280 |
# data variables |
|---|
| 281 |
('air_temp', NC.FLOAT, ('ntime',)), |
|---|
| 282 |
('humidity', NC.FLOAT, ('ntime',)), |
|---|
| 283 |
('dew_temp', NC.FLOAT, ('ntime',)), |
|---|
| 284 |
('air_pressure', NC.FLOAT, ('ntime',)), |
|---|
| 285 |
('wspd', NC.FLOAT, ('ntime',)), |
|---|
| 286 |
('wdir', NC.FLOAT, ('ntime',)), |
|---|
| 287 |
('wchill', NC.FLOAT, ('ntime',)), |
|---|
| 288 |
('rainfall_rate', NC.FLOAT, ('ntime',)), |
|---|
| 289 |
('rainfall_day', NC.FLOAT, ('ntime',)), |
|---|
| 290 |
('rainfall_month', NC.FLOAT, ('ntime',)), |
|---|
| 291 |
('rainfall_term', NC.FLOAT, ('ntime',)), |
|---|
| 292 |
) |
|---|
| 293 |
|
|---|
| 294 |
# subset data only to month being processed (see raw2proc.process()) |
|---|
| 295 |
i = data['in'] |
|---|
| 296 |
|
|---|
| 297 |
# var data |
|---|
| 298 |
var_data = ( |
|---|
| 299 |
('lat', platform_info['lat']), |
|---|
| 300 |
('lon', platform_info['lon']), |
|---|
| 301 |
('z', 6), |
|---|
| 302 |
# |
|---|
| 303 |
('time', data['time'][i]), |
|---|
| 304 |
('air_temp', data['air_temp'][i]), |
|---|
| 305 |
('humidity', data['humidity'][i]), |
|---|
| 306 |
('dew_temp', data['dew_temp'][i]), |
|---|
| 307 |
('air_pressure', data['air_pressure'][i]), |
|---|
| 308 |
('wspd', data['wspd'][i]), |
|---|
| 309 |
('wdir', data['wdir'][i]), |
|---|
| 310 |
('wchill', data['wchill'][i]), |
|---|
| 311 |
('rainfall_rate', data['rainfall_rate'][i]), |
|---|
| 312 |
('rainfall_day', data['rainfall_day'][i]), |
|---|
| 313 |
('rainfall_month', data['rainfall_month'][i]), |
|---|
| 314 |
('rainfall_term', data['rainfall_term'][i]), |
|---|
| 315 |
) |
|---|
| 316 |
|
|---|
| 317 |
return (global_atts, var_atts, dim_inits, var_inits, var_data) |
|---|
| 318 |
|
|---|
| 319 |
def updater(platform_info, sensor_info, data): |
|---|
| 320 |
# |
|---|
| 321 |
global_atts = { |
|---|
| 322 |
# update times of data contained in file (yyyy-mm-dd HH:MM:SS) |
|---|
| 323 |
# last date in monthly file |
|---|
| 324 |
'end_date' : data['dt'][-1].strftime("%Y-%m-%d %H:%M:%S"), |
|---|
| 325 |
'release_date' : now_dt.strftime("%Y-%m-%d %H:%M:%S"), |
|---|
| 326 |
# |
|---|
| 327 |
'modification_date' : now_dt.strftime("%Y-%m-%d %H:%M:%S"), |
|---|
| 328 |
} |
|---|
| 329 |
|
|---|
| 330 |
# data variables |
|---|
| 331 |
# update any variable attributes like range, min, max |
|---|
| 332 |
var_atts = {} |
|---|
| 333 |
# var_atts = { |
|---|
| 334 |
# 'u': {'max': max(data.u), |
|---|
| 335 |
# 'min': min(data.v), |
|---|
| 336 |
# }, |
|---|
| 337 |
# 'v': {'max': max(data.u), |
|---|
| 338 |
# 'min': min(data.v), |
|---|
| 339 |
# }, |
|---|
| 340 |
# } |
|---|
| 341 |
|
|---|
| 342 |
# subset data only to month being processed (see raw2proc.process()) |
|---|
| 343 |
i = data['in'] |
|---|
| 344 |
|
|---|
| 345 |
# data |
|---|
| 346 |
var_data = ( |
|---|
| 347 |
('time', data['time'][i]), |
|---|
| 348 |
('air_temp', data['air_temp'][i]), |
|---|
| 349 |
('humidity', data['humidity'][i]), |
|---|
| 350 |
('dew_temp', data['dew_temp'][i]), |
|---|
| 351 |
('air_pressure', data['air_pressure'][i]), |
|---|
| 352 |
('wspd', data['wspd'][i]), |
|---|
| 353 |
('wdir', data['wdir'][i]), |
|---|
| 354 |
('wchill', data['wchill'][i]), |
|---|
| 355 |
('rainfall_rate', data['rainfall_rate'][i]), |
|---|
| 356 |
('rainfall_day', data['rainfall_day'][i]), |
|---|
| 357 |
('rainfall_month', data['rainfall_month'][i]), |
|---|
| 358 |
('rainfall_term', data['rainfall_term'][i]), |
|---|
| 359 |
) |
|---|
| 360 |
|
|---|
| 361 |
return (global_atts, var_atts, var_data) |
|---|
| 362 |
|
|---|
| 363 |
# |
|---|
