def load_obs(self, forecast_hour=6, madis=True, variance=False):
"""
Loads the observations corresponding with n hours after ensemble was
initialized (default 6 hours). Returns the observations from the text file.
-Loads MADIS observations if madis=True, loads gridded observations if False.
-If variance == True, loads gridded observations which also contain
ensemble variance at the ob location.
-Gridded and MADIS observations must be generated/obtained before calling this function.
Returns a list of observations.
"""
dty, dtm, dtd, dth = ef.dt_str_timedelta(self.date,forecast_hour)
ob_str = ef.var_string([self.ob_type])
# directory where the observations are
if madis==True:
obs_file = '/home/disk/hot/stangen/Documents/surface_obs/MADIS/'+dty+dtm+'/combined_'+self.ob_type+'/'+self.ob_type+'_'+dty+dtm+dtd+'_'+dth+'00.txt'
elif madis==False:
if self.new_format == False:
obs_file = '/home/disk/hot/stangen/Documents/gridded_obs/'+self.ens_type+'/'+dty+dtm+'/'+self.ob_type+'/'+self.ob_type+'_'+dty+dtm+dtd+'_'+dth+'00'
elif self.new_format == True:
obs_file = '/home/disk/hot/stangen/Documents/gridded_obs/'+self.ens_type+'/'+dty+dtm+'/'+self.ob_type+'/'+dty+dtm+dtd+'_'+dth+'00_'+str(self.l)+'_'+str(self.r)+'_'+str(self.t)+'_'+str(self.b)+'_'+str(self.s)
if variance==True:
obs_file += '_variance'
obs_file += '.txt'
print('loading '+ob_str+' obs from '+dty+dtm+dtd+'_'+dth+'00')
f1 = open(obs_file, 'r')
obs = f1.readlines()
return obs
def load_ens_netcdf(self, forecast_hour=0):
"""
Loads the ensemble from n forecast hours after the forecast was
initialized and uses its 0-hour forecast as the "observation" grid.
Returns the variable of interest and the lats/lons.
The filepath loads non-EFA'd netCDF files (it loads the prior).
var is nlats x nlons x nmems. (at time t=0)
lats, lons are 1-d float arrays (masked).
"""
dty, dtm, dtd, dth = ef.dt_str_timedelta(self.date,forecast_hour)
print('loading analysis grid: '+self.ens_type+' '+dty+dtm+dtd+'_'+dth+'00')
if self.new_format == False:
infile = '/home/disk/hot/stangen/Documents/prior_ensembles/'+self.ens_type+'/'+dty+dtm+'/'+dty+'-'+dtm+'-'+dtd+'_'+dth+'_'+self.ens_type+'_'+self.var_string+'.nc'
elif self.new_format == True:
infile = '/home/disk/hot/stangen/Documents/prior_ensembles/'+self.ens_type+'/'+dty+dtm+'/'+dty+'-'+dtm+'-'+dtd+'_'+dth+'_'+self.efh+'_'+self.var_string+'.nc'
ncdata = Dataset(infile,'r')
#gridded ensemble 0-hour forecasts n forecast hours after the ensemble
#we are updating was initialized
var = ncdata.variables[self.ob_type][0,:,:,:]
lats = ncdata.variables['lat'][:]
lons = ncdata.variables['lon'][:]
return var, lats, lons
#dictionaries for plotting
obtype_dict = {'madis': 'Metar & Maritime', 'gridded': 'Gridded'}
var_dict = {
'T2M': '2-Meter Temperature',
'ALT': 'Altimeter',
'IWV': 'Integrated Water Vapor',
'IVT': 'Integrated Vapor Transport'
}
var_unit = {'T2M': '(K)', 'ALT': 'hPa', 'IWV': 'mm', 'IVT': 'kg/m/s'}
save_dir = '/home/disk/hot/stangen/Documents/EFA/duplicate_madaus/plots/'
#get date strings from datetime object for accessing file
y, m, d, h = ef.dt_str_timedelta(date)
dstr = y + m + d
time = h + '00'
#Open MADIS text data file
#f = open('/home/disk/hot/stangen/Documents/EFA/duplicate_madaus/plots/2013040106obs_allmaritime.txt','r')
if ob_type == 'madis':
f = open(
"/home/disk/hot/stangen/Documents/surface_obs/MADIS/" + dstr[0:6] +
"/combined_" + variable + "/" + variable + "_" + dstr + "_" + time +
".txt", "r")
elif ob_type == 'gridded':
f = open(
"/home/disk/hot/stangen/Documents/gridded_obs/" + ens + "/" +
dstr[0:6] + "/" + variable + "/" + dstr + "_" + time + "_" + grid +
".txt", "r")
def save_gridded_obs(self, forecast_hour=0, get_variance=False):
"""
Loads the ensemble from n hours after the forecast was initialized
and uses its 0-hour forecast as the "observation" grid.
Saves information about the generated gridded obs to a .txt file,
with the same format as MADIS observations.
If get_variance is true, will also save the variance of the ensemble
at the observation locations at the end of each line.
"""
basedir = '/home/disk/hot/stangen/Documents/gridded_obs/'
#get the list of points
points = ef.get_ob_points(self.l,self.r,self.t,self.b,self.s)
#get the 0-hour ensemble forecast, n hours after the model was initialized
dt0 = self.date
dt = dt0.replace(minute = 0, second=0, microsecond=0)
dt = dt + timedelta(hours=forecast_hour)
#convert to epoch time for saving observation
epoch = str(dt.replace(tzinfo=pytz.utc).timestamp())
dty, dtm, dtd, dth = ef.dt_str_timedelta(self.date,forecast_hour)
print('starting saving of '+self.ens_type+' gridded '+self.ob_type+ ' "obs" at: '+dty+dtm+dtd+'_'+dth+'00')
var, lats, lons = self.load_ens_netcdf(forecast_hour)
#obtain the mean of the ensemble (nlats x nlons)
ens_mean = var.mean(axis=-1)
#obtain variance of the ensemble (nlats x nlons)
variance = np.var(var,axis=-1,ddof=1)
#initialize the obs list to append to
obs = []
#loop through each point (lat/lon pair)
for i, p in enumerate(points):
ob_lat = p[0]
ob_lon = p[1]
#get the ensemble value at the lat/lon pair
ob_value, ob_variance = ef.closest_points(ob_lat,ob_lon,lats,lons,variable=ens_mean,
need_interp=True,gen_obs=True,variance=variance)
obs.append(str(i)+','+str(ob_lat)+','+str(ob_lon)+','+str(0)+','+epoch+','+str(ob_value)+',GRIDDED,'+str(0))
if get_variance == True:
obs.append(','+str(ob_variance))
obs.append('\n')
#save directory for the observations
if (os.path.isdir(basedir+self.ens_type+'/'+dty+dtm+'/'+self.ob_type+'/')):
pass
else:
os.makedirs(basedir+self.ens_type+'/'+dty+dtm+'/'+self.ob_type+'/')
#save the list of observations
if self.new_format == False:
f = open(basedir+self.ens_type+'/'+dty+dtm+'/'+self.ob_type+'/'+self.ob_type+'_'+dty+dtm+dtd+'_'+dth+'00.txt',"w")
elif self.new_format == True:
savestr = basedir+self.ens_type+'/'+dty+dtm+'/'+self.ob_type+'/'+dty+dtm+dtd+'_'+dth+'00_'+str(self.l)+'_'+str(self.r)+'_'+str(self.t)+'_'+str(self.b)+'_'+str(self.s)
if get_variance == True:
savestr += '_variance'
savestr += '.txt'
f = open(savestr,"w")
for s in obs:
f.write(s)
f.close()