def _handler(self, request, response):
init_process_logger('log.txt')
response.outputs['output_log'].file = 'log.txt'
process_start_time = time.time() # measure process execution time ...
response.update_status('execution started at : %s ' % dt.now(), 5)
start_time = time.time() # measure init ...
resource = archiveextract(
resource=rename_complexinputs(request.inputs['resource']))
refSt = request.inputs['refSt'][0].data
refEn = request.inputs['refEn'][0].data
dateSt = request.inputs['dateSt'][0].data
dateEn = request.inputs['dateEn'][0].data
regrset = request.inputs['regrset'][0].data
# fix 31 December issue
# refSt = dt.combine(refSt,dt_time(12,0))
# refEn = dt.combine(refEn,dt_time(12,0))
# dateSt = dt.combine(dateSt,dt_time(12,0))
# dateEn = dt.combine(dateEn,dt_time(12,0))
seasonwin = request.inputs['seasonwin'][0].data
nanalog = request.inputs['nanalog'][0].data
# bbox = [-80, 20, 50, 70]
# TODO: Add checking for wrong cordinates and apply default if nesessary
bbox = []
bboxStr = request.inputs['BBox'][0].data
bboxStr = bboxStr.split(',')
bbox.append(float(bboxStr[0]))
bbox.append(float(bboxStr[2]))
bbox.append(float(bboxStr[1]))
bbox.append(float(bboxStr[3]))
direction = request.inputs['direction'][0].data
normalize = request.inputs['normalize'][0].data
distance = request.inputs['dist'][0].data
outformat = request.inputs['outformat'][0].data
timewin = request.inputs['timewin'][0].data
model_var = request.inputs['reanalyses'][0].data
model, var = model_var.split('_')
try:
if direction == 're2mo':
anaSt = dt.combine(dateSt, dt_time(
0, 0)) #dt.strptime(dateSt[0], '%Y-%m-%d')
anaEn = dt.combine(dateEn, dt_time(
0, 0)) #dt.strptime(dateEn[0], '%Y-%m-%d')
refSt = dt.combine(refSt, dt_time(
12, 0)) #dt.strptime(refSt[0], '%Y-%m-%d')
refEn = dt.combine(refEn, dt_time(
12, 0)) #dt.strptime(refEn[0], '%Y-%m-%d')
r_time_range = [anaSt, anaEn]
m_time_range = [refSt, refEn]
elif direction == 'mo2re':
anaSt = dt.combine(dateSt, dt_time(
12, 0)) #dt.strptime(refSt[0], '%Y-%m-%d')
anaEn = dt.combine(dateEn, dt_time(
12, 0)) #dt.strptime(refEn[0], '%Y-%m-%d')
refSt = dt.combine(refSt, dt_time(
0, 0)) #dt.strptime(dateSt[0], '%Y-%m-%d')
refEn = dt.combine(refEn, dt_time(
0, 0)) #dt.strptime(dateEn[0], '%Y-%m-%d')
r_time_range = [refSt, refEn]
m_time_range = [anaSt, anaEn]
else:
LOGGER.exception(
'failed to find time periods for comparison direction')
except:
msg = 'failed to put simulation and reference time in order'
LOGGER.exception(msg)
raise Exception(msg)
if normalize == 'None':
seacyc = False
else:
seacyc = True
if outformat == 'ascii':
outformat = '.txt'
elif outformat == 'netCDF':
outformat = '.nc'
else:
LOGGER.exception('output format not valid')
try:
if model == 'NCEP':
getlevel = True
if 'z' in var:
level = var.strip('z')
variable = 'hgt'
# conform_units_to='hPa'
else:
variable = 'slp'
level = None
# conform_units_to='hPa'
elif '20CRV2' in model:
getlevel = False
if 'z' in var:
variable = 'hgt'
level = var.strip('z')
# conform_units_to=None
else:
variable = 'prmsl'
level = None
# conform_units_to='hPa'
else:
LOGGER.exception('Reanalyses model not known')
LOGGER.info('environment set')
except:
msg = 'failed to set environment'
LOGGER.exception(msg)
raise Exception(msg)
# LOGGER.exception("init took %s seconds.", time.time() - start_time)
response.update_status('Read in the arguments', 6)
#################
# get input data
#################
# TODO: do not forget to select years
start_time = time.time() # measure get_input_data ...
response.update_status('fetching input data', 7)
try:
if direction == 're2mo':
nc_reanalyses = reanalyses(start=anaSt.year,
end=anaEn.year,
variable=var,
dataset=model,
getlevel=getlevel)
else:
nc_reanalyses = reanalyses(start=refSt.year,
end=refEn.year,
variable=var,
dataset=model,
getlevel=getlevel)
if type(nc_reanalyses) == list:
nc_reanalyses = sorted(
nc_reanalyses,
key=lambda i: path.splitext(path.basename(i))[0])
else:
nc_reanalyses = [nc_reanalyses]
# For 20CRV2 geopotential height, daily dataset for 100 years is about 50 Gb
# So it makes sense, to operate it step-by-step
# TODO: need to create dictionary for such datasets (for models as well)
# TODO: benchmark the method bellow for NCEP z500 for 60 years, may be use the same (!)
# TODO Now everything regrid to the reanalysis
if ('20CRV2' in model) and ('z' in var):
tmp_total = []
origvar = get_variable(nc_reanalyses)
for z in nc_reanalyses:
tmp_n = 'tmp_%s' % (uuid.uuid1())
b0 = call(resource=z,
variable=origvar,
level_range=[int(level), int(level)],
geom=bbox,
spatial_wrapping='wrap',
prefix='levdom_' + path.basename(z)[0:-3])
tmp_total.append(b0)
tmp_total = sorted(
tmp_total,
key=lambda i: path.splitext(path.basename(i))[0])
inter_subset_tmp = call(resource=tmp_total,
variable=origvar,
time_range=r_time_range)
# Clean
for i in tmp_total:
tbr = 'rm -f %s' % (i)
#system(tbr)
# Create new variable
ds = Dataset(inter_subset_tmp, mode='a')
z_var = ds.variables.pop(origvar)
dims = z_var.dimensions
new_var = ds.createVariable('z%s' % level,
z_var.dtype,
dimensions=(dims[0], dims[2],
dims[3]))
new_var[:, :, :] = squeeze(z_var[:, 0, :, :])
# new_var.setncatts({k: z_var.getncattr(k) for k in z_var.ncattrs()})
ds.close()
nc_subset = call(inter_subset_tmp, variable='z%s' % level)
else:
nc_subset = call(
resource=nc_reanalyses,
variable=var,
geom=bbox,
spatial_wrapping='wrap',
time_range=r_time_range,
# conform_units_to=conform_units_to
)
# nc_subset = call(resource=nc_reanalyses, variable=var, geom=bbox, spatial_wrapping='wrap') # XXXXXX wrap
# LOGGER.exception("get_input_subset_model took %s seconds.", time.time() - start_time)
response.update_status('**** Input reanalyses data fetched', 10)
except:
msg = 'failed to fetch or subset input files'
LOGGER.exception(msg)
raise Exception(msg)
########################
# input data preperation
########################
response.update_status('Start preparing input data', 12)
# Filter resource:
if type(resource) == list:
resource = sorted(resource,
key=lambda i: path.splitext(path.basename(i))[0])
else:
resource = [resource]
tmp_resource = []
m_start = m_time_range[0]
m_end = m_time_range[1]
for re in resource:
s, e = get_timerange(re)
tmpSt = dt.strptime(s, '%Y%m%d')
tmpEn = dt.strptime(e, '%Y%m%d')
if ((tmpSt <= m_end) and (tmpEn >= m_start)):
tmp_resource.append(re)
LOGGER.debug('Selected file: %s ' % (re))
resource = tmp_resource
start_time = time.time() # mesure data preperation ...
# TODO: Check the callendars ! for model vs reanalyses.
# TODO: Check the units! model vs reanalyses.
try:
m_total = []
modvar = get_variable(resource)
# resource properties
ds = Dataset(resource[0])
m_var = ds.variables[modvar]
dims = list(m_var.dimensions)
dimlen = len(dims)
try:
model_id = ds.getncattr('model_id')
except AttributeError:
model_id = 'Unknown model'
LOGGER.debug('MODEL: %s ' % (model_id))
lev_units = 'hPa'
if (dimlen > 3):
lev = ds.variables[dims[1]]
# actually index [1] need to be detected... assuming zg(time, plev, lat, lon)
lev_units = lev.units
if (lev_units == 'Pa'):
m_level = str(int(level) * 100)
else:
m_level = level
else:
m_level = None
if level == None:
level_range = None
else:
level_range = [int(m_level), int(m_level)]
for z in resource:
tmp_n = 'tmp_%s' % (uuid.uuid1())
# select level and regrid
b0 = call(
resource=z,
variable=modvar,
level_range=level_range,
spatial_wrapping='wrap', #cdover='system',
regrid_destination=nc_reanalyses[0],
regrid_options='bil',
prefix=tmp_n)
# select domain
b01 = call(resource=b0,
geom=bbox,
spatial_wrapping='wrap',
prefix='levregr_' + path.basename(z)[0:-3])
tbr = 'rm -f %s' % (b0)
#system(tbr)
tbr = 'rm -f %s' % (tmp_n)
#system(tbr)
# get full resource
m_total.append(b01)
ds.close()
model_subset = call(m_total, time_range=m_time_range)
for i in m_total:
tbr = 'rm -f %s' % (i)
#system(tbr)
if m_level is not None:
# Create new variable in model set
ds = Dataset(model_subset, mode='a')
mod_var = ds.variables.pop(modvar)
dims = mod_var.dimensions
new_modvar = ds.createVariable('z%s' % level,
mod_var.dtype,
dimensions=(dims[0], dims[2],
dims[3]))
new_modvar[:, :, :] = squeeze(mod_var[:, 0, :, :])
# new_var.setncatts({k: z_var.getncattr(k) for k in z_var.ncattrs()})
ds.close()
mod_subset = call(model_subset, variable='z%s' % level)
else:
mod_subset = model_subset
# if direction == 're2mo':
# try:
# response.update_status('Preparing simulation data', 15)
# reanalyses_subset = call(resource=nc_subset, time_range=[anaSt, anaEn])
# except:
# msg = 'failed to prepare simulation period'
# LOGGER.exception(msg)
# try:
# response.update_status('Preparing target data', 17)
# var_target = get_variable(resource)
# # var_simulation = get_variable(simulation)
# model_subset_tmp = call(resource=resource, variable=var_target,
# time_range=[refSt, refEn],
# t_calendar='standard',
# spatial_wrapping='wrap',
# regrid_destination=nc_reanalyses[0],
# regrid_options='bil')
# # model_subset = call(resource=resource, variable=var_target,
# # time_range=[refSt, refEn],
# # geom=bbox,
# # t_calendar='standard',
# # # conform_units_to=conform_units_to,
# # spatial_wrapping='wrap',
# # regrid_destination=reanalyses_subset,
# # regrid_options='bil') # XXXXXXXXXXXX ADD WRAP rem calendar
# model_subset = call(resource=model_subset_tmp,variable=var_target, geom=bbox, spatial_wrapping='wrap', t_calendar='standard')
# # ISSUE: the regrided model has white border with null! Check it.
# # check t_calendar!
# except:
# msg = 'failed subset archive model'
# LOGGER.exception(msg)
# raise Exception(msg)
# else:
# try:
# response.update_status('Preparing target data', 15)
# var_target = get_variable(resource)
# # var_simulation = get_variable(simulation)
# model_subset = call(resource=resource, variable=var_target,
# time_range=[refSt, refEn],
# geom=bbox,
# t_calendar='standard',
# # conform_units_to=conform_units_to,
# # spatial_wrapping='wrap',
# )
# except:
# msg = 'failed subset archive model'
# LOGGER.exception(msg)
# raise Exception(msg)
# try:
# response.update_status('Preparing simulation data', 17)
# reanalyses_subset = call(resource=nc_subset,
# time_range=[anaSt, anaEn],
# regrid_destination=model_subset,
# regrid_options='bil')
# except:
# msg = 'failed to prepare simulation period'
# LOGGER.exception(msg)
except:
msg = 'failed to subset simulation or reference data'
LOGGER.exception(msg)
raise Exception(msg)
# --------------------------------------------
try:
if direction == 'mo2re':
simulation = mod_subset
archive = nc_subset
base_id = model
sim_id = model_id
elif direction == 're2mo':
simulation = nc_subset
archive = mod_subset
base_id = model_id
sim_id = model
else:
LOGGER.exception('direction not valid: %s ' % direction)
except:
msg = 'failed to find comparison direction'
LOGGER.exception(msg)
raise Exception(msg)
try:
if level is not None:
out_var = 'z%s' % level
else:
var_archive = get_variable(archive)
var_simulation = get_variable(simulation)
if var_archive != var_simulation:
rename_variable(archive,
oldname=var_archive,
newname=var_simulation)
out_var = var_simulation
LOGGER.info('varname %s in netCDF renamed to %s' %
(var_archive, var_simulation))
except:
msg = 'failed to rename variable in target files'
LOGGER.exception(msg)
raise Exception(msg)
try:
if seacyc is True:
seasoncyc_base, seasoncyc_sim = analogs.seacyc(
archive, simulation, method=normalize)
else:
seasoncyc_base = None
seasoncyc_sim = None
except:
msg = 'failed to prepare seasonal cycle reference files'
LOGGER.exception(msg)
raise Exception(msg)
ip, output = mkstemp(dir='.', suffix='.txt')
output_file = path.abspath(output)
files = [path.abspath(archive), path.abspath(simulation), output_file]
# LOGGER.exception("data preperation took %s seconds.", time.time() - start_time)
############################
# generating the config file
############################
response.update_status('writing config file', 18)
start_time = time.time() # measure write config ...
try:
config_file = analogs.get_configfile(
files=files,
seasoncyc_base=seasoncyc_base,
seasoncyc_sim=seasoncyc_sim,
base_id=base_id,
sim_id=sim_id,
timewin=timewin,
varname=var,
seacyc=seacyc,
cycsmooth=91,
nanalog=nanalog,
seasonwin=seasonwin,
distfun=distance,
outformat=outformat,
calccor=True,
silent=False,
period=[
dt.strftime(refSt, '%Y-%m-%d'),
dt.strftime(refEn, '%Y-%m-%d')
],
bbox="%s,%s,%s,%s" % (bbox[0], bbox[2], bbox[1], bbox[3]))
except:
msg = 'failed to generate config file'
LOGGER.exception(msg)
raise Exception(msg)
# LOGGER.exception("write_config took %s seconds.", time.time() - start_time)
#######################
# CASTf90 call
#######################
import subprocess
import shlex
start_time = time.time() # measure call castf90
response.update_status('Start CASTf90 call', 20)
try:
# response.update_status('execution of CASTf90', 50)
cmd = 'analogue.out %s' % path.relpath(config_file)
# system(cmd)
args = shlex.split(cmd)
output, error = subprocess.Popen(
args, stdout=subprocess.PIPE,
stderr=subprocess.PIPE).communicate()
LOGGER.info('analogue.out info:\n %s ' % output)
LOGGER.exception('analogue.out errors:\n %s ' % error)
response.update_status('**** CASTf90 suceeded', 90)
except:
msg = 'CASTf90 failed'
LOGGER.exception(msg)
raise Exception(msg)
LOGGER.debug("castf90 took %s seconds.", time.time() - start_time)
response.update_status('preparting output', 91)
# Stopper to keep twitcher results, for debug
# dummy=dummy
response.outputs[
'config'].file = config_file #config_output_url # config_file )
response.outputs['analogs'].file = output_file
response.outputs['output_netcdf'].file = simulation
response.outputs['target_netcdf'].file = archive
########################
# generate analog viewer
########################
formated_analogs_file = analogs.reformat_analogs(output_file)
# response.outputs['formated_analogs'].storage = FileStorage()
response.outputs['formated_analogs'].file = formated_analogs_file
LOGGER.info('analogs reformated')
response.update_status('reformatted analog file', 95)
viewer_html = analogs.render_viewer(
# configfile=response.outputs['config'].get_url(),
configfile=config_file,
# datafile=response.outputs['formated_analogs'].get_url())
datafile=formated_analogs_file)
response.outputs['output'].file = viewer_html
response.update_status('Successfully generated analogs viewer', 99)
LOGGER.info('rendered pages: %s ', viewer_html)
response.update_status('execution ended', 100)
LOGGER.debug("total execution took %s seconds.",
time.time() - process_start_time)
return response
def _handler(self, request, response):
init_process_logger('log.txt')
response.outputs['output_log'].file = 'log.txt'
LOGGER.info('Start process')
response.update_status('execution started at : {}'.format(dt.now()), 5)
process_start_time = time.time() # measure process execution time ...
start_time = time.time() # measure init ...
################################
# reading in the input arguments
################################
try:
response.update_status('read input parameter : %s ' % dt.now(), 7)
refSt = request.inputs['refSt'][0].data
refEn = request.inputs['refEn'][0].data
dateSt = request.inputs['dateSt'][0].data
dateEn = request.inputs['dateEn'][0].data
seasonwin = request.inputs['seasonwin'][0].data
nanalog = request.inputs['nanalog'][0].data
timres = request.inputs['timeres'][0].data
# bbox = [-80, 20, 50, 70]
# TODO: Add checking for wrong cordinates and apply default if nesessary
bbox = []
bboxStr = request.inputs['BBox'][0].data
bboxStr = bboxStr.split(',')
bbox.append(float(bboxStr[0]))
bbox.append(float(bboxStr[2]))
bbox.append(float(bboxStr[1]))
bbox.append(float(bboxStr[3]))
LOGGER.debug('BBOX for ocgis: %s ' % (bbox))
LOGGER.debug('BBOX original: %s ' % (bboxStr))
normalize = request.inputs['normalize'][0].data
detrend = request.inputs['detrend'][0].data
distance = request.inputs['dist'][0].data
outformat = request.inputs['outformat'][0].data
timewin = request.inputs['timewin'][0].data
model_var = request.inputs['reanalyses'][0].data
model, var = model_var.split('_')
# experiment = self.getInputValues(identifier='experiment')[0]
# dataset, var = experiment.split('_')
# LOGGER.info('environment set')
LOGGER.info('input parameters set')
response.update_status('Read in and convert the arguments', 8)
except Exception as e:
msg = 'failed to read input prameter %s ' % e
LOGGER.exception(msg)
raise Exception(msg)
######################################
# convert types and set environment
######################################
try:
response.update_status('Preparing enviroment converting arguments',
9)
LOGGER.debug('date: %s %s %s %s ' %
(type(refSt), refEn, dateSt, dateSt))
start = min(refSt, dateSt)
end = max(refEn, dateEn)
#
# refSt = dt.strftime(refSt, '%Y-%m-%d')
# refEn = dt.strftime(refEn, '%Y-%m-%d')
# dateSt = dt.strftime(dateSt, '%Y-%m-%d')
# dateEn = dt.strftime(dateEn, '%Y-%m-%d')
if normalize == 'None':
seacyc = False
else:
seacyc = True
if outformat == 'ascii':
outformat = '.txt'
elif outformat == 'netCDF':
outformat = '.nc'
else:
LOGGER.exception('output format not valid')
except Exception as e:
msg = 'failed to set environment %s ' % e
LOGGER.exception(msg)
raise Exception(msg)
###########################
# set the environment
###########################
response.update_status('fetching data from archive', 10)
try:
if model == 'NCEP':
getlevel = False
if 'z' in var:
level = var.strip('z')
conform_units_to = None
else:
level = None
conform_units_to = 'hPa'
elif '20CRV2' in model:
getlevel = False
if 'z' in var:
level = var.strip('z')
conform_units_to = None
else:
level = None
conform_units_to = 'hPa'
else:
LOGGER.exception('Reanalyses dataset not known')
LOGGER.info('environment set for model: %s' % model)
except Exception:
msg = 'failed to set environment'
LOGGER.exception(msg)
raise Exception(msg)
##########################################
# fetch Data from original data archive
##########################################
# NOTE: If ref is say 1950 - 1990, and sim is just 1 week in 2017 - ALL the data will be downloaded, 1950 - 2017
try:
model_nc = rl(start=start.year,
end=end.year,
dataset=model,
variable=var,
timres=timres,
getlevel=getlevel)
LOGGER.info('reanalyses data fetched')
except Exception:
msg = 'failed to get reanalyses data'
LOGGER.exception(msg)
raise Exception(msg)
response.update_status('subsetting region of interest', 17)
# from flyingpigeon.weatherregimes import get_level
LOGGER.debug("start and end time: %s - %s" % (start, end))
time_range = [start, end]
# For 20CRV2 geopotential height, daily dataset for 100 years is about 50 Gb
# So it makes sense, to operate it step-by-step
# TODO: need to create dictionary for such datasets (for models as well)
# TODO: benchmark the method bellow for NCEP z500 for 60 years
# if ('20CRV2' in model) and ('z' in var):
if ('z' in var):
tmp_total = []
origvar = get_variable(model_nc)
for z in model_nc:
tmp_n = 'tmp_%s' % (uuid.uuid1())
b0 = call(resource=z,
variable=origvar,
level_range=[int(level), int(level)],
geom=bbox,
spatial_wrapping='wrap',
prefix='levdom_' + os.path.basename(z)[0:-3])
tmp_total.append(b0)
tmp_total = sorted(
tmp_total,
key=lambda i: os.path.splitext(os.path.basename(i))[0])
inter_subset_tmp = call(resource=tmp_total,
variable=origvar,
time_range=time_range)
# Clean
for i in tmp_total:
tbr = 'rm -f %s' % (i)
os.system(tbr)
# Create new variable
ds = Dataset(inter_subset_tmp, mode='a')
z_var = ds.variables.pop(origvar)
dims = z_var.dimensions
new_var = ds.createVariable('z%s' % level,
z_var.dtype,
dimensions=(dims[0], dims[2], dims[3]))
new_var[:, :, :] = squeeze(z_var[:, 0, :, :])
# new_var.setncatts({k: z_var.getncattr(k) for k in z_var.ncattrs()})
ds.close()
model_subset_tmp = call(inter_subset_tmp, variable='z%s' % level)
else:
model_subset_tmp = call(
resource=model_nc,
variable=var,
geom=bbox,
spatial_wrapping='wrap',
time_range=time_range,
# conform_units_to=conform_units_to
)
# If dataset is 20CRV2 the 6 hourly file should be converted to daily.
# Option to use previously 6h data from cache (if any) and not download daily files.
if '20CRV2' in model:
if timres == '6h':
from cdo import Cdo
cdo = Cdo()
model_subset = '%s.nc' % uuid.uuid1()
tmp_f = '%s.nc' % uuid.uuid1()
cdo_op = getattr(cdo, 'daymean')
cdo_op(input=model_subset_tmp, output=tmp_f)
sti = '00:00:00'
cdo_op = getattr(cdo, 'settime')
cdo_op(sti, input=tmp_f, output=model_subset)
LOGGER.debug('File Converted from: %s to daily' % (timres))
else:
model_subset = model_subset_tmp
else:
model_subset = model_subset_tmp
LOGGER.info('Dataset subset done: %s ', model_subset)
response.update_status('dataset subsetted', 19)
# BLOCK OF DETRENDING of model_subset !
# Original model subset kept to further visualisaion if needed
# Now is issue with SLP:
# TODO 1 Keep trend as separate file
# TODO 2 Think how to add options to plot abomalies AND original data...
# May be do archive and simulation = call.. over NOT detrended data and keep it as well
# TODO 3 Check with faster smoother add removing trend of each grid
if detrend == 'None':
orig_model_subset = model_subset
else:
orig_model_subset = remove_mean_trend(model_subset, varname=var)
# ======================================
############################################################
# get the required bbox and time region from resource data
############################################################
#
#
# try:
# if dataset == 'NCEP':
# if 'z' in var:
# variable = 'hgt'
# level = var.strip('z')
# # conform_units_to=None
# else:
# variable = 'slp'
# level = None
# # conform_units_to='hPa'
# elif '20CRV2' in var:
# if 'z' in level:
# variable = 'hgt'
# level = var.strip('z')
# # conform_units_to=None
# else:
# variable = 'prmsl'
# level = None
# # conform_units_to='hPa'
# else:
# LOGGER.exception('Reanalyses dataset not known')
# LOGGER.info('environment set')
# except Exception as e:
# msg = 'failed to set environment %s ' % e
# LOGGER.exception(msg)
# # raise Exception(msg)
#
# LOGGER.debug("init took %s seconds.", time.time() - start_time)
# response.update_status('Read in and convert the arguments done', 8)
#
# #################
# # get input data
# #################
# start_time = time.time() # measure get_input_data ...
# response.update_status('fetching input data', 7)
# try:
# input = reanalyses(start=start.year, end=end.year,
# variable=var, dataset=dataset)
# LOGGER.info('input files %s' % input)
# nc_subset = call(resource=input, variable=var,
# geom=bbox, spatial_wrapping='wrap')
# except Exception as e:
# msg = 'failed to fetch or subset input files %s' % e
# LOGGER.exception(msg)
# # raise Exception(msg)
LOGGER.debug("get_input_subset_dataset took %s seconds.",
time.time() - start_time)
response.update_status('**** Input data fetched', 20)
########################
# input data preperation
########################
response.update_status('Start preparing input data', 22)
start_time = time.time() # measure data preperation ...
try:
# Construct descriptive filenames for the three files
# listed in config file
# TODO check strftime for years <1900 (!)
refDatesString = dt.strftime(
refSt, '%Y-%m-%d') + "_" + dt.strftime(refEn, '%Y-%m-%d')
simDatesString = dt.strftime(
dateSt, '%Y-%m-%d') + "_" + dt.strftime(dateEn, '%Y-%m-%d')
archiveNameString = "base_" + var + "_" + refDatesString + '_%.1f_%.1f_%.1f_%.1f' \
% (bbox[0], bbox[2], bbox[1], bbox[3])
simNameString = "sim_" + var + "_" + simDatesString + '_%.1f_%.1f_%.1f_%.1f' \
% (bbox[0], bbox[2], bbox[1], bbox[3])
archive = call(resource=model_subset,
time_range=[refSt, refEn],
prefix=archiveNameString)
simulation = call(resource=model_subset,
time_range=[dateSt, dateEn],
prefix=simNameString)
LOGGER.info('archive and simulation files generated: %s, %s' %
(archive, simulation))
except Exception as e:
msg = 'failed to prepare archive and simulation files %s ' % e
LOGGER.exception(msg)
raise Exception(msg)
try:
if seacyc is True:
LOGGER.info('normalization function with method: %s ' %
normalize)
seasoncyc_base, seasoncyc_sim = analogs.seacyc(
archive, simulation, method=normalize)
else:
seasoncyc_base = seasoncyc_sim = None
except Exception as e:
msg = 'failed to generate normalization files %s ' % e
LOGGER.exception(msg)
raise Exception(msg)
output_file = 'output.txt'
files = [
os.path.abspath(archive),
os.path.abspath(simulation), output_file
]
LOGGER.debug("Data preperation took %s seconds.",
time.time() - start_time)
############################
# generate the config file
############################
config_file = analogs.get_configfile(
files=files,
seasoncyc_base=seasoncyc_base,
seasoncyc_sim=seasoncyc_sim,
base_id=model,
sim_id=model,
timewin=timewin,
varname=var,
seacyc=seacyc,
cycsmooth=91,
nanalog=nanalog,
seasonwin=seasonwin,
distfun=distance,
outformat=outformat,
calccor=True,
silent=False,
period=[
dt.strftime(refSt, '%Y-%m-%d'),
dt.strftime(refEn, '%Y-%m-%d')
],
bbox="{0[0]},{0[2]},{0[1]},{0[3]}".format(bbox))
response.update_status('generated config file', 25)
#######################
# CASTf90 call
#######################
start_time = time.time() # measure call castf90
# -----------------------
try:
import ctypes
# TODO: This lib is for linux
mkl_rt = ctypes.CDLL('libmkl_rt.so')
nth = mkl_rt.mkl_get_max_threads()
LOGGER.debug('Current number of threads: %s' % (nth))
mkl_rt.mkl_set_num_threads(ctypes.byref(ctypes.c_int(64)))
nth = mkl_rt.mkl_get_max_threads()
LOGGER.debug('NEW number of threads: %s' % (nth))
# TODO: Does it \/\/\/ work with default shell=False in subprocess... (?)
os.environ['MKL_NUM_THREADS'] = str(nth)
os.environ['OMP_NUM_THREADS'] = str(nth)
except Exception as e:
msg = 'Failed to set THREADS %s ' % e
LOGGER.debug(msg)
# -----------------------
response.update_status('Start CASTf90 call', 30)
try:
# response.update_status('execution of CASTf90', 50)
cmd = ['analogue.out', config_file]
LOGGER.debug("castf90 command: %s", cmd)
output = subprocess.check_output(cmd, stderr=subprocess.STDOUT)
LOGGER.info('analogue output:\n %s', output)
response.update_status('**** CASTf90 suceeded', 70)
except CalledProcessError as e:
msg = 'CASTf90 failed:\n{0}'.format(e.output)
LOGGER.exception(msg)
raise Exception(msg)
LOGGER.debug("castf90 took %s seconds.", time.time() - start_time)
# TODO: Add try - except for pdfs
analogs_pdf = analogs.plot_analogs(configfile=config_file)
response.update_status('preparing output', 75)
# response.outputs['config'].storage = FileStorage()
response.outputs['analog_pdf'].file = analogs_pdf
response.outputs['config'].file = config_file
response.outputs['analogs'].file = output_file
response.outputs['output_netcdf'].file = simulation
response.outputs['target_netcdf'].file = archive
if seacyc is True:
response.outputs['base_netcdf'].file = seasoncyc_base
response.outputs['sim_netcdf'].file = seasoncyc_sim
else:
# TODO: Still unclear how to overpass unknown number of outputs
dummy_base = 'dummy_base.nc'
dummy_sim = 'dummy_sim.nc'
with open(dummy_base, 'a'):
os.utime(dummy_base, None)
with open(dummy_sim, 'a'):
os.utime(dummy_sim, None)
response.outputs['base_netcdf'].file = dummy_base
response.outputs['sim_netcdf'].file = dummy_sim
########################
# generate analog viewer
########################
formated_analogs_file = analogs.reformat_analogs(output_file)
# response.outputs['formated_analogs'].storage = FileStorage()
response.outputs['formated_analogs'].file = formated_analogs_file
LOGGER.info('analogs reformated')
response.update_status('reformatted analog file', 80)
viewer_html = analogs.render_viewer(
# configfile=response.outputs['config'].get_url(),
configfile=config_file,
# datafile=response.outputs['formated_analogs'].get_url())
datafile=formated_analogs_file)
response.outputs['output'].file = viewer_html
response.update_status('Successfully generated analogs viewer', 90)
LOGGER.info('rendered pages: %s ', viewer_html)
response.update_status('execution ended', 100)
LOGGER.debug("total execution took %s seconds.",
time.time() - process_start_time)
return response
def _handler(self, request, response):
init_process_logger('log.txt')
response.outputs['output_log'].file = 'log.txt'
LOGGER.info('Start process')
response.update_status('execution started at : {}'.format(dt.now()), 5)
process_start_time = time.time() # measure process execution time ...
start_time = time.time() # measure init ...
################################
# reading in the input arguments
################################
response.update_status('execution started at : %s ' % dt.now(), 5)
start_time = time.time() # measure init ...
################################
# reading in the input arguments
################################
try:
response.update_status('read input parameter : %s ' % dt.now(), 5)
resource = archiveextract(resource=rename_complexinputs(request.inputs['resource']))
refSt = request.inputs['refSt'][0].data
refEn = request.inputs['refEn'][0].data
dateSt = request.inputs['dateSt'][0].data
dateEn = request.inputs['dateEn'][0].data
seasonwin = request.inputs['seasonwin'][0].data
nanalog = request.inputs['nanalog'][0].data
# bbox = [-80, 20, 50, 70]
# TODO: Add checking for wrong cordinates and apply default if nesessary
#level = 500
level = request.inputs['level'][0].data
if (level == 500):
dummylevel = 1000 # dummy workaround for cdo sellevel
else:
dummylevel = 500
LOGGER.debug('LEVEL selected: %s hPa' % (level))
bbox=[]
bboxStr = request.inputs['BBox'][0].data
bboxStr = bboxStr.split(',')
#for i in bboxStr: bbox.append(int(i))
bbox.append(float(bboxStr[0]))
bbox.append(float(bboxStr[2]))
bbox.append(float(bboxStr[1]))
bbox.append(float(bboxStr[3]))
LOGGER.debug('BBOX for ocgis: %s ' % (bbox))
LOGGER.debug('BBOX original: %s ' % (bboxStr))
# if bbox_obj is not None:
# LOGGER.info("bbox_obj={0}".format(bbox_obj.coords))
# bbox = [bbox_obj.coords[0][0],
# bbox_obj.coords[0][1],
# bbox_obj.coords[1][0],
# bbox_obj.coords[1][1]]
# LOGGER.info("bbox={0}".format(bbox))
# else:
# bbox = None
# region = self.getInputValues(identifier='region')[0]
# bbox = [float(b) for b in region.split(',')]
# bbox_obj = self.BBox.getValue()
normalize = request.inputs['normalize'][0].data
distance = request.inputs['dist'][0].data
outformat = request.inputs['outformat'][0].data
timewin = request.inputs['timewin'][0].data
# model_var = request.inputs['reanalyses'][0].data
# model, var = model_var.split('_')
# experiment = self.getInputValues(identifier='experiment')[0]
# dataset, var = experiment.split('_')
# LOGGER.info('environment set')
LOGGER.info('input parameters set')
response.update_status('Read in and convert the arguments', 5)
except Exception as e:
msg = 'failed to read input prameter %s ' % e
LOGGER.error(msg)
raise Exception(msg)
######################################
# convert types and set environment
######################################
try:
# refSt = dt.strptime(refSt[0], '%Y-%m-%d')
# refEn = dt.strptime(refEn[0], '%Y-%m-%d')
# dateSt = dt.strptime(dateSt[0], '%Y-%m-%d')
# dateEn = dt.strptime(dateEn[0], '%Y-%m-%d')
#not nesessary if fix ocgis_module.py
refSt = dt.combine(refSt,dt_time(12,0))
refEn = dt.combine(refEn,dt_time(12,0))
dateSt = dt.combine(dateSt,dt_time(12,0))
dateEn = dt.combine(dateEn,dt_time(12,0))
# refSt = refSt.replace(hour=12)
# refEn = refEn.replace(hour=12)
# dateSt = dateSt.replace(hour=12)
# dateEn = dateEn.replace(hour=12)
if normalize == 'None':
seacyc = False
else:
seacyc = True
if outformat == 'ascii':
outformat = '.txt'
elif outformat == 'netCDF':
outformat = '.nc'
else:
LOGGER.error('output format not valid')
start = min(refSt, dateSt)
end = max(refEn, dateEn)
# if bbox_obj is not None:
# LOGGER.info("bbox_obj={0}".format(bbox_obj.coords))
# bbox = [bbox_obj.coords[0][0],
# bbox_obj.coords[0][1],
# bbox_obj.coords[1][0],
# bbox_obj.coords[1][1]]
# LOGGER.info("bbox={0}".format(bbox))
# else:
# bbox = None
LOGGER.info('environment set')
except Exception as e:
msg = 'failed to set environment %s ' % e
LOGGER.error(msg)
raise Exception(msg)
LOGGER.debug("init took %s seconds.", time.time() - start_time)
response.update_status('Read in and convert the arguments', 5)
########################
# input data preperation
########################
# TODO: Check if files containing more than one dataset
response.update_status('Start preparing input data', 12)
start_time = time.time() # mesure data preperation ...
try:
# TODO: Add selection of the level. maybe bellow in call(..., level_range=[...,...])
if type(resource) == list:
#resource.sort()
resource = sorted(resource, key=lambda i: path.splitext(path.basename(i))[0])
else:
resource=[resource]
#===============================================================
# TODO: REMOVE resources which are out of interest from the list
# (years > and < than requested for calculation)
tmp_resource = []
for re in resource:
s,e = get_timerange(re)
tmpSt = dt.strptime(s,'%Y%m%d')
tmpEn = dt.strptime(e,'%Y%m%d')
if ((tmpSt <= end ) and (tmpEn >= start)):
tmp_resource.append(re)
LOGGER.debug('Selected file: %s ' % (re))
resource = tmp_resource
# ===============================================================
#================================================================
# Try to fix memory issue... (ocgis call for files like 20-30 gb... )
# IF 4D - select pressure level before domain cut
#
# resource properties
ds = Dataset(resource[0])
variable = get_variable(resource[0])
var = ds.variables[variable]
dims = list(var.dimensions)
dimlen = len(dims)
try:
model_id = ds.getncattr('model_id')
except AttributeError:
model_id = 'Unknown model'
LOGGER.debug('MODEL: %s ' % (model_id))
lev_units = 'hPa'
if (dimlen>3) :
lev = ds.variables[dims[1]]
# actually index [1] need to be detected... assuming zg(time, plev, lat, lon)
lev_units = lev.units
if (lev_units=='Pa'):
level = level*100
dummylevel=dummylevel*100
# TODO: OR check the NAME and units of vertical level and find 200 , 300, or 500 mbar in it
# Not just level = level * 100.
# Get Levels
from cdo import Cdo
cdo = Cdo()
lev_res=[]
if(dimlen>3):
for res_fn in resource:
tmp_f = 'lev_' + path.basename(res_fn)
comcdo = '%s,%s' % (level,dummylevel)
cdo.sellevel(comcdo, input=res_fn, output=tmp_f)
lev_res.append(tmp_f)
else:
lev_res = resource
# Get domain
regr_res=[]
for res_fn in lev_res:
tmp_f = 'dom_' + path.basename(res_fn)
comcdo = '%s,%s,%s,%s' % (bbox[0],bbox[2],bbox[1],bbox[3])
cdo.sellonlatbox(comcdo, input=res_fn, output=tmp_f)
regr_res.append(tmp_f)
#archive_tmp = call(resource=resource, time_range=[refSt, refEn], geom=bbox, spatial_wrapping='wrap')
#simulation_tmp = call(resource=resource, time_range=[dateSt, dateEn], geom=bbox, spatial_wrapping='wrap')
#============================
archive_tmp = call(resource=regr_res, time_range=[refSt, refEn], spatial_wrapping='wrap')
simulation_tmp = call(resource=regr_res, time_range=[dateSt, dateEn], spatial_wrapping='wrap')
#######################################################################################
# TEMORAL dirty workaround to get the level and it's units - will be func in utils.py
if (dimlen>3) :
archive = get_level(archive_tmp, level = level)
simulation = get_level(simulation_tmp,level = level)
variable = 'z%s' % level
# TODO: here should be modulated
else:
archive = archive_tmp
simulation = simulation_tmp
# 3D, move forward
#######################################################################################
if seacyc is True:
seasoncyc_base, seasoncyc_sim = analogs.seacyc(archive, simulation, method=normalize)
else:
seasoncyc_base = None
seasoncyc_sim = None
except Exception as e:
msg = 'failed to prepare archive and simulation files %s ' % e
LOGGER.debug(msg)
raise Exception(msg)
ip, output = mkstemp(dir='.', suffix='.txt')
output_file = path.abspath(output)
files = [path.abspath(archive), path.abspath(simulation), output_file]
LOGGER.debug("data preperation took %s seconds.", time.time() - start_time)
############################
# generating the config file
############################
# TODO: add MODEL name as argument
response.update_status('writing config file', 15)
start_time = time.time() # measure write config ...
try:
config_file = analogs.get_configfile(
files=files,
seasoncyc_base=seasoncyc_base,
seasoncyc_sim=seasoncyc_sim,
base_id=model_id,
sim_id=model_id,
timewin=timewin,
varname=variable,
seacyc=seacyc,
cycsmooth=91,
nanalog=nanalog,
seasonwin=seasonwin,
distfun=distance,
outformat=outformat,
calccor=True,
silent=False,
period=[dt.strftime(refSt, '%Y-%m-%d'), dt.strftime(refEn, '%Y-%m-%d')],
bbox="%s,%s,%s,%s" % (bbox[0], bbox[2], bbox[1], bbox[3]))
except Exception as e:
msg = 'failed to generate config file %s ' % e
LOGGER.debug(msg)
raise Exception(msg)
LOGGER.debug("write_config took %s seconds.", time.time() - start_time)
##############
# CASTf90 call
##############
import subprocess
import shlex
start_time = time.time() # measure call castf90
response.update_status('Start CASTf90 call', 20)
try:
# response.update_status('execution of CASTf90', 50)
cmd = 'analogue.out %s' % path.relpath(config_file)
# system(cmd)
args = shlex.split(cmd)
output, error = subprocess.Popen(args, stdout=subprocess.PIPE, stderr=subprocess.PIPE).communicate()
LOGGER.info('analogue.out info:\n %s ' % output)
LOGGER.debug('analogue.out errors:\n %s ' % error)
response.update_status('**** CASTf90 suceeded', 70)
except Exception as e:
msg = 'CASTf90 failed %s ' % e
LOGGER.error(msg)
raise Exception(msg)
LOGGER.debug("castf90 took %s seconds.", time.time() - start_time)
response.update_status('preparing output', 70)
response.outputs['config'].file = config_file #config_output_url # config_file )
response.outputs['analogs'].file = output_file
response.outputs['output_netcdf'].file = simulation
########################
# generate analog viewer
########################
formated_analogs_file = analogs.reformat_analogs(output_file)
# response.outputs['formated_analogs'].storage = FileStorage()
response.outputs['formated_analogs'].file = formated_analogs_file
LOGGER.info('analogs reformated')
response.update_status('reformatted analog file', 80)
viewer_html = analogs.render_viewer(
# configfile=response.outputs['config'].get_url(),
configfile=config_file,
# datafile=response.outputs['formated_analogs'].get_url())
datafile=formated_analogs_file)
response.outputs['output'].file = viewer_html
response.update_status('Successfully generated analogs viewer', 90)
LOGGER.info('rendered pages: %s ', viewer_html)
response.update_status('execution ended', 100)
LOGGER.debug("total execution took %s seconds.",
time.time() - process_start_time)
return response