# print('')
# print(' +++ processing shift/roll +++ ')
# CPU.Shift(shift=72, axis='lon', byteShift=True, flush=False)
# print('\n')
# get results
CPU.sync(flush=True)
# print('')
# print(sink)
# print('')
# add geolocators
if grid is not 'GPCC':
sink = addGeoLocator(sink, griddef=griddef, lgdal=True, lcheck=True)
# add landmask
#sink.mask(sink.landmask)
#print sink.dataset
addLandMask(sink) # create landmask from precip mask
#sink.stations.mask(sink.landmask) # mask all fields using the new landmask
# add length and names of month
addLengthAndNamesOfMonth(sink, noleap=False)
# newvar = sink.precip
# print
# print newvar.name, newvar.masked
# print newvar.fillValue
# print newvar.data_array.__class__
# print
def performRegridding(dataset, mode, griddef, dataargs, loverwrite=False, varlist=None, lwrite=True,
lreturn=False, ldebug=False, lparallel=False, pidstr='', logger=None):
''' worker function to perform regridding for a given dataset and target grid '''
# input checking
if not isinstance(dataset,basestring): raise TypeError
if not isinstance(dataargs,dict): raise TypeError # all dataset arguments are kwargs
if not isinstance(griddef,GridDefinition): raise TypeError
if lparallel:
if not lwrite: raise IOError, 'Can only write to disk in parallel mode (i.e. lwrite = True).'
if lreturn: raise IOError, 'Can not return datasets in parallel mode (i.e. lreturn = False).'
# logging
if logger is None: # make new logger
logger = logging.getLogger() # new logger
logger.addHandler(logging.StreamHandler())
else:
if isinstance(logger,basestring):
logger = logging.getLogger(name=logger) # connect to existing one
elif not isinstance(logger,logging.Logger):
raise TypeError, 'Expected logger ID/handle in logger KW; got {}'.format(str(logger))
## extract meta data from arguments
dataargs, loadfct, srcage, datamsgstr = getMetaData(dataset, mode, dataargs)
dataset_name = dataargs.dataset_name; periodstr = dataargs.periodstr; avgfolder = dataargs.avgfolder
# get filename for target dataset and do some checks
filename = getTargetFile(dataset=dataset, mode=mode, dataargs=dataargs, lwrite=lwrite,
grid=griddef.name.lower(), period=None, filetype=None)
# prepare target dataset
if ldebug: filename = 'test_' + filename
if not os.path.exists(avgfolder): raise IOError, "Dataset folder '{:s}' does not exist!".format(avgfolder)
lskip = False # else just go ahead
if lwrite:
if lreturn: tmpfilename = filename # no temporary file if dataset is passed on (can't rename the file while it is open!)
else:
if lparallel: tmppfx = 'tmp_regrid_{:s}_'.format(pidstr[1:-1])
else: tmppfx = 'tmp_regrid_'.format(pidstr[1:-1])
tmpfilename = tmppfx + filename
filepath = avgfolder + filename
tmpfilepath = avgfolder + tmpfilename
if os.path.exists(filepath):
if not loverwrite:
age = datetime.fromtimestamp(os.path.getmtime(filepath))
# if source file is newer than sink file or if sink file is a stub, recompute, otherwise skip
if age > srcage and os.path.getsize(filepath) > 1e6:
lskip = True
if hasattr(griddef, 'filepath') and griddef.filepath is not None:
gridage = datetime.fromtimestamp(os.path.getmtime(griddef.filepath))
if age < gridage: lskip = False
# N.B.: NetCDF files smaller than 1MB are usually incomplete header fragments from a previous crashed
if not lskip: os.remove(filepath) # recompute
# depending on last modification time of file or overwrite setting, start computation, or skip
if lskip:
# print message
skipmsg = "\n{:s} >>> Skipping: file '{:s}' in dataset '{:s}' already exists and is newer than source file.".format(pidstr,filename,dataset_name)
skipmsg += "\n{:s} >>> ('{:s}')\n".format(pidstr,filepath)
logger.info(skipmsg)
else:
## actually load datasets
source = loadfct() # load source
# check period
if 'period' in source.atts and dataargs.periodstr != source.atts.period: # a NetCDF attribute
raise DateError, "Specifed period is inconsistent with netcdf records: '{:s}' != '{:s}'".format(periodstr,source.atts.period)
# print message
if mode == 'climatology': opmsgstr = 'Regridding Climatology ({:s}) to {:s} Grid'.format(periodstr, griddef.name)
elif mode == 'time-series': opmsgstr = 'Regridding Time-series to {:s} Grid'.format(griddef.name)
else: raise NotImplementedError, "Unrecognized Mode: '{:s}'".format(mode)
# print feedback to logger
logger.info('\n{0:s} *** {1:^65s} *** \n{0:s} *** {2:^65s} *** \n'.format(pidstr,datamsgstr,opmsgstr))
if not lparallel and ldebug: logger.info('\n'+str(source)+'\n')
## create new sink/target file
# set attributes
atts=source.atts.copy()
atts['period'] = periodstr; atts['name'] = dataset_name; atts['grid'] = griddef.name
if mode == 'climatology': atts['title'] = '{:s} Climatology on {:s} Grid'.format(dataset_name, griddef.name)
elif mode == 'time-series': atts['title'] = '{:s} Time-series on {:s} Grid'.format(dataset_name, griddef.name)
# make new dataset
if lwrite: # write to NetCDF file
if os.path.exists(tmpfilepath): os.remove(tmpfilepath) # remove old temp files
sink = DatasetNetCDF(folder=avgfolder, filelist=[tmpfilename], atts=atts, mode='w')
else: sink = Dataset(atts=atts) # ony create dataset in memory
# initialize processing
CPU = CentralProcessingUnit(source, sink, varlist=varlist, tmp=False, feedback=ldebug)
# perform regridding (if target grid is different from native grid!)
if griddef.name != dataset:
# reproject and resample (regrid) dataset
CPU.Regrid(griddef=griddef, flush=True)
# get results
CPU.sync(flush=True)
# add geolocators
sink = addGeoLocator(sink, griddef=griddef, lgdal=True, lreplace=True, lcheck=True)
# N.B.: WRF datasets come with their own geolocator arrays - we need to replace those!
# add length and names of month
if mode == 'climatology' and not sink.hasVariable('length_of_month') and sink.hasVariable('time'):
addLengthAndNamesOfMonth(sink, noleap=True if dataset.upper() in ('WRF','CESM') else False)
# print dataset
if not lparallel and ldebug:
logger.info('\n'+str(sink)+'\n')
# write results to file
if lwrite:
sink.sync()
writemsg = "\n{:s} >>> Writing to file '{:s}' in dataset {:s}".format(pidstr,filename,dataset_name)
writemsg += "\n{:s} >>> ('{:s}')\n".format(pidstr,filepath)
logger.info(writemsg)
# rename file to proper name
if not lreturn:
sink.unload(); sink.close(); del sink # destroy all references
if os.path.exists(filepath): os.remove(filepath) # remove old file
os.rename(tmpfilepath,filepath) # this would also overwrite the old file...
# N.B.: there is no temporary file if the dataset is returned, because an open file can't be renamed
# clean up and return
source.unload(); del source, CPU
if lreturn:
return sink # return dataset for further use (netcdf file still open!)
else:
return 0 # "exit code"
def performRegridding(dataset,
mode,
griddef,
dataargs,
loverwrite=False,
varlist=None,
lwrite=True,
lreturn=False,
ldebug=False,
lparallel=False,
pidstr='',
logger=None):
''' worker function to perform regridding for a given dataset and target grid '''
# input checking
if not isinstance(dataset, basestring): raise TypeError
if not isinstance(dataargs, dict):
raise TypeError # all dataset arguments are kwargs
if not isinstance(griddef, GridDefinition): raise TypeError
if lparallel:
if not lwrite:
raise IOError, 'Can only write to disk in parallel mode (i.e. lwrite = True).'
if lreturn:
raise IOError, 'Can not return datasets in parallel mode (i.e. lreturn = False).'
# logging
if logger is None: # make new logger
logger = logging.getLogger() # new logger
logger.addHandler(logging.StreamHandler())
else:
if isinstance(logger, basestring):
logger = logging.getLogger(name=logger) # connect to existing one
elif not isinstance(logger, logging.Logger):
raise TypeError, 'Expected logger ID/handle in logger KW; got {}'.format(
str(logger))
## extract meta data from arguments
dataargs, loadfct, srcage, datamsgstr = getMetaData(
dataset, mode, dataargs)
dataset_name = dataargs.dataset_name
periodstr = dataargs.periodstr
avgfolder = dataargs.avgfolder
# get filename for target dataset and do some checks
filename = getTargetFile(
dataset=dataset,
mode=mode,
dataargs=dataargs,
lwrite=lwrite,
grid=griddef.name.lower(),
)
# prepare target dataset
if ldebug: filename = 'test_' + filename
if not os.path.exists(avgfolder):
raise IOError, "Dataset folder '{:s}' does not exist!".format(
avgfolder)
lskip = False # else just go ahead
if lwrite:
if lreturn:
tmpfilename = filename # no temporary file if dataset is passed on (can't rename the file while it is open!)
else:
if lparallel: tmppfx = 'tmp_regrid_{:s}_'.format(pidstr[1:-1])
else: tmppfx = 'tmp_regrid_'.format(pidstr[1:-1])
tmpfilename = tmppfx + filename
filepath = avgfolder + filename
tmpfilepath = avgfolder + tmpfilename
if os.path.exists(filepath):
if not loverwrite:
age = datetime.fromtimestamp(os.path.getmtime(filepath))
# if source file is newer than sink file or if sink file is a stub, recompute, otherwise skip
if age > srcage and os.path.getsize(filepath) > 1e6:
lskip = True
if hasattr(griddef,
'filepath') and griddef.filepath is not None:
gridage = datetime.fromtimestamp(
os.path.getmtime(griddef.filepath))
if age < gridage: lskip = False
# N.B.: NetCDF files smaller than 1MB are usually incomplete header fragments from a previous crashed
# depending on last modification time of file or overwrite setting, start computation, or skip
if lskip:
# print message
skipmsg = "\n{:s} >>> Skipping: file '{:s}' in dataset '{:s}' already exists and is newer than source file.".format(
pidstr, filename, dataset_name)
skipmsg += "\n{:s} >>> ('{:s}')\n".format(pidstr, filepath)
logger.info(skipmsg)
else:
## actually load datasets
source = loadfct() # load source
# check period
if 'period' in source.atts and dataargs.periodstr != source.atts.period: # a NetCDF attribute
raise DateError, "Specifed period is inconsistent with netcdf records: '{:s}' != '{:s}'".format(
periodstr, source.atts.period)
# print message
if mode == 'climatology':
opmsgstr = 'Regridding Climatology ({:s}) to {:s} Grid'.format(
periodstr, griddef.name)
elif mode == 'time-series':
opmsgstr = 'Regridding Time-series to {:s} Grid'.format(
griddef.name)
else:
raise NotImplementedError, "Unrecognized Mode: '{:s}'".format(mode)
# print feedback to logger
logger.info(
'\n{0:s} *** {1:^65s} *** \n{0:s} *** {2:^65s} *** \n'
.format(pidstr, datamsgstr, opmsgstr))
if not lparallel and ldebug: logger.info('\n' + str(source) + '\n')
## create new sink/target file
# set attributes
atts = source.atts.copy()
atts['period'] = periodstr
atts['name'] = dataset_name
atts['grid'] = griddef.name
if mode == 'climatology':
atts['title'] = '{:s} Climatology on {:s} Grid'.format(
dataset_name, griddef.name)
elif mode == 'time-series':
atts['title'] = '{:s} Time-series on {:s} Grid'.format(
dataset_name, griddef.name)
# make new dataset
if lwrite: # write to NetCDF file
if os.path.exists(tmpfilepath):
os.remove(tmpfilepath) # remove old temp files
sink = DatasetNetCDF(folder=avgfolder,
filelist=[tmpfilename],
atts=atts,
mode='w')
else:
sink = Dataset(atts=atts) # ony create dataset in memory
# initialize processing
CPU = CentralProcessingUnit(source,
sink,
varlist=varlist,
tmp=False,
feedback=ldebug)
# perform regridding (if target grid is different from native grid!)
if griddef.name != dataset:
# reproject and resample (regrid) dataset
CPU.Regrid(griddef=griddef, flush=True)
# get results
CPU.sync(flush=True)
# add geolocators
sink = addGeoLocator(sink,
griddef=griddef,
lgdal=True,
lreplace=True,
lcheck=True)
# N.B.: WRF datasets come with their own geolocator arrays - we need to replace those!
# add length and names of month
if mode == 'climatology' and not sink.hasVariable(
'length_of_month') and sink.hasVariable('time'):
addLengthAndNamesOfMonth(
sink,
noleap=True if dataset.upper() in ('WRF', 'CESM') else False)
# print dataset
if not lparallel and ldebug:
logger.info('\n' + str(sink) + '\n')
# write results to file
if lwrite:
sink.sync()
writemsg = "\n{:s} >>> Writing to file '{:s}' in dataset {:s}".format(
pidstr, filename, dataset_name)
writemsg += "\n{:s} >>> ('{:s}')\n".format(pidstr, filepath)
logger.info(writemsg)
# rename file to proper name
if not lreturn:
sink.unload()
sink.close()
del sink # destroy all references
if os.path.exists(filepath):
os.remove(filepath) # remove old file
os.rename(
tmpfilepath,
filepath) # this would also overwrite the old file...
# N.B.: there is no temporary file if the dataset is returned, because an open file can't be renamed
# clean up and return
source.unload()
del source, CPU
if lreturn:
return sink # return dataset for further use (netcdf file still open!)
else:
return 0 # "exit code"
# print('')
# print(' +++ processing shift/roll +++ ')
# CPU.Shift(shift=72, axis='lon', byteShift=True, flush=False)
# print('\n')
# get results
CPU.sync(flush=True)
# print('')
# print(sink)
# print('')
# add geolocators
if grid is not 'GPCC':
sink = addGeoLocator(sink,
griddef=griddef,
lgdal=True,
lcheck=True)
# add landmask
#sink.mask(sink.landmask)
#print sink.dataset
addLandMask(sink) # create landmask from precip mask
#sink.stations.mask(sink.landmask) # mask all fields using the new landmask
# add length and names of month
addLengthAndNamesOfMonth(sink, noleap=False)
# newvar = sink.precip
# print
# print newvar.name, newvar.masked
# print newvar.fillValue
# print newvar.data_array.__class__
