def loadNARR_LTM(name=dataset_name, varlist=None, grid=None, interval='monthly', varatts=None, filelist=None, folder=ltmfolder):
''' Get a properly formatted dataset of daily or monthly NARR climatologies (LTM). '''
if grid is None:
# load from original time-series files
if folder is None: folder = orig_ts_folder
# prepare input
if varatts is None: varatts = ltmvaratts.copy()
if varlist is None: varlist = ltmvarlist
if interval == 'monthly':
pfx = '.mon.ltm.nc'; tlen = 12
elif interval == 'daily':
pfx = '.day.ltm.nc'; tlen = 365
else: raise DatasetError, "Selected interval '%s' is not supported!"%interval
# translate varlist
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
# axes dictionary, primarily to override time axis
axes = dict(time=Axis(name='time',units='day',coord=(1,tlen,tlen)),load=True)
if filelist is None: # generate default filelist
filelist = [special[var]+pfx if var in special else var+pfx for var in varlist if var not in nofile]
# load dataset
dataset = DatasetNetCDF(name=name, folder=folder, filelist=filelist, varlist=varlist, varatts=varatts,
axes=axes, atts=projdict, multifile=False, ncformat='NETCDF4_CLASSIC')
# add projection
projection = getProjFromDict(projdict, name='{0:s} Coordinate System'.format(name))
dataset = addGDALtoDataset(dataset, projection=projection, geotransform=None, folder=grid_folder)
else:
# load from neatly formatted and regridded time-series files
if folder is None: folder = avgfolder
raise NotImplementedError, "Need to implement loading neatly formatted and regridded time-series!"
# return formatted dataset
return dataset
def loadGPCC_TS(name=dataset_name, grid=None, varlist=None, resolution='25', varatts=None, filelist=None,
folder=None, lautoregrid=None):
''' Get a properly formatted dataset with the monthly GPCC time-series. '''
if grid is None:
# load from original time-series files
if folder is None: folder = orig_ts_folder
# prepare input
if resolution not in ('05', '10', '25'): raise DatasetError, "Selected resolution '%s' is not available!"%resolution
# translate varlist
if varatts is None: varatts = tsvaratts.copy()
if varlist is None: varlist = varatts.keys()
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
if filelist is None: # generate default filelist
filelist = []
if 'p' in varlist: filelist.append(orig_ts_file.format('precip',resolution))
if 's' in varlist: filelist.append(orig_ts_file.format('statio',resolution))
# load dataset
dataset = DatasetNetCDF(name=name, folder=folder, filelist=filelist, varlist=varlist, varatts=varatts, multifile=False, ncformat='NETCDF4_CLASSIC')
# replace time axis with number of month since Jan 1979
data = np.arange(0,len(dataset.time),1, dtype='int16') + (1901-1979)*12 # month since 1979 (Jan 1979 = 0)
timeAxis = Axis(name='time', units='month', coord=data, atts=dict(long_name='Month since 1979-01'))
dataset.replaceAxis(dataset.time, timeAxis, asNC=False, deepcopy=False)
# add GDAL info
dataset = addGDALtoDataset(dataset, projection=None, geotransform=None)
# N.B.: projection should be auto-detected as geographic
else:
# load from neatly formatted and regridded time-series files
if folder is None: folder = avgfolder
grid, resolution = checkGridRes(grid, resolution, period=None, lclim=False)
dataset = loadObservations(name=name, folder=folder, projection=None, resolution=resolution, grid=grid,
period=None, varlist=varlist, varatts=varatts, filepattern=tsfile,
filelist=filelist, lautoregrid=lautoregrid, mode='time-series')
# return formatted dataset
return dataset
def loadCRU_TS(name=dataset_name, grid=None, varlist=None, resolution=None, varatts=None, filelist=None,
folder=None, lautoregrid=None):
''' Get a properly formatted CRU dataset with monthly mean time-series. '''
if grid is None:
# load from original time-series files
if folder is None: folder = orig_ts_folder
# translate varlist
if varatts is None: varatts = tsvaratts.copy()
if varlist is None: varlist = varatts.keys()
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
# assemble filelist
if filelist is None: # generate default filelist
filelist = [orig_ts_file.format(var) for var in varlist if var not in nofile]
# load dataset
dataset = DatasetNetCDF(name=name, folder=folder, filelist=filelist, varlist=varlist, varatts=varatts,
multifile=False, ncformat='NETCDF4_CLASSIC')
# replace time axis with number of month since Jan 1979
data = np.arange(0,len(dataset.time),1, dtype='int16') + (1901-1979)*12 # month since 1979 (Jan 1979 = 0)
timeAxis = Axis(name='time', units='month', coord=data, atts=dict(long_name='Month since 1979-01'))
dataset.replaceAxis(dataset.time, timeAxis, asNC=False, deepcopy=False)
# add projection
dataset = addGDALtoDataset(dataset, projection=None, geotransform=None, gridfolder=grid_folder)
# N.B.: projection should be auto-detected as geographic
else:
# load from neatly formatted and regridded time-series files
if folder is None: folder = avgfolder
dataset = loadObservations(name=name, folder=folder, projection=None, resolution=None, grid=grid,
period=None, varlist=varlist, varatts=varatts, filepattern=tsfile,
filelist=filelist, lautoregrid=lautoregrid, mode='time-series')
# return formatted dataset
return dataset
def loadNARR_TS(name=dataset_name, grid=None, varlist=None, resolution=None, varatts=None, filelist=None,
folder=None, lautoregrid=None):
''' Get a properly formatted NARR dataset with monthly mean time-series. '''
if grid is None:
# load from original time-series files
if folder is None: folder = orig_ts_folder
# translate varlist
if varatts is None: varatts = tsvaratts.copy()
if varlist is None: varlist = tsvarlist
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
if filelist is None: # generate default filelist
filelist = [orig_ts_file.format(special[var]) if var in special else orig_ts_file.format(var) for var in varlist
if var not in nofile and var in varatts]
# load dataset
dataset = DatasetNetCDF(name=name, folder=folder, filelist=filelist, varlist=varlist, varatts=varatts,
atts=projdict, multifile=False, ncformat='NETCDF4_CLASSIC')
# replace time axis with number of month since Jan 1979
data = np.arange(0,len(dataset.time),1, dtype='int16') # month since 1979 (Jan 1979 = 0)
timeAxis = Axis(name='time', units='month', coord=data, atts=dict(long_name='Month since 1979-01'))
dataset.replaceAxis(dataset.time, timeAxis, asNC=False, deepcopy=False)
# add projection
projection = getProjFromDict(projdict, name='{0:s} Coordinate System'.format(name))
dataset = addGDALtoDataset(dataset, projection=projection, geotransform=None, gridfolder=grid_folder)
else:
# load from neatly formatted and regridded time-series files
if folder is None: folder = avgfolder
dataset = loadObservations(name=name, folder=folder, projection=None, resolution=None, grid=grid,
period=None, varlist=varlist, varatts=varatts, filepattern=tsfile,
filelist=filelist, lautoregrid=lautoregrid, mode='time-series')
# return formatted dataset
return dataset
def loadPCIC_LTM(name=dataset_name,
varlist=None,
varatts=ltmvaratts,
filelist=None,
folder=ltmfolder):
''' Get a properly formatted dataset the monthly PCIC PRISM climatology. '''
# translate varlist
if varlist is None: varlist = varatts.keys()
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
# generate file list
filelist = [
ltmfile.format(var) for var in varlist
if var not in ('time', 'lat', 'lon')
]
# load variables separately
dataset = DatasetNetCDF(name=name,
folder=folder,
filelist=filelist,
varlist=varlist,
varatts=varatts,
ncformat='NETCDF4')
dataset = addGDALtoDataset(dataset,
projection=None,
geotransform=None,
gridfolder=grid_folder)
# N.B.: projection should be auto-detected as geographic
# return formatted dataset
return dataset
def loadGPCC_LTM(
name=dataset_name, varlist=None, resolution="025", varatts=ltmvaratts, filelist=None, folder=ltmfolder
):
""" Get a properly formatted dataset the monthly accumulated GPCC precipitation climatology. """
# prepare input
if resolution not in ("025", "05", "10", "25"):
raise DatasetError, "Selected resolution '%s' is not available!" % resolution
# translate varlist
if varlist is None:
varlist = varatts.keys()
if varlist and varatts:
varlist = translateVarNames(varlist, varatts)
# load variables separately
if "p" in varlist:
dataset = DatasetNetCDF(
name=name,
folder=folder,
filelist=["normals_v2011_%s.nc" % resolution],
varlist=["p"],
varatts=varatts,
ncformat="NETCDF4_CLASSIC",
)
if "s" in varlist:
gauges = nc.Dataset(folder + "normals_gauges_v2011_%s.nc" % resolution, mode="r", format="NETCDF4_CLASSIC")
stations = Variable(data=gauges.variables["p"][0, :, :], axes=(dataset.lat, dataset.lon), **varatts["s"])
# consolidate dataset
dataset.addVariable(stations, asNC=False, copy=True)
dataset = addGDALtoDataset(dataset, projection=None, geotransform=None, gridfolder=grid_folder)
# N.B.: projection should be auto-detected as geographic
# return formatted dataset
return dataset
def loadCFSR_TS(name=dataset_name, grid=None, varlist=None, varatts=None, resolution='hires',
filelist=None, folder=None, lautoregrid=None):
''' Get a properly formatted CFSR dataset with monthly mean time-series. '''
if grid is None:
# load from original time-series files
if folder is None: folder = orig_ts_folder
# translate varlist
if varatts is None: varatts = tsvaratts.copy()
if varlist is None:
if resolution == 'hires' or resolution == '03' or resolution == '031': varlist = varlist_hires
elif resolution == 'lowres' or resolution == '05': varlist = varlist_lowres
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
if filelist is None: # generate default filelist
if resolution == 'hires' or resolution == '03' or resolution == '031':
files = [hiresfiles[var] for var in varlist if var in hiresfiles]
elif resolution == 'lowres' or resolution == '05':
files = [lowresfiles[var] for var in varlist if var in lowresfiles]
# load dataset
dataset = DatasetNetCDF(name=name, folder=folder, filelist=files, varlist=varlist, varatts=varatts,
check_override=['time'], multifile=False, ncformat='NETCDF4_CLASSIC')
# load static data
if filelist is None: # generate default filelist
if resolution == 'hires' or resolution == '03' or resolution == '031':
files = [hiresstatic[var] for var in varlist if var in hiresstatic]
elif resolution == 'lowres' or resolution == '05':
files = [lowresstatic[var] for var in varlist if var in lowresstatic]
# load constants, if any (and with singleton time axis)
if len(files) > 0:
staticdata = DatasetNetCDF(name=name, folder=folder, filelist=files, varlist=varlist, varatts=varatts,
axes=dict(lon=dataset.lon, lat=dataset.lat), multifile=False,
check_override=['time'], ncformat='NETCDF4_CLASSIC')
# N.B.: need to override the axes, so that the datasets are consistent
if len(staticdata.variables) > 0:
for var in staticdata.variables.values():
if not dataset.hasVariable(var.name):
var.squeeze() # remove time dimension
dataset.addVariable(var, copy=False) # no need to copy... but we can't write to the netcdf file!
# replace time axis with number of month since Jan 1979
data = np.arange(0,len(dataset.time),1, dtype='int16') # month since 1979 (Jan 1979 = 0)
timeAxis = Axis(name='time', units='month', coord=data, atts=dict(long_name='Month since 1979-01'))
dataset.replaceAxis(dataset.time, timeAxis, asNC=False, deepcopy=False)
# add projection
dataset = addGDALtoDataset(dataset, projection=None, geotransform=None, gridfolder=grid_folder)
# N.B.: projection should be auto-detected as geographic
else:
# load from neatly formatted and regridded time-series files
if folder is None: folder = avgfolder
grid, resolution = checkGridRes(grid, resolution)
dataset = loadObservations(name=name, folder=folder, projection=None, resolution=resolution, grid=grid,
period=None, varlist=varlist, varatts=varatts, filepattern=tsfile,
filelist=filelist, lautoregrid=lautoregrid, mode='time-series')
# return formatted dataset
return dataset
def loadPCIC_LTM(name=dataset_name, varlist=None, varatts=ltmvaratts, filelist=None, folder=ltmfolder):
''' Get a properly formatted dataset the monthly PCIC PRISM climatology. '''
# translate varlist
if varlist is None: varlist = varatts.keys()
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
# generate file list
filelist = [ltmfile.format(var) for var in varlist if var not in ('time','lat','lon')]
# load variables separately
dataset = DatasetNetCDF(name=name, folder=folder, filelist=filelist, varlist=varlist, varatts=varatts, ncformat='NETCDF4')
dataset = addGDALtoDataset(dataset, projection=None, geotransform=None, gridfolder=grid_folder)
# N.B.: projection should be auto-detected as geographic
# return formatted dataset
return dataset
def loadGPCC_LTM(name=dataset_name,
varlist=None,
resolution='025',
varatts=ltmvaratts,
filelist=None,
folder=ltmfolder):
''' Get a properly formatted dataset the monthly accumulated GPCC precipitation climatology. '''
# prepare input
if resolution not in ('025', '05', '10', '25'):
raise DatasetError, "Selected resolution '%s' is not available!" % resolution
# translate varlist
if varlist is None: varlist = varatts.keys()
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
# load variables separately
if 'p' in varlist:
dataset = DatasetNetCDF(name=name,
folder=folder,
filelist=['normals_v2011_%s.nc' % resolution],
varlist=['p'],
varatts=varatts,
ncformat='NETCDF4_CLASSIC')
if 's' in varlist:
gauges = nc.Dataset(folder + 'normals_gauges_v2011_%s.nc' % resolution,
mode='r',
format='NETCDF4_CLASSIC')
stations = Variable(data=gauges.variables['p'][0, :, :],
axes=(dataset.lat, dataset.lon),
**varatts['s'])
# consolidate dataset
dataset.addVariable(stations, asNC=False, copy=True)
dataset = addGDALtoDataset(dataset,
projection=None,
geotransform=None,
gridfolder=grid_folder)
# N.B.: projection should be auto-detected as geographic
# return formatted dataset
return dataset
def loadCFSR_TS(name=dataset_name,
grid=None,
varlist=None,
varatts=None,
resolution='hires',
filelist=None,
folder=None,
lautoregrid=None):
''' Get a properly formatted CFSR dataset with monthly mean time-series. '''
if grid is None:
# load from original time-series files
if folder is None: folder = orig_ts_folder
# translate varlist
if varatts is None: varatts = tsvaratts.copy()
if varlist is None:
if resolution == 'hires' or resolution == '03' or resolution == '031':
varlist = varlist_hires
elif resolution == 'lowres' or resolution == '05':
varlist = varlist_lowres
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
if filelist is None: # generate default filelist
if resolution == 'hires' or resolution == '03' or resolution == '031':
files = [
hiresfiles[var] for var in varlist if var in hiresfiles
]
elif resolution == 'lowres' or resolution == '05':
files = [
lowresfiles[var] for var in varlist if var in lowresfiles
]
# load dataset
dataset = DatasetNetCDF(name=name,
folder=folder,
filelist=files,
varlist=varlist,
varatts=varatts,
check_override=['time'],
multifile=False,
ncformat='NETCDF4_CLASSIC')
# load static data
if filelist is None: # generate default filelist
if resolution == 'hires' or resolution == '03' or resolution == '031':
files = [
hiresstatic[var] for var in varlist if var in hiresstatic
]
elif resolution == 'lowres' or resolution == '05':
files = [
lowresstatic[var] for var in varlist if var in lowresstatic
]
# create singleton time axis
staticdata = DatasetNetCDF(name=name,
folder=folder,
filelist=files,
varlist=varlist,
varatts=varatts,
axes=dict(lon=dataset.lon,
lat=dataset.lat),
multifile=False,
check_override=['time'],
ncformat='NETCDF4_CLASSIC')
# N.B.: need to override the axes, so that the datasets are consistent
if len(staticdata.variables) > 0:
for var in staticdata.variables.values():
if not dataset.hasVariable(var.name):
var.squeeze() # remove time dimension
dataset.addVariable(
var, copy=False
) # no need to copy... but we can't write to the netcdf file!
# replace time axis with number of month since Jan 1979
data = np.arange(0, len(dataset.time), 1,
dtype='int16') # month since 1979 (Jan 1979 = 0)
timeAxis = Axis(name='time',
units='month',
coord=data,
atts=dict(long_name='Month since 1979-01'))
dataset.replaceAxis(dataset.time, timeAxis, asNC=False, deepcopy=False)
# add projection
dataset = addGDALtoDataset(dataset,
projection=None,
geotransform=None,
gridfolder=grid_folder)
# N.B.: projection should be auto-detected as geographic
else:
# load from neatly formatted and regridded time-series files
if folder is None: folder = avgfolder
grid, resolution = checkGridRes(grid, resolution)
dataset = loadObservations(name=name,
folder=folder,
projection=None,
resolution=resolution,
grid=grid,
period=None,
varlist=varlist,
varatts=varatts,
filepattern=tsfile,
filelist=filelist,
lautoregrid=lautoregrid,
mode='time-series')
# return formatted dataset
return dataset
def __init__(self):
self.name = 'const'
self.atts = dict(orog = dict(name='zs', units='m'), # surface altitude
# axes (don't have their own file)
class Axes(FileType):
''' A mock-filetype for axes. '''
def __init__(self):
self.atts = dict(time = dict(name='time', units='days', offset=-47116, atts=dict(long_name='Month since 1979')), # time coordinate (days since 1979-01-01)
# NOTE THAT THE CMIP5 DATASET HAVE DIFFERENT TIME OFFSETS BETWEEN MEMBERS !!!
# N.B.: the time coordinate is only used for the monthly time-series data, not the LTM
# the time offset is chose such that 1979 begins with the origin (time=0)
lon = dict(name='lon', units='deg E'), # west-east coordinate
lat = dict(name='lat', units='deg N'), # south-north coordinate
plev = dict(name='lev', units='')) # hybrid pressure coordinate
self.vars = self.atts.keys()
# Time-Series (monthly)
def loadCMIP5_TS(experiment=None, name=None, grid=None, filetypes=None, varlist=None, varatts=None,
translateVars=None, lautoregrid=None, load3D=False, ignore_list=None, lcheckExp=True,
lreplaceTime=True, lwrite=False, exps=None):
''' Get a properly formatted CESM dataset with a monthly time-series. (wrapper for loadCESM)'''
return loadCMIP5_All(experiment=experiment, name=name, grid=grid, period=None, station=None,
filetypes=filetypes, varlist=varlist, varatts=varatts, translateVars=translateVars,
lautoregrid=lautoregrid, load3D=load3D, ignore_list=ignore_list, mode='time-series',
lcheckExp=lcheckExp, lreplaceTime=lreplaceTime, lwrite=lwrite, exps=exps)
# load minimally pre-processed CESM climatology files
def loadCMIP5(experiment=None, name=None, grid=None, period=None, filetypes=None, varlist=None,
varatts=None, translateVars=None, lautoregrid=None, load3D=False, ignore_list=None,
lcheckExp=True, lreplaceTime=True, lencl=False, lwrite=False, exps=None):
''' Get a properly formatted monthly CESM climatology as NetCDFDataset. '''
return loadCMIP5_All(experiment=experiment, name=name, grid=grid, period=period, station=None,
filetypes=filetypes, varlist=varlist, varatts=varatts, translateVars=translateVars,
lautoregrid=lautoregrid, load3D=load3D, ignore_list=ignore_list, exps=exps,
mode='climatology', lcheckExp=lcheckExp, lreplaceTime=lreplaceTime, lwrite=lwrite)
# load any of the various pre-processed CESM climatology and time-series files
def loadCMIP5_All(experiment=None, name=None, grid=None, station=None, shape=None, period=None,
varlist=None, varatts=None, translateVars=None, lautoregrid=None, load3D=False,
ignore_list=None, mode='climatology', cvdp_mode=None, lcheckExp=True, exps=None,
lreplaceTime=True, filetypes=None, lencl=False, lwrite=False, check_vars=None):
''' Get any of the monthly CESM files as a properly formatted NetCDFDataset. '''
# period
if isinstance(period,(tuple,list)):
if not all(isNumber(period)): raise ValueError
elif isinstance(period,basestring): period = [int(prd) for prd in period.split('-')]
elif isinstance(period,(int,np.integer)) or period is None : pass # handled later
else: raise DateError, "Illegal period definition: {:s}".format(str(period))
# prepare input
lclim = False; lts = False; lcvdp = False; ldiag = False # mode switches
if mode.lower() == 'climatology': # post-processed climatology files
lclim = True
folder,experiment,name = getFolderName(name=name, experiment=experiment, folder=None, mode='avg', exps=exps)
if period is None: raise DateError, 'Currently CESM Climatologies have to be loaded with the period explicitly specified.'
elif mode.lower() in ('time-series','timeseries'): # concatenated time-series files
lts = True
folder,experiment,name = getFolderName(name=name, experiment=experiment, folder=None, mode='avg', exps=exps)
lclim = False; period = None; periodstr = None # to indicate time-series (but for safety, the input must be more explicit)
if lautoregrid is None: lautoregrid = False # this can take very long!
elif mode.lower() == 'cvdp': # concatenated time-series files
lcvdp = True
folder,experiment,name = getFolderName(name=name, experiment=experiment, folder=None, mode='cvdp',
cvdp_mode=cvdp_mode, exps=exps)
if period is None:
if not isinstance(experiment,Exp): raise DatasetError, 'Periods can only be inferred for registered datasets.'
period = (experiment.beginyear, experiment.endyear)
elif mode.lower() == 'diag': # concatenated time-series files
ldiag = True
folder,experiment,name = getFolderName(name=name, experiment=experiment, folder=None, mode='diag', exps=exps)
raise NotImplementedError, "Loading AMWG diagnostic files is not supported yet."
else: raise NotImplementedError,"Unsupported mode: '{:s}'".format(mode)
# cast/copy varlist
if isinstance(varlist,basestring): varlist = [varlist] # cast as list
elif varlist is not None: varlist = list(varlist) # make copy to avoid interference
# handle stations and shapes
if station and shape: raise ArgumentError
elif station or shape:
if grid is not None: raise NotImplementedError, 'Currently CESM station data can only be loaded from the native grid.'
if lcvdp: raise NotImplementedError, 'CVDP data is not available as station data.'
if lautoregrid: raise GDALError, 'Station data can not be regridded, since it is not map data.'
lstation = bool(station); lshape = bool(shape)
# add station/shape parameters
if varlist:
params = stn_params if lstation else shp_params
for param in params:
if param not in varlist: varlist.append(param)
else:
lstation = False; lshape = False
# period
if isinstance(period,(int,np.integer)):
if not isinstance(experiment,Exp): raise DatasetError, 'Integer periods are only supported for registered datasets.'
period = (experiment.beginyear, experiment.beginyear+period)
if lclim: periodstr = '_{0:4d}-{1:4d}'.format(*period)
elif lcvdp: periodstr = '{0:4d}-{1:4d}'.format(period[0],period[1]-1)
else: periodstr = ''
# N.B.: the period convention in CVDP is that the end year is included
# generate filelist and attributes based on filetypes and domain
if filetypes is None: filetypes = ['atm','lnd']
elif isinstance(filetypes,(list,tuple,set,basestring)):
if isinstance(filetypes,basestring): filetypes = [filetypes]
else: filetypes = list(filetypes)
# interprete/replace WRF filetypes (for convenience)
tmp = []
for ft in filetypes:
if ft in ('const','drydyn3d','moist3d','rad','plev3d','srfc','xtrm','hydro'):
if 'atm' not in tmp: tmp.append('atm')
elif ft in ('lsm','snow'):
if 'lnd' not in tmp: tmp.append('lnd')
elif ft in ('aux'): pass # currently not supported
# elif ft in (,):
# if 'atm' not in tmp: tmp.append('atm')
# if 'lnd' not in tmp: tmp.append('lnd')
else: tmp.append(ft)
filetypes = tmp; del tmp
if 'axes' not in filetypes: filetypes.append('axes')
else: raise TypeError
atts = dict(); filelist = []; typelist = []
for filetype in filetypes:
fileclass = fileclasses[filetype]
if lclim and fileclass.climfile is not None: filelist.append(fileclass.climfile)
elif lts and fileclass.tsfile is not None: filelist.append(fileclass.tsfile)
elif lcvdp and fileclass.cvdpfile is not None: filelist.append(fileclass.cvdpfile)
elif ldiag and fileclass.diagfile is not None: filelist.append(fileclass.diagfile)
typelist.append(filetype)
atts.update(fileclass.atts)
# figure out ignore list
if ignore_list is None: ignore_list = set(ignore_list_2D)
elif isinstance(ignore_list,(list,tuple)): ignore_list = set(ignore_list)
elif not isinstance(ignore_list,set): raise TypeError
if not load3D: ignore_list.update(ignore_list_3D)
if lautoregrid is None: lautoregrid = not load3D # don't auto-regrid 3D variables - takes too long!
# translate varlist
if varatts is not None: atts.update(varatts)
lSST = False
if varlist is not None:
varlist = list(varlist)
if 'SST' in varlist: # special handling of name SST variable, as it is part of Ts
varlist.remove('SST')
if not 'Ts' in varlist: varlist.append('Ts')
lSST = True # Ts is renamed to SST below
if translateVars is None: varlist = list(varlist) + translateVarNames(varlist, atts) # also aff translations, just in case
elif translateVars is True: varlist = translateVarNames(varlist, atts)
# N.B.: DatasetNetCDF does never apply translation!
# NetCDF file mode
ncmode = 'rw' if lwrite else 'r'
# get grid or station-set name
if lstation:
# the station name can be inserted as the grid name
gridstr = '_'+station.lower(); # only use lower case for filenames
griddef = None
elif lshape:
# the station name can be inserted as the grid name
gridstr = '_'+shape.lower(); # only use lower case for filenames
griddef = None
else:
if grid is None or grid == experiment.grid:
gridstr = ''; griddef = None
else:
gridstr = '_'+grid.lower() # only use lower case for filenames
griddef = loadPickledGridDef(grid=grid, res=None, filename=None, folder=grid_folder, check=True)
# insert grid name and period
filenames = []
for filetype,fileformat in zip(typelist,filelist):
if lclim: filename = fileformat.format(gridstr,periodstr) # put together specfic filename for climatology
elif lts: filename = fileformat.format(gridstr) # or for time-series
elif lcvdp: filename = fileformat.format(experiment.name if experiment else name,periodstr) # not implemented: gridstr
elif ldiag: raise NotImplementedError
else: raise DatasetError
filenames.append(filename) # append to list (passed to DatasetNetCDF later)
# check existance
filepath = '{:s}/{:s}'.format(folder,filename)
if not os.path.exists(filepath):
nativename = fileformat.format('',periodstr) # original filename (before regridding)
nativepath = '{:s}/{:s}'.format(folder,nativename)
if os.path.exists(nativepath):
if lautoregrid:
from processing.regrid import performRegridding # causes circular reference if imported earlier
griddef = loadPickledGridDef(grid=grid, res=None, folder=grid_folder)
dataargs = dict(experiment=experiment, filetypes=[filetype], period=period)
print("The '{:s}' (CESM) dataset for the grid ('{:s}') is not available:\n Attempting regridding on-the-fly.".format(name,filename,grid))
if performRegridding('CESM','climatology' if lclim else 'time-series', griddef, dataargs): # default kwargs
raise IOError, "Automatic regridding failed!"
print("Output: '{:s}'".format(name,filename,grid,filepath))
else: raise IOError, "The '{:s}' (CESM) dataset '{:s}' for the selected grid ('{:s}') is not available - use the regrid module to generate it.".format(name,filename,grid)
else: raise IOError, "The '{:s}' (CESM) dataset file '{:s}' does not exits!\n({:s})".format(name,filename,folder)
# load dataset
#print varlist, filenames
if experiment: title = experiment.title
else: title = name
dataset = DatasetNetCDF(name=name, folder=folder, filelist=filenames, varlist=varlist, axes=None,
varatts=atts, title=title, multifile=False, ignore_list=ignore_list,
ncformat='NETCDF4', squeeze=True, mode=ncmode, check_vars=check_vars)
# replace time axis
if lreplaceTime:
if lts or lcvdp:
# check time axis and center at 1979-01 (zero-based)
if experiment is None: ys = period[0]; ms = 1
else: ys,ms,ds = [int(t) for t in experiment.begindate.split('-')]; assert ds == 1
if dataset.hasAxis('time'):
ts = (ys-1979)*12 + (ms-1); te = ts+len(dataset.time) # month since 1979 (Jan 1979 = 0)
atts = dict(long_name='Month since 1979-01')
timeAxis = Axis(name='time', units='month', coord=np.arange(ts,te,1, dtype='int16'), atts=atts)
dataset.replaceAxis(dataset.time, timeAxis, asNC=False, deepcopy=False)
if dataset.hasAxis('year'):
ts = ys-1979; te = ts+len(dataset.year) # month since 1979 (Jan 1979 = 0)
atts = dict(long_name='Years since 1979-01')
yearAxis = Axis(name='year', units='year', coord=np.arange(ts,te,1, dtype='int16'), atts=atts)
dataset.replaceAxis(dataset.year, yearAxis, asNC=False, deepcopy=False)
elif lclim:
if dataset.hasAxis('time') and not dataset.time.units.lower() in monthlyUnitsList:
atts = dict(long_name='Month of the Year')
timeAxis = Axis(name='time', units='month', coord=np.arange(1,13, dtype='int16'), atts=atts)
assert len(dataset.time) == len(timeAxis), dataset.time
dataset.replaceAxis(dataset.time, timeAxis, asNC=False, deepcopy=False)
elif dataset.hasAxis('year'): raise NotImplementedError, dataset
# rename SST
if lSST: dataset['SST'] = dataset.Ts
# correct ordinal number of shape (should start at 1, not 0)
if lshape:
# mask all shapes that are incomplete in dataset
if lencl and 'shp_encl' in dataset: dataset.mask(mask='shp_encl', invert=True)
if dataset.hasAxis('shapes'): raise AxisError, "Axis 'shapes' should be renamed to 'shape'!"
if not dataset.hasAxis('shape'): raise AxisError
if dataset.shape.coord[0] == 0: dataset.shape.coord += 1
# check
if len(dataset) == 0: raise DatasetError, 'Dataset is empty - check source file or variable list!'
# add projection, if applicable
if not ( lstation or lshape ):
dataset = addGDALtoDataset(dataset, griddef=griddef, gridfolder=grid_folder, lwrap360=True, geolocator=True)
# return formatted dataset
return dataset
## Dataset API
dataset_name = 'CMIP5' # dataset name
root_folder # root folder of the dataset
avgfolder # root folder for monthly averages
outfolder # root folder for direct WRF output
ts_file_pattern = 'cmip5{0:s}{1:s}_monthly.nc' # filename pattern: filetype, grid
clim_file_pattern = 'cmip5{0:s}{1:s}_clim{2:s}.nc' # filename pattern: filetype, grid, period
data_folder = root_folder # folder for user data
grid_def = {'':None} # there are too many...
grid_res = {'':1.} # approximate grid resolution at 45 degrees latitude
default_grid = None
# functions to access specific datasets
loadLongTermMean = None # WRF doesn't have that...
loadClimatology = loadCESM # pre-processed, standardized climatology
loadTimeSeries = loadCESM_TS # time-series data
#loadStationClimatology = loadCESM_Stn # pre-processed, standardized climatology at stations
#loadStationTimeSeries = loadCESM_StnTS # time-series data at stations
#loadShapeClimatology = loadCESM_Shp # climatologies without associated grid (e.g. provinces or basins)
#loadShapeTimeSeries = loadCESM_ShpTS # time-series without associated grid (e.g. provinces or basins)
## (ab)use main execution for quick test
if __name__ == '__main__':
# set mode/parameters
# mode = 'test_climatology'
# mode = 'test_timeseries'
# mode = 'test_ensemble'
# mode = 'test_point_climatology'
# mode = 'test_point_timeseries'
# mode = 'test_point_ensemble'
# mode = 'test_cvdp'
mode = 'pickle_grid'
# mode = 'shift_lon'
# experiments = ['Ctrl-1', 'Ctrl-A', 'Ctrl-B', 'Ctrl-C']
# experiments += ['Ctrl-2050', 'Ctrl-A-2050', 'Ctrl-B-2050', 'Ctrl-C-2050']
experiments = ('Ctrl-1',)
periods = (15,)
filetypes = ('atm',) # ['atm','lnd','ice']
grids = ('cesm1x1',)*len(experiments) # grb1_d01
# pntset = 'shpavg'
pntset = 'ecprecip'
from projects.CESM_experiments import Exp, CESM_exps, ensembles
# N.B.: importing Exp through CESM_experiments is necessary, otherwise some isinstance() calls fail
# pickle grid definition
if mode == 'pickle_grid':
for grid,experiment in zip(grids,experiments):
print('')
print(' *** Pickling Grid Definition for {0:s} *** '.format(grid))
print('')
# load GridDefinition
dataset = loadCESM(experiment=CESM_exps[experiment], grid=None, filetypes=['lnd'], period=(1979,1989))
griddef = dataset.griddef
#del griddef.xlon, griddef.ylat
print griddef
griddef.name = grid
print(' Loading Definition from \'{0:s}\''.format(dataset.name))
# save pickle
filename = '{0:s}/{1:s}'.format(grid_folder,griddef_pickle.format(grid))
if os.path.exists(filename): os.remove(filename) # overwrite
filehandle = open(filename, 'w')
pickle.dump(griddef, filehandle)
filehandle.close()
print(' Saving Pickle to \'{0:s}\''.format(filename))
print('')
# load pickle to make sure it is right
del griddef
griddef = loadPickledGridDef(grid, res=None, folder=grid_folder)
print(griddef)
print('')
print griddef.wrap360
def loadGPCC_TS(name=dataset_name,
grid=None,
varlist=None,
resolution='25',
varatts=None,
filelist=None,
folder=None,
lautoregrid=None):
''' Get a properly formatted dataset with the monthly GPCC time-series. '''
if grid is None:
# load from original time-series files
if folder is None: folder = orig_ts_folder
# prepare input
if resolution not in ('05', '10', '25'):
raise DatasetError, "Selected resolution '%s' is not available!" % resolution
# translate varlist
if varatts is None: varatts = tsvaratts.copy()
if varlist is None: varlist = varatts.keys()
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
if filelist is None: # generate default filelist
filelist = []
if 'p' in varlist:
filelist.append(orig_ts_file.format('precip', resolution))
if 's' in varlist:
filelist.append(orig_ts_file.format('statio', resolution))
# load dataset
dataset = DatasetNetCDF(name=name,
folder=folder,
filelist=filelist,
varlist=varlist,
varatts=varatts,
multifile=False,
ncformat='NETCDF4_CLASSIC')
# replace time axis with number of month since Jan 1979
data = np.arange(0, len(dataset.time), 1, dtype='int16') + (
1901 - 1979) * 12 # month since 1979 (Jan 1979 = 0)
timeAxis = Axis(name='time',
units='month',
coord=data,
atts=dict(long_name='Month since 1979-01'))
dataset.replaceAxis(dataset.time, timeAxis, asNC=False, deepcopy=False)
# add GDAL info
dataset = addGDALtoDataset(dataset, projection=None, geotransform=None)
# N.B.: projection should be auto-detected as geographic
else:
# load from neatly formatted and regridded time-series files
if folder is None: folder = avgfolder
grid, resolution = checkGridRes(grid,
resolution,
period=None,
lclim=False)
dataset = loadObservations(name=name,
folder=folder,
projection=None,
resolution=resolution,
grid=grid,
period=None,
varlist=varlist,
varatts=varatts,
filepattern=tsfile,
filelist=filelist,
lautoregrid=lautoregrid,
mode='time-series')
# return formatted dataset
return dataset
def loadCRU_TS(name=dataset_name,
grid=None,
varlist=None,
resolution=None,
varatts=None,
filelist=None,
folder=None,
lautoregrid=None):
''' Get a properly formatted CRU dataset with monthly mean time-series. '''
if grid is None:
# load from original time-series files
if folder is None: folder = orig_ts_folder
# translate varlist
if varatts is None: varatts = tsvaratts.copy()
if varlist is None: varlist = varatts.keys()
if varlist and varatts: varlist = translateVarNames(varlist, varatts)
# assemble filelist
if filelist is None: # generate default filelist
filelist = [
orig_ts_file.format(var) for var in varlist
if var not in nofile
]
# load dataset
dataset = DatasetNetCDF(name=name,
folder=folder,
filelist=filelist,
varlist=varlist,
varatts=varatts,
multifile=False,
ncformat='NETCDF4_CLASSIC')
# replace time axis with number of month since Jan 1979
data = np.arange(0, len(dataset.time), 1, dtype='int16') + (
1901 - 1979) * 12 # month since 1979 (Jan 1979 = 0)
timeAxis = Axis(name='time',
units='month',
coord=data,
atts=dict(long_name='Month since 1979-01'))
dataset.replaceAxis(dataset.time, timeAxis, asNC=False, deepcopy=False)
# add projection
dataset = addGDALtoDataset(dataset,
projection=None,
geotransform=None,
gridfolder=grid_folder)
# N.B.: projection should be auto-detected as geographic
else:
# load from neatly formatted and regridded time-series files
if folder is None: folder = avgfolder
dataset = loadObservations(name=name,
folder=folder,
projection=None,
resolution=None,
grid=grid,
period=None,
varlist=varlist,
varatts=varatts,
filepattern=tsfile,
filelist=filelist,
lautoregrid=lautoregrid,
mode='time-series')
# return formatted dataset
return dataset