def __call__(self,
lparallel=False,
NP=None,
inner_list=None,
outer_list=None,
callback=None,
**kwargs):
''' this method is called instead of a class or instance method; it applies the arguments
'kwargs' to each ensemble member; it also supports argument expansion with inner and
outer product (prior to application to ensemble) and parallelization using multiprocessing '''
# expand kwargs to ensemble list
kwargs_list = expandArgumentList(inner_list=inner_list,
outer_list=outer_list,
**kwargs)
if len(kwargs_list) == 1:
kwargs_list = kwargs_list * len(self.klass.members)
elif len(kwargs_list) != len(self.klass.members):
raise ArgumentError(
'Length of expanded argument list does not match ensemble size! {} ~= {}'
.format(len(kwargs_list), len(self.klass.members)))
# loop over ensemble members and execute function
if lparallel:
# parallelize method execution using multiprocessing
pool = multiprocessing.Pool(processes=NP) # initialize worker pool
if callback is not None and not callable(callback):
raise TypeError(callback)
# N.B.: the callback function is passed a result from the apply_method function,
# which returns a tuple of the form (member, exit_code)
# define work loads (function and its arguments) and start tasks
results = [
pool.apply_async(apply_method, (member, self.attr),
kwargs,
callback=callback)
for member, kwargs in zip(self.klass.members, kwargs_list)
]
# N.B.: Beware Pickling!!!
pool.close()
pool.join() # wait to finish
# retrieve and assemble results
results = [result.get() for result in results]
# divide members and results (apply_method returns both, in case members were modified)
self.klass.members = [result[0] for result in results]
results = [result[1] for result in results]
else:
# get instance methods
methods = [
getattr(member, self.attr) for member in self.klass.members
]
# just apply sequentially
results = [
method(**kwargs)
for method, kwargs in zip(methods, kwargs_list)
]
if len(results) != len(self.klass.members):
raise ArgumentError(
'Length of results list does not match ensemble size! {} ~= {}'
.format(len(results), len(self.klass.members)))
return tuple(results)
def __call__(self, load_list=None, lproduct='outer', inner_list=None, outer_list=None,
lensemble=None, ens_name=None, ens_title=None, **kwargs):
''' wrap original function: expand argument list, execute load_fct over argument list,
and return a list or Ensemble of datasets '''
# decide, what to do
if load_list is None and inner_list is None and outer_list is None:
# normal operation: no expansion
datasets = self.load_fct(**kwargs)
else:
# expansion required
lensemble = ens_name is not None if lensemble is None else lensemble
# figure out arguments
kwargs_list = expandArgumentList(expand_list=load_list, lproduct=lproduct,
inner_list=inner_list, outer_list=outer_list, **kwargs)
# load datasets
datasets = []
for kwargs in kwargs_list:
# load dataset
datasets.append(self.load_fct(**kwargs))
# construct ensemble
if lensemble:
datasets = Ensemble(members=datasets, name=ens_name, title=ens_title, basetype='Dataset')
# return list or ensemble of datasets
return datasets
def __call__(self, load_list=None, lproduct='outer', inner_list=None, outer_list=None,
lensemble=None, ens_name=None, ens_title=None, **kwargs):
''' wrap original function: expand argument list, execute load_fct over argument list,
and return a list or Ensemble of datasets '''
# decide, what to do
if load_list is None and inner_list is None and outer_list is None:
# normal operation: no expansion
datasets = self.load_fct(**kwargs)
else:
# expansion required
lensemble = ens_name is not None if lensemble is None else lensemble
# figure out arguments
kwargs_list = expandArgumentList(expand_list=load_list, lproduct=lproduct,
inner_list=inner_list, outer_list=outer_list, **kwargs)
# load datasets
datasets = []
for kwargs in kwargs_list:
# load dataset
datasets.append(self.load_fct(**kwargs))
# construct ensemble
if lensemble:
datasets = Ensemble(members=datasets, name=ens_name, title=ens_title, basetype='Dataset')
# return list or ensemble of datasets
return datasets
def __call__(self, lparallel=False, NP=None, inner_list=None, outer_list=None, callback=None, **kwargs):
''' this method is called instead of a class or instance method; it applies the arguments
'kwargs' to each ensemble member; it also supports argument expansion with inner and
outer product (prior to application to ensemble) and parallelization using multiprocessing '''
# expand kwargs to ensemble list
kwargs_list = expandArgumentList(inner_list=inner_list, outer_list=outer_list, **kwargs)
if len(kwargs_list) == 1: kwargs_list = kwargs_list * len(self.klass.members)
elif len(kwargs_list) != len(self.klass.members):
raise ArgumentError('Length of expanded argument list does not match ensemble size! {} ~= {}'.format(
len(kwargs_list),len(self.klass.members)))
# loop over ensemble members and execute function
if lparallel:
# parallelize method execution using multiprocessing
pool = multiprocessing.Pool(processes=NP) # initialize worker pool
if callback is not None and not callable(callback): raise TypeError(callback)
# N.B.: the callback function is passed a result from the apply_method function,
# which returns a tuple of the form (member, exit_code)
# define work loads (function and its arguments) and start tasks
results = [pool.apply_async(apply_method, (member,self.attr), kwargs, callback=callback)
for member,kwargs in zip(self.klass.members,kwargs_list)]
# N.B.: Beware Pickling!!!
pool.close(); pool.join() # wait to finish
# retrieve and assemble results
results = [result.get() for result in results]
# divide members and results (apply_method returns both, in case members were modified)
self.klass.members = [result[0] for result in results]
results = [result[1] for result in results]
else:
# get instance methods
methods = [getattr(member,self.attr) for member in self.klass.members]
# just apply sequentially
results = [method(**kwargs) for method,kwargs in zip(methods,kwargs_list)]
if len(results) != len(self.klass.members):
raise ArgumentError('Length of results list does not match ensemble size! {} ~= {}'.format(
len(results),len(self.klass.members)))
return tuple(results)
def loadEnsembleTS(names=None, name=None, title=None, varlist=None, aggregation=None, season=None, prov=None,
slices=None, obsslices=None, years=None, reduction=None, shape=None, station=None,
constraints=None, filetypes=None, domain=None, ldataset=False, lcheckVar=False,
lwrite=False, ltrimT=True, name_tags=None, dataset_mode='time-series', lminmax=False,
master=None, lall=True, ensemble_list=None, ensemble_product='inner', lensembleAxis=False,
WRF_exps=None, CESM_exps=None, WRF_ens=None, CESM_ens=None, **kwargs):
''' a convenience function to load an ensemble of time-series, based on certain criteria; works
with either stations or regions; seasonal/climatological aggregation is also supported '''
# prepare ensemble
if varlist is not None:
varlist = list(varlist)[:] # copy list
if station:
for var in stn_params: # necessary to select stations
if var not in varlist: varlist.append(var)
if shape:
for var in shp_params: # necessary to select shapes
if var not in varlist: varlist.append(var)
# perpare ensemble and arguments
if ldataset and ensemble_list: raise ArgumentError()
elif not ldataset: ensemble = Ensemble(name=name, title=title, basetype='Dataset')
# expand argument list
if ensemble_list is None: ensemble_list = ['names'] if not ldataset else None
loadargs = expandArgumentList(names=names, station=station, prov=prov, shape=shape, varlist=varlist,
mode=dataset_mode, filetypes=filetypes, domains=domain, lwrite=lwrite,
slices=slices, obsslices=obsslices, name_tags=name_tags, ltrimT=ltrimT,
years=years, expand_list=ensemble_list, lproduct=ensemble_product,
lensembleAxis=lensembleAxis)
for loadarg in loadargs:
# clean up argumetns
name = loadarg.pop('names',None); name_tag = loadarg.pop('name_tags',None)
slcs = loadarg.pop('slices',None); obsslcs = loadarg.pop('obsslices',None)
# load individual dataset
dataset = loadDataset(name=name, WRF_exps=WRF_exps, CESM_exps=CESM_exps, WRF_ens=WRF_ens, CESM_ens=CESM_ens, **loadarg)
if name_tag is not None:
if name_tag[0] == '_': dataset.name += name_tag
else: dataset.name = name_tag
# apply slicing
if obsslcs and ( dataset.name[:3].lower() == 'obs' or dataset.name.isupper() ):
slcs = dict() if slcs is None else slcs.copy()
slcs.update(**obsslcs) # add special slices for obs
# N.B.: currently VarNC's can only be sliced once, because we can't combine slices yet
if slcs: dataset = dataset(lminmax=lminmax, **slcs) # slice immediately
if not ldataset: ensemble += dataset.load() # load data and add to ensemble
# if input was not a list, just return dataset
if ldataset: ensemble = dataset.load() # load data
# select specific stations (if applicable)
if not ldataset and station and constraints:
from datasets.EC import selectStations
ensemble = selectStations(ensemble, stnaxis='station', master=master, linplace=False, lall=lall,
lcheckVar=lcheckVar, **constraints)
# make sure all have cluster meta data
for varname in stn_params + shp_params:
# find valid instance
var = None
for ds in ensemble:
if varname in ds: var = ds[varname]; break
# give to those who have not
if var is not None:
var.load() # load data and add as regular variable (not VarNC)
for ds in ensemble:
if varname not in ds: ds.addVariable(var.copy())
# apply general reduction operations
if reduction is not None:
for ax,op in reduction.iteritems():
if isinstance(op, basestring): ensemble = getattr(ensemble,op)(axis=ax)
elif isinstance(op, (int,np.integer,float,np.inexact)): ensemble = ensemble(**{ax:op})
# extract seasonal/climatological values/extrema
if (ldataset and len(ensemble)==0): raise EmptyDatasetError(varlist)
if not ldataset and any([len(ds)==0 for ds in ensemble]): raise EmptyDatasetError(ensemble)
# N.B.: the operations below should work with Ensembles as well as Datasets
if aggregation:
method = aggregation if aggregation.isupper() else aggregation.title()
if season is None:
ensemble = getattr(ensemble,'clim'+method)(taxis='time', **kwargs)
else:
ensemble = getattr(ensemble,'seasonal'+method)(season=season, taxis='time', **kwargs)
elif season: # but not aggregation
ensemble = ensemble.seasonalSample(season=season)
# return dataset
return ensemble
def loadEnsembleTS(names=None, name=None, title=None, varlist=None, aggregation=None, season=None, prov=None,
slices=None, obsslices=None, years=None, reduction=None, shape=None, station=None,
constraints=None, filetypes=None, domain=None, ldataset=False, lcheckVar=False,
lwrite=False, ltrimT=True, name_tags=None, dataset_mode='time-series', lminmax=False,
master=None, lall=True, ensemble_list=None, ensemble_product='inner', lensembleAxis=False,
WRF_exps=None, CESM_exps=None, WRF_ens=None, CESM_ens=None, **kwargs):
''' a convenience function to load an ensemble of time-series, based on certain criteria; works
with either stations or regions; seasonal/climatological aggregation is also supported '''
# prepare ensemble
if varlist is not None:
varlist = list(varlist)[:] # copy list
if station:
for var in stn_params: # necessary to select stations
if var not in varlist: varlist.append(var)
if shape:
for var in shp_params: # necessary to select shapes
if var not in varlist: varlist.append(var)
# perpare ensemble and arguments
if ldataset and ensemble_list: raise ArgumentError
elif not ldataset: ensemble = Ensemble(name=name, title=title, basetype='Dataset')
# expand argument list
if ensemble_list is None: ensemble_list = ['names'] if not ldataset else None
loadargs = expandArgumentList(names=names, station=station, prov=prov, shape=shape, varlist=varlist,
mode=dataset_mode, filetypes=filetypes, domains=domain, lwrite=lwrite,
slices=slices, obsslices=obsslices, name_tags=name_tags, ltrimT=ltrimT,
years=years, expand_list=ensemble_list, lproduct=ensemble_product,
lensembleAxis=lensembleAxis)
for loadarg in loadargs:
# clean up argumetns
name = loadarg.pop('names',None); name_tag = loadarg.pop('name_tags',None)
slcs = loadarg.pop('slices',None); obsslcs = loadarg.pop('obsslices',None)
# load individual dataset
dataset = loadDataset(name=name, WRF_exps=WRF_exps, CESM_exps=CESM_exps, WRF_ens=WRF_ens, CESM_ens=CESM_ens, **loadarg)
if name_tag is not None:
if name_tag[0] == '_': dataset.name += name_tag
else: dataset.name = name_tag
# apply slicing
if obsslcs and ( dataset.name[:3].lower() == 'obs' or dataset.name.isupper() ):
if slcs is None: slcs = obsslcs
else: slcs.update(**obsslcs) # add special slices for obs
# N.B.: currently VarNC's can only be sliced once, because we can't combine slices yet
if slcs: dataset = dataset(lminmax=lminmax, **slcs) # slice immediately
if not ldataset: ensemble += dataset.load() # load data and add to ensemble
# if input was not a list, just return dataset
if ldataset: ensemble = dataset.load() # load data
# select specific stations (if applicable)
if not ldataset and station and constraints:
from datasets.EC import selectStations
ensemble = selectStations(ensemble, stnaxis='station', master=master, linplace=False, lall=lall,
lcheckVar=lcheckVar, **constraints)
# make sure all have cluster meta data
for varname in stn_params + shp_params:
# find valid instance
var = None
for ds in ensemble:
if varname in ds: var = ds[varname]; break
# give to those who have not
if var is not None:
var.load() # load data and add as regular variable (not VarNC)
for ds in ensemble:
if varname not in ds: ds.addVariable(var.copy())
# apply general reduction operations
if reduction is not None:
for ax,op in reduction.iteritems():
if isinstance(op, basestring): ensemble = getattr(ensemble,op)(axis=ax)
elif isinstance(op, (int,np.integer,float,np.inexact)): ensemble = ensemble(**{ax:op})
# extract seasonal/climatological values/extrema
if (ldataset and len(ensemble)==0): raise EmptyDatasetError, varlist
if not ldataset and any([len(ds)==0 for ds in ensemble]): raise EmptyDatasetError, ensemble
# N.B.: the operations below should work with Ensembles as well as Datasets
if aggregation:
method = aggregation if aggregation.isupper() else aggregation.title()
if season is None:
ensemble = getattr(ensemble,'clim'+method)(taxis='time', **kwargs)
else:
ensemble = getattr(ensemble,'seasonal'+method)(season=season, taxis='time', **kwargs)
elif season: # but not aggregation
ensemble = ensemble.seasonalSample(season=season)
# return dataset
return ensemble
def __init__(self, inner_list=None, outer_list=None, **kwargs):
''' initialize an ensemble of HGS simulations based on HGS arguments and project descriptors;
all keyword arguments are automatically expanded based on inner/outer product rules, defined
using the inner_list/outer_list arguments; the expanded argument lists are used to initialize
the individual ensemble members; note that a string substitution is applied to all folder
variables (incl. 'rundir') prior to constructing the HGS instance, i.e. rundir.format(**kwargs) '''
self.lreport = kwargs.get('lreport', self.lreport)
self.loverwrite = kwargs.get('loverwrite', self.loverwrite)
self.lindicator = kwargs.get('lindicator', self.lindicator)
self.lrunfailed = kwargs.get('lrunfailed', self.lrunfailed)
self.lrestart = kwargs.get('lrestart', self.lrestart)
# expand argument list (plain, nothing special)
kwargs_list = expandArgumentList(inner_list=inner_list,
outer_list=outer_list,
**kwargs)
# loop over ensemble members
self.members = []
self.rundirs = []
self.hgsargs = [] # ensemble lists
for kwargs in kwargs_list:
# isolate folder variables and perform variable substitution
for folder_type in ('rundir', 'template_folder', 'input_folder',
'pet_folder', 'precip_inc', 'pet_inc',
'ic_files'):
if folder_type in kwargs:
folder = kwargs[folder_type]
if isinstance(folder, str):
# perform keyword substitution with all available arguments
if folder_type is 'ic_files':
# we need to preserve '{FILETYPE}' for later
kwargs[folder_type] = folder.format(
FILETYPE='{FILETYPE}', **kwargs)
else:
kwargs[folder_type] = folder.format(**kwargs)
elif folder is None:
pass
else:
raise TypeError(folder)
# check rundir
rundir = kwargs['rundir']
kwargs[
'restart'] = False # this keyword argument should be controlled by the Ensemble handler
if rundir in self.rundirs:
raise ArgumentError(
"Multiple occurence of run directory:\n '{}'".format(
rundir))
# figure out skipping
if os.path.exists(rundir):
if self.loverwrite:
if self.lreport:
print(
("Overwriting existing experiment folder '{:s}'.".
format(rundir)))
lskip = False
elif self.lindicator and os.path.exists(
'{}/SCHEDULED'.format(rundir)):
if self.lreport:
print(
("Skipping experiment folder '{:s}' (scheduled).".
format(rundir)))
lskip = True
elif self.lindicator and os.path.exists(
'{}/IN_PROGRESS'.format(rundir)):
if self.lrestart:
shutil.move(os.path.join(rundir, 'IN_PROGRESS'),
os.path.join(rundir, 'RESTARTED'))
if self.lreport:
print((
"Restarting experiment in folder '{:s}' (was in progress)."
.format(rundir)))
lskip = False
kwargs['restart'] = True
else:
if self.lreport:
print((
"Skipping experiment folder '{:s}' (in progress)."
.format(rundir)))
lskip = True
elif self.lindicator and os.path.exists(
'{}/COMPLETED'.format(rundir)):
if self.lreport:
print(
("Skipping experiment folder '{:s}' (completed).".
format(rundir)))
lskip = True
elif self.lindicator and os.path.exists(
'{}/FAILED'.format(rundir)):
# this should be the last option, so as to prevent overwriting data
if self.lrunfailed:
if self.lreport:
print(
("Overwriting failed experiment folder '{:s}'."
.format(rundir)))
lskip = False # rundir will be deleted
else:
if self.lreport:
print(
("Skipping experiment folder '{:s}' (failed).".
format(rundir)))
lskip = True
else: # no/unknown indicator file
if self.lreport:
print(
("Overwriting existing experiment folder '{:s}'.".
format(rundir)))
lskip = False # rundir will be deleted
else:
if self.lreport:
print(("Creating new experiment folder '{:s}'.".format(
rundir)))
lskip = False
if not lskip:
self.rundirs.append(rundir)
# isolate HGS constructor arguments
hgsargs = inspect.getargspec(
HGS.__init__
).args # returns args, varargs, kwargs, defaults
hgsargs = {
arg: kwargs[arg]
for arg in hgsargs if arg in kwargs
}
self.hgsargs.append(hgsargs)
# initialize HGS instance
hgs = HGS(**hgsargs)
self.members.append(hgs)
# final check
if len(self.members) == 0:
raise EnsembleError("No experiments to run (empty list).")
def readRasterArray(file_pattern, lgzip=None, lgdal=True, dtype=np.float32, lmask=True, fillValue=None, lfeedback=False,
lgeotransform=True, axes=None, lna=False, lskipMissing=False, path_params=None, **kwargs):
''' function to load a multi-dimensional numpy array from several structured ASCII raster files '''
if axes is None: raise NotImplementedError
#TODO: implement automatic detection of axes arguments and axes order
## expand path argument and figure out dimensions
# collect axes arguments
shape = []; axes_kwargs = dict()
for ax in axes:
if ax not in kwargs: raise AxisError(ax)
coord = kwargs.pop(ax)
shape.append(len(coord))
axes_kwargs[ax] = coord
assert len(axes) == len(shape) == len(axes_kwargs)
shape = tuple(shape)
#TODO: add handling of embedded inner product expansion
# argument expansion using outer product
file_kwargs_list = expandArgumentList(outer_list=axes, **axes_kwargs)
assert np.prod(shape) == len(file_kwargs_list)
## load data from raster files and assemble array
path_params = dict() if path_params is None else path_params.copy() # will be modified
# find first valid 2D raster to determine shape
i0 = 0
path_params.update(file_kwargs_list[i0]) # update axes parameters
filepath = file_pattern.format(**path_params) # construct file name
if not os.path.exists(filepath):
if lskipMissing: # find first valid
while not os.path.exists(filepath):
i0 += 1 # go to next raster file
if i0 >= len(file_kwargs_list):
raise IOError("No valid input raster files found!\n'{}'".format(filepath))
if lfeedback: print ' ',
path_params.update(file_kwargs_list[i0]) # update axes parameters
filepath = file_pattern.format(**path_params) # nest in line
else: # or raise error
raise IOError(filepath)
# read first 2D raster file
data2D = readASCIIraster(filepath, lgzip=lgzip, lgdal=lgdal, dtype=dtype, lna=True,
lmask=lmask, fillValue=fillValue, lgeotransform=lgeotransform, **kwargs)
if lgeotransform: data2D, geotransform0, na = data2D
else: data2D, na = data2D # we might still need na, but no need to check if it is the same
shape2D = data2D.shape # get 2D raster shape for later use
# allocate data array
list_shape = (np.prod(shape),)+shape2D # assume 3D shape to concatenate 2D rasters
if lmask:
data = ma.empty(list_shape, dtype=dtype)
if fillValue is None: data._fill_value = data2D._fill_value
else: data._fill_value = fillValue
data.mask = True # initialize everything as masked
else: data = np.empty(list_shape, dtype=dtype) # allocate the array
assert data.shape[0] == len(file_kwargs_list), (data.shape, len(file_kwargs_list))
# insert (up to) first raster before continuing
if lskipMissing and i0 > 0:
data[:i0,:,:] = ma.masked if lmask else fillValue # mask all invalid rasters up to first valid raster
data[i0,:,:] = data2D # add first (valid) raster
# loop over remaining 2D raster files
for i,file_kwargs in enumerate(file_kwargs_list[i0:]):
path_params.update(file_kwargs) # update axes parameters
filepath = file_pattern.format(**path_params) # construct file name
if os.path.exists(filepath):
if lfeedback: print '.', # indicate data with bar/pipe
# read 2D raster file
data2D = readASCIIraster(filepath, lgzip=lgzip, lgdal=lgdal, dtype=dtype, lna=False,
lmask=lmask, fillValue=fillValue, lgeotransform=lgeotransform, **kwargs)
# check geotransform
if lgeotransform:
data2D, geotransform = data2D
if not geotransform == geotransform0:
raise AxisError(geotransform) # to make sure all geotransforms are identical!
else: geotransform = None
# size information
if not shape2D == data2D.shape:
raise AxisError(data2D.shape) # to make sure all geotransforms are identical!
# insert 2D raster into 3D array
data[i+i0,:,:] = data2D # raster shape has to match
elif lskipMissing:
# fill with masked values
data[i+i0,:,:] = ma.masked # mask missing raster
if lfeedback: print ' ', # indicate missing with dot
else:
raise IOError(filepath)
# complete feedback with linebreak
if lfeedback: print ''
# reshape and check dimensions
assert i+i0 == data.shape[0]-1, (i,i0)
data = data.reshape(shape+shape2D) # now we have the full shape
gc.collect() # remove duplicate data
# return data and optional meta data
if lgeotransform or lna:
return_data = (data,)
if lgeotransform: return_data += (geotransform,)
if lna: return_data += (na,)
else:
return_data = data
return return_data
def __init__(self, inner_list=None, outer_list=None, **kwargs):
''' initialize an ensemble of HGS simulations based on HGS arguments and project descriptors;
all keyword arguments are automatically expanded based on inner/outer product rules, defined
using the inner_list/outer_list arguments; the expanded argument lists are used to initialize
the individual ensemble members; note that a string substitution is applied to all folder
variables (incl. 'rundir') prior to constructing the HGS instance, i.e. rundir.format(**kwargs) '''
self.lreport = kwargs.get('lreport',self.lreport)
self.loverwrite = kwargs.get('loverwrite',self.loverwrite)
self.lindicator = kwargs.get('lindicator',self.lindicator)
self.lrunfailed = kwargs.get('lrunfailed',self.lrunfailed)
self.lrestart = kwargs.get('lrestart',self.lrestart)
# expand argument list (plain, nothing special)
kwargs_list = expandArgumentList(inner_list=inner_list, outer_list=outer_list, **kwargs)
# loop over ensemble members
self.members = []; self.rundirs = []; self.hgsargs = [] # ensemble lists
for kwargs in kwargs_list:
# isolate folder variables and perform variable substitution
for folder_type in ('rundir','template_folder','input_folder','pet_folder','precip_inc','pet_inc','ic_files'):
if folder_type in kwargs:
folder = kwargs[folder_type]
if isinstance(folder,str):
# perform keyword substitution with all available arguments
if folder_type is 'ic_files':
# we need to preserve '{FILETYPE}' for later
kwargs[folder_type] = folder.format(FILETYPE='{FILETYPE}', **kwargs)
else: kwargs[folder_type] = folder.format(**kwargs)
elif folder is None: pass
else: raise TypeError(folder)
# check rundir
rundir = kwargs['rundir']
kwargs['restart'] = False # this keyword argument should be controlled by the Ensemble handler
if rundir in self.rundirs:
raise ArgumentError("Multiple occurence of run directory:\n '{}'".format(rundir))
# figure out skipping
if os.path.exists(rundir):
if self.loverwrite:
if self.lreport: print(("Overwriting existing experiment folder '{:s}'.".format(rundir)))
lskip = False
elif self.lindicator and os.path.exists('{}/SCHEDULED'.format(rundir)):
if self.lreport: print(("Skipping experiment folder '{:s}' (scheduled).".format(rundir)))
lskip = True
elif self.lindicator and os.path.exists('{}/IN_PROGRESS'.format(rundir)):
if self.lrestart:
shutil.move(os.path.join(rundir,'IN_PROGRESS'),os.path.join(rundir,'RESTARTED'))
if self.lreport: print(("Restarting experiment in folder '{:s}' (was in progress).".format(rundir)))
lskip = False
kwargs['restart'] = True
else:
if self.lreport: print(("Skipping experiment folder '{:s}' (in progress).".format(rundir)))
lskip = True
elif self.lindicator and os.path.exists('{}/COMPLETED'.format(rundir)):
if self.lreport: print(("Skipping experiment folder '{:s}' (completed).".format(rundir)))
lskip = True
elif self.lindicator and os.path.exists('{}/FAILED'.format(rundir)):
# this should be the last option, so as to prevent overwriting data
if self.lrunfailed:
if self.lreport: print(("Overwriting failed experiment folder '{:s}'.".format(rundir)))
lskip = False # rundir will be deleted
else:
if self.lreport: print(("Skipping experiment folder '{:s}' (failed).".format(rundir)))
lskip = True
else: # no/unknown indicator file
if self.lreport: print(("Overwriting existing experiment folder '{:s}'.".format(rundir)))
lskip = False # rundir will be deleted
else:
if self.lreport: print(("Creating new experiment folder '{:s}'.".format(rundir)))
lskip = False
if not lskip:
self.rundirs.append(rundir)
# isolate HGS constructor arguments
hgsargs = inspect.getargspec(HGS.__init__).args # returns args, varargs, kwargs, defaults
hgsargs = {arg:kwargs[arg] for arg in hgsargs if arg in kwargs}
self.hgsargs.append(hgsargs)
# initialize HGS instance
hgs = HGS(**hgsargs)
self.members.append(hgs)
# final check
if len(self.members) == 0:
raise EnsembleError("No experiments to run (empty list).")
def loadShapeObservations(obs=None, seasons=None, basins=None, provs=None, shapes=None, stations=None, varlist=None, slices=None,
aggregation='mean', dataset_mode='time-series', lWSC=True, WSC_period=None, shapetype=None,
variable_list=None, basin_list=None, lforceList=True, obs_ts=None, obs_clim=None,
name=None, title=None, obs_list=None, ensemble_list=None, ensemble_product='inner', **kwargs):
''' convenience function to load shape observations based on 'aggregation' and 'varlist' (mainly add WSC gage data) '''
if obs_list is None: obs_list = observational_datasets
if name is None: name = 'obs'
if title is None: title = 'Observations'
# variables for which ensemble expansion is not supported
not_supported = ('season','seasons','varlist','mode','dataset_mode','provs','basins','shapes',)
# resolve variable list (no need to maintain order)
if isinstance(varlist,str): varlist = [varlist]
variables = set(shp_params)
for name in varlist:
if name in variable_list: variables.update(variable_list[name].vars)
elif lforceList: raise VariableError("Variable list '{}' does not exist.".format(name))
else: variables.add(name)
variables = list(variables)
# determine if we need gage dataset
lWSC = isinstance(basins,str) and any([var in WSC_vars for var in variables]) and lWSC # doesn't work if multiple basins are loaded
# default obs list
if obs is None: obs = ['Observations',]
elif isinstance(obs,str): obs = [obs]
elif isinstance(obs,tuple): obs = list(obs)
elif not isinstance(obs,list): raise TypeError(obs)
# configure slicing (extract basin/province/shape and period)
expand_vars = ('basins','stations','provs','shapes','slices') # variables that need to be added to slices (and expanded first)
if ensemble_list: expand_list = [varname for varname in expand_vars if varname in ensemble_list]
if ensemble_list and expand_list:
local_vars = locals(); exp_args = dict()
for varname in expand_vars: # copy variables to expand right away
exp_args[varname] = local_vars[varname]
for varname in expand_list: # remove entries from ensemble expansion
if varname != 'slices': ensemble_list.remove(varname) # only 'slices' will continue to be expanded
if 'slices' not in ensemble_list: ensemble_list.append('slices')
slices = [_configSlices(**arg_dict) for arg_dict in expandArgumentList(expand_list=expand_list, lproduct=ensemble_product, **exp_args)]
else:
slices = _configSlices(slices=slices, basins=basins, provs=provs, shapes=shapes, stations=stations, period=None)
# substitute default observational dataset and seperate aggregation methods
iobs = None; clim_ens = None
for i,obs_name in reverse_enumerate(obs):
# N.B.: we need to iterate in reverse order, so that deleting items does not interfere with the indexing
if obs_name in obs_aliases or obs_name not in timeseries_datasets:
if iobs is not None: raise ArgumentError("Can only resolve one default dataset: {}".format(obs))
if aggregation == 'mean' and seasons is None and obs_clim is not None:
# remove dataset entry from list (and all the arguments)
del obs[i]; iobs = i # remember position of default obs in ensemble
clim_args = kwargs.copy(); slc = slices; shp = shapetype
# clean up variables for ensemble expansion, if necessary
if ensemble_list and ensemble_product.lower() == 'inner':
if 'names' in ensemble_list:
obs_names = [obs_clim]
for arg in ensemble_list:
if arg in ('slices','shape'): pass # dealt with separately
elif arg in not_supported:
raise ArgumentError("Expansion of keyword '{:s}' is currently not supported in ensemble expansion.".format(arg))
elif arg in kwargs:
clim_args[arg] = kwargs[arg][iobs]; del kwargs[arg][iobs]
else:
raise ArgumentError("Keyword '{:s}' not found in keyword arguments.".format(arg))
if 'slices' in ensemble_list: slc = slices[iobs]; del slices[iobs]
if 'shape' in ensemble_list: shp = shapetype[iobs]; del shapetype[iobs]
clim_len = 1 # expect length of climatology ensemble
else:
obs_names = obs_clim # no name expansion
clim_len = None # expect length of climatology ensemble
for arg in ensemble_list:
if arg in not_supported:
raise ArgumentError("Expansion of keyword '{:s}' is currently not supported in ensemble expansion.".format(arg))
elif 'slices' in ensemble_list: l = len(slc)
elif 'shape' in ensemble_list: l = len(shp)
elif arg in clim_args: l = len(clim_args[arg])
else: raise ArgumentError("Keyword '{:s}' not found in keyword arguments.".format(arg))
if clim_len is None: clim_len = l
elif l != clim_len: raise ArgumentError(arg,l,clim_len)
elif ensemble_list and ensemble_product.lower() == 'outer':
clim_len = 1
for arg in ensemble_list:
if arg != 'names':
assert isinstance(clim_args[arg],(list,tuple)), clim_args[arg]
clim_len *= len(clim_args[arg])
obs_names = [obs_clim] if 'names' in ensemble_list else obs_clim
else:
obs_names = [obs_clim]; clim_len = 1
# now load climtology instead of time-series and skip aggregation
try:
clim_ens = loadEnsemble(names=obs_names, season=seasons, aggregation=None, slices=slc, varlist=variables,
ldataset=False, dataset_mode='climatology', shape=shp,
ensemble_list=ensemble_list, ensemble_product=ensemble_product,
obs_list=obs_list, basin_list=basin_list, **clim_args)
assert len(clim_ens) == clim_len, clim_ens
except EmptyDatasetError: pass
else:
obs[i] = obs_ts # trivial: just substitute default name and load time-series
# prepare and load ensemble of observations
if len(obs) > 0:
if len(obs) == 1 and ensemble_list and 'names' not in ensemble_list: obs = obs[0]
try:
obsens = loadEnsemble(names=obs, season=seasons, aggregation=aggregation, slices=slices,
varlist=variables, ldataset=False, dataset_mode=dataset_mode,
shape=shapetype, obs_list=obs_list, basin_list=basin_list,
ensemble_list=ensemble_list, ensemble_product=ensemble_product, **kwargs)
except EmptyDatasetError:
obsens = Ensemble(name=name, title=title, obs_list=obs_list, basetype=Dataset)
else:
obsens = Ensemble(name=name, title=title, obs_list=obs_list, basetype=Dataset)
# add default obs back in if they were removed earlier
if clim_ens is not None:
for clim_ds in clim_ens[::-1]: # add observations in correct order: adding backwards allows successive insertion ...
obsens.insertMember(iobs,clim_ds) # ... at the point where the name block starts
# load stream gage data from WSC; should not interfere with anything else; append to ensemble
if lWSC: # another special case: river hydrographs
from datasets.WSC import GageStationError, loadGageStation
try:
if aggregation is not None and seasons is None: dataset_mode = 'climatology' # handled differently with gage data
if WSC_period is None: WSC_period = kwargs.get('obs_period',kwargs.get('period',None))
dataset = loadGageStation(basin=basins, varlist=['runoff'], aggregation=aggregation, period=WSC_period,
mode=dataset_mode, filetype='monthly', basin_list=basin_list, lfill=True, lexpand=True) # always load runoff/discharge
if seasons:
method = aggregation if aggregation.isupper() else aggregation.title()
if aggregation: dataset = getattr(dataset,'seasonal'+method)(season=seasons, taxis='time')
else: dataset = dataset.seasonalSample(season=seasons)
if slices is not None: dataset = dataset(**slices) # slice immediately
obsens += dataset.load()
except GageStationError:
pass # just ignore, if gage station data is missing
# return ensembles (will be wrapped in a list, if BatchLoad is used)
return obsens
def readRasterArray(file_pattern,
lgzip=None,
lgdal=True,
dtype=np.float32,
lmask=True,
fillValue=None,
lfeedback=False,
lgeotransform=True,
axes=None,
lna=False,
lskipMissing=False,
path_params=None,
**kwargs):
''' function to load a multi-dimensional numpy array from several structured ASCII raster files '''
if axes is None: raise NotImplementedError
#TODO: implement automatic detection of axes arguments and axes order
## expand path argument and figure out dimensions
# collect axes arguments
shape = []
axes_kwargs = dict()
for ax in axes:
if ax not in kwargs: raise AxisError(ax)
coord = kwargs.pop(ax)
shape.append(len(coord))
axes_kwargs[ax] = coord
assert len(axes) == len(shape) == len(axes_kwargs)
shape = tuple(shape)
#TODO: add handling of embedded inner product expansion
# argument expansion using outer product
file_kwargs_list = expandArgumentList(outer_list=axes, **axes_kwargs)
assert np.prod(shape) == len(file_kwargs_list)
## load data from raster files and assemble array
path_params = dict() if path_params is None else path_params.copy(
) # will be modified
# find first valid 2D raster to determine shape
i0 = 0
path_params.update(file_kwargs_list[i0]) # update axes parameters
filepath = file_pattern.format(**path_params) # construct file name
if not os.path.exists(filepath):
if lskipMissing: # find first valid
while not os.path.exists(filepath):
i0 += 1 # go to next raster file
if i0 >= len(file_kwargs_list):
raise IOError(
"No valid input raster files found!\n'{}'".format(
filepath))
if lfeedback: print ' ',
path_params.update(
file_kwargs_list[i0]) # update axes parameters
filepath = file_pattern.format(**path_params) # nest in line
else: # or raise error
raise IOError(filepath)
# read first 2D raster file
data2D = readASCIIraster(filepath,
lgzip=lgzip,
lgdal=lgdal,
dtype=dtype,
lna=True,
lmask=lmask,
fillValue=fillValue,
lgeotransform=lgeotransform,
**kwargs)
if lgeotransform: data2D, geotransform0, na = data2D
else:
data2D, na = data2D # we might still need na, but no need to check if it is the same
shape2D = data2D.shape # get 2D raster shape for later use
# allocate data array
list_shape = (np.prod(shape),
) + shape2D # assume 3D shape to concatenate 2D rasters
if lmask:
data = ma.empty(list_shape, dtype=dtype)
if fillValue is None: data._fill_value = data2D._fill_value
else: data._fill_value = fillValue
data.mask = True # initialize everything as masked
else:
data = np.empty(list_shape, dtype=dtype) # allocate the array
assert data.shape[0] == len(file_kwargs_list), (data.shape,
len(file_kwargs_list))
# insert (up to) first raster before continuing
if lskipMissing and i0 > 0:
data[:
i0, :, :] = ma.masked if lmask else fillValue # mask all invalid rasters up to first valid raster
data[i0, :, :] = data2D # add first (valid) raster
# loop over remaining 2D raster files
for i, file_kwargs in enumerate(file_kwargs_list[i0:]):
path_params.update(file_kwargs) # update axes parameters
filepath = file_pattern.format(**path_params) # construct file name
if os.path.exists(filepath):
if lfeedback: print '.', # indicate data with bar/pipe
# read 2D raster file
data2D = readASCIIraster(filepath,
lgzip=lgzip,
lgdal=lgdal,
dtype=dtype,
lna=False,
lmask=lmask,
fillValue=fillValue,
lgeotransform=lgeotransform,
**kwargs)
# check geotransform
if lgeotransform:
data2D, geotransform = data2D
if not geotransform == geotransform0:
raise AxisError(
geotransform
) # to make sure all geotransforms are identical!
else:
geotransform = None
# size information
if not shape2D == data2D.shape:
raise AxisError(
data2D.shape
) # to make sure all geotransforms are identical!
# insert 2D raster into 3D array
data[i + i0, :, :] = data2D # raster shape has to match
elif lskipMissing:
# fill with masked values
data[i + i0, :, :] = ma.masked # mask missing raster
if lfeedback: print ' ', # indicate missing with dot
else:
raise IOError(filepath)
# complete feedback with linebreak
if lfeedback: print ''
# reshape and check dimensions
assert i + i0 == data.shape[0] - 1, (i, i0)
data = data.reshape(shape + shape2D) # now we have the full shape
gc.collect() # remove duplicate data
# return data and optional meta data
if lgeotransform or lna:
return_data = (data, )
if lgeotransform: return_data += (geotransform, )
if lna: return_data += (na, )
else:
return_data = data
return return_data
