def binedges(bins=None, binedgs=None, limits=None, lcheckVar=True):
''' utility function to generate and validate bins and binegdes from either one '''
# check input
if bins is None and binedgs is None: raise ArgumentError
elif bins is not None and binedgs is not None:
if len(bins)+1 != len(binedgs): raise ArgumentError(len(bins))
if bins is not None:
if limits is not None: vmin, vmax = limits
else: raise ArgumentError(bins)
# expand bins (values refer to center of bins)
if isinstance(bins,(int,np.integer)):
if bins == 1: bins = np.asarray(( (vmin+vmax)/2. ,))
else: bins = np.linspace(vmin,vmax,bins)
elif isinstance(bins,(tuple,list)) and 0 < len(bins) < 4:
bins = np.linspace(*bins)
elif not isinstance(bins,(list,np.ndarray)): raise TypeError(bins)
if len(bins) == 1:
tmpbinedgs = np.asarray((vmin,vmax))
else:
hbd = np.diff(bins) / 2. # make sure this is a float!
tmpbinedgs = np.hstack((bins[0]-hbd[0],bins[1:]-hbd,bins[-1]+hbd[-1])) # assuming even spacing
if binedgs is None: binedgs = tmpbinedgs # computed from bins
elif lcheckVar: assert isEqual(binedgs, np.asarray(tmpbinedgs, dtype=binedgs.dtype))
if binedgs is not None:
# expand bin edges
if not isinstance(binedgs,(tuple,list)): binedgs = np.asarray(binedgs)
elif not isinstance(binedgs,np.ndarray): raise TypeError(binedgs)
tmpbins = binedgs[1:] - ( np.diff(binedgs) / 2. ) # make sure this is a float!
if bins is None: bins = tmpbins # compute from binedgs
elif lcheckVar: assert isEqual(bins, np.asarray(tmpbins, dtype=bins.dtype))
# return bins and binegdes
return bins, binedgs
def binedges(bins=None, binedgs=None, limits=None, lcheckVar=True):
''' utility function to generate and validate bins and binegdes from either one '''
# check input
if bins is None and binedgs is None: raise ArgumentError
elif bins is not None and binedgs is not None:
if len(bins)+1 != len(binedgs): raise ArgumentError
if bins is not None:
if limits is not None: vmin, vmax = limits
else: raise ArgumentError
# expand bins (values refer to center of bins)
if isinstance(bins,(int,np.integer)):
if bins == 1: bins = np.asarray(( (vmin+vmax)/2. ,))
else: bins = np.linspace(vmin,vmax,bins)
elif isinstance(bins,(tuple,list)) and 0 < len(bins) < 4:
bins = np.linspace(*bins)
elif not isinstance(bins,(list,np.ndarray)): raise TypeError
if len(bins) == 1:
tmpbinedgs = np.asarray((vmin,vmax))
else:
hbd = np.diff(bins) / 2. # make sure this is a float!
tmpbinedgs = np.hstack((bins[0]-hbd[0],bins[1:]-hbd,bins[-1]+hbd[-1])) # assuming even spacing
if binedgs is None: binedgs = tmpbinedgs # computed from bins
elif lcheckVar: assert isEqual(binedgs, np.asarray(tmpbinedgs, dtype=binedgs.dtype))
if binedgs is not None:
# expand bin edges
if not isinstance(binedgs,(tuple,list)): binedgs = np.asarray(binedgs)
elif not isinstance(binedgs,np.ndarray): raise TypeError
tmpbins = binedgs[1:] - ( np.diff(binedgs) / 2. ) # make sure this is a float!
if bins is None: bins = tmpbins # compute from binedgs
elif lcheckVar: assert isEqual(bins, np.asarray(tmpbins, dtype=bins.dtype))
# return bins and binegdes
return bins, binedgs
def train(self, dataset, observations, **kwargs):
''' loop over variables that need to be corrected and call method-specific training function '''
# figure out varlist
if self.varlist is None:
self._getVarlist(
dataset,
observations) # process all that are present in both datasets
# loop over variables that will be corrected
self._correction = dict()
for varname in self.varlist:
# get variable object
var = dataset[varname]
if not var.data:
var.load() # assume it is a VarNC, if there is no data
obsvar = observations[varname] # should be loaded
if not obsvar.data:
obsvar.load() # assume it is a VarNC, if there is no data
assert var.data and obsvar.data, obsvar.data
# check if they are actually equal
if isEqual(var.data_array,
obsvar.data_array,
eps=eps,
masked_equal=True):
correction = None
else:
correction = self._trainVar(var, obsvar, **kwargs)
# save correction parameters
self._correction[varname] = correction
def run_test(fct, kw=0, laax=True): ff = partial(fct, kw=kw) shape = (500,100) data = np.arange(np.prod(shape), dtype='float').reshape(shape) assert data.shape == shape # parallel implementation using my wrapper pres = apply_along_axis(ff, axis, data, NP=2, ldebug=True, laax=laax) print pres.shape assert pres.shape == data.shape assert isZero(pres.mean(axis=axis)+kw) and isZero(pres.std(axis=axis)-1.) # straight-forward numpy version res = np.apply_along_axis(ff, axis, data) assert res.shape == data.shape assert isZero(res.mean(axis=axis)+kw) and isZero(res.std(axis=axis)-1.) # final test assert isEqual(pres, res)
def run_test(fct, kw=0, laax=True): ff = partial(fct, kw=kw) shape = (500,100) data = np.arange(np.prod(shape), dtype='float').reshape(shape) assert data.shape == shape # parallel implementation using my wrapper pres = apply_along_axis(ff, axis, data, NP=2, ldebug=True, laax=laax) print pres.shape assert pres.shape == data.shape assert isZero(pres.mean(axis=axis)+kw) and isZero(pres.std(axis=axis)-1.) # straight-forward numpy version res = np.apply_along_axis(ff, axis, data) assert res.shape == data.shape assert isZero(res.mean(axis=axis)+kw) and isZero(res.std(axis=axis)-1.) # final test assert isEqual(pres, res)
def train(self, dataset, observations, **kwargs):
''' loop over variables that need to be corrected and call method-specific training function '''
# figure out varlist
if self.varlist is None:
self._getVarlist(dataset, observations) # process all that are present in both datasets
# loop over variables that will be corrected
self._correction = dict()
for varname in self.varlist:
# get variable object
var = dataset[varname]
if not var.data: var.load() # assume it is a VarNC, if there is no data
obsvar = observations[varname] # should be loaded
if not obsvar.data: obsvar.load() # assume it is a VarNC, if there is no data
assert var.data and obsvar.data, obsvar.data
# check if they are actually equal
if isEqual(var.data_array, obsvar.data_array, eps=eps, masked_equal=True):
correction = None
else:
correction = self._trainVar(var, obsvar, **kwargs)
# save correction parameters
self._correction[varname] = correction
