def pdf(self, fit=True, params=[], force=False, min=None, max=None,
return_samples=False, psamples=None,numsamples=None):
if not self.params and not params:
raise ValueError("Cannot generate PDF for response function without params.")
if params:
saved_params = self.params
saved_vars = self.vars
for newp in params:
for i, p in enumerate(self.params):
if p.name == newp.name:
print "REPLACING\n\t%s\nWITH\n\t%s\n" % (p, newp)
if not force:
self.check_pdf_range(p, newp)
self.params[i] = newp
self.vars = self.params2vars(self.params)
# get parameter pdf samples
if psamples is None:
xseed = get_psamples(self.params,num=numsamples) #FR
else:
xseed = psamples
results = np.array(self.evala(xseed))
if min is None or max is None:
calc_min, calc_max = self.minmax()
if min is None:
if np.min(results) < calc_min:
min = np.min(results)
else:
min = calc_min
if max is None:
if np.max(results) > calc_max:
max = np.max(results)
else:
max = calc_max
if params:
self.params = saved_params
self.vars = saved_vars
if return_samples:
return ExperimentalPDF(results, fit=fit, min=min, max=max, force=force), results
else:
return ExperimentalPDF(results, fit=fit, min=min, max=max, force=force)
def pdf(self, fit=True, params=[], force=False, min=None, max=None,
return_samples=False, psamples=None):
if not self.params and not params:
raise ValueError("Cannot generate PDF for response function without params.")
if params:
saved_params = self.params
saved_vars = self.vars
for newp in params:
for i, p in enumerate(self.params):
if p.name == newp.name:
print("REPLACING\n\t%s\nWITH\n\t%s\n" % (p, newp))
if not force:
self.check_pdf_range(p, newp)
self.params[i] = newp
self.vars = self.params2vars(self.params)
# get parameter pdf samples
if psamples is None:
xseed = get_psamples(self.params)
else:
xseed = psamples
results = self.evala(xseed)
# If the response surface is constant, 'results' is a constant.
# We will need to return an appropriate array filled with it.
if type(results) != np.ndarray:
val = results
results = np.empty(xseed.shape[0])
results.fill(val)
if min is None:
min = np.min(results)
if max is None:
max = np.max(results)
if params:
self.params = saved_params
self.vars = saved_vars
if return_samples:
return ExperimentalPDF(results, fit=fit, min=min, max=max, force=force), results
else:
return ExperimentalPDF(results, fit=fit, min=min, max=max, force=force)
class CustomParameter(Parameter):
'''
Class implementing a Parameter with a Custom distribution.
Args:
name: Name of the parameter. This should be a short name,
like a variable.
description: A longer description of the parameter.
kwargs: Keyword args. Valid args are:
============ ===============================================
Arg Description
============ ===============================================
pdf :class:`PDF`
use_samples Use data samples attached to pdf (if available)
============ ===============================================
'''
def __init__(self, name, description, **kwargs):
Parameter.__init__(self, name, description, **kwargs)
self.use_samples = kwargs.get('use_samples')
self.pdf = kwargs.get('pdf')
if self.pdf is None and self.caldata is None:
self.usage(0)
if self.pdf is not None and (isinstance(self.caldata, list) or isinstance(self.caldata, PDF)):
self.usage(1)
# If calibration data was supplied and nothing else, fit it to a PDF.
if self.caldata is not None and self.pdf is None:
self.pdf = self.caldata
if self.caldata is not None:
if isinstance(self.caldata, list):
# A list of PDFs. Sample from all of them to produce a PDF
d = np.array([x.ds(200) for x in self.caldata]).flatten()
self.pdf = ExperimentalPDF(fit=1, data=d)
elif isinstance(self.caldata, PDF):
self.pdf = self.caldata
# if pdf was an array or list of PDFs, fix it
if isinstance(self.pdf, np.ndarray):
self.pdf = ExperimentalPDF(self.pdf, fit=1)
elif isinstance(self.pdf, list):
# A list of PDFs. Sample from all of them to produce a PDF
d = np.array([x.ds(200) for x in self.pdf]).flatten()
self.pdf = ExperimentalPDF(fit=1, data=d)
def usage(self, msg):
if msg == 0:
raise ValueError("Error: You must specify a pdf, data, or caldata.")
elif msg == 1:
raise ValueError("Error: You specified a pdf and caldata consisting of a PDF or list of PDFs.")
# This is what you see when the object is printed
def __str__(self):
return "CustomParameter %s (%s)\n%s" %\
(self.name, self.description, self.pdf.__str__())
def __init__(self, name, description, **kwargs):
Parameter.__init__(self, name, description, **kwargs)
self.use_samples = kwargs.get('use_samples')
self.pdf = kwargs.get('pdf')
if self.pdf is None and self.caldata is None:
self.usage(0)
if self.pdf is not None and (isinstance(self.caldata, list) or isinstance(self.caldata, PDF)):
self.usage(1)
# If calibration data was supplied and nothing else, fit it to a PDF.
if self.caldata is not None and self.pdf is None:
self.pdf = self.caldata
if self.caldata is not None:
if isinstance(self.caldata, list):
# A list of PDFs. Sample from all of them to produce a PDF
d = np.array([x.ds(200) for x in self.caldata]).flatten()
self.pdf = ExperimentalPDF(fit=1, data=d)
elif isinstance(self.caldata, PDF):
self.pdf = self.caldata
# if pdf was an array or list of PDFs, fix it
if isinstance(self.pdf, np.ndarray):
self.pdf = ExperimentalPDF(self.pdf, fit=1)
elif isinstance(self.pdf, list):
# A list of PDFs. Sample from all of them to produce a PDF
d = np.array([x.ds(200) for x in self.pdf]).flatten()
self.pdf = ExperimentalPDF(fit=1, data=d)
def _do_pdf(self, hf, data):
if self.response:
# The response surface was built using Uniform distributions.
# We are interested in the mean and deviation of the data
# that would have been produced using the real PDFs. For this,
# we need to compute a weighted mean and deviation
weights = np.prod([p.pdf.pdf(p.values) for p in self.params], 0)
tweight = np.sum(weights)
mean = np.average(data, weights=weights)
dev = np.sqrt(np.dot(weights, (data - mean)**2) / tweight)
rsd = np.vstack(([p.values for p in self.params], data))
rs = pickle(SampledFunc(*rsd, params=self.params))
print "Mean = %s" % mean
print "StdDev = %s" % dev
return [('response', rs), ('mean', mean), ('dev', dev)]
else:
pdf = ExperimentalPDF(data, fit=0)
mean = np.mean(data)
dev = np.std(data)
print "Mean = %s" % mean
print "StdDev = %s" % dev
return [('pdf', pickle(pdf)), ('samples', data), ('mean', mean),
('dev', dev)]
def _do_pdf(self, hf, data):
if self.response:
print('Morris method does not support creating response surfaces')
raise ValueError
else:
pdf = ExperimentalPDF(data, fit=0)
mean = np.mean(data)
dev = np.std(data)
print "Mean = %s" % mean
print "StdDev = %s" % dev
#############
#analyze results
############
#get the inputs
inputs = hf['/input/params']
numparams = len(inputs)
#N(D+1) x D
# realizations=np.empty((np.size(data,0),numparams ))
# f=open(self._salib_paramFile,'w')
# i=0
# for p in inputs:
# aParam=unpickle(hf['/input/params'][p].value)
# print(aParam.name)
# #we now have a parameter
# f.write('{}\t{}\t{}\n'.format(aParam.name,aParam.pdf.range[0],aParam.pdf.range[1]))
# # get the values
# realizations[:,i]=aParam.values
# i+=1
# f.close()
#check to make sure the order in which the parameters were initially sampled by SALib
#was the order in which they were actually sampled by puq
# np.savetxt(self._salib_realizationsFile,realizations)
# if os.path.getsize(self._salib_realizationsFile_verify) == os.path.getsize(self._salib_realizationsFile):
# if not filecmp.cmp(self._salib_realizationsFile_verify, self._salib_realizationsFile, shallow=False):
# raise Exception('The order in which the parameter samples were constructed is different than the sampled order!')
# else:
# raise Exception('The order in which the parameter samples were constructed is different than the sampled order!')
#get the outputs
outputs = hf['/output/data']
numputputs = len(outputs)
#SALib expects each output variable in a single column
np.savetxt(self._salib_analysisFile, data)
#Note: the delimiters for all the files passed to the analyze function must be the same
s = SAa.morris.analyze(self._salib_paramFile,
self._salib_realizationsFile,
self._salib_analysisFile,
column=0)
#put things in the same format as the smolyak module
sens = {}
for key, val in s.iteritems():
sens[key] = {
'u': val[0],
'std': val[1],
'ustar': val[2],
'ustar_conf95': val[3]
}
#senstxt+='{}\t{}\t{}\t{}'.format(key,val[0],val[1],val[2],val[3])
sorted_list = sorted(
sens.items(), lambda x, y: cmp(y[1]['ustar'], x[1]['ustar']))
#os.remove(salib_paramFile)
return [('pdf', pickle(pdf)), ('samples', data), ('mean', mean),
('dev', dev), ('sensitivity', pickle(sorted_list))]