def getSensitivityAnalysisResultsMetamodel(self, metamodel, doe_sobol, size, N_LHS, N_KL_Young, N_KL_Diam, R2):
dim = doe_sobol.getDimension()
try :
meta_response = sequentialFunctionEvaulation(metamodel.__kriging_metamodel__, doe_sobol)
except Exception as e:
print('Caugt exception:\n',e)
print('filling response with zeros...')
meta_response = ot.Sample(np.zeros((doe_sobol.getSize(),1)))
sensitivity_analysis = klfs.SobolKarhunenLoeveFieldSensitivityAlgorithm()
sensitivity_analysis.setDesign(doe_sobol, meta_response, size)
sensitivity_analysis.setEstimator(ot.MartinezSensitivityAlgorithm())
FO_indices = sensitivity_analysis.getFirstOrderIndices()[0]
conf_level = sensitivity_analysis.getFirstOrderIndicesInterval()[0]
lb = conf_level.getLowerBound()
ub = conf_level.getUpperBound()
result_point = ot.PointWithDescription([('meta',1.),('N_LHS',N_LHS),('size',size),('kl_dimension',dim),
('N_KL_Young',N_KL_Young), ('N_KL_Diam',N_KL_Diam), ('R2',R2),
('SI_E',FO_indices[0][0]),('SI_E_lb',lb[0]),('SI_E_ub',ub[0]),
('SI_D',FO_indices[1][0]),('SI_D_lb',lb[1]),('SI_D_ub',ub[1]),
('SI_FP',FO_indices[2][0]),('SI_FP_lb',lb[2]),('SI_FP_ub',ub[2]),
('SI_FN',FO_indices[3][0]),('SI_FN_lb',lb[3]),('SI_FN_ub',ub[3])])
print('------------- RESULTS ------------')
print('------------ META MODEL ----------')
print('-----------SIZE LHS : {} ---------'.format(int(N_LHS)))
print(result_point)
return result_point
def run(self):
"""
Compute the Sobol indices with the chosen algorithm.
"""
# create the NumericalMathFunction which computes the POD for a given
# realization and for all defect sizes.
if self._podType == "kriging":
self._PODaggr = ot.NumericalMathFunction(
PODaggrKriging(self._POD, self._dim, self._defectSizes,
self._detectionBoxCox))
elif self._podType == "chaos":
self._PODaggr = ot.NumericalMathFunction(
PODaggrChaos(self._POD, self._dim, self._defectSizes,
self._detectionBoxCox, self._simulationSize))
if self._method == "Saltelli":
self._sa = ot.SaltelliSensitivityAlgorithm(self._distribution,
self._N, self._PODaggr,
False)
elif self._method == "Martinez":
self._sa = ot.MartinezSensitivityAlgorithm(self._distribution,
self._N, self._PODaggr,
False)
elif self._method == "Jansen":
self._sa = ot.JansenSensitivityAlgorithm(self._distribution,
self._N, self._PODaggr,
False)
elif self._method == "MauntzKucherenko":
self._sa = ot.MauntzKucherenkoSensitivityAlgorithm(
self._distribution, self._N, self._PODaggr, False)
def myMartinezSobolEstimator(distribution, size, model):
inputDesign = ot.SobolIndicesExperiment(distribution, size,
True).generate()
outputDesign = model(inputDesign)
sensitivityAnalysis = ot.MartinezSensitivityAlgorithm(
inputDesign, outputDesign, size)
return sensitivityAnalysis
def run(self):
"""
Compute the Sobol indices with the chosen algorithm.
"""
# create the Function which computes the POD for a given
# realization and for all defect sizes.
if self._podType == "kriging":
self._PODaggr = ot.Function(
PODaggrKriging(self._POD, self._dim, self._defectSizes,
self._detectionBoxCox))
elif self._podType == "chaos":
self._PODaggr = ot.Function(
PODaggrChaos(self._POD, self._dim, self._defectSizes,
self._detectionBoxCox, self._simulationSize))
input_design = ot.SobolIndicesExperiment(self._distribution, self._N,
False).generate()
output_design = self._PODaggr(input_design)
# remove the output marginal when the variance is null because it causes
# a failure. Must remove also the associated defect sizes.
selected_marginal_index = []
for index_output in range(output_design.getDimension()):
if output_design.getMarginal(
index_output)[:self._N].computeCovariance()[0, 0] != 0:
selected_marginal_index.append(index_output)
if len(selected_marginal_index) != output_design.getDimension():
self.setDefectSizes(self._defectSizes[selected_marginal_index])
selected_output_design = np.array(
output_design)[:, selected_marginal_index]
logging.warning("Warning : some output variances are null. " + \
"Only the following defect sizes are taken into " + \
"account : {}".format(self._defectSizes))
else:
selected_output_design = output_design
if self._method == "Saltelli":
self._sa = ot.SaltelliSensitivityAlgorithm(input_design,
selected_output_design,
self._N)
elif self._method == "Martinez":
self._sa = ot.MartinezSensitivityAlgorithm(input_design,
selected_output_design,
self._N)
elif self._method == "Jansen":
self._sa = ot.JansenSensitivityAlgorithm(input_design,
selected_output_design,
self._N)
elif self._method == "MauntzKucherenko":
self._sa = ot.MauntzKucherenkoSensitivityAlgorithm(
input_design, selected_output_design, self._N)
self._sa.setUseAsymptoticDistribution(True)
def getSensitivityAnalysisResults(self, sample_in, sample_out, size, N_KL_Young, N_KL_Diam):
dim = sample_in.getDimension() # Dimensoin of the KL input vector
sensitivity_analysis = klfs.SobolKarhunenLoeveFieldSensitivityAlgorithm()
sensitivity_analysis.setDesign(sample_in, sample_out, size)
sensitivity_analysis.setEstimator(ot.MartinezSensitivityAlgorithm())
FO_indices = sensitivity_analysis.getFirstOrderIndices()[0]
conf_level = sensitivity_analysis.getFirstOrderIndicesInterval()[0]
lb = conf_level.getLowerBound()
ub = conf_level.getUpperBound()
result_point = ot.PointWithDescription([('meta',0.),('N_LHS',-1.),('size',size),('kl_dimension',dim),
('N_KL_Young',N_KL_Young), ('N_KL_Diam',N_KL_Diam), ('R2',-1),
('SI_E',round(FO_indices[0][0],5)),('SI_E_lb',round(lb[0],5)),('SI_E_ub',round(ub[0],5)),
('SI_D',round(FO_indices[1][0],5)),('SI_D_lb',round(lb[1],5)),('SI_D_ub',round(ub[1],5)),
('SI_FP',round(FO_indices[2][0],5)),('SI_FP_lb',round(lb[2],5)),('SI_FP_ub',round(ub[2],5)),
('SI_FN',round(FO_indices[3][0],5)),('SI_FN_lb',round(lb[3],5)),('SI_FN_ub',round(ub[3],5))])
print('------------- RESULTS ------------')
print('------------ REAL MODEL ----------')
print('----------- SIZE DOE = {} -----------'.format(str(int(size))))
print(result_point)
return result_point
alpha = (Zm - Zv)/L
H = (Q/(Ks*B*alpha**0.5))**0.6
Zc = H + Zv
S = Zc - Zd
return [S]
myFunction = ot.PythonFunction(4, 1, flooding)
myParam = ot.GumbelAB(1013.0, 558.0)
Q = ot.ParametrizedDistribution(myParam)
Q = ot.TruncatedDistribution(Q, 0.0, ot.SpecFunc.MaxScalar)
Ks = ot.Normal(30.0, 7.5)
Ks = ot.TruncatedDistribution(Ks, 0.0, ot.SpecFunc.MaxScalar)
Zv = ot.Uniform(49.0, 51.0)
Zm = ot.Uniform(54.0, 56.0)
inputX = ot.ComposedDistribution([Q, Ks, Zv, Zm])
inputX.setDescription(["Q","Ks", "Zv", "Zm"])
size = 5000
computeSO = True
inputDesign = ot.SobolIndicesExperiment(inputX, size, computeSO).generate()
outputDesign = myFunction(inputDesign)
sensitivityAnalysis = ot.MartinezSensitivityAlgorithm(inputDesign, outputDesign, size)
graph = sensitivityAnalysis.draw()
fig = plt.figure(figsize=(8, 4))
plt.suptitle(graph.getTitle())
axis = fig.add_subplot(111)
axis.set_xlim(auto=True)
View(graph, figure=fig, axes=[axis], add_legend=True)
# Case 1 : Estimation of sensitivity using estimator and no bootstrap
for method in methods:
sensitivity_algorithm = eval(
'ot.' + method + "SensitivityAlgorithm(inputDesign, outputDesign, size)")
# Get first order indices
fo = sensitivity_algorithm.getFirstOrderIndices()
print("Method of evaluation=", method)
print("First order indices = ", fo)
# Get total order indices
to = sensitivity_algorithm.getTotalOrderIndices()
print("Total order indices = ", to)
# Case 2 : Estimation of sensitivity using Martinez estimator and bootstrap
nr_bootstrap = 100
confidence_level = 0.95
sensitivity_algorithm = ot.MartinezSensitivityAlgorithm(
inputDesign, outputDesign, size)
sensitivity_algorithm.setBootstrapSize(nr_bootstrap)
sensitivity_algorithm.setBootstrapConfidenceLevel(confidence_level)
# Get first order indices
fo = sensitivity_algorithm.getFirstOrderIndices()
to = sensitivity_algorithm.getTotalOrderIndices()
print("Martinez method : indices")
print("First order indices = ", fo)
print("Total order indices = ", to)
# Get the confidence interval thanks to Bootstrap
interval_fo = sensitivity_algorithm.getFirstOrderIndicesInterval()
interval_to = sensitivity_algorithm.getTotalOrderIndicesInterval()
print("Martinez method : bootstrap intervals")
print("First order indices interval = ", interval_fo)
print("Total order indices interval = ", interval_to)
# In the case of Martinez, if output is Gaussian, we may use the Fisher
