f = ot.ParametricFunction(f_base, [1], [1.0])
x = [1.0]
measures = [otrobopt.MeanMeasure(f, thetaDist),
otrobopt.VarianceMeasure(f, thetaDist),
otrobopt.WorstCaseMeasure(f, ot.Uniform(-1.0, 4.0)),
otrobopt.WorstCaseMeasure(f, ot.Uniform(-1.0, 4.0), False),
otrobopt.JointChanceMeasure(
f, ot.Normal(1.0, 1.0), ot.GreaterOrEqual(), 0.95),
otrobopt.IndividualChanceMeasure(
f, ot.Normal(1.0, 1.0), ot.GreaterOrEqual(), [0.95]),
otrobopt.MeanStandardDeviationTradeoffMeasure(f, thetaDist, [0.8]),
otrobopt.QuantileMeasure(f, thetaDist, 0.99)
]
aggregated = otrobopt.AggregatedMeasure(measures)
measures.append(aggregated)
for measure in measures:
print(measure, '(continuous)', measure(x))
N = 10000
experiment = ot.LHSExperiment(N)
factory = otrobopt.MeasureFactory(experiment)
discretizedMeasure = factory.build(measure)
print(discretizedMeasure, '(discretized LHS)', discretizedMeasure(x))
N = 4
experiment = ot.GaussProductExperiment([N])
factory = otrobopt.MeasureFactory(experiment)
discretizedMeasure = factory.build(measure)
print(discretizedMeasure, '(discretized Gauss)', discretizedMeasure(x))
from __future__ import print_function import openturns as ot import otrobopt full_fun = ot.SymbolicFunction(['x', 'theta'], ['theta*x']) param_fun = ot.ParametricFunction(full_fun, [1], [1.0]) # Normal distribution associated to parameter theta thetaDist = ot.Normal(2.0, 0.1) # Definition of "analytical" mean measure associated to the parametric function mean_measure = otrobopt.MeanMeasure(param_fun, thetaDist) variance_measure = otrobopt.VarianceMeasure(param_fun, thetaDist) # Definition of "discretized" mean measure N = 10 experiment = ot.LHSExperiment(thetaDist, N) factory = otrobopt.MeasureFactory(experiment) discretized_mean_measure_evaluation = factory.build(mean_measure) coll = [mean_measure, variance_measure] discretizedColl = factory.buildCollection(coll) print(coll) x = [1.0] print(otrobopt.AggregatedMeasure(coll)(x))