dim = model.getInputDimension()
# We create a normal distribution point of dimension 1
mean = [50.0, 1.0, 10.0, 5.0] # E, F, L, I
sigma = [1.0] * dim
R = ot.IdentityMatrix(dim)
myDistribution = ot.Normal(mean, sigma, R)
# We create a 'usual' RandomVector from the Distribution
vect = ot.RandomVector(myDistribution)
# We create a composite random vector
composite = ot.CompositeRandomVector(model, vect)
ot.RandomGenerator.SetSeed(42)
algo = ot.ExpectationSimulationAlgorithm(composite)
algo.setMaximumOuterSampling(250000)
algo.setBlockSize(2)
# algo.setMaximumCoefficientOfVariation(1e-6)
algo.setStandardDeviationCriterionType('MAX')
algo.setCoefficientOfVariationCriterionType('NONE')
# algo.setMaximumStandardDeviation(1.6)
# print(algo.getMaximumStandardDeviation())
# algo.setProgressCallback(progress)
# algo.setStopCallback(stop)
print('algo=', algo)
# Perform the simulation
algo.run()
View(Zm.drawPDF()).show()
# 4. Create the joint distribution function,
# the output and the event.
X = ot.ComposedDistribution([Q, Ks, Zv, Zm])
Y = ot.RandomVector(g, ot.RandomVector(X))
# 5. Estimate expectation with simple Monte-Carlo
sampleSize = 10000
sampleX = X.getSample(sampleSize)
sampleY = g(sampleX)
sampleMean = sampleY.computeMean()
print("Mean by MC = %f" % (sampleMean[0]))
# 6. Estimate expectation with algorithm
algo = ot.ExpectationSimulationAlgorithm(Y)
algo.setMaximumOuterSampling(1000)
algo.setBlockSize(1)
algo.setCoefficientOfVariationCriterionType('NONE')
algo.run()
result = algo.getResult()
expectation = result.getExpectationEstimate()
print("Mean by ESA = %f " % expectation[0])
expectationDistribution = result.getExpectationDistribution()
View(expectationDistribution.drawPDF())
pl.savefig("MeanDistribution.pdf")
# Sensitivity analysis
estimator = ot.SaltelliSensitivityAlgorithm()
estimator.setUseAsymptoticDistribution(True)
# %%
# We create a random vector that follows the distribution of the input variables.
inputVector = ot.RandomVector(distribution)
# %%
# The output vector is a :class:`~openturns.CompositeRandomVector`.
outputVector = ot.CompositeRandomVector(model, inputVector)
# %%
# The mean of the output vector is
print("Mean of the output random vector : %.5f" % im.expectation)
# %%
# We define the algorithm simply by calling it with the output vector :
algo = ot.ExpectationSimulationAlgorithm(outputVector)
# %%
# We can also set the algorithm parameters :
algo.setMaximumOuterSampling(80000)
algo.setBlockSize(1)
algo.setCoefficientOfVariationCriterionType('NONE')
# %%
# We are then ready to launch the algorithm and store the result.
algo.run()
result = algo.getResult()
# %%
# As usual for Monte Carlo estimation we can draw the convergence history.
graphConvergence = algo.drawExpectationConvergence()