def fit(self, X, y, **fit_params):
input_dimension = X.shape[1]
if self.distribution is None:
self.distribution = BuildDistribution(X)
if self.enumerate == 'linear':
enumerateFunction = ot.LinearEnumerateFunction(input_dimension)
elif self.enumerate == 'hyperbolic':
enumerateFunction = ot.HyperbolicAnisotropicEnumerateFunction(input_dimension, self.q)
else:
raise ValueError('enumerate should be "linear" or "hyperbolic"')
polynomials = [ot.StandardDistributionPolynomialFactory(self.distribution.getMarginal(i)) for i in range(input_dimension)]
productBasis = ot.OrthogonalProductPolynomialFactory(polynomials, enumerateFunction)
adaptiveStrategy = ot.FixedStrategy(productBasis, enumerateFunction.getStrataCumulatedCardinal(self.degree))
if self.sparse:
projectionStrategy = ot.LeastSquaresStrategy(ot.LeastSquaresMetaModelSelectionFactory(ot.LARS(), ot.CorrectedLeaveOneOut()))
else:
projectionStrategy = ot.LeastSquaresStrategy(X, y.reshape(-1, 1))
algo = ot.FunctionalChaosAlgorithm(X, y.reshape(-1, 1), self.distribution, adaptiveStrategy, projectionStrategy)
algo.run()
self._result = algo.getResult()
output_dimension = self._result.getMetaModel().getOutputDimension()
# sensitivity
si = ot.FunctionalChaosSobolIndices(self._result)
if output_dimension == 1:
self.feature_importances_ = [si.getSobolIndex(i) for i in range(input_dimension)]
else:
self.feature_importances_ = [[0.0] * input_dimension] * output_dimension
for k in range(output_dimension):
for i in range(input_dimension):
self.feature_importances_[k][i] = si.getSobolIndex(i, k)
self.feature_importances_ = np.array(self.feature_importances_)
return self
def _buildChaosAlgo(self, inputSample, outputSample):
"""
Build the functional chaos algorithm without running it.
"""
if self._distribution is None:
# create default distribution : Uniform between min and max of the
# input sample
inputSample = ot.Sample(inputSample)
inputMin = inputSample.getMin()
inputMin[0] = np.min(self._defectSizes)
inputMax = inputSample.getMax()
inputMax[0] = np.max(self._defectSizes)
marginals = [ot.Uniform(inputMin[i], inputMax[i]) for i in range(self._dim)]
self._distribution = ot.ComposedDistribution(marginals)
# put description of the inputSample into decription of the distribution
self._distribution.setDescription(inputSample.getDescription())
if self._adaptiveStrategy is None:
# Create the adaptive strategy : default is fixed strategy of degree 5
# with linear enumerate function
polyCol = [0.]*self._dim
for i in range(self._dim):
polyCol[i] = ot.StandardDistributionPolynomialFactory(
self._distribution.getMarginal(i))
enumerateFunction = ot.LinearEnumerateFunction(self._dim)
multivariateBasis = ot.OrthogonalProductPolynomialFactory(polyCol, enumerateFunction)
# default degree is 3 (in __init__)
indexMax = enumerateFunction.getStrataCumulatedCardinal(self._degree)
self._adaptiveStrategy = ot.FixedStrategy(multivariateBasis, indexMax)
if self._projectionStrategy is None:
# sparse polynomial chaos
basis_sequence_factory = ot.LARS()
fitting_algorithm = ot.KFold()
approximation_algorithm = ot.LeastSquaresMetaModelSelectionFactory(
basis_sequence_factory, fitting_algorithm)
self._projectionStrategy = ot.LeastSquaresStrategy(inputSample,
outputSample, approximation_algorithm)
return ot.FunctionalChaosAlgorithm(inputSample, outputSample, \
self._distribution, self._adaptiveStrategy, self._projectionStrategy)
])
# %%
# Prepare the input/output samples
sampleSize = 250
X = distribution.getSample(sampleSize)
Y = myModel(X)
dimension = X.getDimension()
# %%
# build the orthogonal basis
coll = [
ot.StandardDistributionPolynomialFactory(distribution.getMarginal(i))
for i in range(dimension)
]
enumerateFunction = ot.LinearEnumerateFunction(dimension)
productBasis = ot.OrthogonalProductPolynomialFactory(coll, enumerateFunction)
# %%
# create the algorithm
degree = 6
adaptiveStrategy = ot.FixedStrategy(
productBasis, enumerateFunction.getStrataCumulatedCardinal(degree))
projectionStrategy = ot.LeastSquaresStrategy()
algo = ot.FunctionalChaosAlgorithm(X, Y, distribution, adaptiveStrategy,
projectionStrategy)
algo.run()
# %%
# get the metamodel function
result = algo.getResult()
# %%
# Create the input independent joint distribution
distribution = ot.Normal(2)
distribution.setDescription(['X1', 'X2'])
# %%
# Create the correlated input distribution
S = ot.CorrelationMatrix(2)
S[1, 0] = 0.3
R = ot.NormalCopula.GetCorrelationFromSpearmanCorrelation(S)
copula = ot.NormalCopula(R)
distribution_corr = ot.ComposedDistribution([ot.Normal()] * 2, copula)
# %%
# ANCOVA needs a functional decomposition of the model
enumerateFunction = ot.LinearEnumerateFunction(2)
productBasis = ot.OrthogonalProductPolynomialFactory([ot.HermiteFactory()] * 2,
enumerateFunction)
adaptiveStrategy = ot.FixedStrategy(
productBasis, enumerateFunction.getStrataCumulatedCardinal(4))
samplingSize = 250
projectionStrategy = ot.LeastSquaresStrategy(
ot.MonteCarloExperiment(samplingSize))
algo = ot.FunctionalChaosAlgorithm(model, distribution, adaptiveStrategy,
projectionStrategy)
algo.run()
result = ot.FunctionalChaosResult(algo.getResult())
# %%
# Create the input sample taking account the correlation
size = 2000
# %%
polyColl[0] = ot.HermiteFactory()
polyColl[1] = ot.LegendreFactory()
polyColl[2] = ot.LaguerreFactory(2.75)
# Parameter for the Jacobi factory : 'Probabilty' encoded with 1
polyColl[3] = ot.JacobiFactory(2.5, 3.5, 1)
# %%
# Create the enumeration function.
# %%
# The first possibility is to use the `LinearEnumerateFunction`.
# %%
enumerateFunction = ot.LinearEnumerateFunction(inputDimension)
# %%
# Another possibility is to use the `HyperbolicAnisotropicEnumerateFunction`, which gives less weight to interactions.
# %%
q = 0.4
enumerateFunction_1 = ot.HyperbolicAnisotropicEnumerateFunction(
inputDimension, q)
# %%
# Create the multivariate orthonormal basis which is the the cartesian product of the univariate basis.
# %%
multivariateBasis = ot.OrthogonalProductPolynomialFactory(
polyColl, enumerateFunction)
# %%
# The coefficients of marginal i
i = 1
result.getCoefficients()[i]
# %%
# Get the indices of the selected polynomials : K
subsetK = result.getIndices()
subsetK
# %%
# Get the composition of the polynomials
# of the truncated multivariate basis
for i in range(subsetK.getSize()):
print("Polynomial number ", i, " in truncated basis <-> polynomial number ",
subsetK[i], " = ", ot.LinearEnumerateFunction(dimension)(subsetK[i]), " in complete basis")
# %%
# Get the multivariate basis
# as a collection of Function
reduced = result.getReducedBasis()
# %%
# Get the orthogonal basis
orthgBasis = result.getOrthogonalBasis()
# %%
# Get the distribution of variables Z
orthgBasis.getMeasure()
# %%
# The coefficients of marginal i
i = 1
result.getCoefficients()[i]
# %%
# Get the indices of the selected polynomials : K
subsetK = result.getIndices()
subsetK
# %%
# Get the composition of the polynomials
# of the truncated multivariate basis
for i in range(subsetK.getSize()):
print("Polynomial number ", i,
" in truncated basis <-> polynomial number ", subsetK[i], " = ",
ot.LinearEnumerateFunction(dimension)(subsetK[i]),
" in complete basis")
# %%
# Get the multivariate basis
# as a collection of Function
reduced = result.getReducedBasis()
# %%
# Get the orthogonal basis
orthgBasis = result.getOrthogonalBasis()
orthgBasis
# %%
# Get the distribution of variables Z
orthgBasis.getMeasure()
def fit(self, X, y, **fit_params):
"""Fit PC regression model.
Parameters
----------
X : array-like, shape = (n_samples, n_features)
Training data.
y : array-like, shape = (n_samples, [n_output_dims])
Target values.
Returns
-------
self : returns an instance of self.
"""
if len(X) == 0:
raise ValueError(
"Can not perform chaos expansion with empty sample")
# check data type is accurate
if (len(np.shape(X)) != 2):
raise ValueError("X has incorrect shape.")
input_dimension = len(X[1])
if (len(np.shape(y)) != 2):
raise ValueError("y has incorrect shape.")
if self.distribution is None:
self.distribution = ot.MetaModelAlgorithm.BuildDistribution(X)
if self.enumeratef == 'linear':
enumerateFunction = ot.LinearEnumerateFunction(input_dimension)
elif self.enumeratef == 'hyperbolic':
enumerateFunction = ot.HyperbolicAnisotropicEnumerateFunction(
input_dimension, self.q)
else:
raise ValueError('enumeratef should be "linear" or "hyperbolic"')
polynomials = [
ot.StandardDistributionPolynomialFactory(
self.distribution.getMarginal(i))
for i in range(input_dimension)
]
productBasis = ot.OrthogonalProductPolynomialFactory(
polynomials, enumerateFunction)
adaptiveStrategy = ot.FixedStrategy(
productBasis,
enumerateFunction.getStrataCumulatedCardinal(self.degree))
if self.sparse:
# Filter according to the sparse_fitting_algorithm key
if self.sparse_fitting_algorithm == "cloo":
fitting_algorithm = ot.CorrectedLeaveOneOut()
else:
fitting_algorithm = ot.KFold()
# Define the correspondinding projection strategy
projectionStrategy = ot.LeastSquaresStrategy(
ot.LeastSquaresMetaModelSelectionFactory(
ot.LARS(), fitting_algorithm))
else:
projectionStrategy = ot.LeastSquaresStrategy(X, y)
algo = ot.FunctionalChaosAlgorithm(X, y, self.distribution,
adaptiveStrategy,
projectionStrategy)
algo.run()
self.result_ = algo.getResult()
output_dimension = self.result_.getMetaModel().getOutputDimension()
# sensitivity
si = ot.FunctionalChaosSobolIndices(self.result_)
if output_dimension == 1:
self.feature_importances_ = [
si.getSobolIndex(i) for i in range(input_dimension)
]
else:
self.feature_importances_ = [[0.0] * input_dimension
] * output_dimension
for k in range(output_dimension):
for i in range(input_dimension):
self.feature_importances_[k][i] = si.getSobolIndex(i, k)
self.feature_importances_ = np.array(self.feature_importances_)
return self
def train(self):
self.input_dim = self.training_points[None][0][0].shape[1]
x_train = ot.Sample(self.training_points[None][0][0])
y_train = ot.Sample(self.training_points[None][0][1])
# Distribution choice of the inputs to Create the input distribution
distributions = []
dist_specs = self.options["uncertainty_specs"]
if dist_specs:
if len(dist_specs) != self.input_dim:
raise SurrogateOpenturnsException(
"Number of distributions should be equal to input \
dimensions. Should be {}, got {}".format(
self.input_dim, len(dist_specs)
)
)
for ds in dist_specs:
dist_klass = getattr(sys.modules["openturns"], ds["name"])
args = [ds["kwargs"][name] for name in DISTRIBUTION_SIGNATURES[ds["name"]]]
distributions.append(dist_klass(*args))
else:
for i in range(self.input_dim):
mean = np.mean(x_train[:, i])
lower, upper = 0.95 * mean, 1.05 * mean
if mean < 0:
lower, upper = upper, lower
distributions.append(ot.Uniform(lower, upper))
distribution = ot.ComposedDistribution(distributions)
# Polynomial basis
# step 1 - Construction of the multivariate orthonormal basis:
# Build orthonormal or orthogonal univariate polynomial families
# (associated to associated input distribution)
polynoms = [0.0] * self.input_dim
for i in range(distribution.getDimension()):
polynoms[i] = ot.StandardDistributionPolynomialFactory(
distribution.getMarginal(i)
)
enumerateFunction = ot.LinearEnumerateFunction(self.input_dim)
productBasis = ot.OrthogonalProductPolynomialFactory(
polynoms, enumerateFunction
)
# step 2 - Truncation strategy of the multivariate orthonormal basis:
# a strategy must be chosen for the selection of the different terms
# of the multivariate basis.
# Truncature strategy of the multivariate orthonormal basis
# We choose all the polynomials of degree <= degree
degree = self.options["pce_degree"]
index_max = enumerateFunction.getStrataCumulatedCardinal(degree)
adaptive_strategy = ot.FixedStrategy(productBasis, index_max)
basis_sequenceFactory = ot.LARS()
fitting_algorithm = ot.CorrectedLeaveOneOut()
approximation_algorithm = ot.LeastSquaresMetaModelSelectionFactory(
basis_sequenceFactory, fitting_algorithm
)
projection_strategy = ot.LeastSquaresStrategy(
x_train, y_train, approximation_algorithm
)
algo = ot.FunctionalChaosAlgorithm(
x_train, y_train, distribution, adaptive_strategy, projection_strategy
)
# algo = ot.FunctionalChaosAlgorithm(X_train_NS, Y_train_NS)
algo.run()
self._pce_result = algo.getResult()
