FAST¶

class
FAST
(*args)¶ Fourier Amplitude Sensitivity Testing (FAST).
Refer to Sensivity analysis by Fourier decomposition.
 Available constructor:
FAST(model, distribution, N, Nr=1, M=4)
 Parameters
 model
Function
Definition of the model to analyse.
 distribution
Distribution
Contains the distributions of each model’s input. Its dimension must be equal to the number of inputs.
 Nint,
Size of the sample from which the Fourier series are calculated. It represents the length of the discretization of the sspace.
 Nrint,
Number of resamplings. The extended FAST method involves a part of randomness in the computation of the indices. So it can be asked to realize the procedure Nr times and then to calculate the arithmetic means of the results over the Nr estimates.
 Mint,
Interference factor usually equal to 4 or higher. It corresponds to the truncation level of the Fourier series, i.e. the number of harmonics that are retained in the decomposition.
 model
Notes
FAST is a sensitivity analysis method which is based upon the ANOVA decomposition of the variance of the model response , the latter being represented by its Fourier expansion. is an input random vector of independent components.
OpenTURNS implements the extended FAST method consisting in computing alternately the first order and the totaleffect indices of each input. This approach, widely described in the paper by [saltelli1999], relies upon a Fourier decomposition of the model response. Its key idea is to recast this representation as a function of a scalar parameter , by defining parametric curves exploring the support of the input random vector .
Then the Fourier expansion of the model response is:
where and are Fourier coefficients whose estimates are:
The first order indices are estimated by:
and the total order indices by:
where is the total variance, the portion of arising from the uncertainty of the input and is the part of the variance due to all the inputs except the input.
is the size of the sample using to compute the Fourier series and is the interference factor. Saltelli et al. (1999) recommanded to set to a value in the range . is a set of integer frequencies assigned to each input . The frequency associated with the input for which the sensitivity indices are computed, is set to the maximum admissible frequency satisfying the Nyquist criterion (which ensures to avoid aliasing effects):
In the paper by Saltelli et al. (1999), for high sample size, it is suggested that .
Examples
>>> import openturns as ot >>> ot.RandomGenerator.SetSeed(0) >>> formulaIshigami = ['sin(pi_*X1)+7*sin(pi_*X2)*sin(pi_*X2)+0.1*((pi_*X3)*(pi_*X3)*(pi_*X3)*(pi_*X3))*sin(pi_*X1)'] >>> modelIshigami = ot.SymbolicFunction(['X1', 'X2', 'X3'], formulaIshigami) >>> distributions = ot.ComposedDistribution([ot.Uniform(1.0, 1.0)] * 3) >>> sensitivityAnalysis = ot.FAST(modelIshigami, distributions, 101) >>> print(sensitivityAnalysis.getFirstOrderIndices()) [0.311097,0.441786,0.000396837]
Methods
getBlockSize
(self)Get the block size.
getFFTAlgorithm
(self)Accessor to the FFT algorithm implementation.
getFirstOrderIndices
(self[, marginalIndex])Accessor to the first order indices.
getTotalOrderIndices
(self[, marginalIndex])Accessor to the total order indices.
setBlockSize
(self, blockSize)Set the block size.
setFFTAlgorithm
(self, fft)Accessor to the FFT algorithm implementation.

__init__
(self, *args)¶ Initialize self. See help(type(self)) for accurate signature.

getBlockSize
(self)¶ Get the block size.
 Returns
 kpositive int
Size of each block the sample is splitted into, this allows to save space while allowing multithreading, when available we recommend to use the number of available CPUs, set by default to 1.

getFFTAlgorithm
(self)¶ Accessor to the FFT algorithm implementation.
 Returns
 ffta
FFT
A FFT algorithm.
 ffta

getFirstOrderIndices
(self, marginalIndex=0)¶ Accessor to the first order indices.
 Parameters
 marginalIndexint, , optional
Index of the model’s marginal used to estimate the indices. By default, marginalIndex is equal to 0.
 Returns
 indices
Point
List of the first order indices of all the inputs.
 indices

getTotalOrderIndices
(self, marginalIndex=0)¶ Accessor to the total order indices.
 Parameters
 marginalIndexint, , optional
Index of the model’s marginal used to estimate the indices. By default, marginalIndex is equal to 0.
 Returns
 indices
Point
List of the totaleffect order indices of all the inputs.
 indices

setBlockSize
(self, blockSize)¶ Set the block size.
 Parameters
 kpositive int
Size of each block the sample is splitted into, this allows to save space while allowing multithreading, when available we recommend to use the number of available CPUs, set by default to .