Scilab Home Page | Wiki | Bug Tracker | Forge | Mailing List Archives | Scilab Online Help | File Exchange
ATOMS : NISP details
Please login or create an account

NISP

(2097/9188 downloads)
Non Intrusive Spectral Projection
Details
Version
2.3-1
Most recent version: 2.7
Author(s)
Jean-Marc Martinez
Michael Baudin
Entity
CEA / INRIA
Package maintainer
Michael Baudin
License
Supported Scilab Versions
>= 5.2
Dependencies
Assert module (any version)
Specfun (any version)
Apifun (any version)
Creation Date
25th of February 2011
ATOMS packaging system
Available on
How To Install
atomsInstall('NISP')
Description
This module allows to perform sensitivity analysis. This is the analysis of the uncertainty in the output of a given model, depending on the uncertainty in its inputs. The analysis is based on chaos polynomials, which are orthogonal polynomials which are used as an approximation of the original model. Once the coefficients of the chaos polynomial are computed, the associated sensitivity indices are straightforward to get. This toolbox has been created in the context of the OPUS project : http://opus-project.fr/ within the workpackage 2.1.1 "Construction de méta-modèles". This project has received funding by Agence Nationale de la recherche : http://www.agence-nationale-recherche.fr/ See in the help provided in the help/en_US directory of the toolbox for more information about its use. Use cases are presented in the demos directory. Features -------- Main Features: * randvar: * Manage various types of random variables * uniform, normal, exponential, log-normal * setrandvar: * Manage various sampling methods for sets of random variables * Monte-Carlo, Sobol Quasi-Random, Latin Hypercube Sampling, LHS Max Min sampling, and various samplings based on Smolyak Cubature points. * polychaos: * Manage polynomial chaos expansion and get specific outputs * mean, variance, sensitivity indices, quantiles, Wilks quantiles, correlation, etc... * Generate a stand-alone C source code which computes the output of the polynomial chaos expansion. Configuration Functions: * nisp_destroyall : Destroy all current objects. * nisp_getpath : Returns the path to the current module. * nisp_initseed : Sets the seed of the uniform random number generator. * nisp_printall : Prints all current objects. * nisp_shutdown : Shuts down the NISP toolbox. * nisp_startup : Starts up the NISP toolbox. * nisp_verboselevelget : Returns the current verbose level. * nisp_verboselevelset : Sets the current verbose level. Sensitivity Analysis Functions: * nisp_bruteforcesa : Compute sensitivity indices by brute force. * nisp_sobolsa : Compute sensitivity indices by Sobol, Ishigami, Homma. Support functions: * nisp_buildlhs : Creates a LHS design * nisp_corrcoef : Returns the linear correlation coefficient of x and y. * nisp_cov : Returns the empirical covariance matrix of x and y. * nisp_erfcinv : Computes the inverse erfc function. * nisp_expcdf : Computes the Exponential CDF. * nisp_expinv : Computes the Exponential quantile. * nisp_exppdf : Computes the Exponential PDF. * nisp_lognormalcdf : Computes the Lognormal CDF. * nisp_lognormalinv : Computes the Lognormal quantile. * nisp_lognormalpdf : Computes the Lognormal PDF. Test functions: * nisp_ishigami : Returns the Ishigami function. * nisp_ishigamisa : Exact sensitivity analysis for the Ishigami function * nisp_product : Returns the value of the Product function * nisp_productsa : Exact sensitivity analysis for the Product function * nisp_sum : Returns the value of the Product function * nisp_sumsa : Returns the sensitivity indices of the Sum function Acknowledgements ---------------- * Paul Beaucaire * Allan Cornet
Files (7)
[12.77 Mo] NISP_2.3-1.bin.windows.zip
Windows version (i686)
Automatically generated by the ATOMS compilation chain

[5.98 Mo] NISP_2.3-1.bin.x86_64.darwin.tar.gz
MacOSX version
Automatically generated by the ATOMS compilation chain

[6.03 Mo] NISP_2.3-1.bin.x86_64.linux.tar.gz
Linux version (x86_64)
Automatically generated by the ATOMS compilation chain

[6.04 Mo] NISP_2.3-1.bin.i686.linux.tar.gz
Linux version (i686)
Automatically generated by the ATOMS compilation chain

[2.53 Ko] changelog_NISP_v2.3.txt
This is the changelog for the v2.3.
[13.15 Mo] NISP_2.3-1.bin.x64.windows.zip
Windows version (x64)
Automatically generated by the ATOMS compilation chain

News (0)
Comments (10)
    Leave a comment 
Comment from Michael Baudin -- 18th of March 2011, 08:53:54 AM    
Hi,

NISP v2.3 actually requires Scilab 5.3 (because it depends on specfun).
See bug : http://bugzilla.scilab.org/show_bug.cgi?id=9216

Regards,

Michaël
Comment from Yann Collette -- 18th of March 2011, 04:35:14 PM    
There is a problem after installation:

atomsLoad: The file 'C:\Program Files\scilab-5.3.1\contrib\NISP\2.3-1\loader.sce' doesn't
exist or is not read accessible.

When I look in this directory, there is no loader.sce

YC
Answer from Michael Baudin -- 18th of March 2011, 05:10:09 PM    
> There is a problem after installation:
> 
> atomsLoad: The file 'C:\Program Files\scilab-5.3.1\contrib\NISP\2.3-1\loader.sce'
> doesn't
> exist or is not read accessible.
> 
> When I look in this directory, there is no loader.sce
> 
> YC


Hi,

Thank you for the report! On what specific OS ?

Regards,

Michaël
Comment from Michael Baudin -- 18th of March 2011, 05:10:44 PM    
I mean: Windows 32 or 64 ?

Michaël
Answer from Yann Collette -- 22nd of March 2011, 01:12:47 PM    
> I mean: Windows 32 or 64 ?


Windows XP 64 bits.

> Michaël
Answer from Michael Baudin -- 24th of March 2011, 11:53:51 AM    
Thanks for the report: I'm looking into this issue.

> > I mean: Windows 32 or 64 ?
> Windows XP 64 bits.

Answer from Michael Baudin -- 24th of March 2011, 02:40:00 PM    
This is fixed, thanks to Simon.

> Thanks for the report: I'm looking into this issue.
> 
> > > I mean: Windows 32 or 64 ?
> > Windows XP 64 bits.

Comment from Michael Baudin -- 24th of March 2011, 03:28:13 PM    
This comment has been deleted.
Comment from Michael Baudin -- 24th of March 2011, 03:44:10 PM    
This comment has been deleted.
Comment from Michael Baudin -- 24th of March 2011, 03:52:42 PM    
This comment has been deleted.
Answer from Michael Baudin -- 24th of March 2011, 04:01:39 PM    
This answer has been deleted.
Comment from Michael Baudin -- 24th of March 2011, 04:17:02 PM    
This comment has been deleted.
Comment from Michael Baudin -- 24th of March 2011, 04:18:40 PM    
This comment has been deleted.
Comment from Michael Baudin -- 24th of March 2011, 04:25:40 PM    
This comment has been deleted.
Answer from Michael Baudin -- 24th of March 2011, 04:26:02 PM    
This answer has been deleted.
Comment from Michael Baudin -- 12th of February 2013, 07:23:15 PM    
Here is the changelog for the v2.3.

The main changes for this release are the following.
 * Performances of the examples and demos are improved, based on vectorization.
   This makes us benefit from Scilab's multi-core capabilities.
   We can perform 100 000 simulations in less than a second. 
 * The help page are clearer and better organized. 
 * New functions have been created: nisp_buildlhs, nisp_corrcoef, nisp_cov.
 * The User's Manual has been entirely updated. 
   A complete chapter is now devoted to Sensitivity Analysis, 
   with an introduction to the theory and many examples.
 * New test functions have been created: nisp_ishigami, nisp_ishigamisa, 
   nisp_product, nisp_productsa, nisp_sum, nisp_sumsa. 
   We provide both the test function and the exact expectation, variance
   and first and total sensitivity indices.
   This simplifies the testing of the module.
 * New methods for sensitivity analysis were included:
   a brute-force algorithm and the Sobol method for sensitivity 
   indices.
   These functions are vectorized, which improves the performance.
 * The module now depends on the Specfun module, which simplifies 
   the Sobol method for sensitivity analysis.
 * The demonstrations were updated and new demos were created: 
   the module now provides 25 demonstrations, which present the 
   use of chaos polynomials, SRC indices, brute force and the 
   Sobol method on 3 functions including the sum function, the 
   product function, the Ishigami function.
   We included a Scilab port of the AxialStressedBeam demo of Open Turns.

Detailed changelog:
    * Updated manual: filled linear model.
    * Fixed ticket #252: The nisp_exppdf unit test did not pass on Linux.
    * Fixed ticket #254: The ticket_209 test does not pass on Linux.
    * Fixed ticket #256 : The polychaos_getquantwilks test in polychaos failed.
    * Fixed ticket #255: The polychaos_getquantile made the polychaos unit test fail.
    * Fixed ticket #253: The polychaos1 unit test did not pass on Linux (getgroupind).
    * Update manual: filled first part of ishigami analysis.
    * Update manual: computed the variance of the ishigami model.
    * Update manual: moved light png figures into pdf.
    * Added comments in the demos.
    * Vectorized all scripts.
    * Added the ishigami demo with Sobol method.
    * Update manual: added ishigami analysis with Sobol method.
    * Created nisp_cov and nisp_corrcoef.
    * Updated manual: added a section on the LHS samplings.
    * Added demos on the LHS designs.
    * Simplified the demos for the setrandvar samplings.
    * Updated manual: added a separate note on performance.
    * Updated manual: filled decomposition of the variance.
    * Updated manual: filled sensitivity analysis of Ishigami.
    * Updated demos: computed exact sensitivity indices of Ishigami.
    * Added nisp_sobolsa, the Sobol method for sensitivity analysis.
    * Updated manual: filled numerical results for Ishigami.
    * Updated manual: partial fill for Sobol method of SA.
    * Updated manual: filled particular case for product.
    * Added 3 test functions and their exact SI: Sum, Product, Ishigami.
    * Updated the tests, the demos according to the new functions.
    * Improved robustness of the test functions.
    * Created a bruteforce Sensitivity Indices function.
    * Disabled (pragma) the optimization for the Sobol sequence: failed 
      to compile on some Windows.
    * Split the tests for polychaos.
    * Fixed ticket #237: The unit test dataset for erfcinv was wrong.
    * Fixed ticket #249: The parameter b of a normal variable in randvar 
      was unclear.
    * Improved robustness and flexibility of lognormal and exponential
      PDF, CDF and Inv.
    * Fixed ticket #228: The output arguments of many methods of polychaos 
      were undocumented.
    * Created separated unit test directory for support functions.
    * Created unit tests for nisp_buildlhs, nisp_corrcoef, nisp_cov.
    * Fixed bug in nisp_corrcoef.
    * Organized demos.
    * Updated the Axial Stressed Beam demo.
Leave a comment
You need to log in before you can leave a comment.