Tree [2a9c08] default /
 History

Read Only access


File Date Author Commit
 .pc 2016-01-19 Julien Bect Julien Bect [68308c] maint: Commit .pc directory (needed to build ta...
 admin 2017-07-03 Julien Bect Julien Bect [2a9c08] Fusion avec 2.5.x
 arrays 2017-07-02 Julien Bect Julien Bect [df9b0d] @stk_dataframe/stk_dataframe.m: Fix a typo in o...
 core 2017-07-03 Julien Bect Julien Bect [fdb3b4] @stk_model_gpposterior/stk_predict.m: Skip main...
 covfcs 2016-12-14 Julien Bect Julien Bect [57e376] covfcs/rbf/stk_rbf_spherical.m: Fix typo
 doc 2017-07-01 Julien Bect Julien Bect [ccd80a] Remove all occurences of response_name
 examples 2017-07-02 Julien Bect Julien Bect [5da22f] stk_predict_leaveoneout.m: nargout == 0 => crea...
 iago 2017-06-16 Julien Bect Julien Bect [f23e8f] source formatting: CG#07
 lm 2017-01-22 Julien Bect Julien Bect [ab4ef0] Implement isequal to maintain compatiblity with...
 misc 2017-07-01 Julien Bect Julien Bect [afa98f] Move important plotting functions to 'utils' di...
 param 2017-07-03 Julien Bect Julien Bect [13328e] stk_param_estim.m: Do not use model.param as a ...
 sampling 2017-06-28 Julien Bect Julien Bect [a26b16] Change mnemonic 'IncorrectArgument' to 'Invalid...
 utils 2017-07-01 Julien Bect Julien Bect [751c4d] stk_plot_probdom2d.m: New function
 .hgignore 2016-12-09 Julien Bect Julien Bect [c46c92] Save M/O version info when compiling MEX-files ...
 .hgtags 2017-07-03 Julien Bect Julien Bect [7c4d1e] Tag beta release 2.5.0-beta1
 AUTHORS 2016-02-23 Julien Bect Julien Bect [dd7ada] AUTHORS: Add T. Assouline, F. Autret and S. Duh...
 CITATION 2017-07-03 Julien Bect Julien Bect [579ae2] Start the preparation of release 2.5.0
 COPYING 2014-09-02 Julien Bect Julien Bect [31d4f5] Rename LICENSE to COPYING.
 ChangeLog 2017-07-03 Julien Bect Julien Bect [13328e] stk_param_estim.m: Do not use model.param as a ...
 Makefile 2017-03-09 Julien Bect Julien Bect [bcc698] Makefile: Conform to OF release instructions
 NEWS 2017-07-03 Julien Bect Julien Bect [2a9c08] Fusion avec 2.5.x
 README.md 2017-01-22 Julien Bect Julien Bect [1c663d] README.md: Raise minimal Octave version to 3.2.4
 stk_init.m 2017-07-03 Julien Bect Julien Bect [2a9c08] Fusion avec 2.5.x
 stk_version.m 2017-07-03 Julien Bect Julien Bect [579ae2] Start the preparation of release 2.5.0

Read Me

STK: a Small (Matlab/Octave) Toolbox for Kriging

This README file is part of

STK: a Small (Matlab/Octave) Toolbox for Kriging
http://sourceforge.net/projects/kriging

STK is free software: you can redistribute it and/or modify it under
the terms of the GNU General Public License as published by the Free
Software Foundation, either version 3 of the License, or (at your
option) any later version.

STK is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public
License for more details.

You should have received a copy of the GNU General Public License
along with STK. If not, see http://www.gnu.org/licenses/.

General information

Version: See stk_version.m

Authors: See AUTHORS file

Maintainers: Julien Bect julien.bect@centralesupelec.fr
and Emmanuel Vazquez emmanuel.vazquez@centralesupelec.fr

Description: The STK is a (not so) Small Toolbox for Kriging. Its
primary focus is on the interpolation/regression
technique known as kriging, which is very closely related
to Splines and Radial Basis Functions, and can be
interpreted as a non-parametric Bayesian method using a
Gaussian Process (GP) prior. The STK also provides tools
for the sequential and non-sequential design of
experiments. Even though it is, currently, mostly geared
towards the Design and Analysis of Computer Experiments
(DACE), the STK can be useful for other applications
areas (such as Geostatistics, Machine Learning,
Non-parametric Regression, etc.).

Copyright: Large portions are Copyright (C) 2011-2014 SUPELEC.
See individual copyright notices for more details.

License: GNU General Public License, version 3 (GPLv3).
See COPYING for the full license.

URL: http://sourceforge.net/projects/kriging

One toolbox, two flavours

The STK toolbox comes in two flavours:

  • an "all purpose" release, which is suitable for use both with
    GNU Octave
    and with Matlab.
  • an Octave package, for people who want to install and use STK as a
    regular Octave package.

Hint: if you're not sure about the version that you have...

  • the "all purpose" release has this file (README.md) and the stk_init
    function (stk_init.m) in the top-level directory,
  • the Octave package has a DESCRIPTION file in the top-level directory
    and this file in the doc/ subdirectory.

Quick Start

Quick start with the "all purpose" release (Matlab/Octave)

Download and unpack an archive of the "all purpose" release from the
STK project
file release system
on SourceForge.

Run stk_init.m in either Octave or Matlab.

After that, you should be able to run the examples located in the examples
directory. All of them are scripts, the file name of which starts with
the stk_example_ prefix.

For instance, type stk_example_kb03 to run the third example in the "Kriging
basics" series.

Quick start with the Octave package release (Octave only)

Assuming that you have a working Internet connection, typing pkg install -forge stk
(from within Octave) will automatically download the latest STK package tarball from the
Octave Forge
file release system
on SourceForge and install it for you.

Alternatively, if you want to install an older (or beta) release, you can download
the tarball from either the STK project FRS or the Octave Forge FRS, and install it
with pkg install FILENAME.tar.gz.

After that, you can load STK using pkg load stk.

To check that STK is properly loaded, try for instance stk_example_kb03 to run
the third example in the "Kriging basics" series.

Requirements and recommendations

Common requirement

Your installation must be able to compile C mex files.

Requirements and recommendations for use with GNU Octave

The STK is tested to work with GNU Octave 3.2.4 or newer.

Requirements and recommendations for use with Matlab

The STK works with Matlab R2007a or newer.

The Optimization Toolbox is recommended.

The Parallel Computing Toolbox is optional.

Content

By publishing this toolbox, the idea is to provide a convenient and
flexible research tool for working with kriging-based methods. The
code of the toolbox is meant to be easily understandable, modular,
and reusable. By way of illustration, it is very easy to use this
toolbox for implementing the EGO algorithm [1].
Besides, this toolbox can serve as a basis for the implementation
of advanced algorithms such as Stepwise Uncertainty Reduction (SUR)
algorithms [2].

The toolbox consists of three parts:

  1. The first part is the implementation of a number of covariance
    functions, and tools to compute covariance vectors and matrices.
    The structure of the STK makes it possible to use any kind of
    covariances: stationary or non-stationary covariances, aniso-
    tropic covariances, generalized covariances, etc.

  2. The second part is the implementation of a REMAP procedure to
    estimate the parameters of the covariance. This makes it possible
    to deal with generalized covariances and to take into account
    prior knowledge about the parameters of the covariance.

  3. The third part consists of prediction procedures. In its current
    form, the STK has been optimized to deal with moderately large
    data sets.

References

[1] D. R. Jones, M. Schonlau, and William J. Welch. Efficient global
optimization of expensive black-box functions
. Journal of Global
Optimization, 13(4):455-492, 1998.

[2] J. Bect, D. Ginsbourger, L. Li, V. Picheny, and E. Vazquez.
Sequential design of computer experiments for the estimation of a
probability of failure
. Statistics and Computing, pages 1-21, 2011.
DOI: 10.1007/s11222-011-9241-4.

Ways to get help, report bugs, ask for new features...

Use the "help" mailing-list:

kriging-help@lists.sourceforge.net
https://sourceforge.net/p/kriging/mailman

to ask for help on STK, and the ticket manager:

https://sourceforge.net/p/kriging/tickets

to report bugs or ask for new features.