Getting started

Prerequisites

SMT setup requires numpy, ensure you have it installed.

As some surrogates are written in C++, SMT setup uses Cython to compile them. If Cython is not found, SMT setup tries to install it, but as this step is not robust for all environments it is better to ensure you have it properly installed before hand. If compilation with Cython fails then RBF, IDW, RMTB and RMTC surrogates will not be available.

Note: if you use Anaconda Python distribution, it is best to install dependencies: numpy, scipy, sklearn, Cython with conda command then use pip command as follows to terminate the SMT installation.

Installing

To install the latest released version of SMT:

pip install smt

Or else to install the current version from the GitHub repository master:

pip install git+https://github.com/SMTOrg/smt.git@master

If you want to contribute to SMT, see Contributing to SMT section.

Notebooks

Several notebooks are available to get up to speed with SMT:

Uninstalling

If you want to uninstall SMT:

pip uninstall smt