HTTPS SSH

Transport Maps

This package provides basic functionalities for the construction of monotonic transport maps.

Supported systems

  • *nix like OS (Linux, Unix, ...)
  • Mac OS

Other operating systems have not been tested and they likely require a more complex procedure for the installation (this includes the Microsoft Windows family..).

We reccommend to work in a virtual environment using virtualenv or Anaconda.

Installation requirements

  • gcc (or an alternative C/C++ compiler)
  • gfortran (or an alternative Fortran compiler)

Automatic installation

First of all make sure to have the latest version of pip installed

$ pip install --upgrade pip

The package and its python dependencies can be installed running the command:

$ pip install --upgrade numpy $ pip install --upgrade TransportMaps

If one whish to enable some of the optional dependencies:

$ MPI=True SPHINX=True PLOT=True H5PY=True pip install --upgrade TransportMaps

These options will install the following modules:

  • MPI -- parallelization routines (see the tutorial). It requires the separate installation of an MPI backend (openMPI, mpich, etc.). The following Python modules will be installed: * mpi4py * mpi_map
  • PLOT -- plotting capabilities:
  • SPHINX -- documentation generation routines:
  • H5PY -- routines for the storage of big data-set. It requires the separate installation of the hdf5 backend.
  • PYHMC -- routines for Hamiltonian Markov Chain Monte Carlo

Manual installation

If anything goes wrong with the automatic installation you can try to install manually the following packages.

Mandatory Back-end packages (usually installed with numpy):

  • BLAS (with development/header files)
  • LAPACK (with development/header files)

Mandatory Python packages:

Finally install TransportMaps:

$ pip install TransportMaps

Running the Unit Tests

Unit tests are available and can be run through the command:

>>> import TransportMaps as TM
>>> TM.tests.run_all()

There are >3500 unit tests, and it will take some time to run all of them.

Credits

This sofware has been developed and is being maintained by the Uncertainty Quantification Group at MIT, under the guidance of Prof. Youssef Marzouk.

Developing team

Daniele Bigoni – [www]
Alessio Spantini
Rebecca Morrison
Ricardo M. Baptista