S-timator is a (pure) Python package that is installable from the Python Package Index.
However, S-timator relies heavily on the “Scientific Python ecossystem”, a set of Python libraries that brings high-performance scientific computing to the Python programming language.
In practical terms, this means that the installation of a standard Python distribution will not be enough to use S-timator. Instead, either the mandatory dependencies are installed one by one, or, more conveniently, Python is installed through a “scientific distribution”.
One of the following “scientific python” distributions is recommended, as they all provide an easy installation of all requirements:
S-timator supports Python versions 2.6 and up, but support of 3.x is coming soon.
S-timator depends on a “scientific python stack”. The mandatory requirements for S-timator are the following libraries:
The installation of these Python libraries is optional, but strongly recommended:
The Anaconda Python Distribution, from “Continuum Analytics” is, arguably, the most convenient distribution. The full installation will provide all S-timator requirements, except wxPython, which has to be installed after installing Python.
From the same company, the Miniconda “slim” distribution is also an alternative, for those that worry about disk space. In this case, the necessary conda install‘s must be run for the dependencies, after installing Python.
S-timator is on the Python Package Index (pypi), so , after installing the required libraries, (Python, numpy, scipy, matplotlib, pandas, seaborn and pip) the easiest way to install S-timator is with pip:
$ pip install stimator