pyAM

Python package for solving assortative matching models with two-sided heterogeneity. The theoretical framework behind the class of models solved by pyAM is described in Eeckhout and Kircher (2012).

Installation

Assuming you have pip on your computer (as will be the case if you've installed Anaconda) you can install the latest stable release of pyam by typing

$ pip install pyam

at a terminal prompt.

Contributing

If you wish to contribute to the project you will likely want to install from source. First your will need to fork and then clone the source repository.

$ git clone https://github.com/YOUR-USERNAME/pyAM.git

Next create a new conda development environment

$ conda create -n pyam-dev python anaconda

activate the newly created development environment

$ source activate pyam-dev

and install additional dependencies not available within Anaconda.

$ pip install pycollocation
$ pip install seaborn

Finally, change into your local clone of the pyam source directory and install the package in development mode.

$ pip install -e .

Example notebooks

At the moment there are two example notebooks, one for positive assortative matching and one for negative assortative matching in the examples directory. The positive assortative matching works fine; the negative assortative matching, however, does not yet work (I suspect because of a poor algorithm for the initial guess).