pseudopeople is a Python package that generates realistic simulated data about a fictional United States population, designed for use in testing entity resolution (record linkage) methods or other data science algorithms at scale.
pseudopeople requires Python 3.10-3.11 to run
You can install pseudopeople from PyPI with pip:
> pip install pseudopeople
or build it from source with
> git clone https://github.com/ihmeuw/pseudopeople.git
> cd pseudopeople
> python setup.py install
You can view documentation at https://pseudopeople.readthedocs.io/en/latest/
To receive updates about this software package join the mailing list here.