py-irt: A Scalable Item Response Theory Library for Python

TL;DR

py-irt is a Python library that enables scalable Bayesian IRT model fitting using GPU acceleration, suitable for large datasets and various IRT applications.

Contribution

It introduces a GPU-accelerated Python library for Bayesian IRT modeling built on Pyro and PyTorch, supporting large-scale data analysis.

Findings

Supports large datasets with GPU acceleration

Estimates latent traits of subjects and items

Flexible for various IRT models

Abstract

py-irt is a Python library for fitting Bayesian Item Response Theory (IRT) models. py-irt estimates latent traits of subjects and items, making it appropriate for use in IRT tasks as well as ideal-point models. py-irt is built on top of the Pyro and PyTorch frameworks and uses GPU-accelerated training to scale to large data sets. Code, documentation, and examples can be found at https://github.com/nd-ball/py-irt. py-irt can be installed from the GitHub page or the Python Package Index (PyPI).