Ugtm: A Python Package for Data Modeling and Visualization Using Generative Topographic Mapping

Abstract

ugtm is a Python package that implements generative topographic mapping (GTM), a dimensionality reduction algorithm by Bishop, Svensén and Williams. Because of its probabilistic framework, GTM can also be used to build classification and regression models, and is an attractive alternative to t-distributed neighbour embedding (t-SNE) or other non-linear dimensionality reduction methods. The package is compatible with scikit-learn, and includes a GTM transformer (eGTM), a GTM classifier (eGTC) and a GTM regressor (eGTR). The input and output of these functions are numpy arrays. The package implements supplementary functions for GTM visualization and kernel GTM (kGTM). The code is under MIT license and available on GitHub (<a href="https://github.com/hagax8/ugtm" target="_blank">https://github.com/hagax8/ugtm</a>). For installation instructions and documentation, cf. <a href="https://ugtm.readthedocs.io/" target="_blank">https://ugtm.readthedocs.io</a>. <strong>Funding statement:</strong> HG acknowledges funding from the US National Institute of Mental Health (PGC3: U01 MH109528).