pygtc: beautiful parameter covariance plots (aka. Giant Triangle Confusograms)
S. Bocquet, Faustin W. Carter · The Journal of Open Source Software · 2016
Multi-dimensional model parameter spaces are commonly sampled using Markov Chain Monte-Carlo (MCMC) methods or more advanced algorithms as implemented, for instance, in emcee (Foreman-Mackey et al. 2013) or PyMultiNest (Buchner et al. 2014).The recovered parameter constraints are usually displayed on a grid in which the diagonal shows the 1-dimensional posteriors and the lower-left half shows the pairwise projections.Due to the triangular appearance, such plots are typically referred to as "triangle" plots.If the parameter space is large, the resulting plot can be visually overwhelming; we refer to such a figure as a Giant Triangle Confusogram (GTC).