Creating animations with MCMC – Towards Data Science

Markov Chain Monte Carlo (MCMC) is a widely popular technique in Bayesian statistics. It is used for posteriori distribution sampling since the analytical form is very often non-trackable. In this post, however, we are going to use it to generate animations from static images/logos. Incidentally, it might serve as an introduction to MCMC and Rejection sampling. The idea is based on a great open source package imcmc that is built upon PyMC3.