Bayesian Modeling and Computation in Python is a free, web-hosted textbook by Osvaldo A. Martin, Ravin Kumar, and Junpeng Lao, published by Chapman & Hall/CRC. It teaches Bayesian statistical modeling and computation through hands-on, code-driven examples built on the Python probabilistic programming ecosystem, primarily PyMC, ArviZ, and Bambi.
The book spans 11 chapters that move from foundational ideas — Bayesian inference, exploratory analysis of Bayesian models, and linear models — to more specialized techniques such as splines, time series analysis, Bayesian additive regression trees, approximate Bayesian computation, and end-to-end probabilistic programming workflows.
Who it's for
This resource suits practitioners, data scientists, and students who already have some background in statistics and Python and want a practical, implementation-focused path into Bayesian methods. It works well both as a structured cover-to-cover course and as a reference to dip into for specific modeling techniques.
The full text is available online at no cost under a Creative Commons license, with accompanying code released separately and kept updated for compatibility with current library versions.