pymc-devs/pymc-examples

Examples of PyMC models, including a library of Jupyter notebooks.

What it solves

PyMC Examples gives learners and practitioners a ready-made set of Jupyter notebooks that demonstrate how to apply PyMC for Bayesian statistical modeling and probabilistic machine learning. Instead of starting from scratch, users can explore worked examples, follow step-by-step demonstrations, and adapt them to their own problems.

How it works

The project is a collection of notebooks hosted on GitHub and presented in an online gallery. Each notebook includes a binder badge so visitors can launch an interactive session directly in the browser without installing anything locally. The README points to a getting started guide, a main PyMC tutorial, and an API reference. It also lists several books (like "Probabilistic Programming and Bayesian Methods for Hackers" and "Statistical Rethinking") whose code examples are built with PyMC, as well as recorded talks on YouTube. Users can ask questions on the PyMC Discourse forum, report issues for notebooks or the library itself, and contribute by reading the contributing guide and code of conduct.

Who it's for

This resource is for anyone wanting to learn or use Bayesian statistics with Python: data scientists, statisticians, researchers, students, and developers who prefer hands-on code examples over theory-only explanations. It is also useful for instructors looking for ready-to-run demonstrations and for people who already know Bayesian ideas but need PyMC-specific recipes.

Highlights

  • Curated example gallery with a binder badge on every notebook for instant interactive use.
  • Direct links to a getting started guide, the main PyMC tutorial, and the API reference.
  • Companion resources: books that teach Bayesian analysis with PyMC code, plus a YouTube playlist of talks.
  • Community support through PyMC Discourse, separate issue trackers for examples and the library, and contribution guidelines.

Related

  • Project
    SciML/SciMLSensitivity.jl

    A sensitivity analysis utility package for the SciML ecosystem that helps determine how model outputs change relative to input parameters.

  • Project
    yeshenpy/Awesome-Evolutionary-Reinforcement-Learning

    A companion repository to a comprehensive survey on evolutionary reinforcement learning (ERL), indexing 270 canonical papers with verified code links and 86 bilingual reading-guide mappings to help researchers study, reproduce, and extend hybrid EA-RL methods.

  • Project
    MLCIL/scikit-fingerprints

    A Python package that gives chemists and ML practitioners a scikit-learn–compatible toolkit for converting molecules into fingerprint vectors, filtering them, measuring similarity, and building trainable pipelines — with 30+ fingerprints, 30+ filters, benchmark datasets, and a uniform API.

  • Project
    SimplexLab/TorchJD

    A PyTorch library for training neural networks with multiple losses, offering scalarization and Jacobian descent methods to resolve optimization conflicts.