An introduction to PyMC3

on YouTube ↗44m

" summary

Concrete demos show PyMC3 building full Bayesian models, running HMC and variational inference in a notebook, and diagnosing failures with divergences and R_hat / effective sample size warnings. Examples replace normals with Student‑t to capture outliers, reparameterize to remove a funnel and recover correct posteriors, and run posterior predictive checks on real trading returns. A PDE groundwater inverse problem uses a mesh to infer transmissivity fields and produces thousands of posterior samples.

AI-written summary · about

" chapters (15)

1. 0:00Intro
2. 1:08What does PyMC do
3. 2:15Bayesian vs Frequentist approach
4. 3:08What do we need
5. 7:32Free parameters
6. 8:02Reasonable explanations
7. 10:14Probability
8. 11:56Sample
9. 20:18Problems
10. 22:28Warnings
11. 27:12Re parameterizing
12. 28:05posterior predictive distribution
13. 31:01groundwater flow
14. 33:51statistical model
15. 35:31true values

" related talks

• 39mProbablistic Programming Data Science with PyMC3Thomas Wiecki · PyData London 2016
• 57mA Quickstart Guide to PyMC3Nicole Carlson · PyData Chicago 2016
• 42mBayesian Non-parametric Models for Data Science using PyMC3Christopher Fonnesbeck · PyCon 2018
• 01h 31mProbabilistic Programming and Bayesian Inference in PythonLara Kattan · PyOhio 2019
• 01h 30mAn introduction to Markov Chain Monte Carlo using PyMC3Chris Fonnesbeck · PyData London 2019
• 39mProbablistic Programming Data Science with PyMC3Thomas Wiecki · PyData London 2016
• 01h 27mProbabilistic Python: An Introduction to Bayesian Modeling with PyMCChris Fonnesbeck · PyData London 2022
• 42mSolving Real-World Business Problems with Bayesian ModelingThomas Wiecki · PyData London 2022