Build, fit, and validate Bayesian models with PyMC workflows.
npx skills add https://github.com/crazymsn/academic-skills --skill pymc-crazymsn
Please help me install this Agent Skill. Skill: pymc Source: https://github.com/crazymsn/academic-skills/tree/main/academic-skills/pymc Command: npx skills add https://github.com/crazymsn/academic-skills --skill pymc-crazymsn
PyMC enables building, fitting, validating, and comparing Bayesian models with a modern Python API, covering hierarchical models, MCMC, variational inference, and model comparison.
Install PyMC, define a simple model, and run sampling to inspect the posterior.
High-intent search queries and answers about installing and using this skill.
You can build and validate a Bayesian hierarchical model by defining priors, specifying the model structure, sampling with MCMC NUTS, and running posterior predictive checks with ArviZ diagnostics.
Bayesian inference for uncertainty quantification is best handled by applying a full probabilistic workflow, utilizing MCMC or variational inference, and validating posterior distributions through prior and posterior predictive checks.
Yes, the probabilistic programming workflow supports both MCMC NUTS and variational inference ADVI, allowing you to fit models and generate diagnostics using ArviZ for multi-method inference.
Yes, you can use ArviZ for model comparison and diagnostics within the Bayesian workflow to evaluate sampling performance, validate posterior distributions, and compare different probabilistic models.
Prior predictive checks are performed by simulating data from the model using only the defined priors before fitting, ensuring the priors are plausible and preventing unintended posterior distributions.
Variational inference is used instead of MCMC when faster approximate inference is needed for large-scale Bayesian modeling, trading exact posterior exploration for computational speed during the probabilistic workflow.
lamm-mitCreate statistical visualizations from pandas DataFrames using seaborn.
pur3v4d3rBuild, fit, and validate Bayesian models with PyMC using MCMC and variational inference.
SciMate-AISolve Bayesian modeling tasks with PyMC for probabilistic programming.
ovachieverBuild, fit, and evaluate Bayesian models with PyMC using MCMC sampling.
