pymc-labs/pymc-modeling

pymc-mlflow

Track PyMC experiments with MLflow, record sampling configuration and diagnostics, save and retrieve DataTree artifacts, and compare runs. Use for pymc_marketing.mlflow autologging, MMM model persistence and MLflow registry preparation, or CLV fit tracking.…

Idioma do texto original: inglês

pymc-modeling

Build, revise, and debug Bayesian models with PyMC. Use when choosing likelihoods and priors, specifying model/data dimensions, fitting hierarchical models, GPs, time series, mixtures, BART or splines, using pymc-extras distributions, marginalization,…

Idioma do texto original: inglês

pytensor-workflows

Build, differentiate, compile, and debug PyTensor symbolic computations for models. Use for symbolic tensor shape or dtype errors, named dimensions, indexing and broadcasting, vectorization and scan, numerical or sparse operations, symbolic RNG state, graph…

Idioma do texto original: inglês

prior-elicitation

Elicit and check Bayesian prior assumptions in meaningful units. Use for expert quantiles, PreliZ, constrained priors, prior-predictive plausibility and prior sensitivity, including power scaling, regularized horseshoe and R2D2 assumptions.

Idioma do texto original: inglês

arviz-diagnostics

Diagnose existing Bayesian inference output and evaluate fitted predictions with modern ArviZ DataTree summaries, divergences, rank R-hat, ESS and Monte Carlo precision. Use for posterior predictive checks, calibration, LOO/ELPD, Pareto k, stacking, grouped…

Idioma do texto original: inglês