Pymc Python Packages

causalpy

A Python package for causal inference in quasi-experimental settings

simba-mcp

MCP server for SIMBA — connect AI assistants (Claude, Cursor) to Bayesian Marketing Mix Models. Upload data, build models, optimize budgets, and run scenarios through natural language.

ptgp

GPs in PyTensor

calibr8

Toolbox for non-linear calibration modeling.

oreum-core

Core tools for use on client projects

gp3bayespy

Contract-first Bayesian workflows for hierarchical behavioural data, posterior validation, predictive diagnostics, sensitivity analysis, PSIS-LOO, reproducibility, and dynamic pupillometry.

distparams

Single source of truth for statistical distribution parameterizations. Convert between PyMC, scipy, Stan, R, jStat, TFP, NumPyro, and stdlib random

erotica

Gaia open-cluster analysis in Python: HDBSCAN membership with calibrated probabilities, unbinned Poisson point-process radial profiles (King, EFF, Plummer, King+corona) in PyMC, DR3 selection functions, isochrones, dynamics, and an identifiability toolkit that asks whether a parameter is measured before it is quoted.

bayesian-pricing

Hierarchical Bayesian models for insurance pricing — PyMC 5, thin-data segments, credibility factors

insurance-spatial

BYM2 spatial territory ratemaking for insurance pricing — PyMC 5 ICAR, adjacency, Moran's I diagnostics

actuarcredibility

Credibility models for actuarial pricing: Bühlmann, Bühlmann-Straub, Jewell hierarchical, Hachemeister regression, classical, and Bayesian (PyMC). pip install actuarcredibility

levy-stable-jax

Lévy's alpha-stable distribution for the Jax numerical framework

pytensor-federated

Distributed, differentiable and async graph computation for PyTensor

survivalpredict

Python survival analysis/survival curves, with a scikit-learn-like api

bioanchor

🔬 Autonomous Bayesian scientific agent — MCMC analysis, uncertainty quantification, and permanent decentralized archiving. The reproducibility layer for DeSci.

setu-sbi

Bridging simulators to probabilistic programming in JAX

nowcasting-sus

Bayesian nowcasting for Brazilian disease surveillance data (Sinan) - corrects reporting delay in real time with PyMC. `pip install nowcasting-sus`

tumoroscope-pymc

Python package of the 'Tumoroscope' model implemented in PyMC.