astro-informatics/harmonic
Machine learning assisted marginal likelihood (Bayesian evidence) estimation for Bayesian model selection
When analyzing complex data, scientists often need to choose the best theoretical model to explain their observations. This tool helps by taking samples generated from your Bayesian model (like those from MCMC simulations) and calculates a crucial metric called the 'marginal likelihood' or 'Bayesian evidence'. This value helps researchers like astrophysicists, cosmologists, or statisticians compare and select the most appropriate model to fit their data.
Available on PyPI.
Use this if you are performing Bayesian model selection and need an efficient, machine-learning-assisted method to estimate the marginal likelihood from your posterior samples.
Not ideal if you are not working with Bayesian models or if you do not have posterior samples from your model simulations.
Stars
77
Forks
11
Language
Jupyter Notebook
License
GPL-3.0
Category
Last pushed
Mar 13, 2026
Commits (30d)
0
Dependencies
18
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/astro-informatics/harmonic"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
tensorflow/probability
Probabilistic reasoning and statistical analysis in TensorFlow
erdogant/bnlearn
Python package for Causal Discovery by learning the graphical structure of Bayesian networks....
pyro-ppl/pyro
Deep universal probabilistic programming with Python and PyTorch
probml/pyprobml
Python code for "Probabilistic Machine learning" book by Kevin Murphy
google/edward2
A simple probabilistic programming language.