Metadata-Version: 2.1
Name: BayesBoom
Version: 0.0.2
Summary: Tools for Bayesian modeling.
Home-page: https://github.com/steve-the-bayesian/BOOM
Author: Steven L. Scott
Author-email: steve.the.bayesian@gmail.com
License: UNKNOWN
Platform: UNKNOWN
Description-Content-Type: text/plain
Requires-Dist: pybind11 (>=2.3)

Boom stands for 'Bayesian object oriented modeling'.
It is also the sound your computer makes when it crashes.

The main part of the Boom library is formulated in terms of abstractions
for Model, Data, Params, and PosteriorSampler.  A Model is primarily an
environment where parameters can be learned from data.  The primary
learning method is Markov chain Monte Carlo, with custom samplers defined
for specific models.

The archetypal Boom program looks something like this:

import BoomBayes as Boom

some_data = 3 * np.random.randn(100) + 7
model = Boom.GaussianModel()
model.set_data(some_data)
precision_prior = Boom.GammaModel(0.5, 1.5)
mean_prior = Boom.GaussianModel(0, 10**2)
poseterior_sampler = Boom.GaussianSemiconjugateSampler(
    model, mean_prior, precision_prior)
model.set_method(poseterior_sampler)
niter = 100
mean_draws = np.zeros(niter)
sd_draws = np.zeros(niter)
for i in range(100):
    model.sample_posterior()
    mean_draws[i] = model.mu()
    sd_draws[i] = model.sigma()



