Skip to main content

Tools for Bayesian modeling.

Project description

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 BayesBoom 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()


Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page