Data and analysis in BayesDB form the concept of a population.
Along with the release of Bayeslite 0.1, the MIT Probabilistic Computing Project released a snapshot of BayesDB applied to a database of Earth satellites maintained by the Union of Concerned Scientists:
The data is a catalogue of satellites. Each row of the data represents a satellite and each column is a feature of that satellite such as dry mass, orbit type, launch date, perigee, etc. Along with the snapshot comes a demo iPython notebook that uses this snapshot to explore and clean the data.
To launch the population from an install of bayeslite and bdbcontrib, run
Have some data you would like to see modeled with a BayseDB population? Some BayesDB functionality, including machine assisted modeling, is currently only available through private alpha. Private alpha users are expected to share more about their data and experience with the probcomp research team.