Bayeslite is a BQL database built on SQLite3. BQL is an extension to SQL that supports queries about the probable implications of data.

Bayeslite is part of an ongoing research project. For more information, contact bayesdb@mit.edu.

Bayeslite is written in Python 2.7, using the sqlite3 module with SQLite3 >=3.7.17.

Bayeslite depends on:

• Crosscat, a general-purpose nonparametric Bayesian population model which serves as a default in the absence of a domain-specific model.
• numpy, a library of vectorized numerical algorithms
• requests, an HTTP/HTTPS library, which we use to track users.

The bayeslite automatic tests depend on:

• pytest
• pandas, a library for tabular data structures

The bayeslite documentation depends on:

• Sphinx

To check that everything will work, before installing:

$ ./check.sh

To install system-wide, or into the current virtual environment:

$ python setup.py build
$ python setup.py install

Import the bayeslite module. See the documentation for details on the Python API.

To build the documentation (requires sphinx):

$ make doc

The result will be placed in build/doc, with one subdirectory per output format.

To build only one output format, e.g. HTML because you don't want to install TeX:

$ make html