an open-source python toolbox to analyze mobile phone metadata
.. image:: https://img.shields.io/pypi/v/bandicoot.svg :target: https://pypi.python.org/pypi/bandicoot :alt: Version
.. image:: https://img.shields.io/pypi/l/bandicoot.svg :target: https://github.com/computationalprivacy/bandicoot/blob/master/LICENSE :alt: MIT License
.. image:: https://img.shields.io/pypi/dm/bandicoot.svg :target: https://pypi.python.org/pypi/bandicoot :alt: PyPI downloads
.. image:: https://img.shields.io/travis/computationalprivacy/bandicoot.svg :target: https://travis-ci.org/computationalprivacy/bandicoot :alt: Continuous integration
bandicoot (http://bandicoot.mit.edu) is Python toolbox to analyze mobile phone metadata. It provides a complete, easy-to-use environment for data-scientist to analyze mobile phone metadata. With only a few lines of code, load your datasets, visualize the data, perform analyses, and export the results.
.. image:: https://raw.githubusercontent.com/computationalprivacy/bandicoot/master/docs/_static/bandicoot-dashboard.png :alt: Bandicoot interactive visualization
The source code is currently hosted on Github at https://github.com/computationalprivacy/bandicoot. Binary installers for the latest released version are available at the Python package index:
.. code-block:: sh
.. code-block:: sh
pip install bandicoot
bandicoot has no dependencies, which allows users to easily compute indicators on a production machine. To run tests and compile the visualization, optional dependencies are needed:
npm_ to compile the js and css files of the dashboard.
The official documentation is hosted on http://bandicoot.mit.edu/docs. It includes a quickstart tutorial, a detailed reference for all functions, and guides on how to use and extend bandicoot. You can also check out our
interactive training notebooks_ to learn how to download your own data from your mobile phone and load it into bandicoot to visualize it or to learn how to use bandicoot indicators in scikit-learn.