Welcome to D3M Interface’s documentation!

d3m-interface is a Python library which enable data scientist to use D3M AutoML systems. It contains an implementation to integrate D3M AutoML systems with Jupyter Notebooks. It provides a familiar interface, that is similar to other AutoML systems like H2O and TPOT, to make easier for people to adopt D3M tools.

d3m-interface allows data scientists to explore, understand, and build trust on the derived models. This allows them to make an informed decision regarding which model to choose, as well as to improve and customize the solution. Through d3m-interface, users can run AlphaD3M and other D3M AutoML systems.

_images/d3m_interface_architecture.png

Overall architecture of d3m-interface

You can find the source code on GitLab: https://gitlab.com/ViDA-NYU/d3m/d3m_interface