Machine Learning Platform (h2o.ai)

H2O Flow is an open-source user interface for H2O. It is a web-based interactive environment that allows you to combine code execution, text, mathematics, plots, and rich media in a single document.

With H2O Flow, you can capture, rerun, annotate, present, and share your workflow. H2O Flow allows you to use H2O interactively to import files, build models, and iteratively improve them. Based on your models, you can make predictions and add rich text to create vignettes of your work - all within Flow’s browser-based environment.

Flow’s hybrid user interface seamlessly blends command-line computing with a modern graphical user interface. However, rather than displaying output as plain text, Flow provides a point-and-click user interface for every H2O operation. It allows you to access any H2O object in the form of well-organized tabular data.

H2O Flow sends commands to H2O as a sequence of executable cells. The cells can be modified, rearranged, or saved to a library. Each cell contains an input field that allows you to enter commands, define functions, call other functions, and access other cells or objects on the page. When you execute the cell, the output is a graphical object, which can be inspected to view additional details.

Many information and guides are availble in the web UI of h2o.ai Flow (right pane) or in their documentation.

Accessing h2o.ai

You can only access the h2o.ai Flow web application with an Amazon WorkSpace, VPN connection or bastion host. The h2o.ai server is deployed in a private subnet of the BDTI environment and is not publicly accessible. The internal endpoint will be distributed by the BDTI technical team.

Authentication & Authorization

h2o.ai is a shared environment with no authentication or authorization on the application level. Access to the h2o.ai endpoint is only given to BDTI users of the pilot environment. The h2o.ai instance is not publicly available.

Amazon S3 Access

h2o.ai instances can be configured to have access to Amazon S3 buckets. You can reference accessible S3 data directly in your data frames in h2o. The image belows depicts a simple example of importing data from S3.