All AI modeling projects start with data. So let’s review how to get your data into DataRobot to make it available for building models, and make it available for use by others across your teams.
First of all, when you first got started with DataRobot, you may have dived directly into beginning a new project by importing your own dataset, from here:
This works for getting a quick start into the modeling process, but soon you’ll notice that the data used does not appear in the AI Catalog. Think of starting a new project in this fashion as a personal sandbox type environment: it’s great for testing an idea without committing anything to your AI Catalog! Starting a project like this is the same as starting a project from the Projects dropdown > Create New Project link (in the upper, right-hand corner of the UI):
If you navigate to the AI Catalog from the top menu, you can upload a dataset either by clicking Add to catalog or + Add new data.
The difference is, any data uploaded into the AI Catalog can be used in a more sophisticated way. Think of it as an asset that can be shared across users. Multiple users can collaborate on an asset in the AI Catalog through modeling, building features lists, or uploading new versions. Basically, if you’re investing in a long-term AI project, upload your data into the AI Catalog, and then start a project from this data asset.
By the way...
I’m well on my way to creating some more tips that I think will help you. If you have some to share with the community, please just send them along! PM me: @MariaVasiliadis. Thanks!
Need a Tip? DataRobot experts are putting together some helpful DataRobot usage tips for the platform, trial, features, etc. You can find these easily in the Tip of the Day board (under Read). Let us know if you've found a good one or have a good one to add!