7 Simple Steps to Standardizing the ML Experiment (Feb. 16)

Welcome to another recap of the Comet ML Office Hours, powered by The Artists of Data Science! This week we’re covering Session 7 of our new series. This session took place Feb. 16th, 2022 and we were joined by Dhruv Nair and Michael Cullan, both of Comet. Be sure to join us for the final session of this series next week!

As a reminder, we’d love to see any and all of you at these fifty minute sessions—so feel free to register for upcoming Office Hours sessions here! As always, there’s a lot more in the full session (which you can find on our YouTube channel), so be sure to check it out, alongside clips from roundtables, webinars, and previous Office Hours.

ML=Iterative

This week was the penultimate episode of our Standardizing the Experiment series. Host Harpreet Sahota gave a quick overview of what we’ve learned in the series so far with a focus on the iterative nature of machine learning and how that lifecycle needs reproducibility to shine.

Creating a common tracking system, such as using Excel sheets, GitHub, or Comet, will help you to create the best models possible and quickly iterate or change them when needed. Be sure to check out the full session for all the highlights.\

Working Sessions

As both Dhruv and Michael were panel guests, Harpreet got more insight into the fantastic working sessions that they’ve been producing. Using the Hacker News dataset, they’re building a model to predict the performance of a Hacker News post.

The final few clips of the working sessions will be available soon, but there was a lesson in reproducibility as both Dhruv and Michael are working with the same data set and same project goal, but their approaches to this project are slightly different. Both discussed their feature engineering choices in this clip:

MLOps Tools

There were also a number of great audience questions, including a few that stumped the panel. One great question came from Shuaib who asked what tools Michael and Dhruv would suggest for practitioners just getting started with MLOps.

Hear what they had to say in the clip below:

Resources

As always, there’s more to be discussed and discovered. Check out Comet’s contributor-led publication Heartbeat as well as our YouTube, Twitter, and LinkedIn for more great information.

• Comet Office Hours Bookshelf
• Office Hours YouTube Playlist
• Follow Comet ML on Twitter
• Connect with Comet on LinkedIn

Curious to Learn More? Join Us!

We run these virtual Office Hours every Wednesday at 11am EST (New York, NY). Completely free to attend and participate, and we’d love to see any and all of you there! We’ve got a great series planned and welcome questions for Harpreet or any of our guests via email to emilie@comet.ml.

But most importantly:

Register for Comet Office Hours