Roman Lutz

Hi @DinaChen! The dashboard requires a running Flask server in the background. As soon as the execution ends the server shuts down and you can't connect to it anymore. In...

Again, in the code you posted initially it seems like the script just finishes. The dashboard is interactive so you need the Python process to keep running otherwise it won't...

@tongyu-microsoft I'm curious what prompted this change. Was this a feature request from somebody? As a user, I'd be a bit surprised about the ordering since we had it by...

@imatiach-msft can you elaborate on what "initial path" means? I can see the tree from the root to the leaves, so it's a bit unclear to me which initial paths...

Just to add to this: this happens in the error analysis widget only. The model analysis widget handles this correctly since it doesn't switch between tabs.

Hi @Harikantipudi, thanks for reaching out! I understand that you run experiments and deploy models using Kubeflow. However, it's not entirely clear to me what's stopping you from using the...

Thanks for clarifying @Harikantipudi . This sounds like what I thought in my initial reply (last paragraph). I believe further steps are necessary that we'd need to figure out, test,...

While very briefly looking at this I noticed that light green is typically the third color, so to reproduce one might have to create and then delete the third cohort.

This reminds me of sensitive features in fairness use cases! They often have to be excluded for legal reasons, but we still want to analyze the results to see if...

This isn't very straightforward. The metrics have lots of additional information in the Typescript code that tells the UI how to display it. For example, every metric has a label...