Welcome to the Dataiku Community: a peer-to-peer community to discuss data preparation, analytics, machine learning and AI on the Dataiku platform.
Head to one of the Q&A or Discussion boards to get help or discuss Dataiku.
Provide your input on Dataiku and the Community.
Explore the various Community programs.
It would be great to be able to export data related to failed or ignored rows within both the visual ml and deployed model diagnostics with a label denoting the reason for not training. This would keep the user from using other methods to a. locate which rows did not get trained and b. the reason for them not getting…
Currently when aborting a partitioned time series model you are able to "rerun" one model on the aborted partitions however seem to be unable to rerun all aborted partitions within a session. For example: Training a partitioned model using seasonal naive and trivial identity in a single session and abort the session. I can…
Hi everyone, My name is Han and I am from the team that is working on Cobuild, which is released on 14.7. https://www.dataiku.com/product/cobuild We are actively working on Cobuild and we'd love to get your quick feedback! Just a couple of short questions to get you started: Does it work for you? What is not working or…
Hello, I installed Dataiku DSS Free Edition on Windows 11 with the Windows launcher for a personal learning project. On the license page I select "Free Edition", fill in the form and click NEXT, but I get "Network error - An attempt to communicate with DSS failed." In the browser developer tools I see: POST…
It would be handy to be able to instead of completely ignore invalid rows in model predictions to have the option to still output them with a potential 'excluded' marker and some diagnostic reason. Currently having to do anti-joins between model outputs and input to figure out which records did not pass adds extra workload…
Ask a Question
Start a Discussion
Create an account to contribute great content, engage with others, and show your appreciation.
Hopefully this sets you in great stead to begin your Community journey - if there is anything else we can help with don’t hesitate to reach out to a member of the Community team:
Michael is happy to make up 100% of the UK based community team. When not working on Dataiku’s Community project he can be found either sailing the high seas or plugged into a strategy game. Staring at maps comes in handy in both cases and Michael is a bit of a cartophile.
Tiago makes sure that everyone gets the technical support they need for whatever project they're working on. On his free time, you'll find him playing his favourite role-playing games, or the electric guitar.
