+1 vote
Currently doesn't seem to be an way for that? trying to reuse an existing model for predicting another column.

how can I do that on dataiku?

Would be very useful. seem very basic need, probably something I'm missing.


1 Answer

0 votes
You should simply create another model, on the top left of the models tab, if you click on the model name you can "Create another model".

Dataiku DSS will redetect the best settings.
thx! understand, but it's not it, that starts/reset everything, clearing everything I just configured, and doesnt allow me to compare different runs,
at the moment created a column target, then I can model/change freely on the script tab, seems to work, but think it really should be possible to change the target, basic option :)
I second this. After manually creating a model, configuring lots of stuff before training, I now want to test the model performance on a lower-level target variable (think city-level instead of state level). In code, I would simply change the target variable string to "cities" instead of "states". In DataIku, I would have to create a new model and then go through all the configuration steps again (select explaining vars, change their interpretation, set their levels, set tree depths...).
1,322 questions
1,341 answers
11,889 users

©Dataiku 2012-2018 - Privacy Policy