Sign up to take part
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
I want evaluate a model. I have train set and test set. I worked on train set and create the best model on this. After that, i scored this model with the test set.
Now, how i can evaluate this model? with which data set exactly? with train set or i have split the train set to create a validation set? Can you explain me in detail please?
Hi,
You can evaluate a deployed model on a new dataset using the Evaluate recipe: https://academy.dataiku.com/latest/tutorial/machine-learning/model-lifecycle.html#monitoring-a-model...
Alternatively, you can specify your test set at the model training stage with the 'explicit extracts' mode: https://doc.dataiku.com/dss/latest/machine-learning/supervised/settings.html#explicit-extracts
Best regards,
Alex