NLP with code tutorial issues
anna_kloska
Dataiku DSS Core Designer, Dataiku DSS Adv Designer, Registered Posts: 1 ✭
Hello,
I have a problem with tutorial project from NLP. It's simple project, where you train a model and then evaluate it. The problem lies in evaluation step, I get an error:
Error in python process: <class 'ValueError'>: The truth value of a DataFrame is ambiguous. Use a.empty, a.bool(), a.item(), a.any() or a.all().
Does anyone knows how to solve this? Thanks!
Answers
-
Hi @anna_kloska
,This issue usually occurs when using a deep learning model as an input to an evaluation recipe.
Could you please check the type of the model that you are using?
Using a deep learning model as the input to the evaluation recipe is not supported. This is mentioned in the documentation here Evaluating DSS models - Limitations.