Cross Validation tool errors when fed Naive Bayes

[deargle]

The error message is:

Error: Cross Validation (58): Tool #4: Error in tab + laplace : non-numeric argument to binary operator

This is odd, because I see that there is special code that handles naive bayes models. Seems that the model$laplace parameter is _not_ null by the time it hits `update`. I'm not sure yet what line is triggering the error.

[DanM]

@deargle

Based on the error it looks like your data types may be incorrect or at least not match the data used to create the model. We can replicate this issue by having incorrect data types for the data input of the Cross Validation model. Please double check your data types and that you have no Nulls.

[deargle]

My test workflow to reproduce this error is to load the "6 Decision Tree" Sample Workflow and to just use a Naive Bayes instead of a decision tree on that "default" dataset, which has no nulls, and on which I perform no data type transformations. I train the model on the full raw dataset, and then I feed that same raw dataset into the Cross Validation tool. The original workflow in which I experienced the error also used the same dataset/datatypes to train as was fed into the CV tool. Attached is a workflow that is breaking on my computer (v11.7).

_6_Decision_Tree-naive bayes-cv.yxzp

[KuoL]

Thanks for bringing this to our attention @deargle. My team is investigating this issue. 

[ColinR]

Hi @deargle!

Thanks for writing in about this issue.  Wanted to let you know that a member of my team is looking into this defect to determine the root cause.  We should have an estimate on the fix time relatively soon and add it to our backlog.

Cheers,

Colin