-
Notifications
You must be signed in to change notification settings - Fork 173
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
"message" : "Attribute with value RegressionTable@targetCategory=1 is not valid" #51
Comments
"Attribute is not valid" - the underlying JPMML-Evaluator library thinks that your logistic regression PMML file is poorly encoded. Specifically, one This exception is thrown here: |
When I tried with the same model file 3 months back, I was able to do it. But now, I am facing this error with the same file which worked perfectly fine before. How can I fix this error? |
BS. This check has been there for ages.
Use a proper PMML conversion software. For example, anything from the JPMML family of libraries would be perfect. Speaking about this specific file, then you can tweak the value of this one problematic |
I had used the pyspark2pmml library(https://github.com/jpmml/pyspark2pmml) for my pmml conversion. |
When I am trying to do Model evaluation using POST /model/${id} in single prediction mode, I am getting the below error.
{
"message" : "Attribute with value RegressionTable@targetCategory=1 is not valid"
}
The above error occurs only when my model is in logistic regression. The PMML files of decision tree and random forest are working fine, but I am getting this error only when my model is in logistic regression.
Whats the reason for this error?
The text was updated successfully, but these errors were encountered: