warning message when using Random Forest

sonicricksonicrick Member Posts: 1 Contributor I
edited November 2018 in Help

I'm new to RapidMiner, and was trying out the Random Forest Model. I read two CSVs separately (training set has 12 attributes, test set has the same minus the label to be predicted). When I run, this message appeared:

PM WARNING: Random Forest Model: The internal nominal mappings are not the same between training and application for attribute 'Pclass'. This will probably lead to wrong results during model application.

The result did seem wrong so I want to investigate what causes the above. Any suggestions where to start?

Thanks in advance,


  • Options
    MariusHelfMariusHelf RapidMiner Certified Expert, Member Posts: 1,869 Unicorn

    I did some quick testing, and it seems that this warning is obsolete - in my case (RapidMiner v6.0) the results look good despite this warning. But I will forward this issue to the developers. They will either remove the warning or, if necessary, fix the code.
    Can you please check if your results look good despite the warning?

    Best regards,
Sign In or Register to comment.