🎉Community Raffle - Win $25

An exclusive raffle opportunity for active members like you! Complete your profile, answer questions and get your first accepted badge to enter the raffle.
Join and Win

Error Cannot execute log reg calibration learning: Error while training the H2O model: Illegal argum

User: "kse"
New Altair Community Member
Updated by Jocelyn
Hi
Im working with Auto Model in Rapid Miner Studio. Previously I make some test with my data (+7000 rows in.csv file), it works perfectly and i get some results. Some days after, I tried to make the same test, but the most of the models shows this error: 
Cannot execute log reg calibration learning: Error while training the H2O model: Illegal argument(s) for GLM model: ERRR on field: _response: Response cannot be constant.

Ethier I cant see my old results form Auto model

Find more posts tagged with

Sort by:
1 - 5 of 51
    User: "varunm1"
    New Altair Community Member
    Hello @kse

    Can you check the data going inside model training by setting a break point before model operator? This error is when data related to single class is going inside algorithm. If you cannot check it, please provide data and process for us to take a look.
    User: "kse"
    New Altair Community Member
    OP
    Hi @varunm1
     
    Can I set a break point before model operator in Auto Model?

    Thank you
    User: "kse"
    New Altair Community Member
    OP
    This is my data. Please, treat this information carefully

    Thank you
    User: "varunm1"
    New Altair Community Member
    Hello @kse

    I imported your data. I have some questions, you can clarify here or if its something private you can send me a direct message through my profile. My questions are, what are you trying to do? Classification or regression? If so, what is the label column in this dataset? Are you using all the columns in this data set? I see you also have a date column are you using that in an auto model?
    User: "sgenzer"
    Altair Employee
    @kse please note this is a public forum. Any data sets you post here are 100% public. If you wish to keep your data private, I would recommend deleting it.

    Scott