Lot of errors by using the auto model to compare the prediction models
Hello everybody,
I am a freshman in Data mining and I don't know which model I should use for my classification task. So I want to use the Auto Model to check which model works best for my data. But no model works, all show errors with these mistakes:
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. ERRR on field: _train: Training data must have at least 2 features (incl. response).
I am a freshman in Data mining and I don't know which model I should use for my classification task. So I want to use the Auto Model to check which model works best for my data. But no model works, all show errors with these mistakes:
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. ERRR on field: _train: Training data must have at least 2 features (incl. response).
Does anyone know what I can do?
In another forum I saw one of these errors and I think it could be a problem, that I have too many outcome variables. I have a data set with approximatly 850 rows and 40 outcome variables. Could this be the problem?
Thank you very much.
Kind regards
Find more posts tagged with
Sort by:
1 - 4 of
41
Hello Varun,
tanks for your answer!
Yes, i have a label with 40 diffrent variables and 7 colums to predict these.
tanks for your answer!
Yes, i have a label with 40 diffrent variables and 7 colums to predict these.
@keb1811
make sure during modelling post selecting the prediction option and attribute you want to predict you are selecting two or more attributes in selection set. Rapidminer deselects all unnecessary attributes itself on the basis of various factors and you may end up with lesser number of attributes in the end
make sure during modelling post selecting the prediction option and attribute you want to predict you are selecting two or more attributes in selection set. Rapidminer deselects all unnecessary attributes itself on the basis of various factors and you may end up with lesser number of attributes in the end
Hello Divyem, thank for your answer.
Yes i selected the 7 attributes and i deselected the unnecessary one before. Rapidminer showed my colors like a traffic light, whether the attributes are useful or not.
Yes i selected the 7 attributes and i deselected the unnecessary one before. Rapidminer showed my colors like a traffic light, whether the attributes are useful or not.
Also, your dataset should have at least one predictor attribute and one label (outcome) attribute.