Open ahbon123 opened 7 years ago
Could you put verbose:true
on these algorithms?
You could show me the parameter line of this algorithm that it fails?
Generally this issue has to do when you run something really large ...
thanks, i'll try to put verbose:true. i've add some models in first layer, but when i check the number of columns in datasettwo_test1 file, which is not equal to the number of my algorithms i used, so i'm not sure which two do not work. btw, two vide columns are in front of last one, so i suppose it should be SklearnExtraTreesRegressor and FRGFRegressor.
@ahbon123
If you have added classifiers, then yes, they produced more columns than just one . Each classifier will output as many columns as you set bins in the command.
I encountered the same issue as well while adding more feature in xgboost. I saw the same issue posted here. Using the verbose option, I can see that the xgboost itself was completed, but there is no .pred file created (was it suppose to be created)?
Hi iFe1er, Could you please copy/paste the full stack trace when verbose is set to True, so that we can have a look at what's happening? Thanks, Olivier.
i run into the same issue here,any ideas?
I think it was caused by memory limitation but not for sure. When I upgraded RAM of my desktop from 8GB to 12GB, problems just disappeared.
Hello @kaz-Anova , have you ever met this issue (system can not find files for several models, which i guess maybe caused vide value of several columns for datasettwo_test files) when you run program? any ideas how to deal with this? thanks.