Prediction with LightSide does not work

Question

I am working with the machine learning workbench LightSide for my MA-thesis. I have successfully trained some models, now I would like to use a trained model to predict new data. However, when I try to do so, the system stops after a few seconds, with the pop-up message "prediction as been stopped" and no hint on why. It happens with different data sets, as well as algorithms used for training...

Has anyone encountered the same problem and found a solution for it? Thank you for your help :)

edit: I tried to export the feature table to WEKA and train models there, but WEKA gets lost in an endless training loop, I assume it has to do with the built-in feature UNIGRAM I use form LightSide. But I am still not closer to predicting on new data...

edit II: LightSide throws an error saying that one feature is not part of the model, when in fact it is

Answer 1

If you have a huge feature space, then lightSIDE might end up saying the prediction has stopped. This happened to me when I tried to use a column (ex: problem_name) that had too many different values as one of the features (during the feature extraction phase). I ended up recomputing another column (ex: problem_difficulty based on problem_name) that had fewer values and lightSIDE could predict new data successfully.

Thanks to Dr. Rose for the solution.