I have large set of molecules. I have partitioned them in 30:70 and build a model initially and predict the 70% of the molecules. Then I want to add the few selected molecules after their prediction into the training set of same model. That process will be iteratively run 10-15 times. But the problem is whenever I add the output of the predictor set to the training set, the model will be changed so the predictor result is going to vanished and it is quite obvious though. So can anyone help me in this issue?
Welcome to KNIME Forum. What did you expect to happen? Why would you re-add scored records to the train set? Every time the composition of your training set changes (you add new records), the model will give a (slightly) different outcome after training.
Thank you for your response. Actually, in my algorithm I am trying to update the model toa chive some better predictions. For that reason, I want to add some good predicted compounds after being predicted to the training set. So, is there any way out by which I can add some predicted compounds from predictor node to the training set within a loop. I want to run this process within a loop iterations. So, it would be helpful if there any workflow any one can share. Thanks.
Yeah you can say it is a part of boosting. But my task is after every iteration i want to add best 10 compounds from the predicted set to the training set. But I dont understand how to do that in knime. It will be great for me if I get any suggestion or workflow.