Feature Elimination Output to classified data

Hello everyone,

'm quite new with KNIME. I recently took Data Mining course and my faculty gave me  project on "GERMAN DATA SET".

I want to do feature elimination and then classify data by SVM.

I have implement till meta node (of feature elimination), (i have replaced naive with my svm). now how to use the output of this meta node to classify data by svm? 

 

2nd Output of meta node is giving filtered table.  Now how to get classified data to apply on the scorer node?

 

Where is the predicted column to compare at scorer?

 

You need to re-train your model with the filtered data, just append another SVM Learner and connect the model output to the SVM Predictor.

Thank you gabriel .

Now i have new problem. I want to make ensemble. I want to apply 3-4 algorithm as- LR, DT, SVM, MLP.  and then ensemble it.  Means I want to take result who have majority.(means if for a record LR give 1 , DT - 1 ,  SVM - 2 , MLP -1 then it choose 1 as a result for that particular record.)

I invsted many hours to find the way but i could not.  Please help me how to generate such a model?

Please see;

 

http://tech.knime.org/forum/knime-general/model-ensembling-getting-result-based-on-majority-for-each-record

 

Simon.