The Altair Community is migrating to a new platform to provide a better experience for you. In preparation for the migration, the Altair Community is on read-only mode from October 28 - November 6, 2024. Technical support via cases will continue to work as is. For any urgent requests from Students/Faculty members, please submit the form linked here
How to use Binary2MultiClassLearner
chenUser4321
Member Posts: 11 
Contributor II
Hi:
I want to wrote code to do multi-label classification. However, many of the existig RM classifiers only support binominal label. Binary2MultiClassLearner seems to be reasonable choice that makes these classifiers do multi-label classification.
However, I could not figure out a clear way to write the codes from rapidminer-4.6-tutorial.pdf and the javadoc. I also did some search in RM discussion forum, but found results are not directly related to development.
Could I have some specific instructions of using this learner? A sample code that shows its usage is greatly appreciated!
Kindly regards,
Daozheng
I want to wrote code to do multi-label classification. However, many of the existig RM classifiers only support binominal label. Binary2MultiClassLearner seems to be reasonable choice that makes these classifiers do multi-label classification.
However, I could not figure out a clear way to write the codes from rapidminer-4.6-tutorial.pdf and the javadoc. I also did some search in RM discussion forum, but found results are not directly related to development.
Could I have some specific instructions of using this learner? A sample code that shows its usage is greatly appreciated!
Kindly regards,
Daozheng
0
Answers
you have to connect an inner operator. See the RapidMiner GUI for understanding how it works in general: The binary2Mutliclass learner uses an inner binary learner to predict for example several one vs all settings and finally computes the output from the confidences.
The used strategy depends on the parameters, but always an inner learner is applied.
If you want to use this in the code, you have to manually create another learning operator and connect it with the inputs and outputs of the subprocess of the binary to multiclass learner.
Greetings,
Sebastian