Github user hhbyyh commented on the issue:
https://github.com/apache/spark/pull/15211
Thanks a lot for the review. @jkbradley
About the class name. AFAIK, typically "linear SVM" and "general SVM" use
different algorithms for implementations. Just like the difference between
[LIBSVM](https://www.csie.ntu.edu.tw/~cjlin/libsvm/) and
[LIBLINEAR](https://www.csie.ntu.edu.tw/~cjlin/liblinear/), also as
[LinearSVC](http://scikit-learn.org/stable/modules/generated/sklearn.svm.LinearSVC.html)
and
[SVC](http://scikit-learn.org/stable/modules/generated/sklearn.svm.SVC.html) in
sklearn. LinearSVC only support SVM classifier with linear kernel and usually
has a better scalability, while SVC support different kernels and does not
really scale well in LIBSVM or sklearn. In a way, LinearSVC is a special
acceleration for general SVM. It has independent public API because it uses
fundamentally different techniques.
I imagine some day in the future, we perhaps need to provide a new
implementation for SVM with kernel. Let me know if you still prefer to have a
unified interface for SVM.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
