Skip to content

d12306/Implementation-of-Transductive-SVM-Sklearn-Compatible

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 

Repository files navigation

Implementation-of-Transductive-SVM-Sklearn-Compatible

The method is based on Quasi-Newton Semi-Supervised Support Vector Machines.

The main code is from https://github.com/tmadl/semisup-learn, but it is very out-dated, so I reimplemented it for correct usage in my own research.

The main class is in tsvm.py

The detailed implementation is in qns3vm.py

Try to set up the transductive setting before you call the sklean-like function, such as setting the labels of the unlabeled dataset to [-1] and concatenate the training and testing set together. The final prediction is the one for all the data points of the inputs. We should split them apart for the training and testing data.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages