Implements the adaptive sampling procedure, a framework for both positive unlabeled learning and learning with class label noise. Yang, P., Ormerod, J., Liu, W., Ma, C., Zomaya, A., Yang, J. (2018)
Implements the AdaSampling procedure, a framework for both positive unlabeled learning and learning with class label noise, which wraps around a traditional classifying algorithm. See our publication for details, documentation and examples.
There are two ways to install the package:
To install from CRAN [https://CRAN.R-project.org/package=AdaSampling]:
To install from github, use:
devtools::install_github("PengyiYang/AdaSampling", build_vignettes = TRUE)library(AdaSampling)
Current version of this package includes two functions:
adaSample()applies the AdaSampling procedure to reduce noise in the training set, and subsequently trains a classifier from the new training set.
adaSvmBenchmark()which allows the performance of the AdaSampling procedure (with an SVM classifier) to be compared against the performance of the SVM classifier on its own.
In order to see demonstrations of these two functions, see:
Yang, P., Ormerod, J., Liu, W., Ma, C., Zomaya, A., Yang, J.(2018) AdaSampling for positive-unlabeled and label noise learning with bioinformatics applications. IEEE Transactions on Cybernetics, [doi:10.1109/TCYB.2018.2816984]
Yang, P., Liu, W., Yang, J. (2017). Positive unlabeled learning via wrapper-based adaptive sampling. Proceedings of the 26th International Joint Conference on Artificial Intelligence (IJCAI), 3273-3279. [fulltext]
The initial github repo of the AdaSampling package was put together by Kukulege Dinuka Perera.