The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

Title: Multiple Approximate Kernel Learning (MAKL)
Version: 1.0.1
Description: R package associated with the Multiple Approximate Kernel Learning (MAKL) algorithm proposed in <doi:10.1093/bioinformatics/btac241>. The algorithm fits multiple approximate kernel learning (MAKL) models that are fast, scalable and interpretable.
License: GPL (≥ 3)
Encoding: UTF-8
RoxygenNote: 7.1.2
Imports: AUC, grplasso
Suggests: rmarkdown, knitr
VignetteBuilder: knitr
NeedsCompilation: no
Packaged: 2022-07-06 13:56:03 UTC; user
Author: Ayyüce Begüm Bektaş ORCID iD [aut, cre], Mehmet Gönen ORCID iD [aut]
Maintainer: Ayyüce Begüm Bektaş <ayyucebektas17@ku.edu.tr>
Repository: CRAN
Date/Publication: 2022-07-06 14:10:02 UTC

Test the Multiple Approximate Kernel Learning (MAKL) Model

Description

Binary classification of the test data, using the MAKL model resulted from makl_train().

Usage

makl_test(X, y, makl_model)

Arguments

X

test dataset, matrix of size T x d.

y

response vector of length T, containing only -1 and 1.

makl_model

a list containing the MAKL model returning from makl_train().

Value

a list containing the predictions for test instances and the area under the ROC curve (AUROC) values with corresponding number of used kernels for prediction.


Train a Multiple Approximate Kernel Learning (MAKL) Model

Description

Train a MAKL model to be used as an input to makl_test().

Usage

makl_train(
  X,
  y,
  D = 100,
  sigma_N = 1000,
  CV = 1,
  lambda_set = c(0.9, 0.8, 0.7, 0.6),
  membership
)

Arguments

X

training dataset, matrix of size N x d.

y

response vector of length N, containing only -1 and 1.

D

numeric value related to the number of random features to be used for approximation.

sigma_N

numeric value preferably smaller than N, used to calculate sigma to create random features.

CV

integer value between 0 and N. If CV is equal to 0 or 1, no cross validation is performed. If CV is greater than or equal to 2, CV is assigned as fold count in the cross validation.

lambda_set

a continuous number between 0 and 1, used for regularization.

membership

a list of length of number of groups, containing feature memberships to each group.

Value

a list containing the MAKL model and related parameters to be used in makl_test().

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.