Version: 2.0-40-9000
Category: Date: 2025-12-14
Text:

Version: 2.0-40
Date: 2025-12-21
Category: Date: 2025-12-14
Text: Updated SL.xgboost to support the new version (3.1) of xgboost

Version: 2.0-29
Date: 2024-02-20
Category: Date: 2024-02-06
Text: Added n.cores argument to SL.gbm

Version: 2.0-29
Date: 2024-02-20
Category: Date: 2024-02-06
Text: fixed formula warning in SL.loess. Note the loess() function is
        limited to 1-4 features

Version: 2.0-29
Date: 2024-02-20
Category: Date: 2024-02-06
Text: fixed version checks to be character instead of numeric

Version: 2.0-29
Date: 2024-02-20
Category: Date: 2024-02-06
Text: removes SL.extraTrees (no longer on CRAN, available at
        SuperLearnerExtra)

Version: 2.0-28
Date: 2021-05-10
Category: Date: 2021-04-13
Text: Updated maintainer email

Version: 2.0-28
Date: 2021-05-10
Category: Date: 2021-04-13
Text: SL.gam added back, but now importing gam to avoid CRAN NOTE on
        usage or require()

Version: 2.0-26
Date: 2019-12-10
Category: Date: 2019-08-12
Text: Added obsWeights and id arguments to the test-glmnet.R file, line
        24

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: Updated listWrappers() to allow search results without
        SuperLearner loaded

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: Fixed error in 'predict.SL.ksvm' and 'predict.SL.glmnet' when
        newdata is a single row (added drop = FALSE)

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: Added control option to 'SuperLearner' to save the internal
        cross-validation algorithm fits as a list. default is FALSE.

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: Removed dbarts from Suggests and the associated wrapper over to
        SuperLearnerExtra. dbarts no longer available on CRAN

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: added prettydoc as a Depends for the vignette

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: changed VignetteBuilder to rmarkdown

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: Removed the SuperLearnerPresent.Rnw file, was a shortcut to
        create the SuperLearnerR vignette

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: Changed .SL.require to use 'requireNamespace()' instead of
        'require()'

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: added '.SL.require("bibmemory")' to 'SL.biglasso.R'

Version: 2.0-25
Date: 2019-08-09
Category: Date: 2019-08-05
Text: allowed SL.gam to use s() instead of gam::s() and 'require'
        instead of 'requireNamespace`

Version: 2.0-24
Date: 2018-08-11
Category: Date: 2018-07-10
Text: remove multicore test in randomForest test. Was generating
        warning note on CRAN devel

Version: 2.0-23
Date: 2018-03-12
Category: Date: 2018-03-09
Text: fixed transformation of outcome in SL.dbarts for binomial family

Version: 2.0-23
Date: 2018-03-12
Category: Date: 2018-03-09
Text: SampleSplitSuperLearner(): support validation sample size of 1
        when observation's row number is passed in via 'split'.

Version: 2.0-23
Date: 2018-03-12
Category: Date: 2018-03-09
Text: Fixed case where single-column X in combination with more than
        one screening algorithm causes failure in SuperLearner(),
        snowSuperLearner(), mcSuperLearner(),
        SampleSplitSuperLearner().

Version: 2.0-23
Date: 2018-03-12
Category: Date: 2018-03-09
Text: methods CC.* modified to handle duplicated columns better (PR
        #106)

Version: 2.0-23
Date: 2018-03-12
Category: Date: 2018-03-09
Text: Updated S3 class name for gam::gam() to be Gam

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added model.matrix to SL.xgboost

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Fixed innerCvControl in CV.SuperLearner to allow multiple
        parameters. It must now be a list of lists.

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: create.Learner(): support character arguments.

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Glmnet: support alternative loss functions; when predicting
        automatically add any missing covariates and remove covariates
        not in the original data.

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added SL.kernelKnn

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added SL.ksvm

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added SL.ranger

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added vignette: "Guide to SuperLearner"

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added SL.biglasso

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added SL.lm, SL.speedlm, and SL.speedglm

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added SL.lda and SL.qda

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added SL.dbarts for C++-based bayesian additive regression trees.

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: SL.lm and SL.glm now have a model argument, defaulting to TRUE
        (matching glm and lm), but can be changed to FALSE to conserve
        memory. Both wrappers also explicitly convert X matrix to a
        data frame.

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Added SL.extraTrees for extremely randomized trees, a random
        forest variant.

Version: 2.0-22
Date: 2017-07-18
Category: Date: 2017-07-07
Text: Fixes prediction when a learner fails for methods: NNLS,
        NNloglik, CC_nloglik, and AUC. NNLS2 and CC_LS still have this
        bug. This fix required that an additional optional argument
        "errorsInLibrary" be passed to methods. This argument is a
        vector set to TRUE for learners that failed during model
        fitting.

Version: 2.0-21
Date: 2016-12-01
Category: Date: 2016-10-03
Text: Add validRows option for CV.SuperLearner. Can now pass a
        cvControl for the outer CV and a list of cvControls, one for
        each cross-validation folds SuperLearner calls. default number
        of folds in CV.SuperLearner is now 10, matching the default
        with cvControl. If the user specifies both V and number of
        folds in cvControl(), an error message is returned.

Version: 2.0-20
Category: Date: 2016-08-09
Text: Added shrinkage parameter to SL.gbm

Version: 2.0-20
Category: Date: 2016-08-09
Text: fixed mtry default in SL.randomForest

Version: 2.0-20
Category: Date: 2016-08-09
Text: in CV.SuperLearner, fixed order for checking parallel options and
        folds argument in parLapply (thanks Chris Kennedy)

Version: 2.0-20
Category: Date: 2016-08-09
Text: updated method.AUC to change defaults on the optimization and add
        warnings for non-convergence

Version: 2.0-20
Category: Date: 2016-08-09
Text: Added wrapper for xgboost (thanks Chris Kennedy)

Version: 2.0-20
Category: Date: 2016-08-09
Text: Added wrapper for bartMachine (thanks Chris Kennedy)

Version: 2.0-20
Category: Date: 2016-08-09
Text: Added travis.ci checks

Version: 2.0-20
Category: Date: 2016-08-09
Text: Added environments for SuperLearner() and CV.SuperLearner()
        wrappers search path (includes SL.*, screen.*, and method.*
        wrappers)

Version: 2.0-20
Category: Date: 2016-08-09
Text: Added binary outcomes for SL.cforest

Version: 2.0-19
Date: 2016-02-04
Category: Date: 2016-02-02
Text: Updated contact information

Version: 2.0-19
Date: 2016-02-04
Category: Date: 2016-02-02
Text: Added additional svm() arguments for SL.svm

Version: 2.0-18
Category: Date: 2014-04-25
Text: Added recombineSL and recombineCVSL functions to re-fit the
        ensemble using a new metalearner in a computationally efficient
        manner

Version: 2.0-18
Category: Date: 2014-04-25
Text: For all wrappers, converted to format package::function when
        calling functions from other namespaces

Version: 2.0-18
Category: Date: 2014-04-25
Text: Added S3 method declarations for all predict.SL.* functions

Version: 2.0-18
Category: Date: 2014-04-25
Text: Added a `SL.nnls` and `predict.SL.nnls` functions

Version: 2.0-17
Category: Date: 2014-04-13
Text: Moved cvAUC to imports

Version: 2.0-16
Category: Date: 2014-08-07
Text: Fixed error when computeCoef was re-run because of algorithms
        failing on full data

Version: 2.0-16
Category: Date: 2014-08-07
Text: Fixed Description field in Description file for CRAN policy

Version: 2.0-15
Date: 2014-07-21
Category: Date: 2014-07-16
Text: Fixed check for method.AUC and family

Version: 2.0-15
Date: 2014-07-21
Category: Date: 2014-07-16
Text: Moved SL.bart over to SuperLearneExtra because BayesTree package
        no longer on CRAN

Version: 2.0-14
Category: Date: 2014-07-14
Text: Added method.AUC, contributed by Erin LeDell

Version: 2.0-13
Category: Date: 2014-04-16
Text: added the SampleSplitSuperLearner function to allow sample split
        validation instead of V-fold cross-validation

Version: 2.0-11
Category: Date: 2013-12-31
Text: fixed package requirement in CV.SuperLearner from multicore to
        parallel

Version: 2.0-11
Category: Date: 2013-12-31
Text: Fixed a conflict with the reorder function in
        plot.CV.SuperLearner (between the stats and gdata namespace)

Version: 2.0-11
Category: Date: 2013-12-31
Text: Fixed a bug in SL.svm when family is binomial to grab the correct
        predicted probabilities (thanks to Jeremy Coyle)

Version: 2.0-11
Category: Date: 2013-12-31
Text: Added .Rbuildignore to not include the README.md file from GitHub
        on CRAN

Version: 2.0-11
Category: Date: 2013-12-31
Text: Removed SuperLearner.Rnw

Version: 2.0-11
Category: Date: 2013-12-31
Text: Moved vignettes to vignettes folder

Version: 2.0-11
Category: Date: 2013-12-31
Text: Changed cluster example to use PSOCK instead of MPI in
        SuperLearner.Rd

Version: 2.0-11
Category: Date: 2013-12-31
Text: removed the ":::" in plot.CV.SuperLearner

Version: 2.0-11
Category: Date: 2013-12-31
Text: moved quadprog from depends to suggests as it is only called if
        the user uses method = "method.NNLS2" not the default.

Version: 2.0-11
Category: Date: 2013-12-31
Text: Added method.CC_LS and method.CC_nloglik. These provide true
        convex combination optimization for the 2 loss functions.
        Contributed by Sam Lendle.

Version: 2.0-9
Date: 2012-09-11
Category: Date: 2012-09-10
Text: Updated help documents

Version: 2.0-9
Date: 2012-09-11
Category: Date: 2012-09-10
Text: Added links to SuperLearnerExtra on Github

Version: 2.0-7
Category: Date: 2012-04-04
Text: Switched from snow and multicore to parallel package

Version: 2.0-7
Category: Date: 2012-04-04
Text: fixed bug in CV.SuperLearner for leave-one-out cross-validation

Version: 2.0-7
Category: Date: 2012-04-04
Text: fixed bug in snowSuperLearner when only one screening algorithm
        is present

Version: 2.0-7
Category: Date: 2012-04-04
Text: method.NNloglik now reports the average -log likelihood instead
        of the sum to be consistent with NNLS

Version: 2.0-6
Date: 2012-03-01
Category: Date: 2012-02-29
Text: Added SL.leekasso (see
        http://simplystatistics.tumblr.com/post/18132467723/prediction-the-lasso-vs-just-using-the-top-10
        for details)

Version: 2.0-6
Date: 2012-03-01
Category: Date: 2012-02-29
Text: fixed parallel argument in CV.SuperLearner. Now always a
        character variable, no longer accepts FALSE.

Version: 2.0-6
Date: 2012-03-01
Category: Date: 2012-02-29
Text: fixed SL.gam to call gam::gam.control in case the mgcv package is
        also loaded after gam.

Version: 2.0-5
Category: Date: 2011-10-12
Text: Fixed bug in CV.SuperLearner not saving SuperLearner objects
        (watch out for ifelse() statements).

Version: 2.0-5
Category: Date: 2011-10-12
Text: Added minbucket to SL.rpart.

Version: 2.0-5
Category: Date: 2011-10-12
Text: Added SL.rpartPrune, a version of SL.rpart with built-in pruning.

Version: 2.0-4
Date: 2011-09-27
Category: Date: 2011-10-01
Text: Minor changes to Rd files to cut build and check time. Time
        intensive examples now wrapped in \dontrun for CRAN.

Version: 2.0-3
Category: Date: 2011-08-05
Text: added plot.CV.SuperLearner

Version: 2.0-2
Category: Date: 2011-06-07
Text: fixed bug when one of the algorithms in SL.library has an error.

Version: 2.0-2
Category: Date: 2011-06-07
Text: fixed mcSuperLearner and snowSuperLearner not saving fitLibrary.

Version: 2.0-2
Category: Date: 2011-06-07
Text: added a placeholder Sweave vignette (SuperLearnerPresent.Rnw) to
        contain the SuperLearner presentation so the file can be found
        using the vignette() and browseVignettes() functions.

Version: 2.0-2
Category: Date: 2011-06-07
Text: CV.SuperLearner now outputs `LibraryNames`, `SL.library`,
        `method` and `Y`.

Version: 2.0-2
Category: Date: 2011-06-07
Text: summary.CV.SuperLearner has returned

Version: 2.0-1
Category: Date: 2011-05-17
Text: added predict.SuperLearner

Version: 2.0-0
Category: Date: 2010-12-27
Text: Version 2.* represents a complete rewrite of the SuperLearner
        package.

Version: 2.0-0
Category: Date: 2010-12-27
Text: Details on the changes from Version 1.* to 2.* can be found in
        ChangeLog.