Package: preprocomb
Type: Package
Title: Tools for Preprocessing Combinations
Version: 0.1.0
Date: 2015-10-11
Author: Markus Vattulainen
Maintainer: Markus Vattulainen <markus.vattulainen@gmail.com>
Description: Preprocessing is often the most time-consuming phase in knowledge
    discovery and preprocessing transformations interdependent in unexpected
    ways. This package helps to make preprocessing faster and more effective. It
    provides an S4 framework for creating and testing preprocessing combinations
    for classification, clustering and outlier detection. The framework supports
    user-defined and domain-specific preprocessors and preprocessing phases.
    Default preprocessors can be used for low variance removal, missing value
    imputation, scaling, outlier removal, noise smoothing, feature selection and
    class imbalance correction.
License: GPL-2
Imports: DMwR, randomForest, caret, caretEnsemble, methods,
        clustertend, e1071, stats, utils
LazyData: TRUE
URL: https://github.com/mvattulainen/preprocomb
BugReports: https://github.com/mvattulainen/preprocomb/issues
Collate: '00Utils.R' '01DataClass.R' '02PhaseClass.R' '03BaseClass.R'
        '04GridClass.R' '05PredictionControlClass.R'
        '06PreProCombClass.R'
Suggests: kernlab
NeedsCompilation: no
Packaged: 2015-10-11 16:21:20 UTC; Markus
Repository: CRAN
Date/Publication: 2015-10-11 18:45:27
