Type: Package
Package: outForest
Title: Multivariate Outlier Detection and Replacement
Version: 0.1.0
Date: 2020-01-09
Authors@R: 
    person(given = "Michael",
           family = "Mayer",
           role = c("aut", "cre"),
           email = "mayermichael79@gmail.com")
Maintainer: Michael Mayer <mayermichael79@gmail.com>
Description: Provides a random forest based implementation of
    the method described in Chapter 7.1.2 (Regression model based anomaly
    detection) of Chandola et al. (2009)
    <doi.acm.org/10.1145/1541880.1541882>. It works as follows: Each
    numeric variable is regressed onto all other variables by a random
    forest. If the scaled absolute difference between observed value and
    out-of-bag prediction of the corresponding random forest is
    suspiciously large, then a value is considered an outlier. The package
    offers different options to replace such outliers, e.g. by realistic
    values found via predictive mean matching. Once the method is trained
    on a reference data, it can be applied to new data.
License: GPL (>= 2)
URL: https://github.com/mayer79/outForest
BugReports: https://github.com/mayer79/outForest/issues
Depends: R (>= 3.5.0)
VignetteBuilder: knitr
Encoding: UTF-8
LazyData: true
Imports: stats, graphics, FNN, ranger, missRanger (>= 2.1.0)
Suggests: dplyr, knitr
RoxygenNote: 7.0.2
NeedsCompilation: no
Packaged: 2020-01-09 18:20:39 UTC; Michael
Author: Michael Mayer [aut, cre]
Repository: CRAN
Date/Publication: 2020-01-13 15:50:03 UTC
