Title: | 'REPPlab' via a Shiny Application |
---|---|
Description: | Performs exploratory projection pursuit via 'REPPlab' (Daniel Fischer, Alain Berro, Klaus Nordhausen & Anne Ruiz-Gazen (2019) <doi:10.1080/03610918.2019.1626880>) using a Shiny app. |
Authors: | Thomas Janka [aut], Klaus Nordhausen [cre, aut] , Anne Ruiz-Gazen [aut] |
Maintainer: | Klaus Nordhausen <[email protected]> |
License: | GPL (>= 2) |
Version: | 0.4.2 |
Built: | 2024-12-15 07:35:58 UTC |
Source: | CRAN |
Prints some information about objects of class epplabshiny
, typically the result of a call to REPPlabShiny
. Printed is only a table with the names, indices and algorithms used for calculated EPPlab
object, not the whole content of the object.
## S3 method for class 'epplabshiny' print(x, ...)
## S3 method for class 'epplabshiny' print(x, ...)
x |
an object of class epplabshiny. |
... |
further arguments passed to or from other methods. |
if(interactive()){ data(ReliabilityData) Repplablistshiny <- REPPlabShiny(ReliabilityData) print(Repplablistshiny) }
if(interactive()){ data(ReliabilityData) Repplablistshiny <- REPPlabShiny(ReliabilityData) print(Repplablistshiny) }
Performs exploratory projection pursuit as implemented in 'REPPlab' via a shiny app where the user can calculate up to five EPPlab objects and work with the results. Suitable for outlier detection or cluster identification. The actions in the Shiny app can be saved for further processing in R.
REPPlabShiny(x)
REPPlabShiny(x)
x |
data matrix or data frame. Can also contain non-numerical variables. The user can choose in the app which rows and columns will be used. |
Returns an object of class epplabshiny
. The object consists of a list of length five containing the calculated EPPlab
objects each having class epplab
. If not five epplab
objects were computed, the corresponding list entry is an empty list. Note that print here only summarizes the output in order not to clutter the screen.
Fischer, D., Berro, A, Nordhausen, K. and Ruiz-Gazen, A. (2019), REPPlab: An R package for detecting clusters and outliers using exploratory projection pursuit, Communications in Statistics - Simulation and Computation, doi:10.1080/03610918.2019.1626880.
if(interactive()){ data(ReliabilityData) str(ReliabilityData) Repplablistshiny <- REPPlabShiny(ReliabilityData) Repplablistshiny str(Repplablistshiny) }
if(interactive()){ data(ReliabilityData) str(ReliabilityData) Repplablistshiny <- REPPlabShiny(ReliabilityData) Repplablistshiny str(Repplablistshiny) }