Skip to content

The fdakmapp package provides the kmap function that jointly performs clustering and alignment of a functional dataset. The centers can be computed by several center methods. The package can be be live tested, also with your own dataset, at https://zitale.shinyapps.io/fdakmapp_webapp/

Notifications You must be signed in to change notification settings

AlessandraColli/fdakmapp

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

49 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

fdakmapp

The fdakmapp package provides the kmap function that jointly performs clustering and alignment of a functional dataset (multidimensional or unidimensional). The centers can be computed by mean or medoid center methods. The parallel version is available.

Getting Started

The source code can be cloned or downloaded directly from github. An R studio project file is provided to open the project in RStudio.

Prerequisites

The package is linked against OpenMP, the BLAS and LAPACK libraries in Makevars.

To install the package locally the packages Rcpp and RcppArmadillo needs to be installed. Using install_github() will install the dependencies (Rcpp and RcppArmadillo) automatically.

Installing

The package can be installed directly from github but devtools is required.

If devtools is not installed use the following comand to install it

install.packages('devtools') 

and then install the package

library(devtools)
install_github('zitale/fdakmapp')

Usually the clag compiler doesn't support OpenMP. For this reason is available a release without -fopenmp.

library(devtools)
install_github('zitale/[email protected]')

Othewise the problem can be solved following the tutorial at: https://clang-omp.github.io/.

Automatic tests

devtools::test()

Example

res<-kmap(x=aneurisk65$x, y=aneurisk65$y, n_clust=2)
kmap_show_results(res,FALSE,FALSE)

Documentation

The R documentation can be found in the main directory in fdakmapp.pdf. The C++ documentation can be found at https://zitale.github.io/fdakmapp/.

About

The fdakmapp package provides the kmap function that jointly performs clustering and alignment of a functional dataset. The centers can be computed by several center methods. The package can be be live tested, also with your own dataset, at https://zitale.shinyapps.io/fdakmapp_webapp/

Resources

Stars

Watchers

Forks

Packages

No packages published

Languages

  • C++ 98.8%
  • Cuda 0.5%
  • CMake 0.4%
  • C 0.2%
  • R 0.1%
  • Java 0.0%