The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.

Encoding: UTF-8
Type: Package
Title: K* Nearest Neighbors Algorithm
Version: 0.1.2
Description: Prediction with k* nearest neighbor algorithm based on a publication by Anava and Levy (2016) <doi:10.48550/arXiv.1701.07266>.
License: GPL-2 | GPL-3 [expanded from: GPL (≥ 2)]
Author: Kei Nakagawa ORCID iD [aut, cre], Shingo Sashida [aut]
Maintainer: Kei Nakagawa <kei.nak.0315@gmail.com>
LazyData: TRUE
Imports: Rcpp
Depends: R(≥ 3.0.2)
LinkingTo: Rcpp(≥ 0.10.6)
RoxygenNote: 6.1.1
NeedsCompilation: yes
Packaged: 2019-03-28 09:53:44 UTC; SSunix
Repository: CRAN
Date/Publication: 2019-04-11 12:02:37 UTC

This function calculates the prediction value of k* nearest neighbors algorithm.

Description

This function calculates the prediction value of k* nearest neighbors algorithm.

Usage

ksNN(Label, Distance, L_C = 1)

Arguments

Label

vectors of the known labels of the samples.

Distance

vectors of the distance between the target sample we want to predict and the other samples.

L_C

parameter of k* nearest neighbors algorithm.

Value

the prediction value(pred) and the weight of the samples(alpha).

Note

This algorithm is based on Anava and Levy(2017).

Examples

  library(ksNN)
  set.seed(1)

  #make the nonlinear regression problem
  X<-runif(100)
  Y<-X^6-3*X^3+5*X^2+2

  suffle<-order(rnorm(length(X)))
  X<-X[suffle]
  Y<-Y[suffle]

  test_X<-X[1]
  test_Y<-Y[1]

  train_X<-X[-1]
  train_Y<-Y[-1]

  Label<-train_Y
  Distance<-sqrt((test_X-train_X)^2)

  pred_ksNN<-ksNN(Label,Distance,L_C=1)

  #the predicted value with k*NN
  pred_ksNN$pred

  #the 'true' value
  test_Y

This function calculates the prediction value of k* nearest neighbors algorithm.

Description

This function calculates the prediction value of k* nearest neighbors algorithm.

Usage

rcpp_ksNN(Label, Distance, L_C = 1)

Arguments

Label

vectors of the known labels of the samples.

Distance

vectors of the distance between the target sample we want to predict and the other samples.

L_C

parameter of k* nearest neighbors algorithm.

Value

the prediction value(pred) and the weight of the samples(alpha).

Note

This algorithm is based on Anava and Levy(2017).

Examples

  library(ksNN)
  set.seed(1)

  #make the nonlinear regression problem
  X<-runif(100)
  Y<-X^6-3*X^3+5*X^2+2

  suffle<-order(rnorm(length(X)))
  X<-X[suffle]
  Y<-Y[suffle]

  test_X<-X[1]
  test_Y<-Y[1]

  train_X<-X[-1]
  train_Y<-Y[-1]

  Label<-train_Y
  Distance<-sqrt((test_X-train_X)^2)

  pred_ksNN<-rcpp_ksNN(Label,Distance,L_C=1)

  #the predicted value with k*NN
  pred_ksNN$pred

  #the 'true' value
  test_Y

These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.