train.kknn {kknn}R Documentation

Training kknn

Description

Training of kknn method via leave-one-out crossvalidation.

Usage

train.kknn(formula, data, kmax = 11, distance = 2, kernel = NULL,
        ykernel = NULL, contrasts = c('unordered' = "contr.dummy",
        ordered = "contr.ordinal"), ...)

Arguments

formula A formula object.
data Matrix or data frame.
kmax Maximum number of k.
distance Parameter of Minkowski distance.
kernel Kernel to use. Possible choices are "rectangular" (which is standard unweighted knn), "triangular", "epanechnikov" (or beta(2,2)), "biweight" (or beta(3,3)), "triweight" (or beta(4,4)), "cos", "inv" and "gaussian".
ykernel
contrasts A vector containing the 'unordered' and 'ordered' contrasts to use.
... Further arguments passed to or from other methods.

Value

train.kknn returns a list-object of class train.kknn including the components

MISCLASS Matrix of misclassification errors.
MEAN.ABS Matrix of mean absolute errors.
MEAN.SQU Matrix of mean squared errors.
fitted.values List of predictions for all combinations of kernel and k.
best.parameters List containing the best parameter value for kernel and k.
response Type of response variable, one of continuous, nominal or ordinal.
distance Parameter of Minkowski distance.
call The matched call.
terms The 'terms' object used.

Author(s)

Klaus P. Schliep K.P.Schliep@massey.ac.nz

References

Hechenbichler K. and Schliep K.P. (2004) Weighted k-Nearest-Neighbor Techniques and Ordinal Classification, Discussion Paper 399, SFB 386, Ludwig-Maximilians University Munich (http://www.stat.uni-muenchen.de/sfb386/papers/dsp/paper399.ps)

Hechenbichler K. (2005) Ensemble-Techniken und ordinale Klassifikation, PhD-thesis

See Also

kknn and simulation

Examples

library(kknn)

data(miete)
(train.con <- train.kknn(nmqm ~ wfl + bjkat + zh, data = miete, 
        kmax = 25, kernel = c("rectangular", "triangular", "epanechnikov",
        "gaussian", "rank")))
plot(train.con)
(train.ord <- train.kknn(wflkat ~ nm + bjkat + zh, miete, kmax = 25,
        kernel = c("rectangular", "triangular", "epanechnikov", "gaussian", 
        "rank")))
plot(train.ord)
(train.nom <- train.kknn(zh ~ wfl + bjkat + nmqm, miete, kmax = 25, 
        kernel = c("rectangular", "triangular", "epanechnikov", "gaussian", 
        "rank")))
plot(train.nom)

data(glass)
glass <- glass[,-1]
(fit.glass1 <- train.kknn(Type ~ ., glass, kmax = 15, kernel = 
        c("triangular", "rectangular", "epanechnikov"), distance = 1))
(fit.glass2 <- train.kknn(Type ~ ., glass, kmax = 15, kernel = 
        c("triangular", "rectangular", "epanechnikov"), distance = 2))
plot(fit.glass1)
plot(fit.glass2)


[Package kknn version 1.0-6 Index]