Combine a set of similar GLoMo objects into 1

Share:

Description

In a crossvalidation setting or similar, often similar GLoMo objects occur: matching the same form of dataset, each of equal size or at least very similar. This is a method that combines them reasonably into 1 GLoMo model object.

Usage

1
combineGLoMos(..., listOfGLoMos=NULL, verbosity=0)

Arguments

...

several GLoMo objects from similar datasets

listOfGLoMos

if you have the parameters already in a list, this is the easier way of passing them.

verbosity

The higher this value, the more levels of progress and debug information is displayed (note: in R for Windows, turn off buffered output)

Value

a GLoMo object

Author(s)

Nick Sabbe (nick.sabbe@ugent.be)

References

"Statistical Analysis with Missing Values"

See Also

GLoMo-package, NumDfr, GLoMo

Examples

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
iris.md<-randomNA(iris, 0.1)
iris.md.nd<-numdfr(iris.md)
iris.nd.rnd<-rCatsAndCntInDfr(iris.md.nd, orgriName=NULL, verbosity=1)
iris.weights<-iris.nd.rnd$weights
iris.nd.rnd<-iris.nd.rnd[,1:5]
halfrows<-1:(as.integer(nrow(iris.nd.rnd)/2))
iris.glomo1<-GLoMo(iris.nd.rnd[halfrows,], weights=iris.weights[halfrows], verbosity=1)
iris.glomo2<-GLoMo(iris.nd.rnd[-halfrows,], weights=iris.weights[-halfrows], verbosity=1)

iris.glomo<-combineGLoMos(iris.glomo1, iris.glomo2, verbosity=1)
iris.pred.cond<-predict(iris.glomo, nobs=100, verbosity=1)