updateGuidData: Update 'GuidData' object from one GLoMo to the next

In GLoMo: Naive General Location Model

Description

During repeated fits of GLoMo, typically some 'glomorows' get lost in the process. This function updates a GuidData object from the 'old' GLoMo to the reduced newer one, so it doesn't have to be fully recalculated (since this implies a grep which could be expensive).

Usage

updateGuidData(oldglomo, newglomo, oldrowsused = seq(nrow(oldglomo$uid)), oldguiddata)

Arguments

oldglomo	old GLoMo object
newglomo	new GLoMo object
oldrowsused	Which of the rows in oldglomo were used for sampling from a certain dataset.
oldguiddata	GuidData object that needs updating to the new

Details

It is the possibleGlomoGuidPerObs of the GuidData that is updated

Value

GuidData object

Note

Will have to see whether this really provides a speedup. Maybe doing the grep again with the reduced uids will be faster than this

Author(s)

Nick Sabbe ([e-mail])

See Also

GLoMo-package, NumDfr, getGuidData

Examples

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$weights
iris.nd.rnd<-iris.nd.rnd[,1:5]
iris.glomo<-GLoMo(iris.nd.rnd, weights=iris.weights, verbosity=1)
iris.guids<-getGuidData(iris.glomo, dfr=iris.md.nd)
emulatedusedrow<-sample(length(iris.glomo$uid), size=2)
iris.guids2<-updateGuidData(oldglomo=iris.glomo, newglomo=iris.glomo,
	oldrowsused = emulatedusedrow, iris.guids)

GLoMo documentation built on May 2, 2019, 5:26 p.m.