predict.GLoMo: Predict (sample) data from GLoMo model
In GLoMo: Naive General Location Model

Description Usage Arguments Value Author(s) References See Also Examples

View source: R/GLoMo.r

Sample data (filling out existing data or sampling a completely new dataset). If a dataset is provided, and it contains 'cells' that are not covered by the naive GLoMo, a warning is issued and marginal probabilities and means are used.

1
2

## S3 method for class 'GLoMo'
predict(object, nobs = 1, newdata = NULL, forrows = seq(nrow(newdata)), reusabledata = NULL, returnRepeats = FALSE, returnSelectedGlomoRows = FALSE, verbosity = 0,...)

`object`	`GLoMo` object
`nobs`	number of observations to sample. Can be a single integer or a vector of the same length as `forrows`.
`newdata`	`NULL` (the default) if you want to sample a completely new dataset. Otherwise, a dataset of the correct column structure, holding `NA` values.
`forrows`	indices of the rows of `newdata` for which data will be sampled. Default is all of them.
`reusabledata`	See `reusableDataForGLoMoSampling`. Some of the calculations can be done for a row so that repeated sampling can go faster. If not provided, this is calculated. Optionally, pass a `GuidData` object or a list of uids for the rows here.
`returnRepeats`	if `TRUE` (not the default), an additional vector of the same length as `forrows` is returned, holding how many rows were sampled for each row.
`returnSelectedGlomoRows`	if `TRUE` (not the default), an additional vector of the same length as the number of rows sampled is returned, holding which row of the `GLoMo` object was used for which row.
`verbosity`	The higher this value, the more levels of progress and debug information is displayed (note: in R for Windows, turn off buffered output)
`...`	Ignored for now

If both returnRepeats and returnSelectedGlomoRows are FALSE, a data.frame or numdfr (dependent on the dfr that was used in the original call to GLoMo that holds the sampled data.

Otherwise, a list with items:

`predicted`	The sampled dataset described above
`glomorowsused`	(only if `returnSelectedGlomoRows` was `TRUE`) vector of the same length as the number of rows sampled is returned, holding which row of the `GLoMo` object was used for which row
`numRepPerRow`	(only if `returnRepeats` was `TRUE`) vector of the same length as `forrows` is returned, holding how many rows were sampled for each row

Nick Sabbe (nick.sabbe@ugent.be)

"Statistical Analysis with Missing Values"

GLoMo-package, NumDfr, predict, GLoMo

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