cnSamples: Samples from Network
In sdnet: Soft-Discretization-Based Bayesian Network Inference

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

Generates samples from of a catNetwork object.

1	cnSamples(object, numsamples = 1, pert = NULL, output="frame", as.index=FALSE, naRate=0)

`object`	a `catNetwork`
`numsamples`	an `integer`, the number of samples to be generated
`pert`	a `vector`, node pert
`output`	a `character`, the output format. Can be a `data.frame` or `matrix`.
`as.index`	a `logical`, the output categorical format
`naRate`	a `numeric`, the proportion of NAs per sample instance

If the output format is "matrix" then the resulting sample matrix is in row-node format - the rows correspond to the object's nodes while the individual samples are represented by columns. If the output format is "frame", which is by default, the result is a data frame with columns representing the nodes and levels the set of categories of the respected nodes. If as.index is set to TRUE, the output sample consists of categorical indices, otherwise, and this is by default, of characters specifying the categories.

A perturbed sample is a sample having nodes with predefined, thus fixed, values. Non-perturbed nodes, the nodes which values have to be set, are designated with zeros in the perturbation vector and their values are generated conditional on the values of their pars. While the non-zero values in the perturbation vector are carried on unchanged to the output.

If naRate is positive, then floor(numnodes*naRate) NA values are randomly placed in each sample instance.

A matrix or data.frame of node categories as integers or characters

N. Balov

cnPredict

  cnet <- cnRandomCatnet(numnodes=10, maxpars=3, numcats=3)
  ## generate a sample of size 100 from cnet
  psamples <- cnSamples(object=cnet, numsamples=100, output="frame", as.index=FALSE)
  ## perturbed sample
  nsamples <- 20
  pert <- rbinom(10, 2, 0.4)
  ## generate a perturbed sample of size 100 from cnet
  psamples <- cnSamples(object=cnet, numsamples=nsamples, pert, as.index=TRUE)