cnFind: Find Network by Complexity
In sdnet: Soft-Discretization-Based Bayesian Network Inference

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

This is a model selection routine that finds a network in a set of networks for a given complx.

1 2	cnFind(object, complx = 0, alpha=0, factor=1) cnFindKL(object, numsamples)

`object`	`catNetworkEvaluate` or `dagEvaluate` or `list` of `catNetwork`s
`complx`	an `integer`, target complx
`alpha`	a `character` or `numeric`
`factor`	a `numeric`
`numsamples`	an `integer`

The complx must be at least the number of nodes of the networks. If no network with the requested complx exists in the list, then the one with the closest complx is returned. Alternatively, one can apply some standard model selection with alpha="BIC" and alpha=AIC.

A catNetwork object.

N. Balov

cnFindAIC, cnFindBIC

  cnet <- cnRandomCatnet(numnodes=10, maxpars=2, numcats=2)
  psamples <- cnSamples(object=cnet, numsamples=100)
  netlist <- cnSearchOrder(data=psamples, maxParentSet=2)
  bnet <- cnFind(object=netlist, complx=cnComplexity(cnet))
  bnet