addrandomarrow {deal} | R Documentation |
Create network with exactly one arrow added/turned/removed randomly chosen.
addrandomarrow(nw,data,prior,trylist=vector("list",nw$n),nocalc=FALSE, timetrace=FALSE) turnrandomarrow(nw,data,prior,trylist=vector("list",nw$n),nocalc=FALSE, timetrace=FALSE) deleterandomarrow(nw,data,prior,trylist=vector("list"),nw$n),nocalc=FALSE, timetrace=timetrace)
nw |
an object of class network , from which arrows are added/removed/turned. |
data |
a data frame used for learning the network, see network . |
prior |
a list describing parameter priors, generated by jointprior . |
trylist |
a list, used internally for reusing learning of nodes, see maketrylist . |
nocalc |
a logical. if TRUE , the learning procedure is not
called. Used if only a random graph is wanted. |
timetrace |
a logical. If TRUE , prints some timing information on the screen. |
Given the starting network, a network is created with exactly
one arrow added/turned/removed. The arrow is chosen randomly amongst all
possibilities. If there are no possibilities, the original network is
returned. All networks are
learned with the data in df
using the prior information in
prior
. Used by perturb
.
A list with two elements
nw |
an object of class networkfamily with all
created networks. All networks have been learned. |
trylist |
an updated list, used internally for reusing learning
of nodes, see maketrylist . |
Susanne Gammelgaard Bøttcher alma@math.auc.dk,
Claus Dethlefsen dethlef@math.auc.dk.
Further information about deal can be found at:
http://www.math.auc.dk/novo/deal.
data(rats) fit <- network(rats,specifygraph=FALSE,inspect=FALSE) fit.prior <- jointprior(fit,12) fit <- learn(fit,rats,fit.prior)$nw set.seed(10) rats.extra <- addrandomarrow(fit,rats,fit.prior)$nw rats.extra <- addrandomarrow(rats.extra,rats,fit.prior)$nw rats.extra <- turnrandomarrow(rats.extra,rats,fit.prior)$nw rats.extra <- deleterandomarrow(rats.extra,rats,fit.prior)$nw plot(rats.extra)