cnNew {catnet} | R Documentation |
Creates a new catNetwork
with specified nodes, categories, parent sets and probability structure.
cnNew(nodes, cats, parents, probs=NULL, p.delta1=0.01, p.delta2=0.01)
nodes |
a |
cats |
a |
parents |
a |
probs |
a |
p.delta1 |
a |
p.delta2 |
a |
If probs
is not specified, then a random probability model is assigned with conditional probability values in the union of the intervals [p.delta1, 0.5-p.delta2] and [0.5+p.delta2, 1-p.delta1].
Because of the nested list hierarchy of the probability structure,
specifying the probability argument explicitly can be very elaborated task for large networks.
In the following example we create a small network with only three nodes.
The first node has no parents and only its marginal distribution is given, c(0.2,0.8)
.
Note that all inner most vectors in the probs
argument, such as (0.4,0.6)
,
represent conditional distributions and thus sum to 1.
A catNetwork
object.
N. Balov, P. Salzman
catNetwork-class
, cnRandomCatnet
library(catnet) cnet <- cnNew( nodes = c("a", "b", "c"), cats = list(c("1","2"), c("1","2"), c("1","2")), parents = list(NULL, c(1), c(1,2)), probs = list( c(0.2,0.8), list(c(0.6,0.4),c(0.4,0.6)), list(list(c(0.3,0.7),c(0.7,0.3)), list(c(0.9,0.1),c(0.1,0.9)))) )