bnlearn (version 0.5)

choose.direction: Try to infer the direction of an undirected arc

Description

Check both possible directed arcs for existence, and choose the one with the lowest p-value.

Usage

choose.direction(x, arc, data, debug = FALSE)

Arguments

x

an object of class "bn".

arc

a character string vector of length 2, the labels of two nodes of the graph.

data

a data frame, containing the data the Bayesian network was learned from.

debug

a boolean value. If TRUE a lot of debugging output is printed; otherwise the function is completely silent.

Value

• choose.direction returns invisibly an updated copy of x.

Examples

data(learning.test)

res = gs(learning.test)
# the arc between E and F has no direction
plot(res)
res = choose.direction(res, c("E", "F"), learning.test, debug = TRUE)
# * testing E - F for direction.
#   > testing E -> F with conditioning set '  '.
#     > p-value is 2.174867e-197 .
#   > testing F -> E with conditioning set ' B '.
#     > p-value is 3.935648e-245 .
#   @ removing E -> F .
# * (re)building cached information about network structure.
#   > detecting neighbourhood, parents and children of node A .
#   > detecting neighbourhood, parents and children of node B .
#   > detecting neighbourhood, parents and children of node C .
#   > detecting neighbourhood, parents and children of node D .
#   > detecting neighbourhood, parents and children of node E .
#   > detecting neighbourhood, parents and children of node F .
# * detecting markov blanket for node A .
#   > neighbourhood is ' B D '.
#   > for child D getting ' A C '.
#   > raw markov blanket then is ' B D A C '.
#   > clean markov blanket then is ' B D C '.
# * detecting markov blanket for node B .
#   > neighbourhood is ' A E '.
#   > for child E getting ' B F '.
#   > raw markov blanket then is ' A E B F '.
#   > clean markov blanket then is ' A E F '.
# * detecting markov blanket for node C .
#   > neighbourhood is ' D '.
#   > for child D getting ' A C '.
#   > raw markov blanket then is ' D A C '.
#   > clean markov blanket then is ' D A '.
# * detecting markov blanket for node D .
#   > neighbourhood is ' A C '.
#   > raw markov blanket then is ' A C '.
#   > clean markov blanket then is ' A C '.
# * detecting markov blanket for node E .
#   > neighbourhood is ' B F '.
#   > raw markov blanket then is ' B F '.
#   > clean markov blanket then is ' B F '.
# * detecting markov blanket for node F .
#   > neighbourhood is ' E '.
#   > for child E getting ' B F '.
#   > raw markov blanket then is ' E B F '.
#   > clean markov blanket then is ' E B '.
plot(res, highlight = c("E", "F"))