itercomp {BiDAG} | R Documentation |
Performance assessment of iterative MCMC scheme against a known Bayesian network
Description
This function compute 8 different metrics of structure fit of an object of class iterativeMCMC
to the ground truth DAG (or CPDAG). Object of class
iterativeMCMC
stores MAP graph at from each search space expansion step. This function computes structure fit of
each of the stored graphs to the ground truth one. Computed metrics include: TP, FP, TPR, FPR, FPRn, FDR, SHD. See metrics description in
see also compareDAGs
.
Usage
itercomp(MCMCmult, truedag, cpdag = TRUE, p = 0.5, trans = TRUE)
## S3 method for class 'itercomp'
plot(x, ..., vars = c("FP", "TP"), type = "b", col = "blue", showit = c())
## S3 method for class 'itercomp'
print(x, ...)
## S3 method for class 'itercomp'
summary(object, ...)
Arguments
MCMCmult |
an object which of class |
truedag |
ground truth DAG which generated the data used in the search procedure; represented by an object of class |
cpdag |
logical, if TRUE (FALSE by default) all DAGs are first converted to their respective equivalence classes (CPDAG) |
p |
threshold such that only edges with a higher posterior probability will be retained in the directed graph summarising the sample of DAGs at each iteration from |
trans |
logical, for DBNs indicates if model comparions are performed for transition structure; when |
x |
object of class 'itercomp' |
... |
ignored |
vars |
a tuple of variables which will be used for 'x' and 'y' axes; possible values: "SHD", "TP", "FP", "TPR", "FPR", "FPRn", "FDR", "score" |
type |
type of line in the plot;"b" by default |
col |
colour of line in the plot; "blue" by default |
showit |
(optional) vector of integers specifying indices of search expansion iterations to be labelled; by default no iterations are labelled |
object |
object of class 'itercomp' |
Value
an object if class itersim
, a matrix with the number of rows equal to the number of expansion iterations in iterativeMCMC
, and 8 columns reporting for
the maximally scoring DAG uncovered at each iteration: the number of true positive edges ('TP'), the number of false positive edges ('FP'),
the true positive rate ('TPR'), the structural Hamming distance ('SHD'), false positive rate ('FPR'),
false discovery rate ('FDR') and the score of the DAG (‘score’).
Author(s)
Polina Suter
Examples
gsim.score<-scoreparameters("bge", gsim)
## Not run:
MAPestimate<-learnBN(gsim.score,"orderIter")
itercomp(MAPestimate, gsimmat)
## End(Not run)