Exact Learning Augmented Naive Bayes Classifier

. 2021 Dec 20;23(12):1703. doi: 10.3390/e23121703

Algorithm A2

G e t B e s t P a r e n t s (V, X_{i}, L S)

$b p s =$ array 1 to $2^{n - 2}$ of variable sets
$b s s =$ array 1 to $2^{n - 2}$ of local scores
for all $c s \subseteq (V ∖ {X_{i}})$ such that $X_{0} \in c s$ in lexicographic order do
$b p s [c s] \leftarrow c s$
$b s s [c s] \leftarrow L S [X_{i}] [c s]$
for all $c s 1 \subset c s$ such that $X_{0} \in c s 1$ and $| c s ∖ c s 1 | = 1$ do
if $b s s [c s 1] > b s s [c s]$ then
$b s s [c s] \leftarrow b s s [c s 1]$
$b p s [c s] \leftarrow b p s [c s 1]$
end if
end for
end for