Convert Knowledge to pcalg Knowledge

pcalg only supports undirected (symmetric) background constraints:

• fixed_gaps - forbidding edges (zeros enforced)

Usage

as_pcalg_constraints(
  kn,
  labels = kn$vars$var,
  directed_as_undirected = lifecycle::deprecated()
)

Arguments

kn

A Knowledge object. Must have no tier information.

labels

Character vector of all variable names, in the exact order of your data columns. Every variable referenced by an edge in kn must appear here.

directed_as_undirected

This argument no longer has any effect and will be removed in a future release. Specify directed edges in both directions in knowledge() instead.

Value

A list with one element, fixed_gaps: an n × n logical matrix corresponding to the pcalg fixedGaps argument.

Details

This function takes a Knowledge object (with only forbidden edges, no tiers) and returns the logical constraint matrix in the exact variable order you supply.

Required edges in a Knowledge object are directed statements. pcalg constraints are adjacency-level only, so a required edge cannot be honored; any required edges are dropped with a warning.

Errors

• If the Knowledge object contains tiered knowledge.

• If any forbidden edge lacks its symmetrical counterpart.

See also

Other knowledge helpers: +.Knowledge(), add_exogenous(), add_tier(), add_to_tier(), add_vars(), as_bnlearn_knowledge(), as_tetrad_knowledge(), convert_tiers_to_forbidden(), deparse_knowledge(), forbid_edge(), get_tiers(), knowledge(), knowledge_to_caugi(), remove_edge(), remove_tiers(), remove_vars(), reorder_tiers(), reposition_tier(), require_edge(), seq_tiers(), set_knowledge(), unfreeze()

Examples

# pcalg supports undirected constraints; build a tierless knowledge and convert
data(tpc_example)

kn <- knowledge(
  tpc_example,
  child_x1 %!-->% youth_x3,
  youth_x3 %!-->% child_x1
)

pc_constraints <- as_pcalg_constraints(kn)
print(pc_constraints)
#> $fixed_gaps
#>           child_x1 child_x2 oldage_x5 oldage_x6 youth_x3 youth_x4
#> child_x1     FALSE    FALSE     FALSE     FALSE     TRUE    FALSE
#> child_x2     FALSE    FALSE     FALSE     FALSE    FALSE    FALSE
#> oldage_x5    FALSE    FALSE     FALSE     FALSE    FALSE    FALSE
#> oldage_x6    FALSE    FALSE     FALSE     FALSE    FALSE    FALSE
#> youth_x3      TRUE    FALSE     FALSE     FALSE    FALSE    FALSE
#> youth_x4     FALSE    FALSE     FALSE     FALSE    FALSE    FALSE
#> 

# error paths
# using tiers
kn <- knowledge(
  tpc_example,
  tier(
    child ~ starts_with("child"),
    youth ~ starts_with("youth"),
    oldage ~ starts_with("old")
  ),
  child_x1 %-->% youth_x3
)

try(as_pcalg_constraints(kn), silent = TRUE) # fails due to tiers

# using directed knowledge
kn <- knowledge(
  tpc_example,
  child_x1 %!-->% youth_x3
)

try(as_pcalg_constraints(kn), silent = TRUE) # fails due to directed knowledge