graphical_model_learning.pcalg

graphical_model_learning.pcalg(nodes, ci_tester: Optional[CI_Tester] = None, skel=None, sepset=None, solve_conflict: bool = False, max_cond_set: Optional[int] = None, verbose: bool = False) → PDAG[source]

Use the PC (Peters-Clark) algorithm to estimate the Markov equivalence class of the data-generating DAG.

Parameters

nodes – Labels of nodes in the graph.
ci_tester – A conditional independence tester, which has a method is_ci taking two sets A and B, and a conditioning set C, and returns True/False.
skel – An estimated skeleton. If not provided, uses the skeleton method to estimate.
sepset – The separating sets for non-adjacent nodes in the estimated skeleton.
solve_conflict – If False, any disagreements on v-structures are simply overwritten. If True, allow both orientations (represented by a bidirected edge).
verbose – If True, print decisions made by the algorithm.