This module implements the GraphProposal class, which generates proposals for graph structures by performing edge operations such as addition, deletion, and reversal.
 
The GraphProposal class is used in structure learning algorithms to explore the space of possible graph structures. It supports constraints through blacklist and whitelist matrices and calculates acceptance ratios for proposed changes.
 
Classes:
    GraphProposal: Generates graph proposals and computes acceptance ratios for structure learning.

Modules
		numpy networkx

Classes
		structure_learning.proposals.proposal.StructureLearningProposal(abc.ABC) GraphProposal   class GraphProposal(structure_learning.proposals.proposal.StructureLearningProposal)     GraphProposal(initial_state: Union[numpy.ndarray, networkx.classes.digraph.DiGraph, structure_learning.data_structures.dag.DAG], blacklist=None, whitelist=None, seed: int = 32)   Graph Proposal by adding, deleting, reversing edges.     Method resolution order: GraphProposal structure_learning.proposals.proposal.StructureLearningProposal abc.ABC builtins.object Methods defined here: __init__(self, initial_state: Union[numpy.ndarray, networkx.classes.digraph.DiGraph, structure_learning.data_structures.dag.DAG], blacklist=None, whitelist=None, seed: int = 32) Initialise GraphProposal instance.   Parameters:     initial_state (networkx.DiGraph | numpy.ndarray): graph     blacklist (numpy.ndarray): mask for edges to ignore in the proposal     whitelist (numpy.ndarray): mask for edges to include in the proposal compute_acceptance_ratio(self, current_state_score, proposed_state_score, current_state_prior=0, proposed_state_prior=0) Calculate log acceptance ratio.   Returns:     (float) get_nodes_to_rescore(self) -> List[str] propose(self) Propose a DAG.   Returns:     (numpy.ndarray): adjacency matrix of proposed graph     (str): operation that generated the proposed graph Data and other attributes defined here: ADD_EDGE = 'add_edge' DELETE_EDGE = 'delete_edge' REVERSE_EDGE = 'reverse_edge' __abstractmethods__ = frozenset() operations = ['add_edge', 'delete_edge', 'reverse_edge', 'stay_still'] Methods inherited from structure_learning.proposals.proposal.StructureLearningProposal: accept(self) Data descriptors inherited from structure_learning.proposals.proposal.StructureLearningProposal: __dict__ dictionary for instance variables __weakref__ list of weak references to the object Data and other attributes inherited from structure_learning.proposals.proposal.StructureLearningProposal: INITIAL = 'initial' STAY_STILL = 'stay_still'

Data
		List = typing.List Union = typing.Union