3 Md @s$dZddlmZdgZdddZdS)zBBasic algorithms for breadth-first searching the nodes of a graph.)generic_bfs_edgesbfs_beam_edgesNc#s6dkrtfdd}t||EdHdS)aIterates over edges in a beam search. The beam search is a generalized breadth-first search in which only the "best" *w* neighbors of the current node are enqueued, where *w* is the beam width and "best" is an application-specific heuristic. In general, a beam search with a small beam width might not visit each node in the graph. Parameters ---------- G : NetworkX graph source : node Starting node for the breadth-first search; this function iterates over only those edges in the component reachable from this node. value : function A function that takes a node of the graph as input and returns a real number indicating how "good" it is. A higher value means it is more likely to be visited sooner during the search. When visiting a new node, only the `width` neighbors with the highest `value` are enqueued (in decreasing order of `value`). width : int (default = None) The beam width for the search. This is the number of neighbors (ordered by `value`) to enqueue when visiting each new node. Yields ------ edge Edges in the beam search starting from `source`, given as a pair of nodes. Examples -------- To give nodes with, for example, a higher centrality precedence during the search, set the `value` function to return the centrality value of the node:: >>> G = nx.karate_club_graph() >>> centrality = nx.eigenvector_centrality(G) >>> source = 0 >>> width = 5 >>> for u, v in nx.bfs_beam_edges(G, source, centrality.get, width): ... print((u, v)) # doctest: +SKIP Ncs ttj|dddS)avReturns a list of the best neighbors of a node. `v` is a node in the graph `G`. The "best" neighbors are chosen according to the `value` function (higher is better). Only the `width` best neighbors of `v` are returned. The list returned by this function is in decreasing value as measured by the `value` function. T)keyreverseN)itersortedZ neighbors)v)GvaluewidthZ/var/www/html/virt/lib/python3.6/site-packages/networkx/algorithms/traversal/beamsearch.py successors=sz"bfs_beam_edges..successors)lenr)r sourcer r rr )r r r r rs2)N)__doc__Zbreadth_first_searchr__all__rr r r r s