Can this breadth-first search be made faster?

Question

I have a data set which is a large unweighted cyclic graph The cycles occur in loops of about 5-6 paths. It consists of about 8000 nodes and each node has from 1-6 (usually abou

Answer 1

Something like this:

#!/usr/bin/env python

from Queue import Queue

def traverse_path(fromNode, toNode, nodes):
    def getNeighbours(current, nodes):
        return nodes[current] if current in nodes else []

    def make_path(toNode, graph):
        result = []
        while 'Root' != toNode:
            result.append(toNode)
            toNode = graph[toNode]
        result.reverse()
        return result

    q = Queue()
    q.put(fromNode)
    graph = {fromNode: 'Root'}

    while not q.empty():
        # get the next node and add its neighbours to queue
        current = q.get()
        for neighbor in getNeighbours(current, nodes):
            # use neighbor only continue if not already visited
            if neighbor not in graph:
                graph[neighbor] = current
                q.put(neighbor)

        # check if destination
        if current == toNode:
            return make_path(toNode, graph)
    return []

if __name__ == '__main__':
    nodes = {
        'E1123': ['D111', 'D222', 'D333', 'D444'],
        'D111': ['C01', 'C02', 'C04'],
        'D222': ['C11', 'C03', 'C05'],
        'D333': ['C01'],
        'C02': ['B1'],
        'B1': ['A3455']
    }
    result = traverse_path('E1123', 'A3455', nodes)
    print result

['E1123', 'D111', 'C02', 'B1', 'A3455']

If you replace your SQL queries with a dictionary of lists (and that would be the tricky part), you will get this performance.