ldp_fea.py 文件源码

def venueNet_feature():
    # output: compute the author centrialy for each venue
    #         venue centrality dict

    CSpaper = pickle.load(open(cspath+"CSvenuePaper","rb")) # all papers in CS venues
    CSvenue_paper = pickle.load(open(cspath+"CSvenue_paper","rb")) #data type, dict, key, value: list
    Citations = pickle.load(open(cspath+"Citations","rb"))
    CSPV = pickle.load( open(cspath+"CSvenuePaper_Venue","rb")) #data type, dict, key, value: list
    nodeSet = set()
    edgeSet = set()
    for key,val in CSvenue_paper.iteritems():
        nodeSet.add(key)
        temp = defaultdict(int)
        for p in val:
            for citing in Citations[p]:
                if citing in CSpaper:
                    temp[(CSPV[citing],key)] +=1
        edges = [(key[0],key[1],val) for key,val in temp.iteritems()]
        edgeSet.update(edges)
    g = nx.DiGraph()
    g.add_nodes_from(nodeSet)
    g.add_weighted_edges_from(edgeSet)

    pr = defaultdict(int)
    for node in g.nodes():
        pr[node]=1

    #DG.add_weighted_edges_from([(1,2,0.5), (3,1,0.75)])
    #pr = nx.pagerank(g) 
    #page rank is time-consuming, replace this in real atmosphere
    pickle.dump(pr,open(cspath+"venue_cen","wb"))
    print 'venueNet_feature finish'