def initialize(inputFileDir, rdr): (parentUserIdToUserDict, parentBusinessIdToBusinessDict, parent_reviews) =\ rdr.readData(inputFileDir) print len(parent_reviews) bnssEdited = 0 for bnssId in parentBusinessIdToBusinessDict.iterkeys(): if bnssId in parentBusinessIdToBusinessDict: parentBusinessIdToBusinessDict[bnssId].setRating(parentBusinessIdToBusinessDict[bnssId].getRating()) bnssEdited+=1 print bnssEdited parent_graph = OldGraphUtil.createGraph(parentUserIdToUserDict,parentBusinessIdToBusinessDict,parent_reviews) # unnecessary_reviews = set() # cc = sorted(networkx.connected_component_subgraphs(parent_graph,False), key=len, reverse=True) # for g in cc: # g.initializeDicts() # # for g in cc: # usr_count = g.getUserCount() # bnss_count = g.getBusinessCount() # if(usr_count==1): # usr = g.getUser(g.getUserIds()[0]) # for bnss in g.neighbors(usr): # review = g.getReview(usr.getId(),bnss.getId()) # unnecessary_reviews.add(review.getId()) # if(bnss_count==1): # bnss = g.getBusiness(g.getBusinessIds()[0]) # for usr in g.neighbors(bnss): # review = g.getReview(usr.getId(),bnss.getId()) # unnecessary_reviews.add(review.getId()) # print len(unnecessary_reviews) # cross_9_months_graphs = SIAUtil.createTimeBasedGraph(parentUserIdToUserDict, parentBusinessIdToBusinessDict, parent_reviews, '9-M') cross_time_graphs = OldGraphUtil.createTimeBasedGraph(parentUserIdToUserDict,\ parentBusinessIdToBusinessDict,\ parent_reviews, '1-Y') beforeThreadTime = datetime.now() cross_time_lbp_runner_threads = [] for time_key in cross_time_graphs.iterkeys(): print '----------------------------------GRAPH-', time_key, '---------------------------------------------\n' lbp_runner = LBPRunnerThread(cross_time_graphs[time_key], 50, 'Initial LBP Runner for Time'+str(time_key)) cross_time_lbp_runner_threads.append(lbp_runner) lbp_runner.start() for lbp_runner in cross_time_lbp_runner_threads: lbp_runner.join() afterThreadTime = datetime.now() print 'Time to be reduced',afterThreadTime-beforeThreadTime return (cross_time_graphs, parent_graph)