Cluster.py 文件源码

def cluster(self, data_set, threshold, verbose=True):
        grp_map = {}
        grp_id = 0
        for index in range(len(data_set)):
            sample = data_set[index]
            if not verbose:
                print "[+] Processing Sample:", sample["id"]
            scores = {}
            for prev_grp_id, prev_grp_data in grp_map.iteritems():
              scores[prev_grp_id] = min([Util.simscore(sample["encoded"], prev["encoded"]) for prev in prev_grp_data])
            if len(scores) == 0 or max(scores.values()) < threshold:
                grp_id += 1
                cur_grp_id = grp_id
                grp_map[cur_grp_id] = []
            else:
                cur_grp_id = max(scores.iteritems(), key=operator.itemgetter(1))[0]
            if not verbose:
                print "[+] Found Closet Cluster:", cur_grp_id
            grp_map[cur_grp_id].append(sample)
        grp_info = {}
        for prev_grp_id, prev_grp_data in grp_map.iteritems():
            grp_info[prev_grp_id] = [prev["id"] for prev in prev_grp_data]
        return grp_info