Cluster.py 文件源码

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