generate_neighbor_dis.py 文件源码

def calc_dis_jarccard2(neighs,neighs2):
    sim_fea = []
    for i in neighs:
        for j in neighs2:
            if i==j:continue
            if (j in index_q) and (i in index_q):
                q_str = index_q[i]
                nei_str = index_q[j]
                s1 = set(q_str.lower().split())
                s2 = set(nei_str.lower().split())
                sim_fea.append(dist_utils._jaccard_coef(s1, s2))
    aggregation_mode = ["mean", "std", "max", "min", "median"]
    aggregator = [None if m == "" else getattr(np, m) for m in aggregation_mode]
    score = []
    for n, agg in enumerate(aggregator):
        if len(sim_fea) == 0:
            s = -1
        try:
            s = agg(sim_fea)
        except:
            s = -1
        score.append(s)
    return score


# sps.spearmanr(train_fea,train['is_duplicate'])[0]