unsupervised_labels.py 文件源码

def get_best_label(label_list,num):
    topic_ls = get_topic_lg(topic_list[num])
    val_dict = {}
    for item in label_list:
        trigrams = [item[i:i+3] for i in range(0, len(item) - 2)] #Extracting letter trigram for label
        label_cnt = Counter(trigrams)
        total = sum(label_cnt.values(), 0.0)
        for key in label_cnt:
            label_cnt[key] /= total
        tot_keys = list(set(topic_ls.keys() + label_cnt.keys()))
        listtopic = []
        listlabel = []
        for elem in tot_keys:
            if elem in topic_ls:
                listtopic.append(topic_ls[elem])
            else:
                listtopic.append(0.0)
            if elem in label_cnt:
                listlabel.append(label_cnt[elem])
            else:
                listlabel.append(0.0)
        val = 1 - cosine(np.array(listtopic),np.array(listlabel))   # Cosine Similarity
        val_dict[item] = val
    list_sorted=sorted(val_dict.items(), key=lambda x:x[1], reverse = True) # Sorting the labels by rank
    return [i[0] for i in list_sorted[:int(args.num_unsup_labels)]]