jeffhj / deer Goto Github PK

    print('cal_cooccur_similarity')
    
    for f_id, save_cooccur__file in enumerate(tqdm.tqdm(save_cooccur__files)):
        with open(save_cooccur__file) as f_in:
            cooccurs = f_in.read().split('\n')
            print("cooccurs is: ", cooccurs)
        data = []
        for line in cooccurs:
            ents = line.split('\t')
            certain_len = len(ents)
            **if len(ents) <= 1:
                data.append('')**
            else:
                temp_data = []
                # valid_entities = []
                matrix = []
                for ent in ents:
                    try:
                        vec = w2vec.get_entity_vector(ent)
                    except:
                        vec = np.zeros(100, dtype=np.float32)
                    matrix.append(vec)
                # Collect pairs between certain entities
                matrix = np.array(matrix)
                result = cosine_similarity(matrix, matrix)
                for i in range(certain_len):
                    for j in range(i+1, certain_len):
                        tup = (float(result[i, j]), ents[i], ents[j])
                        temp_data.append(str(tup))
                data.append('\t'.join(temp_data))
        my_write(save_pair_files[f_id], data)