pre_data.py 文件源码

def get_extra_test():  
##############################extra features##################################
    test_simhash_features=pd.read_csv('data/extra_feature/test_simhash_features.csv')
    test_selftrained_w2v_sim_dist=pd.read_pickle('data/extra_feature/test_selftrained_w2v_sim_dist.pkl')
    test_selftrained_glove_sim_dist=pd.read_pickle('data/extra_feature/test_selftrained_glove_sim_dist.pkl')
    test_pretrained_w2v_sim_dist=pd.read_pickle('data/extra_feature/test_pretrained_w2v_sim_dist.pkl')
    test_distinct_word_stats_selftrained_glove=pd.read_csv('data/extra_feature/test_distinct_word_stats_selftrained_glove.csv')
    test_distinct_word_stats_pretrained=pd.read_csv('data/extra_feature/test_distinct_word_stats_pretrained.csv')
    test_distinct_word_stats=pd.read_csv('data/extra_feature/test_distinct_word_stats.csv')


    X_test=np.hstack([    test_simhash_features,
    test_selftrained_w2v_sim_dist,
    test_selftrained_glove_sim_dist,
    test_pretrained_w2v_sim_dist,
    test_distinct_word_stats_selftrained_glove,
    test_distinct_word_stats_pretrained,
    test_distinct_word_stats,])


    print X_test.shape

    return X_test