FeatureSelect.py 文件源码

def pre_train(train_df, test_df, train_add, test_add):

    train = train_df.values[:,1:-1]
    t = train_add.values[:,1:-1]
    train = np.hstack((train, t))

    dtest = test_df.values[:,1:]
    tA = test_add.values[:,1:]
    dtest = np.hstack((dtest, tA))

    cor_distance = pairwise.pairwise_distances(dtest, train)

    resultset = set()
    for tmp in cor_distance:
        index = np.argsort(tmp)
        for i in range(10):
            resultset.add(index[i])

    index = []
    for i in resultset:
        index.append(i)

    return index