欠采样，即去除一些反例使得正、反例数目接近，然后再进行学习，基本的算法如下：

def undersampling(train, desired_apriori):

    # Get the indices per target value
    idx_0 = train[train.target == 0].index
    idx_1 = train[train.target == 1].index
    # Get original number of records per target value
    nb_0 = len(train.loc[idx_0])
    nb_1 = len(train.loc[idx_1])
    # Calculate the undersampling rate and resulting number of records with target=0
    undersampling_rate = ((1-desired_apriori)*nb_1)/(nb_0*desired_apriori)
    undersampled_nb_0 = int(undersampling_rate*nb_0)
    print('Rate to undersample records with target=0: {}'.format(undersampling_rate))
    print('Number of records with target=0 after undersampling: {}'.format(undersampled_nb_0))
    # Randomly select records with target=0 to get at the desired a priori
    undersampled_idx = shuffle(idx_0, n_samples=undersampled_nb_0)
    # Construct list with remaining indices
    idx_list = list(undersampled_idx) + list(idx_1)
    # Return undersample data frame
    train = train.loc[idx_list].reset_index(drop=True)

    return train