random_forests.py 文件源码

def bias_var(true_preds, sum_preds, counts, n_replicas):
    '''
    compute bias and variance
    @param true_preds: true labels
    @param sum_preds: array of summation of the predictions of each sample
    @param counts: the times each sample is tested (predicted)
    @return: squared bias, variance
    '''
    sample_bias = np.absolute(true_preds - sum_preds / counts)
    sample_var = sample_bias * (1.0 - sample_bias)

    weighted_sample_bias_2 = np.power(sample_bias, 2.0) * (counts / n_replicas)
    weighted_sample_var = sample_var * (counts / n_replicas)
    bias = np.mean(weighted_sample_bias_2)
    var = np.mean(weighted_sample_var)

    return bias, var