split_criterion.py 文件源码

def entropy_score(labels):
    """
    entropy = sum(p*log(1/p))
    """
    n_labels = labels.shape[0]
    if n_labels <= 1:
        return 0.0

    counts = np.bincount(labels)
    probs = counts / float(n_labels)
    n_classes = np.count_nonzero(probs)
    if n_classes <= 1:
        return 0.0

    entropy = 0.0
    for p in probs:
        entropy -= p*np.log(p)

    return entropy