import numpy as np
def entropy(y):
"""
 计算标签集合的信息熵
 
 参数：
 y - 标签数组
 
 返回：
 entropy_value - 熵值
 """
# 获取每个类别的数量
 class_counts = np.bincount(y)
# 计算每个类别的概率
 probabilities = class_counts / len(y)
# 只考虑非零概率
 probabilities = probabilities[probabilities > 0]
# 计算熵
 entropy_value = -np.sum(probabilities * np.log2(probabilities))
return entropy_value
# 示例：计算二分类数据的熵
y_binary = np.array([0, 0, 0, 1, 1, 1])
print(f"二分类数据的熵: {entropy(y_binary):.4f}")
y_pure = np.array([0, 0, 0, 0])
print(f"纯数据的熵: {entropy(y_pure):.4f}")
y_uniform = np.array([0, 1, 2, 3])
print(f"均匀分布的熵: {entropy(y_uniform):.4f}")