【Deep-ML系列】Calculate Covariance Matrix (协方差)

py明天会更好

于 2024-07-18 19:56:21 发布

阅读量258

点赞数 4

分类专栏：深度学习/机器学习文章标签： python 人工智能深度学习协方差

本文链接：https://blog.csdn.net/weixin_56029873/article/details/140531619

版权

深度学习/机器学习专栏收录该内容

16 篇文章 0 订阅

订阅专栏

题目链接：Deep-ML

不使用numpy数组来完成计算：

def calculate_covariance_matrix(vectors: list[list[float]]) -> list[list[float]]:
    # 转置矩阵
    # vectors = [[vectors[j][i] for j in range(len(vectors))] for i in range(len(vectors[0]))]
    n = len(vectors[0])
    p = len(vectors)

    # 计算每个特征的平均值
    M = [sum(feature) / n for feature in vectors]

    # 计算中心化后的矩阵 B
    B = [[vectors[i][j] - M[i] for j in range(n)] for i in range(p)]

    # 计算 B 的转置
    B_T = [[B[j][i] for j in range(p)] for i in range(n)]

    # 计算协方差矩阵
    covariance_matrix = [[sum(B[i][k] * B_T[k][j] for k in range(n)) / (n - 1) for j in range(p)] for i in range(p)]

    return covariance_matrix


if __name__ == '__main__':
    print(calculate_covariance_matrix([[1, 2, 3], [4, 5, 6]]))