在SciPy中，可以使用scipy.spatial.distance模块来计算两个样本集之间的距离和相似性。
from scipy.spatial import distance# 样本集合1X = [[0, 1], [1, 1]]# 样本集合2Y = [[2, 0], [3, 1]]# 计算欧氏距离euclidean_distance = distance.cdist(X, Y, 'euclidean')print("Euclidean Distance:")print(euclidean_distance)# 计算曼哈顿距离manhattan_distance = distance.cdist(X, Y, 'cityblock')print("\nManhattan Distance:")print(manhattan_distance)# 计算闵可夫斯基距离minkowski_distance = distance.cdist(X, Y, 'minkowski', p=2)print("\nMinkowski Distance:")print(minkowski_distance)from scipy.spatial import distance# 样本集合1X = [[0, 1], [1, 1]]# 样本集合2Y = [[2, 0], [3, 1]]# 计算余弦相似度cosine_similarity = 1 - distance.cdist(X, Y, 'cosine')print("Cosine Similarity:")print(cosine_similarity)# 计算皮尔逊相关系数pearson_similarity = 1 - distance.cdist(X, Y, 'correlation')print("\nPearson Correlation:")print(pearson_similarity)以上代码分别展示了如何计算欧氏距禮、曼哈顿距离、闵可夫斯基距离、余弦相似度和皮尔逊相关系数。可以根据具体需求选择合适的距离或相似性度量方法。
