k_means_clust.py 文件源码

def compute_heterogeneity(data, k, centroids, cluster_assignment):

    heterogeneity = 0.0
    for i in range(k):

        # Select all data points that belong to cluster i. Fill in the blank (RHS only)
        member_data_points = data[cluster_assignment==i, :]

        if member_data_points.shape[0] > 0: # check if i-th cluster is non-empty
            # Compute distances from centroid to data points (RHS only)
            distances = pairwise_distances(member_data_points, [centroids[i]], metric='euclidean')
            squared_distances = distances**2
            heterogeneity += np.sum(squared_distances)

    return heterogeneity