Gap_stats.py 文件源码

def KMEANS(data, k):

    if data.shape[0] < 20000:
        centroids, cluster_IDs, _ = k_means(data, k, init = 'k-means++', precompute_distances = 'auto', n_init = 20, max_iter = 200)
    else:
        mbkm = MiniBatchKMeans(k, 'k-means++', max_iter = 100, batch_size = data.shape[0] / k, n_init = 20)
        mbkm.fit(data)

        centroids = mbkm.cluster_centers_
        cluster_IDs = mbkm.labels_

    return centroids, cluster_IDs