使用scikit-learn.k-means库输出最接近每个聚类中心的50个样本 [英] Output 50 samples closest to each cluster center using scikit-learn.k-means library

问题描述

我使用python scikit-learn库为5000多个样本拟合了k-means算法.我想将最接近聚类中心的50个样本作为输出.如何执行此任务?

I have fitted a k-means algorithm on 5000+ samples using the python scikit-learn library. I want to have the 50 samples closest to a cluster center as an output. How do I perform this task?

推荐答案

如果km是k均值模型，则数组X中每个点到j的重心的距离是

If km is the k-means model, the distance to the j'th centroid for each point in an array X is

d = km.transform(X)[:, j]

这给出了一个len(X)距离的数组.最接近质心j的50个索引是

This gives an array of len(X) distances. The indices of the 50 closest to centroid j are

ind = np.argsort(d)[::-1][:50]

最接近质心的50个点是

so the 50 points closest to the centroids are

X[ind]

(或如果您使用 argpartition 最近有足够的NumPy，因为速度要快得多.

(or use argpartition if you have a recent enough NumPy, because that's a lot faster).

这篇关于使用scikit-learn.k-means库输出最接近每个聚类中心的50个样本的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！