SciPy的的集群实施工作，他们也有一个 K-均值一>的实施。

Scipy's clustering implementations work well, and they include a k-means implementation.

还有 SciPy的集群，这确实会凝聚的聚集;的部份有一个你不需要决定簇提前的数量优势。

There's also scipy-cluster, which does agglomerative clustering; ths has the advantage that you don't need to decide on the number of clusters ahead of time.