K-means算法是很典型的基于距离的聚类算法，采用距离作为相似性的评价指标，即认为两个对象的距离越近，其相似度就越大。这是一本介绍K-means算法的英文书籍 -K-means algorithm is very typical distance-based clustering algorithm, using distance as the similarity evaluation, that the closer the two objects, the greater the s