运行k-means（mllib spark scala）之后，我想了解我从使用（和其他变换器）mllib的OneHotEncoder预处理的数据中获得的聚类中心。
中心看起来像这样：
Cluster Center 0 [0.3496378699559276,0.05482645034473324,111.6962521358467,1.770525792286160.0,0.0,08561916265130964,0.014382183950365071,0.0,0.0,0.0,0.47699722692567864,0.0,0.0,0.0,0.04988557988346689,0.0,0.0,0.0,0.8981811028926263,0.9695107580117296,0.0,0.0 ，1.7505886931570156,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0 ，0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0 ，0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0,0.0 ，0.0,0.0,0.0,0.0,0.0,17.771620072281845,0.0,0.0,0.0,0.0]
这显然不是非常人性化...有关如何恢复单热编码并检索原始分类功能的任何想法？ 如果我找到最接近的数据点（使用k-means使用的相同距离度量，我假设是欧几里德距离）到质心然后恢复该特定数据点的编码会怎么样？
答案 0 :(得分：1)
对于群集质心，不可能（强烈建议）反转编码。想象一下，你有6个原始特征“3”，它被编码为[0.0,0.0,1.0,0.0,0.0,0.0]。在这种情况下，很容易从编码中提取3作为正确的特征。
但是在kmeans应用程序之后，您可能会得到一个群集质心，可以查找此功能，如[0.0,0.13,0.0,0.77,0.1,0.0]。如果你想将它解码回你以前的表示，比如6中的“4”，因为功能4具有最大值，那么你将丢失信息并且模型可能会被破坏。
编辑：添加一种可能的方法将数据点上的编码从评论恢复到答案
如果在数据点上有ID，则可以在编码之前将数据点分配给群集以获取旧状态后对ID执行选择/加入操作。