The growclusters package for R implements an enhanced version of k-means clustering that allows discovery of local clusterings or partitions for a collection of data sets that each draw their cluster means from a single, global partition. The package contains functions to estimate a partition structure for multivariate data. Estimation is performed under a penalized optimization derived from Bayesian non-parametric formulations. This paper describes some of the functions and capabilities of the growclusters package, including the creation of R Shiny applications designed to visually illustrate the operation and functionality of the growclusters package.

翻译：R语言的growclusters包实现了一种增强版k-means聚类方法，该方法能够发现一组数据集的局部聚类或划分结构，其中每个数据集均从单一全局划分中抽取其聚类均值。该包包含用于估计多元数据划分结构的函数，其估计过程基于贝叶斯非参数公式推导出的惩罚优化框架进行。本文介绍了growclusters包的部分功能与特性，包括专为可视化展示该包操作流程与功能特性而设计的R Shiny应用程序开发。