The HPCLUS Procedure

The k-means algorithm works only with numeric data sets. One way to apply the k-means algorithm to nominal data is to use data transformation methods to transform the nominal data into a new feature space. However, this approach can be very inefficient, and it does not produce good results. For clustering nominal data sets, the HPCLUS procedure implements the k-modes clustering algorithm, which extends the k-means algorithm by using different dissimilarity measures and a different method for computing cluster centers (Huang 1997).