The correct answer is D. attribute values may be either categorical or numeric.
K-means clustering is a method of vector quantization, originally from signal processing, that aims to partition n observations into k clusters in which each observation belongs to the cluster with the nearest mean, serving as a prototype of the cluster. This results in a partitioning of the data space into Voronoi cells.
The algorithm requires specifying k, the number of clusters to create. The algorithm then proceeds by initializing k cluster centers, typically chosen at random from the data set. Each observation is then assigned to the cluster with the nearest center. The cluster centers are then recomputed as the mean of the points in each cluster. This process is repeated until the cluster centers no longer change significantly.
K-means clustering is a simple and effective method for clustering data. It is often used in machine learning and data mining applications.
Option A is incorrect because the output attribute does not need to be categorical. The output attribute can be either categorical or numeric.
Option B is incorrect because all attribute values do not need to be categorical. Attribute values can be either categorical or numeric.
Option C is incorrect because all attributes do not need to be numeric. Attributes can be either categorical or numeric.