Different Methods of Clustering

k-means is a useful clustering algorithm because it is simple, widely applicable, and scales very well to large datasets. However, it is not the only clustering algorithm available. Each clustering algorithm has its own strengths and weaknesses, so it’s often worth having more than one in your toolkit. We’ll look at some of the other popular clustering algorithms in this section.

Mean-Shift Clustering

Mean-shift clustering is an interesting algorithm in contrast to the k-means algorithm because unlike k-means, it does not require you to specify the number of clusters. Mean-shift clustering works by starting at each data point and shifting the data points toward the area of greatest density. When all of the data points have found their local density peak, the algorithm is complete. This tends to be computationally expensive, so this method does not scale well to large datasets (k-means clustering, on the other hand, scales very well). The following diagram illustrates...