k-means Clustering
The k-means clustering algorithm is one of the most popular clustering techniques. It produces hard (an element can only be a member of one cluster), flat, and polythetic (membership is determined by similarity based on multiple attributes) clusters. The k-means algorithm has no training or testing data per se. It works by creating clusters around centroids. A centroid is an average cluster member; that is, the center of a cluster. k-means requires us to specify the number of clusters (k). It is important to note that the number of clusters specified greatly affects the performance of the k-means algorithm. Deciding on the number of clusters can be informed by domain knowledge. For example, knowing about the features of a given dataset will help to set parameters for clusters. In situations where this information is not available, there are two techniques we can use to help us decide on the correct number of clusters.
Exploratory Data Analysis Using Scatter Plots
In situations...
