Clustering is an example of unsupervised learning as there is no prior knowledge of the groups present in the dataset. It is a method of dividing the dataset into different groups based on various parameters of the dataset. Each group is called a cluster, and the various objects present in a group will be share some similarities as well as dissimilarities when compared with the objects outside the group. We will cover the clustering algorithm in this section.
One of the greatest examples of the clustering algorithm would be the search engine; where the pages that are closely related to each other are shown together, and the pages that are different are kept away as far as possible. The most important factor here is the factor that we consider to measure the similarity or the dissimilarity between the objects.
In order to implement the clustering algorithms in R, we need to load the package fpc
into the R environment. The package fpc
, a flexible procedure for clustering...