Partitional Clustering

partitional Clustering

Partitional clustering is a widely employed technique in industry mainly due to its simplicity. Its primary function is to partition data into distinct, non-overlapping clusters based on their similarities. This means that each data point is assigned to exactly one cluster, and every cluster must contain at least one data point.

Some of the commonly used methods in partitional clustering include:

K-Means
K-Medoid (Partition Around Medoid [PAM])
Clustering Large Applications (CLARA)

Pros:

Easy to use and implement
Efficient and Scalable

Cons:

It is sensitive to initial centroids and outliers
Requires pre defined number of clusters

Example of Partitional Clustering

Overview

Hierarchical Clustering

Density Based Clustering

Distance Measures

Page updated

Google Sites

Report abuse