K-means Clustering Clearly explained

With video explanation | Data Series | Episode 8.1

We have taken a look at linear and logistic regression and how to implement both algorithms in Python. These algorithms are examples of supervised machine learning algorithms since they take a final value output. We will now go on to look at our first unsupervised machine learning algorithm for this series.

What is K-means clustering?

K-means clustering is an unsupervised machine learning algorithm, where its job is to find clusters within data. We can then use these clusters identified by the algorithm to make predictions for which group or cluster a new observation belongs to.

Overview

Imagine we recorded some data and made a scatter plot:

The job of K-means clustering is to identify clusters or groups within the data: