Introduction to k-means clustering

Unsupervised Learning in R

Hank Roark

Senior Data Scientist at Boeing

k-means clustering algorithm

First of two clustering algorithms covered in this course
Breaks observations into pre-defined number of clusters

two groups

k-means in R

# k-means algorithm with 5 centers, run 20 times
kmeans(x, centers = 5, nstart = 20)

One observation per row, one feature per column
k-means has a random component
Run algorithm multiple times to improve odds of the best model

First exercises

First exercise uses synthetic data
Synthetic data generated from 3 subgroups
Selecting the best number of subgroups for k-means
Example with more fun data later in the chapter

Let's practice!

Unsupervised Learning in R

Preparing Video For Download...