How do you run K-means clustering in R and specify the number of clusters?

Conditions

• Requires a numeric dataset.
• Requires specifying the number of clusters (centers).

Reasoning, step by step

1. Load the dataset into R.
2. Call the kmeans() function.
3. Pass the data as the first argument.
4. Set the centers argument to the desired number of clusters.
5. Store the result in a variable.

Example

The video shows the code: kmeans_iris_result <- kmeans(iris_data, centers = 3), which partitions the iris_data into three clusters.

Common misconceptions

• Forgetting to set the centers argument.
• Assuming the kmeans function returns only the cluster assignments without the centers.

Watch the explanation

Explore next

• What information is contained in the object returned by the R kmeans function?
• How can you visualize K-means clusters and their centers using a scatter plot in R?
• Why is it important to set a random seed before running kmeans in R?