1. Wrap-up and review
Congratulations! You have completed the final case study chapter and the course on unsupervised learning in R. I imagine you are ready to be done, so let's quickly wrap up.
2. Case study wrap-up
This last chapter presented an entire data analysis using unsupervised learning, from beginning to end. With the knowledge of how to gather and explore a data set, and a creative approach to modeling using unsupervised learning you are prepared to tackle real world problems.
3. Types of clustering
During this course you have learned how to perform kmeans and hierarchical clustering using R, resulting in finding homogeneous subgroups within a population.
4. Dimensionality reduction
You've learned to decrease the dimensions of data while maintaining maximum data variability using principal components analysis.
5. Model selection
Also, you've seen how to deal with challenges you are likely to experience in your work, such as variable and model selection,
6. Interpreting PCA results
interpreting the results of your modeling,
7. Importance of scaling data
and the importance of scaling and centering your data.
8. Course review
All of this has been done using only a few methods and constructs in the R system, demonstrating some of its known strengths for data analysis work.
9. Dendrogram
Also, you have gained intuition about how each of the algorithms works internally,
10. Strengths and weaknesses of each algorithm
the technical strengths and weakness of each algorithm, and how and when to do model selection.
11. Course review
Finally, you completed an example use case from beginning to end.
12. Hone your skills!
I hope you've enjoyed learning about unsupervised learning in R. The best way to hone your skills is to practice applying them to interesting real-world datasets that you're motivated to explore. Thanks!