In this chapter, we saw some interesting machine learning techniques. We covered one of the fundamental concepts behind machine learning called train/test. We saw how to use train/test to try to find the right degree polynomial to fit a given set of data. We then analyzed the difference between supervised and unsupervised machine learning.

We saw how to implement a spam classifier and enable it to determine whether an email is spam or not using the Naive Bayes technique. We talked about k-means clustering, an unsupervised learning technique, which helps group data into clusters. We also looked at an example using scikit-learn which clustered people based on their income and age.

We then went on to look at the concept of entropy and how to measure it. We walked through the concept of decision trees and how, given a set of training data, you can actually get Python to generate a flowchart for you to actually make a decision. We also built a system that automatically filters out resumes based on the information in them and predicts the hiring decision of a person.

We learned along the way the concept of ensemble learning, and we concluded by talking about support vector machines, which is a very advanced way of clustering or classifying higher dimensional data. We then moved on to use SVM to cluster people using scikit-learn. In the next chapter, we'll talk about recommender systems.