In this chapter you’ll learn about the different pitfalls that one should be aware of and that you will encounter while building machine learning systems. You’ll also learn industry standard-efficient designs practiced to solve them.
Throughout this chapter, we’ll mostly be using a dataset from the UCI repository, “Pima Indian diabetes,” which has 768 records, 8 attributes, 2 classes, 268 (34.9%) positive results for diabetes test, and 500 (65.1%) negative results. All patients were females at least 21 years old of Pima Indian heritage. ...