Summary

In this chapter, we reviewed and analyzed the medical data of 303 patients and linked the features with the diagnosis of heart disease. We checked for outliers and created different visualizations depending on the type of feature we were analyzing. Additionally, we created plots with three features each to understand the relationships between all three. We also created new features from existing features to visualize trends between the presence of heart disease and age and cholesterol.

In the next chapter, we will apply similar data analysis techniques (such as searching for missing values and outliers, creating visualizations, and so on) to a dataset from the retail industry. We will also deal with missing values and outliers, rather than just leaving them be, as we did in this chapter.