Summary

In this chapter, we converted a tab-separated and a pipe separated file into SQLite3. We performed a table join to combine ratings with movie genres because we have datasets that involve multiple tables, and sometimes that requires a table join. We performed a table join followed by a GROUP BY in order to study how movie ratings change with the age of the viewer. Finally, we performed KDE on individual movies and compared the two directly, despite the fact that they have different values in each dataset. So, that is the benefit of the kernel density estimator.