In this chapter, we have learned how to explore data (with some awkwardness) using Go. We plotted some charts and used them as a guiding rod to select variables for the regression. Following that, we implemented a regression model that came with reporting of errors which enabled us to compare models. Lastly, to ensure we were not over fitting, we used a RMSE score to cross-validate our model and came out with a fairly decent score.
This is just a taste of what is to come. The ideas in abstract are repeated over the next chapters—we will be cleaning data, then writing the machine learning model, which will be cross-validated. The only difference will generally be the data, and the models.
In the next chapter, we'll learn a simple way to determine if an email is spam or not.
