From the course: Applied Machine Learning: Foundations
Unlock the full course today
Join today to access over 25,000 courses taught by industry experts.
Root mean squared
From the course: Applied Machine Learning: Foundations
Root mean squared
Let's talk about some other metrics that might be important. The Scikit-Learn, I keep saying this, but one of the reasons I like Scikit-Learn is that it has a consistent interface, and it has a module called metrics, and in that module are a bunch of different metrics that you can leverage. And they all have the same interface. So you can import these metrics and you can run them. A common metric for a regression model is mean squared error. So let's run this. This is a little bit different than the score method. With the score method, you pass in an x_test and a y_test. With the metrics functions that we're going to import here, you pass in a true y and the predictions from y. So what this is telling me is that our mean squared error, if you take all the errors of all of these test cases and you square them, you have this value right here. And it's kind of hard for me to tell what this is. It's like $14 billion squared. So confusing thing about this is that this is in terms of what…