[MUSIC] We've built a simple model just relating
square feet of living space to price of houses and then we explored some
other features like zip codes, and it's clear the zip codes make a big
difference and there's other features, bedrooms, that also
makes a big difference. The question is can we get a better model
by including more features, more of these? And so let's look at that. So we're gonna do here is build a regression model with more features. So this is using this bigger
feature set that we just described. So the first one I called the sqft_model. Let's call this the my_features_model. So the my_features_model is again going to
take graphlab.linear regression.create. So we're gonna create it and
we're gonna use the training data, just like we did before. Our target is again going to be the price,
just like before. However, the features here that I'm
gonna use are going to be those features that are called my
features which I created earlier. So let's go and execute this. So now I use more features and it's
straining and I think it's done it's done. Using those, I forget how many,
eight features. I use, let's just print them out here,
print my_features. So I use bedrooms, bathrooms, square foot of living,
square foot of lot, floors and zip code. Now we have two models. We have the sqft_model and
we have my_features_model. How do they compare in
terms of performance? So here's what I'm going to do. I'm going to print
the sqft_model.evaluate, evaluate all my test data. And I'm also going to print the my_features_model.evaluate
on the same test data. And let's compare,
let's see what happened. Okay, so to start with, we saw that the biggest error in the
simple square foot model was $4 million. Now it's down to $3.4 million,
49, so 3.5 million. So it went down a bit. And root mean squared error,
the average error, went down from $255,000 as we
had over here to a $179,000. Now, if you add more and more features,
your area is likely going to decrease quite a bit more because there's
quite a bit of data here and there's lots that you can learn. But again, just adding some extra features
already helped us with our performance. [MUSIC]