Hey guys, welcome back. In this video, I will present exercise one of section three on machine learning. This exercise is the first of a few ones where we do a little bit of role playing. And we suggest that you've just been hired at a real estate investment firm where they are asking you to build a model to price houses. So we will have to load the data set where there is information about a set of houses, including the number of bedrooms, the size in square feet, the age of the house, and so on. And you have to build a model, so a regression model, that predicts the price. You're guided through nine different steps from loading the data set, plotting the histogram, which by now you should be familiar with. 

Then you have to create two variables called X and Y. X is a matrix with three columns, the square feet, the bedrooms, and the age. And Y is a single column that contains the price. So X is the input, Y is the target. Then create a linear regression model in Keras with the appropriate number of inputs and outputs. Split the data into train and test with a 20% test size. And train the model on the training set checking the accuracy on the test set. Also check the accuracy on the training set so that you can compare the test and the training set accuracy and see if you're doing well or not. Fact, question seven is about how is your model doing and is the loss growing smaller? And then you can try to improve the model with a few experiments, normalizing the features, use a different value for the learning rate, use a different optimizer. 

And we're well aware that at this point in the course, you don't know yet exactly what the learning rate and the optimizer are. We will see them in detail in section five. But you already can experiment and see what happens if you change them. So to form an intuition about their role. Once you're satisfied, check R2score on the test set. So this is exercise one. As usual, try to do it first and then feel free to watch the solution in the next video. Good luck.