Hey guys, welcome back. In this video, we'll review exercise one of section four. In exercise one of section four, we're asked to predict whether or not some people will be diagnosed diabetes from a set of variables of exams. So this is the population of Pima Indians. It's a very famous dataset that we got from UCI and it contains information about the patients including pregnancies, glucose, blood pressure, and then a few other medical examinations, and the last column is the outcome which is a binary variable. 

So it's a classification problem, and you're guided through a series of steps that go from loading the data, creating a histogram to inspect the features, and exploring the correlations between the features and the outcome column. We suggest using the seaborn pairplot, but you can also draw a heat map as we saw in the lecture. Then there are a few open questions. Do features need standardization? And if so, what kind? Are we gonna use MinMax or standard? And then finally, prepare x and y using a machine learning model. Do you need dummy columns? And make sure you define your target variable. So as usual, try to do the exercise first, and then feel free to watch the video with the solution. Good luck.

Please note: the Pima Indians Diabetes dataset can be found at this GitHub repository.