Hello! So, we've broken the greater enrollment problem into a smaller one that just looks at the past 5 years worth of transcripts and sees if it can use that information to predict whether or not a student will take a specific class in the next quarter. I have a function that converts a "transcript" into a bit vector - 1 if the class has been taken and 0 if the class has not been taken. Each vector is ordered exactly the same and each vector is followed by True or False indicating whether or not (in the next quarter) they took the class we're interested in (can easily be turned to 0 or 1). I'm just wondering how I would use logistic regression (scikit-learn) to approach this problem, I'm a little stuck/lost. Also if there are any things you would change or want to clarify, ask away. Thanks!
[link][1 comment]