Code cell # %% [code] # import the libraries Text cell # %% [markdown] # Assignment 2 - Classification For this assignment, you'll need to perform a classification on a dataset, as well as do some prep work on the data. The exact steps of what you need to do are flexible and up to you to some degree, however you should consider some of the important things we've mentioned recently, such as:

• Is the target balanced?
• Are there missing or erroneous values?
• Are there categorical or numerical features?
• Is there colinearity?
• Are there outliers?
• Should we normalize?
• Do the distributions of the features give any indication that some may need work?

Basically, the data is in the original, potentially dirty, format, and you need to find what should be cleaned, and do the cleaning. There is not one "right" answer to what has to be done, and you'll probably need to do it with at least something of an iterative process - find an issue, correct it, check the data, repeat. The target that we are predicting is the loan_status. ## Grading The grades will be broken down as follows:

• 30% - a working predictive model with a reasonable level of accuracy.
  • For the accuracy part, it will not be explicitly graded, but compared to all the others. If you're in the same general range, that's good - if yours is drastically less accurate (or, I guess more accurate), then I'll adjust.