# Assignment Overview

*Note: this information as the same as the assignment pdf*

**Collaboration:** You may do your work individually or in pairs. You may collaborate with other students in the class on the right tools to use and setting up your programming environment but work on your own solution but be done by members of your group alone. Both members of the pair must sign up for a PairGroup in LEARN *and* in Crowdmark.

**Hand in:** One report per person or pair, via the CROWDMARK website in PDF, or image, format. You will need to divide the PDF up into one file for each `[CM#]` question. These files can be multiple pages. Some "questions" in this assignment have no output so no pdf if needed. It is best to start each of `[CM#]` solution on a new page and then drag and drop each onto the relevant question in Crowdmark. You should receive an invite to Crowdmark by email. Overlap and duplicated text between questions is alright, as long as the *entire answer* for each question fully contained within that question's pdf file. Also submit the code/scripts needed to reproduce your work as a python jupyter notebook to the LEARN dropbox.

**Specific objectives:**
-   Load the dataset and perform some data cleaning and exploratory plots to understand the dataset.

-   Study how to apply some of the methods discussed in class and gain experience on the use of classification algorithms: Naive Bayes, decision tree, random forests, XGBoost.

**Tools:** You can use libraries available in python. You need to mention which libraries you are using, any blogs or papers you used to figure out how to carry out your calculations.

## Kaggle Competition
You can use any method from the assignment to produce your answer submission. 
Data from five states *Washington, Tennessee, Iowa, Texas, Illinois* has been held out from the `train` set and will be used for testing your trained algorithms on Kaggle and is available on LEARN (or Kaggle) as `dkmacovidkaggletestfeatures.csv`. 

In this part of your report on Crowdmark you must ***enter your group name and url from kaggle***, so we can find your results. You can also report your results from your last submission to kaggle here. (We will see another score using held out data you do not have access to).