This repository contains the final exam for Applied Data Analysis (CS-401).

The questions are contained in the Jupyter Notebook named "final_exam.ipynb". The "data/" folder contains the data, while the "helpers/" folder contains various utilities you will use during the exam.

Wednesday, January 30th, 2019; 11:15 A.M. (Swiss time)

For the deadline for extramural exams, see the submission subsection.

• Don't forget to add a textual description of your thought process, the assumptions you made, and your results!
• Please write all your comments in English, and use meaningful variable names in your code.
• As we have seen during the semester, data science is all about multiple iterations on the same dataset. Do not obsess over small details in the beginning, and try to complete as many tasks as possible during the first 2 hours. Then, go back to the obtained results, write meaningful comments, and debug your code if you have found any glaring mistake.
• Fully read the instructions for each question before starting to solve it to avoid misunderstandings, and remember to save your notebook often!
• The exam contains 15 questions organised into 4 tasks, and is designed for more than 3 hours. You do not need to solve everything in order to get a 6, and you have some freedom is choosing the tasks you wish to solve.
• You cannot leave the room in the first and last 15 minutes.
• You can use all the online resources you want except for communication tools (emails, web chats, forums, phone, etc.). We will be monitoring the network for unusual activity.
• Remember, this is not a homework assignment -- no teamwork allowed!

• Your file has to be named as "NameSurname_SCIPER.ipynb".
• Make sure you upload your Jupyter Notebook (1 file) to this Google form at the end of the exam, with all the cells already evaluated (except for the Spark-related question, Q7). You need to sign in to Google using your EPFL credentials in order to submit the form.
• In case of problems with the form, send your Jupyter Notebook (along with your name and SCIPER number) as a direct message to @ramtin on Mattermost. This is reserved only for those who encounter problems with the submission -- you need to have a reasonable justification for using this back-up.
• You will have until 11:20 (strict deadline) to turn in your submission. Late submissions will not be accepted. This deadline is for the students taking the exam at EPFL -- students taking the exam extramurally will have their submission deadline as the starting time of the exam plus 3 hours and 5 minutes.