DataCluedo is a hands-on activity session where you have the opportunity to actually apply data science concepts learnt in lecture!! It is also an exercise session in preparation for the ADA final exam. We developed it with two goals in mind:
- as a self-assessment tool for students, to they can understand their readiness for the fast-paced data analysis required during the final exam
- as a way for the teaching team to design a better-suited final exam, based on the statistics and performance gathered from DataCluedo
As such, working on DataCluedo is not mandatory, but it is nevertheless strongly recommended :) Also, your performance on DataCluedo will not count towards your final ADA grade.
What is DataCluedo?
DataCluedo is a small collection of iPython Notebooks, where the data scientist faces seemingly trivial analysis tasks. Most of the analysis is already included in the notebook, so the main effort goes towards reading carefully the instructions, and writing no more than a handful lines of code per notebook. Each notebook is split in 2 sections:
- an initial set of pre-filled cells, that the data scientist should evaluate just to load the needed variables and modules in memory
- a closing section where the data scientist can perform required analyses, and generate insights about the data
This repository contains eight main branches:
one, for students who are assigned to grouping 1
two, for students who are assigned to grouping 2
three, for students who are assigned to grouping 3
four, for students who are assigned to grouping 4
five, for students who are assigned to grouping 5
six, for students who are assigned to grouping 6
seven, for students who are assigned to grouping 7
eight, for students who are assigned to grouping 8
plus the master branch which contains this README.md file. Select one of the eight branches, and begin to solve each notebook following the ordering of the filenames (from Q1 to Q4).
Your sequence of solving the workbooks should be the following:
Please strictly follow this order!!
Depending on how you use
git (i.e., command line, GUI tool, etc.), there are multiple ways to switch branches. You can always clone a specific branch with the following command:
git clone <url of repo> -b <branch name to be cloned> e.g., git clone https://github.com/epfl-ada/DataCluedo.git -b two
Submit your solutions
Once you are done with solving all the 4 workbooks, you can
- upload and submit your solutions using this form