You are a Data Scientist. You are tasked with conducting some exploratory analysis. Your goal is to find “insights” in the data and present those findings to your colleagues.
1. Select, Clean and Wrangle a Dataset (or more)
2. Decide on a story (user story)
3. Using R, create three visualisations
4. Show previous iterations or alternatives
Report to include
Cover Sheet (1 page)
Title of your report
Introduction (1 page)
Problem, Audience, datasets
Pre-processing (1 to 2 pages)
Cleaning and wrangling
Visualisations (1 to 3 pages)
Include a paragraph per visualisation and previous Iterations or alternatives with rationale for changes
Appendices including your code with comments.
R file(s). Make sure your submission is self-contained, i.e. no external files or filename changes are required to run the code. All files required should be attached and installation of libraries included if needed, for example:
if(!require(somepackage)){ install.packages("somepackage") library(somepackage) }
Marking Rubric
1. Selet, Clean and Wrangle a Dataset – 5%
Dataset
One dataset 1%
Two or more datasets 2%
Cleaning of values (missing values, capitalization,standarize names,..)
No cleaning performed 0%
Some level of cleaning 0.5%
Extensive level of cleaning 1%
Wrangling
No wrangling 0%
Basic filtering 1%
Extensive wrangling, filters, calculated fields, groupings,... 2%
2. Decide on a story (user story) – 2%
Story
Basic description of the context 0.5%
Good description of the context 1%
Excellent story with clear questions 2%
3. Using R, create three visualisations 21%
Visualisations 1
Basic visualisation without special features 1%
Good visualisation with a clear message and framing of the question 5%
Excellent visualisation with extra features, clear message, framing of the question and correct focus 7%
4. Show previous iterations or alternatives 2 %
Previous Iterations
No previous iterations 0%
Small changes from previous iterations based on simple chart change 1%
Evidence of exploratory work as well as refinement of selected charts 2%
