This assessment involves writing a report that summarises a data science related investigation that you have
conducted on data that you have collected yourself. The investigation must involve the main topics covered in the
subject, most noticeably data pre-processing (representation, wrangling, tidying) and exploratory data
visualisation using R/RStudio.
It is a merger of all your learnings in this semester. These include all aspects of visualization, data processing
and wrangling. However the pre-processing/exploratory steps to be carried out will not be specified, you have to
make independent choices and decisions.
We have provided you with 4 datasets each with their readme files. The data and the descriptor files are stored in
the Capstone Data subfolder within the Assessment folder, in LearnJCU. You may also find your own data using
good practices. This could include data from the UC Irvine machine learning repository. Your dataset cannot be
smaller than 1000 observations of 5 variables, except if the targeted data science problem to be addressed relates
to spatial-temporal data, case in which less than 5 dimensions could be allowed.
Attachments:
5435618_1_Capstone-Project-MA1580.pdf
Leave a Reply