Final individual project of CodeClan DR22 Professional Data Analysis Course.
For this a fictional brief was created to simulate a request from the Scottish Government to take a high-level look at cancer statistics in Scotland.
Brief (PDF).
The main analysis report combines four different analysis reports together into one document for convenience.
analysis/0_analysis_report_cancer_in_scotland.html
Lessons from death for life.
Remote presentation given at end of project to instructors and the rest of course cohort.
Contains several of the plots from the analysis.
Cancer in Scotland (PDF).
One project output is a prototype of an interactive tool to let the general public see cancer risk for different combinations of cancer type, age range and sex.
This is leveraging the longitudinal dataset that covers over two decades of Scottish cancer incidence health data from 1997 and 2021.
The tool runs in R as an R Shiny Interactive Document.
To run the tool locally using R Studio:
- clone this project
- in R Studio open the file
cancer_risk_tool/index.Rmd
- click "Run Document"
- Choose an "Age Range", "Sex", "Type of Cancer" and a "Number of Results" You should then see a table of how many incidences have been recorded.
Here's a screenshot of how it should look.
- Data
All the data required to regenerate the analysis reports should be available if you clone this repository. Report data is indata_clean
. If you need to recreate the project from scratch run the cleaning scripts in order incleaning_scripts
This project contains data from:
- National Records of Scotland,
© Crown Copyright 2023 - Public Health Scotland,
Contains public sector information licensed under the Open Government Licence v3.0.