All code written at Oxford INET internship in Summer 2019.
At this internship, I worked on two projects.
tech_progress - involved sourcing, cleaning, processing and visualising data on a selection of technologies, specifically on their progress over time. Metrics of progress had to be located amongst the Innovation Studies literature. A final report was then produced for Doyne Farmer.
patents - involved processing a Google Patents Dataset, which contained patent titles primarily. The goal of this project was to investigate whether simple NLP techniques could correct spelling mistakes within the dataset, which was created via OCR techniques at Google. If so, it was theorised that tracking the evolution of the patent titles corpus over time could yield interesting insights for academic Innovation Studies work at INET. A final report was also produced for this project.
Figures - A selection of figures created for each of the reports. Some were excluded from the final document.