Data Science Projects


Rugby Heatmap Generator

  • Tools: Python, Flask, JavaScript, Azure, Git, HTML/CSS, Matplotlib, Seaborn, Google Maps API
  • Skills: Manipulating geospatial data, manipulating user-input data, data visualisation
  • Task: Taking GPX/TCX data and creating heatmaps on a user-defined rugby pitch

    • Sentiment Analysis of Goodreads Reviews

  • Tools: Python, BeautifulSoup, Pandas, NTLK/spaCy, sklearn
  • Skills: Web scraping, dataset creation, data cleaning, text preprocessing, sentiment analysis, logistic regressions
  • Task: Scraping Goodreads for a dataset of reviews and conducting sentiment analysis

    • The Women's Six Nations, 2007-2022

  • Tools: Excel, Tableau
  • Skills: Dataset creation, data cleaning, data visualisation and presentation
  • Task: Compiling and presenting an original dataset of match data and attendances from the Women's Six Nations

    • IN PROGRESS: San Francisco Bike Sharing

  • Tools: SQL/SQLite, Python
  • Skills: Exploratory analysis, time series prediction
  • Task: Exploring a dataset of journeys from San Francisco's public bikes (2013-15) and predicting journey numbers (Github Link)

    • MPhil Research: Classifying Insincerity in Empathetic Speech

  • Tools: Praat, Python, Jupyter Notebooks, Excel, JASP/SPSS
  • Skills: Experimental design, speech data collection, inferential analysis, kNN classification, academic writing
  • Task: MPhil by Thesis experiments and writing to find new ways of modelling insincerity in speech