Projects

Selected work in data science, statistics, and applied research

A selection of projects that reflect my interests in health data, reproducible research, and statistical modelling. Each project links to the relevant GitHub repository where code, data documentation, and writeup are available. For a full list, see my GitHub profile.

Tania Morales

WWI Soldier Records Data Curation

Large-scale data cleaning for the Argyll and Sutherland Highlanders Museum

WWI records project

Volunteer project with the Scottish Tech Army to clean and standardise historical military records. Worked with messy, inconsistent source data spanning multiple decades to produce a structured, queryable dataset for museum researchers.

Stack: Python, fuzzymatching, data standardisation, data validation