A collection of my open-sourced Data Science projects
A brief description of current projects:
- PhD thesis (see image below): Supervised machine learning analysis of neutron scattering data collected from magnetic skyrmion materials at the nuclear reactor at ANSTO.
- SANS-data: Sample Matlab and Python scripts to read, preprocess and extract data from neutron scattering data collected at ANSTO and stored in DAT and HDF data formats. This may be considered as supplementary material for my PhD thesis (published under the CC BY 4.0 License)
- HTRU2: R project that trains and tests Classification algorithms for astrophysics purposes using public data
- PDF-scraping: R-shiny dashboard made with plotly & pdftools. It downloads a PDF report from the United Nations website, scraps data, and feeds the plots. A dockerized version of this app can be tested here
- Scraping-text-analysis: Python Jupyter notebook for web scraping of text to retrieve a large book. Implements text cleaning for the Spanish language
- Superconductivity: Python Jupyter notebook that trains and tests Regression algorithms to predict the superconducting temperature of a material based on public data
You may find detailed comments within each project files.
Let us finish with a bit of science, this is a Neutron Scattering Pattern acquired during my PhD thesis: