🎯 Transitioning into Machine Learning / MLOps — I build small, reproducible projects using Python, SQL, and simple cloud tooling.
- Bikeshare Analysis (Python) — CLI analysis with tiny sample data, tests, and CI (continuous integration).
- Finding Donors — In Progress (notebook) — Udacity ML project; working locally in
starter/finding_donors.ipynb. Portfolio polish/CI will follow after completion. - Dog Breed (PyTorch) — CLI to evaluate pretrained models on pet images; prints per-model accuracy and writes results.csv in one command.
- Reproducibility: every repo runs from a clean clone
- Plain language: define any acronym the first time
- Evidence: tests, CI badges, and small sample data
FastAPI • Docker • SQL (DuckDB/Postgres) • MLflow • Prefect
- LinkedIn: https://www.linkedin.com/in/andigles
Thanks for visiting — feedback and issues welcome!