I help clients turn messy data, documents, websites, spreadsheets, and research workflows into reliable pipelines, automated reporting systems, and decision-ready outputs.
My work combines practical data engineering, statistical rigor, applied machine learning, reproducible delivery, and maintainable implementation. Public examples include portfolio workflows for scraping, PDF/OCR extraction, workbook automation, AI-assisted review packets, and HF-EOLUS geospatial/ML pipelines.
- Data science and statistical analysis
- ETL and automated reporting pipelines
- Machine learning workflows
- AI agents and automation
- R and Python development
- Research data processing and reproducible analysis
- Cloud-based data workflows, especially on AWS
A significant part of my work is hosted in repositories owned by organizations, research groups, or project accounts. I use this profile to highlight the projects where I have been a creator, maintainer, or key contributor.
Repository: GOFUVI/hf-eolus-wind-resource-toolkit
Toolkit for computing wind resource estimates in the HF-EOLUS project.
Repository: GOFUVI/hf_eolus_sar_ingestion
Tools for ingesting Sentinel-1 Level-2 OCN OWI products into GeoParquet-based workflows.
Repository: GOFUVI/hf_eolus_wind_inversion
Toolkit for ANN-based wind inversion from HF-Radar data, including training and inference workflows.
Repository: GOFUVI/SeaSondeR
Open-source tools for processing SeaSonde HF-Radar data.
Repository: JLHC-AI-portfolio/CSV2PDF-portfolio-case-study
Representative portfolio case study showing a CSV-to-PDF automation workflow.
Repository: JLHC-AI-portfolio/community-workshop-listings-pipeline-c13d19ba
Representative portfolio case study showing a Python workflow that collects multiple websites' listings into one normalized catalog using Scrapy, Beautiful Soup, and Playwright.
Open outputs for the HF-EOLUS project are curated in the Zenodo community: https://zenodo.org/communities/hf-eolus/
It brings together datasets, software, reports, and technical documentation related to offshore wind estimation from HF radar.
I am especially interested in projects involving:
- data ingestion and transformation
- reproducible analytics
- survey/report automation
- scientific and research data
- ML model pipelines
- domain-specific AI assistants
- workflow automation for analysts and researchers
Languages
- R
- Python
- SQL
- Bash
- PHP
Data / ML / Analytics
- tidyverse
- pandas
- scikit-learn
- RMarkdown
- Jupyter
- statistical modeling
- machine learning pipelines
Cloud / Engineering
- AWS
- Docker
- GitHub Actions
- ETL workflows
- automation pipelines
Some of the repositories featured here are hosted under organization accounts rather than my personal account. They are included because they represent work I created, led, maintained, or substantially contributed to.
If you are looking for help with data science, analytics automation, or AI-enabled workflows, feel free to contact me through one of the profiles above.