🎯 Applied Data Scientist / Data Analyst (Remote)
⚡ Energy & Power Systems domain background | 🐍 Python | 🔥 PySpark | 📊 Data Analysis | 🧱 ETL mindset

I'm building a portfolio focused on data-driven problem solving in the energy sector, combining analytics + machine learning + scalable processing with PySpark.
I’m currently interested in remote opportunities (USA & Canada) in Data Science / Data Analytics.

A PySpark + ML project using a public outage dataset (77k+ records) to:

• explore outage patterns
• classify outage event types with Random Forest
• predict outage duration with Linear Regression
• visualize results in a notebook workflow

➡️ Repo: OutagesUSA_1
🔗 https://github.com/dogeraldi05/OutagesUSA_1
2

A small collection of practical studies and utilities around:

• decorators
• retry strategies
• time measurement
• ETL-related patterns

➡️ Repo: etl-toolkit-test01
🔗 https://github.com/dogeraldi05/etl-toolkit-test01
3

• penguins_1 — first explorations using the Penguins dataset (EDA practice). 1
• repo_1_crops — notebooks and early experiments (Jupyter). 1
• read — learning repository based on Read the Docs tutorial template. 4
• github-slideshow — GitHub Learning Lab training repository. 5

• Python, PySpark, notebooks (Colab/Jupyter)
• Data analysis & visualization (EDA, metrics, charts)
• Basic ML workflows (classification/regression with Spark MLlib)
• ETL patterns and reliability practices (retry, timing, modular code)

✅ Remote roles in Data Analyst / Applied Data Scientist
✅ Strong interest in energy / utilities / climate / industrial analytics
✅ Teams that value domain knowledge + practical analytics

• LinkedIn: https://www.linkedin.com/in/douglas-geraldi/
• GitHub: https://github.com/dogeraldi05 ``