Tomas Van Pottelbergh
Data Scientist
Summary
🤩
RockstarTomas Van Pottelbergh is a data scientist with four years of hands-on experience applying probabilistic filtering and time-series forecasting techniques. He has contributed to the popular open-source Darts library, improving Gaussian Process and Kalman filter examples, adding tests, handling missing values, and fixing datetime and documentation issues. Comfortable bridging research-grade methods and production-ready code, Tomas focuses on robustness and reproducibility in time-series pipelines. Based in Belgium, he combines attention to detail with a pragmatic approach to debugging and refactoring. Colleagues value his ability to make complex statistical tools more accessible through clear examples and better documentation.
4 years of coding experience
Github Skills (12)
forecasting10
jupyter-notebook10
machine-learning10
forecast10
time-series10
python10
data-science10
gaussian-processes10
kalman-filter9
anomaly-detection9
scikit8
scikit-learn8
Programming languages (9)
Github contributions (5)
unit8co/darts
Jul 2021 - Aug 2022
A python library for user-friendly forecasting and anomaly detection on time series.
Role in this project:
Data Scientist
Data ScientistContributions:41 reviews, 99 commits, 46 PRs in 1 year 1 month
Contributions summary:Tomas made several contributions focused on improving the Gaussian Process filter and Kalman filter examples within the Darts library. They added and modified example notebooks, including enhancements to the Kalman filter and Gaussian Process filter implementations, including adding tests, and handling missing values. Further work involved fixing documentation issues, fixing datetime conversion, and refactoring code to improve formatting.
forecastingpython-libraryanomalypythontime-series-analysis
tomasvanpottelbergh/kedro-azureml
Sep 2022 - Nov 2023
Kedro plugin to support running workflows on Microsoft Azure ML Pipelines
Contributions:6 reviews, 59 pushes, 12 branches in 1 year 3 months
kedro-pluginml-pipelinesazure-mlmlopskedro
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.