Fine-Tuning an LLM to Predict the Rental Value of a Dwelling
Fine-tuning a large language model to predict a dwelling's rental points, treating the points score as a regression task.
+
- Position
- Senior Data Scientist, Woonstad Rotterdam
Articles · 2022 – 2025
24 articles in 5 publications.
Published writing, newest first.
2025
2 publishedCost-Efficient Cloud Gaming on Ultra Settings With Flexible Pay-as-You-Go Model
Cloud gaming on a GPU instance on AWS, paid for by the hour, including Windows games from a Mac with Apple Silicon.
+
- Secondary tools
- aws
2024
6 publishedHow to Setup Your Macbook for Data Science in 2025
The 2025 edition of the data-science MacBook setup: browser, apps, terminal, Python and AI tooling.
Wijzigingen in het beleidsboek huurcommissie WWS januari 2025 (onzelfstandig)
The Huurcommissie's January 2025 changes to its policy book for the rental-points system, for non-self-contained dwellings. Written in Dutch.
+
- Position
- Senior Data Scientist, Woonstad Rotterdam
- About
- woningwaardering
Wijzigingen in het beleidsboek huurcommissie WWS januari 2025 (zelfstandig)
The Huurcommissie's January 2025 changes to its policy book for the rental-points system, for self-contained dwellings. Written in Dutch.
+
- Position
- Senior Data Scientist, Woonstad Rotterdam
- About
- woningwaardering
We Built an Open-Source Data Quality Testframework for PySpark
How and why we built a data-quality test framework for PySpark, and what we learned releasing it as open source.
+
- Position
- Senior Data Scientist, Woonstad Rotterdam
Solving a Tennis Refactoring Challenge in Python using SOLID
Refactoring Emily Bache's Tennis kata step by step in Python, applying the SOLID principles.
+
- Secondary tools
- pytest
How to Setup Your Macbook for Data Science in 2024
Setting up a MacBook for data science work in 2024.
2023
10 publishedHow to Store Historical Data Much More Efficiently
Storing a table's history in as little as 0.01% of its rows without losing information, in PySpark.
+
- Position
- Data Scientist, Woonstad Rotterdam
Succeeding in Data Science: 4 Essential Skills You Didn't Learn in University
Four skills a data science job asks for that a university degree does not teach.
It's Finally Time to Say Goodbye to "git checkout"
Why git switch and git restore should replace the overloaded git checkout.
+
- Secondary tools
- git
6 Python Best Practices that Distinguish Senior Developers from Juniors
Six practices that make Python code read as written by an experienced developer.
Is the ChatGPT Plus subscription worth it? A developer's perspective
Whether ChatGPT Plus, and GPT-4 with it, is worth $20 a month to a developer as a coding assistant.
+
- Secondary tools
- chatgpt
How to Install Your Own Private GitHub Package on Streamlit Cloud
Deploying a Streamlit app that depends on a private GitHub package to Streamlit Cloud.
+
- Secondary tools
- streamlit
I Made ChatGPT Test Its Own Code.
An experiment in whether ChatGPT can write unbiased tests for code it wrote itself.
+
- Secondary tools
- chatgpt
How to Level Up Your Python Skills by Learning From These Professionals
Getting past junior level in Python by reading, and learning from, the code of professional projects.
5 Python Tricks That Distinguish Senior Developers From Juniors
Five Python idioms that mark experienced code, shown through Advent of Code puzzles.
It's a Mistake to Trust the Best Model of a GridSearchCV
Four cases in which the best model a GridSearchCV reports is not the best model to use.
+
- Position
- Machine Learning Engineer, Xccelerated
- Secondary tools
- scikit-learn, pandas
2022
6 publishedSignificantly Increase Your Grid-Search Results With These Parameters
Grid-searching over whole pipeline steps, not only their parameters, with the EstimatorSwitch from extra-datascience-tools.
+
- Position
- Machine Learning Engineer, Xccelerated
- Secondary tools
- scikit-learn, feature-engine, pandas
A highly anticipated Time Series Cross-validator is finally here
Introduces GroupTimeSeriesSplit, the scikit-lego cross-validator for grouped time series whose groups hold unequal numbers of observations.
+
- Position
- Machine Learning Engineer, Xccelerated
- Secondary tools
- scikit-learn, scikit-lego
- About
- GroupTimeSeriesSplit
How to extract more information from categorical plots
Two ways to get more out of a categorical plot — counts beside the x-axis labels, and a strip plot laid over a box plot — both from extra-datascience-tools.
+
- Position
- Machine Learning Engineer, Xccelerated
- Secondary tools
- pandas, matplotlib, seaborn
The latest tool to help you spend less time on debugging
A decorator from extra-datascience-tools that logs a function's arguments and running time, set against the icecream debugging library.
+
- Position
- Machine Learning Engineer, Xccelerated
- Secondary tools
- icecream
How to start any professional Python Package project.
Setting up a Python package project with automated tests, documentation on Read the Docs and publishing to PyPI from the first commit.
+
- Position
- Machine Learning Engineer, Xccelerated
- Secondary tools
- poetry, pyenv, pytest, github-actions, sphinx, black, isort
AdvancedValueCounts: a new method to explore categorical variables
Introduces AdvancedValueCounts, a package that extends pandas' value_counts() for exploring categorical variables.
+
- Secondary tools
- pandas, matplotlib, seaborn