Vincent D Warmerdam
where else to find them
website:https://koaning.io
github:koaning
bluesky:koaning.bsky.social
linkedin:vincentwarmerdam
devto:koaning
what they talk about
all 6 in the filters
where they keep going back
- PyData Eindhoven6 editions2019–2024
- PyData Amsterdam4 editions2016–2025
- PyData London4 editions2016–2019
all 6 in the filters
on a stage with
- Fokko Driesprongonce
who talks about the same things
- Ian Ozsvald17 talks
- Marysia Winkels9 talks
- James Powell43 talks
- Katharine Jarmul25 talks
- Tess Ferrandez-Norlander24 talks
- Aileen Nielsen7 talks
| title | conference | date |
|---|---|---|
| Untitled13.ipynb | PyData Amsterdam 2025 | 2025-09-24 |
Shows a practical rethinking of notebooks: code cells become reactive DAG nodes with immutable globals, updates propagate automatically, and deletion triggers… | ||
| Run a benchmark they said. It will be fun they said. | PyData Amsterdam 2024 | 2024-09-18 |
www.pydata.org
This is the story of a fun idea that turned into a huge benchmark before it turned into a rabbit hole.
I was trying to figure out reasonable… | ||
| Scikit-Learn can do THAT?! | PyData Eindhoven 2024 | 2024-07-11 |
Shows concrete capabilities and results: scikit-learn implements pipeline caching that can halve grid‑search time on a single machine, supports sparse inputs… | ||
| Active Teaching, Human Learning | PyData Eindhoven 2023 | 2023-11-30 |
Empirical claim: active learning often helps but sometimes hurts depending on number of classes, tiny random starts, or huge batch sizes; synthetic… | ||
| Bulk Labelling Techniques | PyData Eindhoven 2022 | 2022-12-01 |
Claim: few‑shot embedding selection reaches ~74% accuracy with four seed sentences using KNN while a bag‑of‑words model needs about 500 labeled examples to… | ||
| Optimal on Paper, Broken in Reality | PyData Eindhoven 2021 | 2021-11-12 |
Shows a concrete method to temper optimistic benchmarks by plotting accuracy versus training size and exposing how grid-search numbers hide sample-size… | ||
| Playing by the Rules-Based-Systems | PyData Eindhoven 2020 | 2020-10-07 |
Rule-based patterns in spacey produce labeled examples that train a machine learning model and reveal concrete differences: the ML model shows higher precision… | ||
| Untitled12.ipynb | PyData Eindhoven 2019 | 2019-11-16 |
Live demo shows messy notebooks turning into a reproducible pipeline by turning cleaning, feature engineering and aggregation into small functions and chaining… | ||
| How to Constrain Artificial Stupidity | PyData London 2019 | 2019-07-12 |
Claims that adding constraints cuts “artificial stupidity”: predict less (add a do not predict threshold and outlier check via a Gaussian mixture model)… | ||
| The profession of solving (the wrong problem) | PyData Amsterdam 2019 | 2019-05-10 |
Concrete outcomes and methods: a classroom regression gives an A+ but misses capacity limits; a recommender stack built with a database, cron/Airflow and A/A… | ||
| Winning with Simple, even Linear, Models | PyData London 2018 | 2018-04-26 |
Claims that linear models beat complex ones when you apply concrete tricks: add an interaction to solve XOR, use radial basis seasonal features and exponential… | ||
| Using Queryable State to update ML Algorithms per datapoint for... | Flink Forward Berlin 2017 | 2017-09-11 |
A streaming matchmaking pipeline built on Apache Flink uses Queryable State to hold per-player Bayesian histograms and updates skill estimates per game event… | ||
| TNaaS - Tech Names as a Service | PyData Berlin 2017 | 2017-06-23 |
A web service generates Pokemon‑like names and actually runs at https://dyccxmwpz9.execute-api.eu-west-1.amazonaws.com/pokemon/poke-names/v2 with the domain… | ||
| SaaaS - Sampling as an Algorithm Service | PyData London 2017 | 2017-05-05 |
Explains that sampling recovers posteriors by building a naked for loop MCMC sampler in Python, then swaps to PyMC3 for speed and applies it to a Santa Kaggle… | ||
| The Duct Tape of Heroes Bayesian statistics | PyData London 2016 | 2016-05-06 |
Many concrete examples and code replace theory with results: a disease-test calculation that compares one versus multiple tests, a censored-exponential… | ||
| The Duct Tape of Heroes: Bayes Rule | PyData Amsterdam 2016 | 2016-03-12 |
Shows concrete claims and demos: uses pomegranate probabilistic programming, builds Bayesian probabilistic graphs for disease testing, model selection, feature… | ||
| PySpark and Warcraft Data | EuroPython 2015 | 2015-07-20 |
Uses PySpark with distributed DataFrame to process a 22Gb json blob of World of Warcraft auction snapshots, provisioning short‑lived EC2 clusters and comparing… | ||
| Visualising Data through Pandas | PyData Berlin 2014 | 2014-07-25 |
Demo shows pandas data frame as the main in‑memory workhorse, using IPython notebooks to load CSVs, resample time series, and run groupby split apply combine… | ||
| nothing matches | ||