Polars Meetup #3 - Vectorized Parquet and Dataframely

On September 17, 2025, we organize our third meetup! This time we will be in Munich for an in-person event. The sessions will be recorded and shared afterwards.

We kick off our first meetup with a technical talk by Gijs a core developer at Polars, who will talk about improvements to the Parquet reader. Gijs discusses how Parquet works and how Polars deals with predicate filters and manages to perform vectorized reading. The talk covers where Parquet stands in Polars and where it will go from here.

The second talk is a community talk by Oliver and Daniel, who work as quantitative analyst and software engineer, respectively, at QuantCo. This second talk covers the migration of a pandas + SQL data pipeline that has been operated for several years to a modern Polars-based data pipeline enhanced by dataframely. They will share their experience with performance gains and improved developer experience, as well as how the combination of Polars and dataframely increased the pipeline’s correctness.

Event Schedule
• 18:00 – Doors open
• 18:45 – Talk #1: Vectorized Parquet reading in Polars – Gijs Burghoorn (Polars)
• 19:15 – Break
• 19:30 – Talk #2: Supercharging Data Pipelines with Polars and dataframely - Oliver Borchert (Quantco) and Daniel Elsner (Quantco)
• 20:00 – Drinks & Networking
• 22:00 – Event ends

Snacks and drinks will be available throughout the evening.
This event is organized in collaboration with our friends at Quantco.