Tutorial
2026 workshop program
LSDB - A Tool for Scalable Analysis
The work
Abstract
Our goal will be to run a cross-matching workflow and stream data into a machine learning pipeline (bring your own AI model/framework). We’ll start with LSDB basics: lazy evaluation, Dask cluster setup for parallel processing, column selection, and spatial filtering. Next, we’ll cover basic data manipulation: filtering rows and creating new columns. Finally, we’ll see how to perform cross-matching and stream the results.
Requirements: GitHub Repo