Scaling Python with Dask
Dask is a general purpose, lightweight parallel computing system in Python. It offers a far range of applications from task scheduling for workflow engines like Apache Airflow or Prefect up to complex distributed computing algorithms to parallelize the PyData scientific computing stack including numpy, pandas, scikit-learn and much more.
This talk will give a general introduction to dask and the dask.distributed task scheduler. After attending you should know why and how to use dask and how to scale out your computation for handling big data.
About the speaker
Open Source Software Engineer, Coiled
Florian is an Open Source Software engineer at Coiled. In his current position he is responsible for the maintenance and development of the dask scheduler.