High-Performance Data Analytics with Python - Day 1
About this course
This three half-day online workshop is meant to give an overview of working with research data in Python using general libraries for storing, processing, analyzing and sharing data. This course mainly covers episodes including scientific data format, efficient array computing, parallel computing, code benchmarking and profiling, code optimization, perforance boosting, and dask for scalable analytics.
After attending the workshop, you should: 1) Have a good overview of available tools and libraries for improving performance in Python; 2) Know what libraries are available for efficiently storing, reading and writing large data; 3) Be comfortable working with NumPy arrays and Pandas dataframes; 4) Be able to explain why Python code is often slow; 5) Understand the concept of vectorisation; 6) Understand the importance of measuring performance and profiling code before optimizing; 7) Be able to describe the difference between “embarrasing”, shared-memory and distributed-memory parallelism; 8) Know the basics of parallel workflows, multiprocessing, multithreading and MPI; 9) Understand pre-compilation and know basic usage of Numba and Cython; , and 10) Have a mental model of how Dask achieves parallelism.
Follow these recording using the lesson material here https://enccs.github.io/hpda-python/
This course was organised by ENCCS (https://enccs.se/).
About the ENCCS
ENCCS (https://enccs.se) is based in Sweden and provides free training and support for accessing and using European supercomputers to companies and public organisations. If you are a company or public authority based in Sweden interested in running your software or code on large European supercomputers please visit https://enccs.se or contact us at [email protected].
Are you located in a European country or an associated country? Contact your local competence centre to get help and advice. For more information on the competence centres please follow this link https://www.eurocc-access.eu.
More information on EuroHPC JU systems you can find by following this link https://eurohpc-ju.europa.eu/supercom...
You can read more about the countries associated with Horizon2020 here https://research-and-innovation.ec.eu...