Profile, Optimize, Repeat: One Core Is All You Need - Boosting Data Analysis Pipeline Performance
Offered By: EuroPython Conference via YouTube
Course Description
Overview
Explore a 42-minute conference talk from EuroPython 2024 that delves into optimizing data analysis pipelines on a single core. Learn how to boost performance, reduce processing time, and cut costs without resorting to parallelization. Follow a step-by-step walkthrough demonstrating tools for identifying bottlenecks through profiling and strategies to address them. Discover techniques to enhance memory and runtime performance using numpy, numba jit-ing, and pybind11 extensions. Gain valuable insights into maximizing efficiency in your data analysis workflows, all while focusing on single-core optimization.
Syllabus
Profile, Optimize, Repeat: One Core Is All You Need™ — Valentin Nieper, Jonathan Striebel
Taught by
EuroPython Conference
Related Courses
Social Network AnalysisUniversity of Michigan via Coursera Intro to Algorithms
Udacity Data Analysis
Johns Hopkins University via Coursera Computing for Data Analysis
Johns Hopkins University via Coursera Health in Numbers: Quantitative Methods in Clinical & Public Health Research
Harvard University via edX