Fundamentals of Accelerated Data Science

Fundamentals of Accelerated Data ScienceFADSNVNvidiaNV-FADS1.0<ul> <li>Implement GPU-accelerated data preparation and feature extraction using cuDF and Apache Arrow data frames</li><li>Apply a broad spectrum of GPU-accelerated machine learning tasks using XGBoost and a variety of cuML algorithms</li><li>Execute GPU-accelerated graph analysis with cuGraph, achieving massive-scale analytics in small amounts of time</li><li>Rapidly achieve massive-scale graph analytics using cuGraph routines</li></ul>Experience with Python, ideally including pandas and NumPy. Suggested resources to satisfy prerequisites: Kaggle's pandas Tutorials, Kaggle's Intro to Machine Learning, Accelerating Data Science Workflows with RAPIDSIntroduction <ul> <li>Meet the instructor.</li><li>Create an account at courses.nvidia.com/join</li></ul>GPU-Accelerated Data Manipulation <ul> <li>Ingest and prepare several datasets (some larger-than-memory) for use in multiple machine learning exercises later in the workshop:<ul> <li>Read data directly to single and multiple GPUs with cuDF and Dask cuDF.</li><li>Prepare population, road network, and clinic information for machine learning tasks on the GPU with cuDF.</li></ul></li></ul>GPU-Accelerated Machine Learning <ul> <li>Apply several essential machine learning techniques to the data that was prepared in the first section:<ul> <li>Use supervised and unsupervised GPU-accelerated algorithms with cuML.</li><li>Train XGBoost models with Dask on multiple GPUs.</li><li>Create and analyze graph data on the GPU with cuGraph.</li></ul></li></ul>Project: Data Analysis to Save the UK <ul> <li>Apply new GPU-accelerated data manipulation and analysis skills with population-scale data to help stave off a simulated epidemic affecting the entire UK population:<ul> <li>Use RAPIDS to integrate multiple massive datasets and perform real-world analysis.</li><li>Pivot and iterate on your analysis as the simulated epidemic provides new data for each simulated day.</li></ul></li></ul>Assessment and Q&A- Implement GPU-accelerated data preparation and feature extraction using cuDF and Apache Arrow data frames - Apply a broad spectrum of GPU-accelerated machine learning tasks using XGBoost and a variety of cuML algorithms - Execute GPU-accelerated graph analysis with cuGraph, achieving massive-scale analytics in small amounts of time - Rapidly achieve massive-scale graph analytics using cuGraph routinesExperience with Python, ideally including pandas and NumPy. Suggested resources to satisfy prerequisites: Kaggle's pandas Tutorials, Kaggle's Intro to Machine Learning, Accelerating Data Science Workflows with RAPIDSIntroduction - Meet the instructor. - Create an account at courses.nvidia.com/join GPU-Accelerated Data Manipulation - Ingest and prepare several datasets (some larger-than-memory) for use in multiple machine learning exercises later in the workshop: - Read data directly to single and multiple GPUs with cuDF and Dask cuDF. - Prepare population, road network, and clinic information for machine learning tasks on the GPU with cuDF. GPU-Accelerated Machine Learning - Apply several essential machine learning techniques to the data that was prepared in the first section: - Use supervised and unsupervised GPU-accelerated algorithms with cuML. - Train XGBoost models with Dask on multiple GPUs. - Create and analyze graph data on the GPU with cuGraph. Project: Data Analysis to Save the UK - Apply new GPU-accelerated data manipulation and analysis skills with population-scale data to help stave off a simulated epidemic affecting the entire UK population: - Use RAPIDS to integrate multiple massive datasets and perform real-world analysis. - Pivot and iterate on your analysis as the simulated epidemic provides new data for each simulated day. Assessment and Q&A1 day500.00500.00500.00500.00500.00420.00500.00690.00