Fundamental of Accelerated Data Science

- 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 RAPIDS

• Use cuDF to accelerate pandas, Polars, and Dask for analyzing datasets of all sizes efficiently
• Utilize a wide variety of machine learning algorithms, including XGBoost, for different data science problems
• Deploy machine learning models on a Triton Inference Server to deliver optimal performance
• Learn and apply powerful graph algorithms to analyze complex networks with NetworkX and cuGraph
• Perform multiple analysis tasks on massive datasets to stave off a simulated epidemic outbreak effecting the UK
  

Module 1:  Introduction

• Meet the instructor.
• Create an account.

Module 2: 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 pandas, Polars, cuDF, and Dask.
• Prepare population, road network, and clinic information for machine learning tasks on the GPU with cuDF.

Module 3: 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.

Module 4: Graph Analytics

• Create and analyze graph data on the GPU with cuGraph.

Module 5: 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.