Introduction to End-to-End RAPIDS Workflows

RAPIDS enables developers to build high performance data solutions without a learning curve using DataFrames, SQL, machine learning, and graph analytics on NVIDIA GPUs. RAPIDS focuses on common data preparation tasks for analytics and data science. This includes a familiar dataframe API that integrates with a variety of machine learning algorithms for end-to-end pipeline accelerations without paying typical serialization costs.

Using NYC CitiBike data, this tutorial will teach developers how to build an end-to-end workflow with cuDF, accelerated XGBoost and SHAP. This tutorial will show you how to ingest data, conduct ETL, perform EDA, train an XGBoost model, and inference using the trained model.