Ryan Lafler
Thursday, December 4, 8:30 AM – 12:30 PM

This hands-on workshop is designed for data scientists, statisticians, programmers, machine learning engineers, researchers, and students who want to train and fine-tune supervised machine learning (ML) models in Python. Participants will gain practical experience with Python’s open-source libraries to build, train, optimize, and evaluate predictive models for both classification and regression tasks.

Through an applied, model-driven approach, the workshop covers how to prepare data for ML pipelines, balance model complexity and interpretability, and address overfitting and underfitting. Attendees will learn how to evaluate model performance, interpret results, and understand feature significance, all within the scikit-learn (sklearn) ecosystem.

Key topics include:

• Data cleaning and exploratory data analysis (EDA) to uncover feature relationships
• Building end-to-end ML pipelines in scikit-learn
• Training and interpreting supervised models, including LASSO regularization, decision trees, random forests, and gradient-boosted ensembles
• Hyperparameter tuning, search spaces, feature selection, and strategies for improving generalization to unseen data
• Model evaluation strategies, data partition techniques, and metric diagnostics for classification and regression
• Understanding the bias-variance tradeoff and model interpretability

All attendees will receive PDF slides, a fully documented Jupyter Notebook with code, the workshop dataset, and the practical skills to confidently train, tune, and evaluate predictive models in Python. Core tools include scikit-learn, pandas, numpy, scipy, matplotlib, and seaborn.

Summary of Content

This half-day, hands-on workshop introduces participants to the supervised machine learning (ML) workflow in Python, focusing on practical model development, tuning, and interpretation using open-source tools. Through an applied, model-driven approach, attendees will learn to prepare data, build and optimize scikit-learn pipelines, and evaluate predictive performance for both classification and regression tasks. Key algorithms include regularized regression, decision trees, random forests, and gradient-boosted ensembles

Benefits of Taking this Class

By taking this workshop, registered attendees will:

• Gain practical experience training, optimizing, and evaluating supervised ML models with scikit-learn
• Conduct exploratory data analysis (EDA) to process, visualize, and prepare data for machine learning
• Learn how to balance model complexity and interpretability
• Develop skills in hyperparameter tuning, feature selection, and evaluation metrics
• Understand and apply the bias-variance tradeoff
• Receive the documented Jupyter notebook with Python code and output, workshop dataset, and PDF slides to continue practicing independently

Prerequisites

• Familiarity with Python programming (basic scripting, working with libraries)
• Prior exposure to statistics or data analysis concepts is helpful but not required

Level

Beginner and Intermediate.

David Bosak and Brian Varney
Thursday, December 4, 2025, 1:30 PM – 5:30 PM ET

Summary of Content

Attendees will learn how to use ChatGPT to perform machine translation of code between SAS and R.  First, we will review the basic features of ChatGPT: how to navigate the interface, how to manage sessions, and how to share chats.  We will also look at how to optimize the editor interface for translation work.  Next, we’ll walk through some simple translations together, explaining how to use prompt engineering to get the best results.  You will then get an opportunity to perform some translations on your own.  Finally, we will provide tips, tricks, and a list of gotchas to watch out for.  By the end of the course, you will be quite comfortable using ChatGPT to translate code between SAS and R.

Benefits of taking this class

Instructors have hundreds of hours experience translating code using AI tools.  This class can get you up to speed very quickly.  Instructors can tell you what to do, and what is a waste of time.  The course will provide many helpful tips to make your translations better and faster.  Workshop will give you hands-on experience with a few programs.  Course materials will include a translation learnings document, with dozens of solutions to SAS/R compatibility problems.

Prerequisites, if any

Attendees should have the following set up prior to the course:

1. Access to SAS.
2. Access to RStudio or Posit Cloud.
3. A ChatGPT account (required), plus plan or higher (preferred).
4. Level – Basic or Intermediate?

Attendees should have intermediate level experience with both SAS and R.  No experience with ChatGPT is necessary.