Geoffrey Boushey
Geoff is a Data Science Specialist. Contact Geoff for help with Python, SQL, and git or Github questions.

Data and Document Analysis with Python, SQL, and AI Workshops Spring 2026

UCSF Library is pleased to offer a ten-part workshop series on Friday mornings, 9 – 11 a.m., from April 3 – June 5, 2026. Designed for UCSF researchers, staff and students, this series provides hands-on training in Python, SQL, machine learning, and AI for real-world data and document analysis.

We will start with foundational Python programming concepts and advance to more complex topics, including data analysis, document analysis, and artificial intelligence (AI)-based research. Throughout the workshops, we will dive into various data types, including numerical, health, text, and image and video, and explore analysis techniques such as regression, classification, and sentiment analysis. The end of the series will focus on text analysis through analyzing documents from the UCSF Industry Document Library.

The series focuses on helping participants build practical skills. Sessions will involve a lot of hands-on coding while keeping lectures and theory to a minimum.

Using AI

This series begins with foundational skills and progressively incorporates AI-assisted programming in later workshops. Intro to Python (Parts 1 and 2) and Intro to SQL will use AI tools sparingly to emphasize core concepts. As the series advances, participants will gradually incorporate more AI-driven techniques and explore the following topics:

  • Web APIs
  • Text analysis
  • Natural language processing
  • Machine learning
  • Regression
  • Document analysis
  • AI system interaction

Throughout the series, we will emphasize careful testing, validation, and critical evaluation of AI-generated code to ensure accuracy, reliability, and sound analytical practice.

Workshop schedule

We designed the series to guide you through practical, hands-on learning at every step. While you are welcome to attend individual workshops, we encourage you to follow the full series for a more cohesive learning experience.

The workshops will be held online via Zoom, and registration is required. Registrants will receive an email with a Zoom link at registration and the day before the workshop.

Date and time
Workshop
Friday, April 3, 2026, 9 – 11 a.m.Intro to Python: Variables, Lists, and Control Flow
Friday, April 10, 2026, 9 – 11 a.m.Intro to Python: Pandas and Data Visualization
Friday, April 17, 2026, 9 – 11 a.m.Intro to SQL for Data Analysis
Friday, April 24, 2026, 9 – 11 a.m.Analyzing COVID Testing Data with Python and SQL
Friday, May 1, 2026, 9 – 11 a.m.Interacting with APIs in Python: Using the Industry Documents Library
Friday, May 8, 2026, 9 – 11 a.m.Machine Learning with Python: Feature Importance and Random Forests
Friday, May 15, 2026, 9 – 11 a.m.Python Background for Text Analysis and NLP
Friday, May 22, 2026, 9 – 11 a.m.Machine Learning for Document Classification and Sentiment Analysis
Friday, May 29, 2026, 9 – 11 a.m.Pre-Trained Open Source Tools for Document Classification & Sentiment Analysis
Friday, June 5, 2026, 9 – 11 a.m.Image, Audio, and Video Transcription and Analysis with Python