Applied Data Science with Python

Info Course Information - Instructor: Christopher Seaman - EA’s: Samantha Chan & Eric Yang - Dates: January 15th - March 11th, 2026 (10 class meetings) - Lecture: Wednesday, 1:00 PM - 3:00 PM, Mission Hall 1407 - Lab: Wednesday, 3:00 PM - 4:30 PM, Mission Hall 1407 - GitHub: https://github.com/christopherseaman/datasci_223 - Course Website: https://christopherseaman.github.io/datasci_223/ - CLE: DATASCI 223: Applied Data Science with Python (Winter 2026)

This repository contains the course materials for UCSF DataSci 223: Applied Data Science with Python.

Course Topics (Winter 2026 - 11 Lectures)

Foundational (L01-L04)

  1. Setup + Debugging - Notebook hygiene, defensive programming, VS Code debugger
  2. Larger-than-Memory Data - Polars lazy evaluation, out-of-core processing, parquet
  3. SQL for Data Analysis - SELECT, JOIN, GROUP BY, window functions, pandas integration
  4. NLP Foundations - Text preprocessing, embeddings, sentiment, clinical text applications

ML/AI Progression (L05-L08)

  1. Classification - Train/test splits, evaluation metrics, Random Forest, XGBoost
  2. Neural Networks - MLP, CNN, RNN/LSTM, PyTorch training loop
  3. Transformers & Deep Learning - Attention mechanism, Hugging Face, tokenization
  4. LLMs - DIY -> API, Agentic & Workflows - nanoGPT walkthrough, embeddings, fine-tuning concepts, API integration, agents, prompt engineering

Applied / Student Choice (L09-L11)

09-11. Student Vote (TBD) - Some options:

  • Computer Vision (transfer learning, medical imaging)
  • Visualization & Dashboards (Altair, Streamlit, MkDocs reports)
  • Time Series & Forecasting (ARIMA, ML regressors)
  • A/B Testing (causal inference, power analysis)
  • Distributed Computing (threads/processes, HPC intro)
  • End-to-End Project (CRISP-DM, capstone guidance)
  • Jobs, technical interviews, & impostor syndrome
  • Generative AI with Images
  • Feature Engineering and Selection
  • Algorithms and complexity notation
  • Local setup with the “Modern Data Stack”
  • Deploying a basic model/app to the web