USP 410/510 Urban Data Science — Resources

Textbooks

Yu and Barter, 2024, Veridical Data Science, MIT Press. https://vdsbook.com/
Downey, 2024, Think Python, 3rd Edition. https://allendowney.github.io/ThinkPython/
Turrell, Python for Data Science. https://aeturrell.github.io/python4DS/
McKinney, 2022, Python for Data Analysis, 3rd Edition. https://wesmckinney.com/book/
Rey, Arribas-Bel, and Wolf, 2023, Geographic Data Science with Python. https://geographicdata.science/book/

Severance, Python for Everybody — data-exploration-oriented intro (CC license). https://www.py4e.com/book
VanderPlas, Python Data Science Handbook — NumPy, pandas, matplotlib, scikit-learn. https://jakevdp.github.io/PythonDataScienceHandbook/
Tenkanen, Heikinheimo, and Whipp, Introduction to Python for Geographic Data Analysis. https://pythongis.org/
Geo-Python course (University of Helsinki) — Python basics through a geoscience lens. https://geo-python-site.readthedocs.io/

Karpathy, 2025, How I Use LLMs (2h11m video). https://www.youtube.com/watch?v=EWvNQjAaOHw
Evkaya and de Carvalho, 2026, “Using ChatGPT for Data Science Analyses,” Harvard Data Science Review, 8(1). https://hdsr.mitpress.mit.edu/pub/u6wp4cy3/release/2
“What Should Data Science Education Do with Large Language Models?” Harvard Data Science Review, 2024. https://hdsr.mitpress.mit.edu/pub/pqiufdew
“How I Use LLMs as a Data Scientist” (Medium, Jan 2026). https://medium.com/data-science-collective/how-i-use-llms-as-a-data-scientist-fa9a85262773

Prompt Engineering Guide (DAIR.AI) — comprehensive open-source guide covering techniques, agents, and RAG. https://www.promptingguide.ai/
Anthropic Interactive Prompt Engineering Tutorial — hands-on Jupyter notebook exercises. https://github.com/anthropics/prompt-eng-interactive-tutorial
OpenAI Prompt Engineering Guide. https://platform.openai.com/docs/guides/prompt-engineering
Anthropic Claude Prompt Engineering Docs. https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/overview

Tool	Cost	Notes
Google Gemini for Students	Free with edu email	Gemini Pro access for students; chat, code generation, research
Google Antigravity	Free	AI-powered IDE with built-in agents (Gemini, Claude); editor + manager views for parallel agent workflows
OpenAI Codex	Included with ChatGPT Plus/Edu	AI coding agent that plans, writes, tests, and fixes code in a cloud sandbox
Google Colab + Data Science Agent	Free (Colab Pro free for some students)	Gemini-powered agent generates notebooks from natural language
GitHub Copilot (Student Plan)	Free for verified students	AI code completion in VS Code; apply via GitHub Education Pack
Jupyter AI (`%%ai` magic)	Free	Prompt LLMs from inside notebook cells; supports Claude, OpenAI, local models
ChatGPT / Claude free tiers	Free (limited)	Quick questions, brainstorming, debugging
Cursor IDE	Free tier available	VS Code fork with deep AI + Jupyter integration
Claude Code (CLI)	Requires Claude Pro ($20/month)	Documentation

Harvard AI Pedagogy Project — free assignments, guides, and classroom activities. https://aipedagogy.org/
Harvard Bok Center: AI Literacy & Ethics. https://bokcenter.harvard.edu/ai-literacy-and-ethics

freeCodeCamp Python Curriculum — free interactive Python course with projects. https://www.freecodecamp.org/learn/python-v9/
Software Carpentry Lessons — free workshops on Python, Git, SQL, and the Unix shell for researchers. https://software-carpentry.org/lessons/
AI Python for Beginners (DeepLearning.AI, Andrew Ng) — learn Python with AI chatbot support. https://www.deeplearning.ai/short-courses/ai-python-for-beginners/
ChatGPT Prompt Engineering for Developers (DeepLearning.AI) — free 1-2 hour short course. https://www.deeplearning.ai/courses/
Generative AI for Everyone (DeepLearning.AI / Coursera) — non-technical introduction. https://www.deeplearning.ai/courses/generative-ai-for-everyone/

The following DataCamp courses are not required but are recommended for students who want to deepen their skills in specific areas:

Understanding Prompt Engineering (1 hour, beginner) — intro to prompting LLMs effectively. https://www.datacamp.com/courses/understanding-prompt-engineering
Prompt Engineering with the OpenAI API (beginner, 4 hours). https://www.datacamp.com/courses/prompt-engineering-with-the-openai-api
Intermediate Python (4 hours, beginner) — dictionaries, pandas basics, logic, control flow, loops. https://www.datacamp.com/courses/intermediate-python
Introduction to Data Science in Python (4 hours, beginner) — overview of pandas, matplotlib, and data types. https://www.datacamp.com/courses/introduction-to-data-science-in-python
Exploratory Data Analysis in Python (4 hours, intermediate) — distributions, relationships, multivariate exploration. https://www.datacamp.com/courses/exploratory-data-analysis-in-python
Web Scraping in Python (4 hours, intermediate) — HTML parsing, XPath, CSS selectors, scrapy. https://www.datacamp.com/courses/web-scraping-with-python
Analyzing US Census Data in Python (5 hours, intermediate) — Census API, ACS, Decennial Census with pandas. https://www.datacamp.com/courses/analyzing-us-census-data-in-python
Building Dashboards with Dash and Plotly (4 hours, intermediate) — interactive dashboards with Plotly and Dash. https://www.datacamp.com/courses/building-dashboards-with-dash-and-plotly

Topic	Resource	URL
Quarto for Python	Official tutorial	https://quarto.org/docs/get-started/hello/jupyter.html
Seaborn visualization	Official tutorial	https://seaborn.pydata.org/tutorial.html
Census data (Python)	censusdis documentation	https://censusdis.readthedocs.io/
Census shapefiles	pygris (by Kyle Walker)	https://walker-data.com/pygris/
Web scraping	BeautifulSoup tutorial (Real Python)	https://realpython.com/beautiful-soup-web-scraper-python/
Dashboards	Streamlit documentation	https://docs.streamlit.io/
Infographic design	Ultimate Infographic Design Guide (Venngage)	https://venngage.com/blog/infographic-design/