Reference Materials¶

UCSF Library Resources¶

UCSF library resources that might be helpful for your class project or future work:

• Library Databases Catalog: Library databases by subject/type/provider
• Research Guides: Great for finding data sources for population health, health service research, and COVID-19 research
• UC Data Week Seminars:
  • Digital Humanities Data
  • Social Sciences/Government Data
  • GIS Data and Mapping
  • Web Archives as Data
  • Recordings and more materials available for search
• Informatics Tools: Seminar materials, including access to high-performance computing, research analysis environment, info commons, patient explorerR, imaging commons, EMERSE for querying and analyzing clinical notes, etc.
• Office Hours related to data assets and info commons: schedule
• Data Science and Open Scholarship Team: DSOS team - help desk hours and consultations for related questions

Python Resources¶

General Introduction¶

• Whirlwind Tour of Python, VanderPlas: author's website
• Think Python, Downey: Green Tea Press
• Hitchhiker's Guide to Python!: official documentation
• Python 101: community resource
• Python for Everybody: author's website
• pythonbooks.org: additional free books available
• Official Python documentation: Python language reference
• Codecademy Python course: Interactive Python learning
• Automate the Boring Stuff with Python: Practical Python programming
• Introduction to Python: Python basics tutorial
• A Byte of Python: Python book for beginners

Data Science & Machine Learning¶

• Python for Data Analysis, McKinney: author's website
• Python Data Science Handbook, VanderPlas: author's website
• Machine Learning from Scratch: author's website - learn the nuts and bolts behind the tools
• Artificial Intelligence: A Modern Approach: author's website - authoritative deep survey of AI topics
• Effective Pandas: author's website - deep dive into a common python library
• Python Machine Learning, Raschka & Mirjalili: author's website

Deep Learning¶

• Deep Learning, Goodfellow, Bengio & Courville: free online
• Deep Learning with Python, Chollet: Manning
• Dive into Deep Learning: authors' website
• Understanding Deep Learning: author's website (WARNING: intense math)
• Deep Learning with PyTorch: Manning
• TensorFlow Tutorials: Official tutorials covering various aspects of TensorFlow
• PyTorch Tutorials: Collection of tutorials for learning and implementing neural networks
• Keras Documentation: Comprehensive guides for building neural networks with Keras
• Stanford CS231n: Convolutional Neural Networks for Visual Recognition
• Coursera: Deep Learning Specialization (Andrew Ng)

O'Reilly Library Access (UCSF Institutional Login)¶

• O'Reilly Library Access: UCSF institutional access
• Hands-on Machine Learning, Géron and companion repository
• Machine Learning with PyTorch and Scikit-Learn, Raschka
• Deep Learning with PyTorch, Viehmann
• Machine Learning Design Patterns, Lakshmanan, et al.
• Practical Time Series Analysis: O'Reilly book

Development Tools & Environments¶

Jupyter Notebook¶

• Jupyter Documentation: Official documentation for Jupyter notebooks
• Dataquest Jupyter Tutorial: Beginner-friendly tutorial

IDEs & Editors¶

• Jetbrains' Learn PyCharm: PyCharm IDE tutorials
• Effective PyCharm Course: Advanced PyCharm training
• VS Code:
  • Tutorial: Get started with Visual Studio Code
  • Getting Started with Python in VS Code

Debugging Resources¶

• Python Debugger (pdb) Documentation: Official pdb documentation
• Real Python Debugging Guide: Practical debugging techniques
• Python Testing with pytest: Testing as a debugging strategy
• Full Stack Python Debugging Guide: Comprehensive debugging techniques
• VS Code Debugging Guide: Visual debugging tutorial
• VS Code Debugging Overview: General debugging concepts

Code Quality Tools¶

• Ruff Documentation: Modern, fast Python linter written in Rust
• Pylint Documentation: Traditional Python linter with extensive rules

Command Line, Git & Markdown Resources¶

Command Line¶

• LinuxCommand.org: Learning the shell
• The Linux Command Line book: Free book by William Shotts
• The Missing Semester: MIT course on developer tools
• Bash manual: Official Bash documentation
• PowerShell documentation: Microsoft's PowerShell docs
• regex101.com: Regular expression testing tool

Git & Version Control¶

• GitHub Foundations: THE tutorial for GitHub
• Atlassian Git tutorial: Comprehensive Git guide

Markdown¶

• Markdown Guide: Markdown syntax reference
• Markdown Tutorial: Interactive Markdown learning
• CommonMark tutorial: CommonMark standard tutorial

SQL Resources¶

• SQL For Web Nerds: A concise introduction to SQL concepts by Philip Greenspun
• SQLZoo: Interactive SQL tutorials with live editors and exercises

Health Data Science Applications¶

Research Papers & Applications¶

• Miotto, R., Wang, F., Wang, S., Jiang, X., & Dudley, J. T. (2018). Deep learning for healthcare: review, opportunities and challenges. Briefings in Bioinformatics, 19(6), 1236-1246. Link
• Esteva, A., et al. (2017). Dermatologist-level classification of skin cancer with deep neural networks. Nature, 542(7639), 115-118. Link
• Rajpurkar, P., et al. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning. arXiv preprint arXiv:1711.05225. Link

Interpretability & Ethics¶

• Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608. Link
• Caruana, R., et al. (2015). Intelligible models for healthcare: Predicting pneumonia risk and hospital 30-day readmission. KDD 2015. Link

Clinical Applications¶

• Clinical Time Series Analysis: NCBI review
• Vital Signs Monitoring: PhysioNet Challenge
• Disease Progression Modeling: Scientific Reports
• Healthcare Time Series Analysis: Nature Digital Medicine

Time Series Analysis¶

General Resources¶

• Python for Time Series Analysis: Statsmodels documentation
• Time Series Forecasting: Forecasting: Principles and Practice

Machine Learning for Time Series¶

• Scikit-learn Documentation: Linear regression
• Feature Engineering for Time Series: Automated feature engineering
• Deep Learning for Time Series: TensorFlow guide
• Time Series Cross-Validation: Scikit-learn