Scientific Data Analysis, Data Science, and Machine Learning in Python

An independent study with two parts:

Part 1: Consolidate and advance our understanding of mainstream and cutting edge scientific data analysis techniques using Chapters 1-8 of Pasha, Astronomical Python

Part 2: Survey data science techniques up to and including neural net and deep learning implementations (which are the relevant preparation for a subsequent study of natural-language processing and LLMs) using Chapters 1-11, 13-15, and 18-19 Grus, Data Science from Scratch, 2nd Ed.

Term 6 of Academic Year 2024-2025, Deep Springs College

Mentor: Prof. Brian Hill

Student: Hexi Jin (DS 23)

Independent Study Application and Preliminary Syllabus

• PDF of Independent Study Application
• PDF of Syllabus (a PDF of the same content as is on these web pages)

Materials

Required

• Imad Pasha, Astronomical Python
  • Pasha’s examples use data hosted at https://zenodo.org/records/10732223
• Joel Grus, Data Science from Scratch, 2nd Edition
  • We may need to copy over resources from Grus’s GitHub repo for the book https://github.com/joelgrus/data-science-from-scratch

Optional

• Both Pasha and Grus include adequate introductions to Python features as they use them, but you may want a more systematic introduction to use as a reference. An excellent one is David Beazley, Python Distilled. It is actually a distillation and update of his time-tested Python: Essential Reference, which was growing overly-long as the Python language feature set kept growing.

Actual Daily Schedules (Kept Retrospectively)

• Daily Schedule - Part 1
• Daily Schedule - Part 2

Looking Beyond

• Looking Beyond

Notes (mostly code samples)

• Brian’s Notes
• Hexi’s Notes