Changelog

Major changes in content are tracked here. A summary of all file-level changes is available through the Git commit history.

ImportantTODO

Stage 1 — Import baseline

Stage 2 — Recompose course

Stage 3 — Port to R

For each session:

Stage 4 — Standardize and finalize

2026-08-11 Plan to import from analytics-and-big-data

Import the relevant source materials unchanged as a migration baseline, then recompose the course section-by-section. Keep the existing machine-learning-for-big-data session structure, course.yml, styling, and session paths authoritative. Separate structural migration, Python-to-R conversion, and content revision into distinct stages.

Stage 1: Import source materials

Copy the relevant materials from analytics-and-big-data unchanged:

  • slides
  • exercises
  • teaching notes
  • required datasets
  • referenced images/includes
  • bibliography entries

Record the source repository and commit SHA in changelog.qmd.

Commit separately:

Import teaching materials from analytics-and-big-data

Stage 2: Recompose into MLBD sessions

Map and rename the imported materials according to the target syllabus:

Target session Main source
1: Big Data Lecture 8 + parts of Lecture 1
1: Basics in R Create anew
2: Analytics Lecture 1
2: Data Preparation Lecture 2 + Exercise 2
3: EDA Lecture 2 + Exercise 2
4: Regression Lecture 4 + Exercise 4
5: Classification Lecture 5 + Exercise 5
6: ML Workflow Lecture 6
7: ML Algorithms Lecture 7
8: Text Lecture 8 + Exercise 8
9: Image, Video, Audio Lecture 9 + Exercise 9
9: Deployment Lecture 10 + Exercise 10

At this stage, retain Python examples unchanged.

Stage 3: Port session-by-session to R

Work through each session:

slides/session_XX.qmd
exercises/session_XX.qmd
notes/session_XX.qmd
data/assets

For each session:

  • convert Python/pandas/scikit-learn examples to R;
  • use tidyverse and tidymodels where appropriate;
  • update exercises and solutions;
  • update teaching notes;
  • verify datasets, figures, and relative paths;
  • render and test the complete session.

Commit completed sessions separately, for example:

Port Session 4 regression materials to R

Stage 4: Standardize course infrastructure

After the content migration:

  • standardize exercise assignment/solution profiles;
  • instead of .ipynb output, use .qmd and knitr (provide a corresponding introductory explanation);
  • remove obsolete Python/Jupyter/Codespaces instructions;
  • update links, survey variables, metadata, and course references;
  • verify the full course render and session overview.

2026-07-20 Consideration of shared-teaching-materials