Back to the catalog

Machine Learning Course Knowledge Bundle

Bundle OKF 0.1 · 5 conceitos · DerAndr/machine_learning_course_basics

Open source Repository Open in the app JSON README (API)

About

# Machine Learning Course Knowledge Bundle

This bundle is the public-safe content backbone for an interactive machine learning textbook. It keeps concise concepts, learning paths, and lab descriptions separate from renderer code and generated site files.

## Interactive textbook

Use the textbook for connected concept explanations, guided learning paths, and browser labs. Start with the course overview or follow a topic route at your own pace.

## Fast interactive reviews

Fast reviews use a short explanation → exploration → quiz → feedback loop for focused practice. They complement the connected textbook and full lecture materials rather than replacing either one. The textbook renderer discovers verified, self-contained review artifacts and makes them available from the homepage and every page sidebar.

* [Supervised learning](supervised-learning/) - Concise concepts and learning paths for supervised machine learning.
* [Learning paths](learning-paths/) - Guided routes through select

Details

Kind
OKF bundles
Topic
No topic detected
Publisher
derandr
Origin
okf_github
Category
dados
Version
0.1
Stars
16
Forks
3
Last push
2026-07-21T01:56:57Z
Repository state
ativo
Language
Jupyter Notebook
License
MIT
Added
2026-09-08 22:07:22
Updated
2026-09-08 22:07:22
Origin id
DerAndr/machine_learning_course_basics:okf/index.md

README

# Machine Learning Course

[![License: MIT](https://img.shields.io/badge/Code-MIT-blue.svg)](LICENSE)
[![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/Content-CC%20BY--NC--SA%204.0-lightgrey.svg)](LICENSE-CONTENT)

An introductory machine learning course with connected textbook pages, focused
interactive reviews, lecture notes and slides, and hands-on notebooks.

## Build Week project: Learning Companions

Learning Companions is a reusable Codex skill that turns repositories and
knowledge bases into short interactive lessons. The ML course is its first
repository-specific implementation.

[Open the portable skill](.agents/skills/interactive-learning-experience-builder/)
· [Try a generated lesson](https://derandr.github.io/machine_learning_course_basics/demos/lecture_05_classification_part_1/)
· [How Codex and GPT-5.6 were used](#how-codex-and-gpt-56-were-used)

The course materials existed before Build Week. During the event, I built the
portable skill, repository adapter, generator, validator, interaction runtime,
and generated learning companions.

## Choose how to learn

| Route | Best for | Open |
|---|---|---|
| Interactive textbook | Connected explanations, learning paths, and browser labs | [Open the textbook](https://derandr.github.io/machine_learning_course_basics/) |
| Fast interactive reviews | Short explanation → exploration → quiz → feedback practice | [Choose a review](#fast-interactive-reviews) |
| Full lecture materials | Notes, slides, examples, and topic references | [Browse all lectures](lectures/README.md) |
| Hands-on notebooks | Guided examples and 90-minute practical sessions | [Choose from the course map](#course-map) |

## Fast interactive reviews

These self-contained learning companions are quick, accessible reviews that
work online or directly from a cloned repository. They complement the textbook
and full lectures.

| Topic | Live | Offline |
|---|---|---|
| Exploratory Data Analysis | [Open live review](https://derandr.github.io/machine_learning_course_basics/demos/lecture_01_eda/) | [`lecture_experiences/lecture_01_eda/index.html`](lecture_experiences/lecture_01_eda/index.html) |
| Regression | [Open live review](https://derandr.github.io/machine_learning_course_basics/demos/lecture_04_regression/) | [`lecture_experiences/lecture_04_regression/index.html`](lecture_experiences/lecture_04_regression/index.html) |
| Classification Part 1 | [Open live review](https://derandr.github.io/machine_learning_course_basics/demos/lecture_05_classification_part_1/) | [`lecture_experiences/lecture_05_classification_part_1/index.html`](lecture_experiences/lecture_05_classification_part_1/index.html) |

The reviews share one portable learning loop but use interactions chosen for
the topic:

- **EDA:** binning, IQR fences, association, and missingness.
- **Regression:** residual diagnostics, Ridge and Lasso shrinkage, and
  MAE and RMSE sensitivity.
- **Classification:** threshold and confusion matrix outcomes plus a
  class-aware decision boundary.

Each review also includes three quiz levels, immediate feedback, keyboard
support, reduced-motion behavior, accessible fallbacks, and focus-friendly and
color-blind-safe controls.

## Course map

| # | Lecture | Notes | Practical |
|---|---|---|---|
| 01 | [Exploratory Data Analysis](lectures/lecture_01_eda/README.md) | [notes](lectures/lecture_01_eda/lecture_notes.md) | [practical](lectures/lecture_01_eda/practical_session/README.md) |
| 02 | [Data Preparation Part 1](lectures/lecture_02_data_preparation_part_1/README.md) | [notes](lectures/lecture_02_data_preparation_part_1/lecture_notes.md) | [practical](lectures/lecture_02_data_preparation_part_1/practical_session/README.md) |
| 03 | [Data Preparation Part 2](lectures/lecture_03_data_preparation_part_2/README.md) | [notes](lectures/lecture_03_data_preparation_part_2/lecture_notes.md) | [practical](lectures/lecture_03_data_preparation_part_2/practical_session/README.md) |
| 04 | [Regression](lectures/lecture_04_regression/README.md) | [notes](lectures/lecture_04_regression/lecture_notes.md) | [practical](lectures/lecture_04_regression/practical_session/README.md) |
| 05 | [Classification Part 1](lectures/lecture_05_classification_part_1/README.md) | [notes](lectures/lecture_05_classification_part_1/lecture_notes.md) | [practical](lectures/lecture_05_classification_part_1/practical_session/README.md) |
| 06 | [Classification Part 2](lectures/lecture_06_classification_part_2/README.md) | [notes](lectures/lecture_06_classification_part_2/lecture_notes.md) | [practical](lectures/lecture_06_classification_part_2/practical_session/README.md) |
| 07 | [Ensembles](lectures/lecture_07_ensembles/README.md) | [notes](lectures/lecture_07_ensembles/lecture_notes.md) | [practical](lectures/lecture_07_ensembles/practical_session/README.md) |
| 08 | [Time Series](lectures/lecture_08_time_series/README.md) | [notes](lectures/lecture_08_time_series/lecture_notes.md) | [practical](lectures/lecture_08_time_series/practical_session/README.md) |
| 09 | [Clustering](lectures/lecture_09_clustering/README.md) | [notes](lectures/lecture_09_clustering/lecture_notes.md) | [practical](lectures/lecture_09_clustering/practical_session/README.md) |
| 10 | [Cross-Validation and HPO](lectures/lecture_10_cross_validation_hpo/README.md) | [notes](lectures/lecture_10_cross_validation_hpo/lecture_notes.md) | [practical](lectures/lecture_10_cross_validation_hpo/practical_session/README.md) |
| 11 | [Explainability and Interpretability](lectures/lecture_11_explainability_interpretability/README.md) | [notes](lectures/lecture_11_explainability_interpretability/lecture_notes.md) | [practical](lectures/lecture_11_explainability_interpretability/practical_session/README.md) |
| 12 | [Introduction to Neural Networks](lectures/lecture_12_intro_neural_networks/README.md) | [notes](lectures/lecture_12_intro_neural_networks/lecture_notes.md) | [practical](lectures/lecture_12_intro_neural_networks/practical_session/README.md) |
| 13 | [Responsible AI](lectures/lecture_13_responsible_ai/README.md) | [notes](lectures/lecture_13_responsible_ai/lecture_notes.md) | [practical](lectures/lecture_13_responsible_ai/practical_session/README.md) |
| 14 | [ML in Production](lectures/lecture_14_ml_in_production/README.md) | [notes](lectures/lecture_14_ml_in_production/lecture_notes.md) | [practical](lectures/lecture_14_ml_in_production/practical_session/README.md) |
| 15 | [Computer Vision](lectures/lecture_15_computer_vision/README.md) | [notes](lectures/lecture_15_computer_vision/lecture_notes.md) | [practical](lectures/lecture_15_computer_vision/practical_session/README.md) |
| 16 | [Natural Language Processing](lectures/lecture_16_nlp_overview/README.md) | [notes](lectures/lecture_16_nlp_overview/lecture_notes.md) | [practical](lectures/lecture_16_nlp_overview/practical_session/README.md) |
| 17 | [Recommender Systems](lectures/lecture_17_recsys/README.md) | [notes](lectures/lecture_17_recsys/lecture_notes.md) | [practical](lectures/lecture_17_recsys/practical_session/README.md) |
| 18 | [LLM Overview](lectures/lecture_18_llm_overview/README.md) | [notes](lectures/lecture_18_llm_overview/lecture_notes.md) | [practical](lectures/lecture_18_llm_overview/practical_session/README.md) |
| 19 | [Course Overview](lectures/lecture_19_course_overview/README.md) | [notes](lectures/lecture_19_course_overview/lecture_notes.md) | — |

Lectures 01–14 are fully packaged with slide decks and example notebooks.
Lectures 15–19 are practical-first drafts and the final course overview. The
repository also includes a [mini-project on NYC Airbnb price prediction](mini_projects/airbnb_nyc/README.md)
and [example midterm questions](docs/midterm_examples.md).

## Create interactive learning materials

Use the skill that matches the source context:

| Goal | Skills |
|---|---|
| Create an experience from a general repository or knowledge base | `$interactive-learning-experience-builder` |
| Create a review for this ML course | `$ml-course-interactive-learning-assistant` with `$interactive-learning-experience-builder` |

The general skill owns the reusable content contract, deterministic generator,
and offline validator. The course skill adds this repository's source,
public-safety, output, and publishing rules. Follow the
[student prompt and installation quickstart](docs/student-learning-companion-quickstart.md)
to use the skills locally or add the generic skill to your personal Codex. Use
the
[operational learning-companion guide](docs/interactive-lecture-learning-assistant.md)
for the full authoring flow, or read the
[Learning companions architecture](docs/learning-companions-architecture.md)
for responsibility boundaries.

## How Codex and GPT-5.6 were used

This course repository existed before Build Week. During the event it was
meaningfully extended from a collection of learning resources into a reusable
learning-companion workflow and a three-topic interactive showcase.

- **Codex** was used to navigate the repository, turn the teaching problem into
  a scoped architecture, implement the portable skill and ML-course adapter,
  integrate the generated reviews, and run automated and browser-based
  verification.
- **GPT-5.6** supported architecture synthesis, source-grounded transformation
  of lecture materials, quiz and feedback design, and review of the
  implementation and documentation.
- **Human decisions remained central:** the teacher defined the learner and
  attention problem, selected authoritative sources, approved the
  core-versus-adapter boundary, chose accessibility and public-safety rules,
  and reviewed the resulting learning experience.

Judges and contributors can follow the
[operational guide](docs/interactive-lecture-learning-assistant.md), inspect
the [integration evidence](docs/build-week-integration-evidence.md), and use
the [submission and testing worksheet](docs/build-week-submission-preparation.md)
for a concise end-to-end test path.

## Local setup

Use `uv` as the environment manager:

```bash
uv sync
uv run python tools/check_notebook_environment.py
uv run jupyter lab
```

See the [student quickstart](docs/student-quickstart.md) for platform details
and optional dependency groups.

## Contributing and reference

- [Student and maintainer textbook workflow](docs/contributing-to-textbook.md)
- [Student learning-companion prompts and setup](docs/student-learning-companion-quickstart.md)
- [OKF authoring guide](docs/okf-authoring-guide.md)
- [Interactive learning-companion operations](docs/interactive-lecture-learning-assistant.md)
- [Learning companions architecture](docs/learning-companions-architecture.md)
- [Deep-learning and Colab guide](docs/deep-learning-colab-guide.md)
- [Agent repository guide](AGENTS.md)

## Repository map

- `lectures/` — lecture notes, slides, examples, practicals, and metadata
- `lecture_experiences/` — grounded payloads and canonical standalone reviews
- `okf/` — durable textbook concepts, learning paths, labs, and metadata
- `site/assets/` and `site/data/` — browser assets and public-safe lab data
- `tools/` — validation, rendering, environment, and maintenance commands
- `tests/` — course, textbook, skill, and learning-companion regression checks
- `docs/` — setup, contribution, architecture, and authoring guidance
- `src/mlcourse/` — shared Python helpers

Generated textbook output lives under `site/_build/` and is not committed.

## License

Unless stated otherwise:

- Source code in `src/`, `tests/`, `tools/`, and standalone `.py` files is
  licensed under the [MIT License](LICENSE).
- Lecture notes, slide decks, PDFs, images, notebooks, and other course content
  are licensed under [CC BY-NC-SA 4.0](LICENSE-CONTENT).

More