# ethen8181/machine-learning

:earth_americas: machine learning tutorials (mainly in Python3)

Repository: https://github.com/ethen8181/machine-learning
Canonical: https://ross.abutalabs.com/products/ethen8181-machine-learning
Language: HTML
License: MIT
License Family: permissive
Topics: machine-learning, data-science, jupyter-notebook, python3, deep-learning, python
Last push: 2026-07-10T18:45:47+00:00

## Health v2 (maintenance only)
Score: 73/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 91, release rhythm 35, longevity 100
- inputs: {"age_days": 4058, "days_push": 54, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3498, forks 675 (observed 2026-08-28T04:08:07.417161+00:00)

## What it is
A continuously updated collection of machine learning and data science tutorials written as Jupyter notebooks in Python 3. It covers topics from linear regression and clustering to deep learning, reinforcement learning, and model deployment, balancing math notation with from-scratch implementations and library usage.

## Use cases
- learn machine learning concepts through annotated jupyter notebooks
- understand how algorithms like softmax regression or CNNs work from scratch
- find tutorials on xgboost, lightgbm, and model deployment
- study text classification and NLP examples in python
- review time series and A/B testing material for data science interviews

## When to choose
- you want educational, notebook-style explanations with from-scratch implementations
- you need a broad survey of ML topics with runnable python code
- you prefer seeing both math and practical library usage side by side

## When to avoid
- you need production-ready, maintained ML software or libraries
- you want a structured course with graded exercises rather than reference notebooks
- you need guaranteed up-to-date coverage of the latest model architectures

## Facets
- artifact type: learning-resource
- maturity: active
- function: machine-learning, deep-learning, data-science, nlp, reinforcement-learning
- domain: machine-learning, data-science, deep-learning, tutorials, time-series
- platform: python, cross-platform
- tags: jupyter-notebooks, tutorials, scikit-learn, tensorflow, pytorch, educational, natural-language-processing

## Member repositories
- ethen8181/machine-learning (main) score 73

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:07.417161+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:35:51.029584+00:00, confidence not recorded.
  - readme: https://github.com/ethen8181/machine-learning (fetched 2026-08-28T04:08:07.417161+00:00, sha a0cd4c9f2684)
- Data as of 2026-08-30T08:39:29.467469+00:00.