# EpistasisLab/tpot

A Python Automated Machine Learning tool that optimizes machine learning pipelines using genetic programming.

Repository: https://github.com/EpistasisLab/tpot
Canonical: https://ross.abutalabs.com/products/tpot
Homepage: http://epistasislab.github.io/tpot/
Language: Jupyter Notebook
License: LGPL-3.0
License Family: copyleft
Topics: machine-learning, python, data-science, automl, automation, scikit-learn, hyperparameter-optimization, model-selection, parameter-tuning, automated-machine-learning, random-forest, gradient-boosting, feature-engineering, aiml, alzheimer, alzheimers, nia, u01ag066833, ag066833, adsp
Last push: 2025-09-11T21:32:19+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 41, release rhythm 16, longevity 100
- inputs: {"age_days": 3956, "days_push": 356, "days_rel": 426, "gap_med": 128, "n_releases_24m": 2}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 10052, forks 1563 (observed 2026-08-28T04:10:39.371848+00:00)

## What it is
TPOT (Tree-based Pipeline Optimization Tool) is a Python automated machine learning library that optimizes scikit-learn machine learning pipelines using genetic programming. It automates pipeline construction, feature selection, model selection, and hyperparameter tuning through evolutionary search.

## Use cases
- automatically find the best machine learning pipeline for my dataset
- automate hyperparameter tuning and model selection
- use genetic programming to optimize an sklearn pipeline
- autoML for feature selection and preprocessing
- compare models and pipelines without manual tuning
- evolve a classification or regression pipeline automatically

## When to choose
- you want automated pipeline search over scikit-learn estimators
- you need multi-objective or customizable evolutionary AutoML
- you want feature selection and preprocessing optimized together with model choice

## When to avoid
- you need deep learning or LLM pipeline optimization
- you want a simple grid search rather than evolutionary optimization
- your data is too large for repeated cross-validation fits during search

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, data-science, etl
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: automl, genetic-programming, hyperparameter-optimization, scikit-learn, pipeline-optimization, evolutionary-computation, feature-engineering, automation

## Member repositories
- EpistasisLab/tpot (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:39.371848+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 2026-08-29T17:19:54.001565+00:00, confidence not recorded.
  - readme: https://github.com/EpistasisLab/tpot (fetched 2026-08-28T04:10:39.371848+00:00, sha 0ed5ced7ae63)
  - homepage: http://epistasislab.github.io/tpot/ (fetched 2026-08-29T08:19:39.820912+00:00, sha 36c6c3c2e4f9)
  - registry_pypi: https://pypi.org/pypi/tpot/json (fetched 2026-08-29T08:19:39.831081+00:00, sha f23441f6e1a6)
- Data as of 2026-08-30T08:39:29.467469+00:00.