# minimaxir/automl-gs

Provide an input CSV and a target field to predict, generate a model + code to run it.

Repository: https://github.com/minimaxir/automl-gs
Canonical: https://ross.abutalabs.com/products/automl-gs
Language: Python
License: MIT
License Family: permissive
Topics: python, tensorflow, keras, xgboost, machine-learning, automl
Last push: 2019-10-22T11:20:40+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2789, "days_push": 2507, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1866, forks 180 (observed 2026-08-28T04:05:46.294383+00:00)

## What it is
automl-gs is a Python AutoML tool that takes an input CSV and a target prediction field and automatically generates a trained machine learning or deep learning model along with native Python pipeline code. It abstracts data transformation, model architecture, and hyperparameter search across frameworks like TensorFlow/Keras and XGBoost with no black-box lock-in.

## Use cases
- predict a target column from a csv without writing model code
- generate a baseline model for tabular data automatically
- get native python code for a trained prediction pipeline
- run automated hyperparameter search on a dataset
- build ml models without deep statistical knowledge
- export a model pipeline with no platform lock-in

## When to choose
- you have tabular csv data and want a strong baseline model quickly
- you want readable, editable generated code instead of a black-box model
- you're a citizen data scientist without deep ML engineering experience
- you want to train models cheaply using TPUs in Google Colaboratory

## When to avoid
- you need state-of-the-art model performance beyond strong baselines
- you need actively maintained tooling with recent updates
- your data is unstructured like images, audio, or free text
- you need a full AutoML platform with extensive framework support

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning, data-science, etl
- domain: machine-learning, data-science
- platform: python, cli, cross-platform
- tags: automl, tabular-data, hyperparameter-search, code-generation, tensorflow, xgboost, citizen-data-science, automation

## Member repositories
- minimaxir/automl-gs (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:46.294383+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 2026-08-30T03:15:32.609617+00:00, confidence not recorded.
  - readme: https://github.com/minimaxir/automl-gs (fetched 2026-08-28T04:05:46.294383+00:00, sha 96ac7022f6f4)
  - registry_pypi: https://pypi.org/pypi/automl-gs/json (fetched 2026-08-29T10:54:35.268308+00:00, sha c1966bccafbf)
- Data as of 2026-08-30T08:39:29.467469+00:00.