# alteryx/featuretools

An open source python library for automated feature engineering

Repository: https://github.com/alteryx/featuretools
Canonical: https://ross.abutalabs.com/products/featuretools
Homepage: https://www.featuretools.com
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: feature-engineering, machine-learning, data-science, automated-machine-learning, automl, python, scikit-learn, automated-feature-engineering
Last push: 2026-07-27T13:04:38+00:00

## Health v2 (maintenance only)
Score: 65/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 94, release rhythm 8, longevity 100
- inputs: {"age_days": 3281, "days_push": 37, "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 7666, forks 914 (observed 2026-08-28T04:10:02.279435+00:00)

## What it is
Featuretools is an open-source Python library for automated feature engineering, using Deep Feature Synthesis (DFS) to generate features from relational and temporal data. It integrates with scikit-learn workflows and supports parallel computation via Dask.

## Use cases
- automatically generate features from multi-table relational data
- prepare features for machine learning models from timestamped transaction data
- apply deep feature synthesis to a customer transactions dataset
- speed up feature engineering for tabular ML problems
- build an automated feature engineering pipeline in Python
- compute features across related tables without manual joins and aggregations

## When to choose
- you have relational or temporal data and want automated feature generation
- you want to reduce manual feature engineering effort in ML pipelines
- you work in Python with pandas, Dask, or scikit-learn ecosystems

## When to avoid
- you need deep learning feature extraction from raw images, audio, or text
- your data is a single flat table with no relational structure and simple features suffice
- you need a no-code GUI AutoML platform rather than a Python library

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, data-science, etl
- domain: machine-learning, data-science
- platform: python
- tags: feature-engineering, automl, deep-feature-synthesis, scikit-learn, data-preparation, automation

## Member repositories
- alteryx/featuretools (main) score 65

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:02.279435+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 2026-08-29T17:36:04.260798+00:00, confidence not recorded.
  - readme: https://github.com/alteryx/featuretools (fetched 2026-08-28T04:10:02.279435+00:00, sha d29008543765)
  - registry_pypi: https://pypi.org/pypi/featuretools/json (fetched 2026-08-29T08:31:44.259951+00:00, sha 3a2670497eba)
- Data as of 2026-08-30T08:39:29.467469+00:00.