# feature-engine/feature_engine

Feature engineering and selection open-source Python library compatible with sklearn.

Repository: https://github.com/feature-engine/feature_engine
Canonical: https://ross.abutalabs.com/products/feature_engine
Homepage: https://feature-engine.trainindata.com/
Language: Python
License: BSD-3-Clause
License Family: permissive
Topics: machine-learning, data-science, python, scikit-learn, feature-engineering, feature-selection, feature-extraction
Last push: 2026-08-26T18:51:22+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 99, release rhythm 62, longevity 100
- inputs: {"age_days": 2803, "days_push": 7, "days_rel": 43, "gap_med": null, "n_releases_24m": 1}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2272, forks 368 (observed 2026-08-28T04:06:33.185212+00:00)

## What it is
Feature-engine is a Python library for feature engineering and feature selection with transformers that follow scikit-learn's fit/transform API. It provides a wide range of transformers for missing data imputation, encoding, discretisation, outlier handling, and variable selection, compatible with sklearn pipelines.

## Use cases
- engineer features for machine learning models in python
- select the most relevant features before training a model
- impute missing values in a dataframe within an sklearn pipeline
- encode categorical variables for scikit-learn estimators
- detect and cap outliers in my dataset
- wrap feature engineering steps in a cross-validation-safe pipeline

## When to choose
- you need sklearn-compatible feature engineering transformers that fit into Pipelines
- you want to avoid data leakage by learning parameters only from the training set
- you need a broad toolkit for imputation, encoding, discretisation, outliers, and selection in one library

## When to avoid
- you need deep learning or GPU-accelerated feature processing
- you work outside the Python/pandas ecosystem
- you only need one-off ad-hoc transformations without pipeline integration

## Facets
- artifact type: library
- maturity: stable
- function: machine-learning, data-science
- domain: machine-learning, data-science
- platform: python
- tags: feature-engineering, feature-selection, scikit-learn-compatible, transformers, data-preprocessing

## Member repositories
- feature-engine/feature_engine (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:33.185212+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 2026-08-30T02:41:42.617100+00:00, confidence not recorded.
  - readme: https://github.com/feature-engine/feature_engine (fetched 2026-08-28T04:06:33.185212+00:00, sha d157450cdf16)
  - registry_pypi: https://pypi.org/pypi/feature_engine/json (fetched 2026-08-29T10:22:35.981120+00:00, sha 3f30a663cc41)
- Data as of 2026-08-30T08:39:29.467469+00:00.