# rasbt/mlxtend

A library of extension and helper modules for Python's data analysis and machine learning libraries.

Repository: https://github.com/rasbt/mlxtend
Canonical: https://ross.abutalabs.com/products/mlxtend
Homepage: https://rasbt.github.io/mlxtend/
Language: Python
License: NOASSERTION
License Family: other
Topics: python, machine-learning, data-science, data-mining, association-rules, supervised-learning, unsupervised-learning
Last push: 2026-08-05T14:38:28+00:00

## Health v2 (maintenance only)
Score: 85/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 96, release rhythm 63, longevity 100
- inputs: {"age_days": 4403, "days_push": 28, "days_rel": 88, "gap_med": 123.0, "n_releases_24m": 5}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5166, forks 911 (observed 2026-08-28T04:09:11.564008+00:00)

## What it is
mlxtend (machine learning extensions) is a Python library of helper tools for day-to-day data science and machine learning tasks. It provides ensemble methods like stacking and voting classifiers, feature selection/extraction, model evaluation utilities, plotting helpers, and frequent pattern mining such as the Apriori algorithm.

## Use cases
- stack multiple scikit-learn classifiers into an ensemble
- mine frequent itemsets and association rules with apriori
- plot decision regions of a classifier
- run statistical tests to compare classifiers like mcnemar or 5x2cv F-test
- perform feature selection with sequential feature selection
- decompose bias and variance of a model
- bootstrap model evaluation scores
- load MNIST or iris datasets for experiments

## When to choose
- you use scikit-learn and need stacking/voting ensembles or evaluation utilities it lacks
- you need association rule mining (Apriori, FP-Growth) in Python
- you want plotting helpers for decision boundaries and confusion matrices
- you need statistical model comparison tests like McNemar's test or Cochran's Q

## When to avoid
- you need deep learning or GPU-accelerated training - use PyTorch or TensorFlow instead
- you need large-scale distributed frequent pattern mining - use Spark MLlib
- you want a full AutoML or end-to-end ML pipeline framework
- your project depends only on scikit-learn features already covering your needs

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, data-science, data-visualization, parser
- domain: machine-learning, data-science
- platform: python, cross-platform
- tags: association-rules, apriori, frequent-pattern-mining, ensemble-learning, stacking, feature-selection, scikit-learn, model-evaluation, algorithms

## Member repositories
- rasbt/mlxtend (main) score 85

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:11.564008+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 2026-08-29T18:01:52.731290+00:00, confidence not recorded.
  - readme: https://github.com/rasbt/mlxtend (fetched 2026-08-28T04:09:11.564008+00:00, sha 17182d455e23)
  - homepage: https://rasbt.github.io/mlxtend/ (fetched 2026-08-29T08:55:54.484485+00:00, sha b3cab08ffa69)
  - registry_pypi: https://pypi.org/pypi/mlxtend/json (fetched 2026-08-29T08:55:54.487501+00:00, sha 5ea1663f6fd4)
- Data as of 2026-08-30T08:39:29.467469+00:00.