---
id: mlxtend
version: "0.25.0"
license: BSD 3-Clause
license_treatment: permissive
maintenance: active
---

# mlxtend — Machine Learning Library Extensions

License: permissive · Maintenance: active · Downloads: 1.1M/mo

## What it is and what it does

Mlxtend is a library of utilities and extensions for machine learning and data science built on top of the scientific Python stack. It fills gaps in common workflows by providing ensemble voting and stacking classifiers, feature selection and extraction techniques, and a suite of visualization helpers for model analysis and decision boundaries.

The library is primarily used for tasks like combining multiple classifiers through weighted voting or stacking, selecting relevant features from high-dimensional data, mining frequent itemsets with the Apriori algorithm, and plotting decision regions and confusion matrices for model interpretation. It depends on scipy, numpy, pandas, scikit-learn, matplotlib, and joblib, and is designed to integrate into existing data science pipelines.

Use it for:

- Build ensemble classifiers that combine predictions from multiple base learners with configurable voting strategies and weights.
- Perform feature selection to identify the most informative features and reduce dimensionality before model training.
- Visualize decision boundaries and regions for classification problems to understand model behavior.
- Mine association rules and frequent itemsets from transactional data using the Apriori algorithm.
- Plot confusion matrices and other model evaluation artifacts for classification model analysis.
- Extract features using automated feature engineering methods.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Mlxtend provides ensemble methods, feature selection, visualization utilities, and frequent pattern mining algorithms for machine learning workflows.

Yes. Mlxtend is actively maintained, has low install friction, carries no known vulnerabilities, and offers a focused set of utilities for ensemble methods, feature selection, and visualization—common tasks in machine learning workflows. The permissive BSD 3-Clause license poses no commercial restrictions. Install it if you need these specific capabilities.

## Install

pip install mlxtend
uv add mlxtend
poetry add mlxtend

## Installing mlxtend

Before you install: Low friction installation as a pure Python wheel with six well-established scientific dependencies. Actively maintained with recent commits and stable production status.

License in practice: Released under permissive BSD 3-Clause license, commercially usable with no warranty. Artistic works in the distribution are separately licensed under Creative Commons Attribution 4.0 International.

Quickstart:

pip install mlxtend

from mlxtend.classifier import EnsembleVoteClassifier
from mlxtend.plotting import plot_decision_regions
from mlxtend.data import iris_data

X, y = iris_data()
eclf = EnsembleVoteClassifier(clfs=[], voting='soft')
eclf.fit(X, y)

Requires Python 3.11 or later.

Verify before relying:

- Whether the Apriori algorithm implementation handles large datasets efficiently or has known performance limits.
- Specific version compatibility guarantees with scipy, numpy, pandas, matplotlib, and joblib beyond the stated runtime dependencies.

## Package facts

- License: BSD 3-Clause (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 1.1M/month (top 5,000 on PyPI)
- Known vulnerabilities: none known

## Tags

ensemble voting stacking classifiers, feature selection extraction machine learning, decision region visualization, apriori association rule mining, model analysis plotting utilities, confusion matrix visualization, frequent itemset mining, ensemble-learning, feature-selection, visualization

[View on SkillFed](https://skillfed.io/packages/mlxtend) · [View on PyPI](https://pypi.org/project/mlxtend/)