autogluon.tabular

What it is and what it does

AutoGluon Tabular is an automated machine learning library that trains and deploys high-accuracy predictive models on structured (tabular) data with minimal user code. It abstracts away the typical ML workflow—data preprocessing, feature engineering, algorithm selection, and hyperparameter tuning—so you can fit and predict in just a few lines. The package is built on top of numpy, scipy, pandas, and scikit-learn, and integrates networkx for graph-based feature interactions and autogluon.core and autogluon.features for its automation engine.

The library is designed for developers and data scientists who want to quickly build production-ready models without deep expertise in tuning individual algorithms. It supports classification and regression tasks on tabular data, and is part of the broader AutoGluon ecosystem (which also handles time series and multimodal data). The package is actively maintained by AWS AI, supports Python 3.10–3.13 across Linux, macOS, and Windows, and carries an Apache-2.0 license.

Use it for:

• Build a classification model for customer churn prediction from historical transaction and demographic data in minutes.
• Rapidly prototype a regression model for sales forecasting without manual feature selection or algorithm tuning.
• Deploy a production ML pipeline for fraud detection by fitting a model on labeled historical transactions.
• Compare multiple baseline models on a new tabular dataset to establish performance benchmarks quickly.
• Automate model retraining on fresh data with minimal code changes in a scheduled batch pipeline.

Worth the install?

AI-flagged interpretation of the facts on this page — verify before relying

Automates machine learning model training and prediction on tabular data with minimal code, handling feature engineering, algorithm selection, and hyperparameter tuning internally.

Yes. The package is actively maintained, has low install friction, carries a permissive license, and solves a real problem—reducing the time and expertise needed to train tabular ML models. It is well-suited for rapid prototyping, production deployment, and learning. No known security vulnerabilities as of the query date.

Install

autogluon-tabular on PyPI

pip install autogluon-tabular

uv add autogluon-tabular

poetry add autogluon-tabular

Installing autogluon.tabular

Before you install

Low install friction with a pure Python wheel distribution. Actively maintained with a recent release; the repository shows strong community engagement with 10596 stars and continuous development.

License in practice

Apache-2.0 permissive license allows commercial and private use with minimal restrictions, making it suitable for most production and research applications.

Quickstart

pip install autogluon.tabular

from autogluon.tabular import TabularPredictor
predictor = TabularPredictor(label="class").fit("train.csv", presets="best")
predictions = predictor.predict("test.csv")

Requires Python 3.10–3.13; depends on numpy, scipy, pandas, scikit-learn, networkx, and autogluon.core and autogluon.features packages.

Verify before relying

• Whether the package supports GPU acceleration and what additional dependencies or setup are required for it.
• Memory and compute requirements for typical tabular datasets (size, feature count, model complexity).
• Specific model types and ensemble strategies used internally during automated training.

Package facts

Evidence: autogluon_tabular-1.6.1-py3-none-any.whl

Tags

More Software Development packages

Further reading