Skip to main content

AutoML for Image, Text, and Tabular Data

Project description

AutoML for Image, Text, Time Series, and Tabular Data

Latest Release Conda Forge Python Versions Downloads GitHub license Discord Twitter Continuous Integration Platform Tests

Install Instructions | Documentation | Release Notes

AutoGluon automates machine learning tasks enabling you to easily achieve strong predictive performance in your applications. With just a few lines of code, you can train and deploy high-accuracy machine learning and deep learning models on image, text, time series, and tabular data.

💾 Installation

AutoGluon is supported on Python 3.8 - 3.11 and is available on Linux, MacOS, and Windows.

You can install AutoGluon with:

pip install autogluon

Visit our Installation Guide for detailed instructions, including GPU support, Conda installs, and optional dependencies.

:zap: Quickstart

Build accurate end-to-end ML models in just 3 lines of code!

from autogluon.tabular import TabularPredictor
predictor = TabularPredictor(label="class").fit("train.csv")
predictions = predictor.predict("test.csv")
AutoGluon Task Quickstart API
TabularPredictor Quick Start API
MultiModalPredictor Quick Start API
TimeSeriesPredictor Quick Start API

:mag: Resources

Hands-on Tutorials / Talks

Below is a curated list of recent tutorials and talks on AutoGluon. A comprehensive list is available here.

Title Format Location Date
:tv: AutoGluon 1.0: Shattering the AutoML Ceiling with Zero Lines of Code Tutorial AutoML Conf 2023 2023/09/12
:sound: AutoGluon: The Story Podcast The AutoML Podcast 2023/09/05
:tv: AutoGluon: AutoML for Tabular, Multimodal, and Time Series Data Tutorial PyData Berlin 2023/06/20
:tv: Solving Complex ML Problems in a few Lines of Code with AutoGluon Tutorial PyData Seattle 2023/06/20
:tv: The AutoML Revolution Tutorial Fall AutoML School 2022 2022/10/18

Scientific Publications

Articles

Train/Deploy AutoGluon in the Cloud

:pencil: Citing AutoGluon

If you use AutoGluon in a scientific publication, please refer to our citation guide.

:wave: How to get involved

We are actively accepting code contributions to the AutoGluon project. If you are interested in contributing to AutoGluon, please read the Contributing Guide to get started.

:classical_building: License

This library is licensed under the Apache 2.0 License.

Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

autogluon.timeseries-1.0.1b20240302.tar.gz (102.8 kB view details)

Uploaded Source

Built Distribution

File details

Details for the file autogluon.timeseries-1.0.1b20240302.tar.gz.

File metadata

File hashes

Hashes for autogluon.timeseries-1.0.1b20240302.tar.gz
Algorithm Hash digest
SHA256 0d703c53a3ab082597ac07688d593bcb9d77947e79cc9e9cbff6b94cef62e2f9
MD5 e9faa16dee2eaf01d9d46402709598eb
BLAKE2b-256 89a42cdbb9bfd27d29ee57ae811df9d9c00f5aabac66e26b9449343ad88989a2

See more details on using hashes here.

File details

Details for the file autogluon.timeseries-1.0.1b20240302-py3-none-any.whl.

File metadata

File hashes

Hashes for autogluon.timeseries-1.0.1b20240302-py3-none-any.whl
Algorithm Hash digest
SHA256 ea30f466341d684f26011fee9b88f6c051ffb868b578bf8ae3d737928d05cd43
MD5 df6d8d0618be5767b085438547b3323e
BLAKE2b-256 f3a671c2fae803ff032435cd399c6770e1dcf64c793ef6a0c4721a510d0b202f

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page