Tutorials

Tabular Prediction

Quick Start Tutorialtabular_prediction/tabular-quickstart.html

5 min tutorial on fitting models with tabular datasets.

In-depth FIT Tutorialtabular_prediction/tabular-indepth.html

In-depth tutorial on controlling various aspects of model fitting.

Deployment Optimizationtabular_prediction/tabular-deployment.html

Tutorial on optimizing the predictor artifact for production deployment.

Kaggle Tutorialtabular_prediction/tabular-kaggle.html

Using AutoGluon for Kaggle competitions with tabular data.

Data Tables Containing Image, Text, and Tabulartabular_prediction/tabular-multimodal.html

Modeling data tables with image, text, numeric, and categorical features.

Data Tables Containing Texttabular_prediction/tabular-multimodal-text-others.html

Modeling data tables with text and numeric/categorical features.

Multi-Label Predictiontabular_prediction/tabular-multilabel.html

How to predict multiple columns in a data table.

Adding a Custom Modeltabular_prediction/tabular-custom-model.html

How to add a custom model to AutoGluon.

Adding a Custom Metrictabular_prediction/tabular-custom-metric.html

How to add a custom metric to AutoGluon.

FAQtabular_prediction/tabular-faq.html

Frequently asked questions about AutoGluon-Tabular.

Multimodal Prediction

Use AutoGluon Multimodal for Text Prediction: Quick Startmultimodal/text_prediction/beginner_text.html

How to train high-quality text prediction models with MultiModalPredictor in under 5 minutes.

Solving Multilingual Problemsmultimodal/text_prediction/multilingual_text.html

How to use MultiModalPredictor to build models on datasets with languages other than English.

Multimodal Data Tables with Textmultimodal/multimodal_prediction/multimodal_text_tabular.html

How MultiModalPredictor can be applied to multimodal data tables with a mix of text, numerical, and categorical columns.

Time Series Forecasting

Quick Starttimeseries/forecasting-quickstart.html

Quick start tutorial on fitting models with time series datasets.

In-depth Tutorialtimeseries/forecasting-indepth.html

Detailed discussion of the time series forecasting capabilities in AutoGluon.

FAQtimeseries/forecasting-faq.html

Frequently asked questions about AutoGluon-TimeSeries.

Cloud Training and Deployment

AutoGluon-Tabular on Amazon SageMaker Autopilothttps://aws.amazon.com/blogs/machine-learning/amazon-sagemaker-autopilot-is-up-to-eight-times-faster-with-new-ensemble-training-mode-powered-by-autogluon/

Checkout managed AutoGluon experience on Amazon SageMaker Autopilot

AutoGluon Cloudcloud_fit_deploy/autogluon-cloud.html

A tutorial on using AutoGluon Cloud module to train/deploy AutoGluon backed models on SageMaker.

Cloud Training with AWS SageMakercloud_fit_deploy/cloud-aws-sagemaker-training.html

A tutorial on fitting an AutoGluon model using AWS SageMaker.

Deploying AutoGluon Models with AWS SageMakercloud_fit_deploy/cloud-aws-sagemaker-deployment.html

A tutorial on how to deploy trained models using AWS SageMaker and Deep Learning Containers.

Deploying AutoGluon models with serverless templatescloud_fit_deploy/cloud-aws-lambda-deployment.html

A tutorial on how to deploy trained models using AWS Lambda.

Exploratory Data Analysis

Automated Dataset Overvieweda/eda-auto-dataset-overview.html

Tool to get a high-level understanding of datasets including basic statistical information and feature information.

Automated Target Variable Analysiseda/eda-auto-target-analysis.html

Automatically analyze and summarize the variable we are trying to predict and it’s relationship with other variables.

Quick Model Fiteda/eda-auto-quick-fit.html

Automatically analyze and summarize the variable we are trying to predict and it’s relationship with other variables.

Covariate Shift Detectioneda/eda-auto-covariate-shift.html

Identify situations where the distribution of features in a dataset changes between the training and testing phases, which can lead to biased model performance.

Feature interaction chartseda/eda-auto-analyze-interaction.html

Simple visualization tool to visualize 1/2/3-way relationships between features. The tool automatically picks a chart type given each property type.