AWS Documentation » Amazon Personalize » Developer Guide » Preparing and Importing Data

This is prerelease documentation for a service in preview release. It is subject to change.

We made breaking changes to the Amazon Personalize API and service model on 3/26/19. To continue using Amazon Personalize with the AWS Command Line Interface or AWS SDK for Python (Boto 3), update your service JSON files by doing steps 3-6 of Setting Up the AWS CLI.

Preparing and Importing Data

Amazon Personalize uses data you provide to train a model. You can provide data from a source file, or you can collect data from live events such as user activity on a website.

If you are providing a source file for import, your data must be in comma-separated values (CSV) format and conform to a schema that Amazon Personalize can understand. You upload your CSV file into an Amazon S3 bucket from which Amazon Personalize imports your data into a dataset. A dataset group contains related datasets. You can upload your data by using the AWS Management Console or by using the AWS SDK.

This section provides information about formatting and importing your historical data into Amazon Personalize. For information about recording live event data, see Recording Events.

Topics

• Datasets and Schemas
• Formating your Input Data
• Uploading to an Amazon S3 Bucket
• Importing your Data